The document proposes a physical-data fusion modeling method to accurately analyze the energy consumption of smart buildings. It first presents thermal and electrical models to analyze a building's energy usage. It then uses a physical-data fusion approach to improve the modeling accuracy by modifying difficult-to-measure parameters in the physical model based on collected data. Case studies on a real-world dataset show the method achieves higher accuracy than traditional physical or data-driven modeling alone.
Reinforcement Learning for Building Energy Optimization Through Controlling o...Power System Operation
This paper presents a novel methodology to control HVAC system and minimize energy cost
on the premise of satisfying power system constraints. A multi-agent architecture based on game theory and
reinforcement learning is developed so as to reduce the cost and computational complexity of the microgrid.
The multi-agent architecture comprising agents, state variables, action variables, reward function and cost
game is formulated. The paper lls the gap between multi-agent HVAC systems control and power system
optimization and planning. The results and analysis indicate that the proposed algorithm is benecial to deal
with the problem of ``curse of dimensionality'' for multi-agent microgrid HVAC system control and speed
up learning of unknown power system conditions.
Data Science for Building Energy Management a reviewMigue.docxrandyburney60861
Data Science for Building Energy Management: a review
Miguel Molina-Solanaa,b, Maŕıa Rosa,∗, M. Dolores Ruiza, Juan Gómez-Romeroa, M.J. Martin-Bautistaa
aDepartment of Computer Science and Artificial Intelligence, Universidad de Granada
bData Science Institute, Imperial College London
Abstract
The energy consumption of residential and commercial buildings has risen steadily in recent years, an
increase largely due to their HVAC systems. Expected energy loads, transportation, and storage as well
as user behavior influence the quantity and quality of the energy consumed daily in buildings. However,
technology is now available that can accurately monitor, collect, and store the huge amount of data involved
in this process. Furthermore, this technology is capable of analyzing and exploiting such data in meaningful
ways. Not surprisingly, the use of data science techniques to increase energy efficiency is currently attracting
a great deal of attention and interest. This paper reviews how Data Science has been applied to address the
most difficult problems faced by practitioners in the field of Energy Management, especially in the building
sector. The work also discusses the challenges and opportunities that will arise with the advent of fully
connected devices and new computational technologies.
1. Introduction
There is a general consensus in the world today that human activities are having a negative impact
on the environment and have accelerated both global warming and climate change. These environmental
threats have been intensified by the emissions produced by the energy required for the lighting and HVAC
(heating, ventilation and air-conditioning) systems in building constructions. According to the International
Energy Agency (IEA), residential and commercial buildings are responsible for up to 32% of the total final
energy consumption. In fact, in most IEA countries, they account for approximately 40% of the primary
energy consumption. Similar statistics are given by the World Business Council for Sustainable Development
(WBCSD) within the framework of its Energy Efficiency in Buildings (EEB) project1. Also provided is a
comprehensive review [1] of the state of the art in building energy use (with a primary focus on energy
demand).
These data indicate that inefficient energy management in aging buildings combined with rising construc-
tion activity in developed countries will cause energy consumption to soar in the near future and heighten the
negative impacts associated with this consumption. Moreover, variable energy costs call for the implemen-
tation of more intelligent strategies to adapt and reduce energy consumption as well as to find alternative
and sustainable energy sources. The relevance of these issues is clearly reflected in the research priorities of
the European Union, as stated in its Horizon2020 Societal Challenge “Secure, Clean and Efficient Energy”.
This work program targets a significant reduction in energy consu.
IRJET- Impact and Control Study of LV Communication Networks with PV Pene...IRJET Journal
This document summarizes a study on the impact and control of low voltage communication networks with photovoltaic-integrated microgrids. The study designs a new smart microgrid system model using power line communication infrastructure. It contains distributed energy resources like photovoltaics and electric vehicles. The system is simulated in Matlab. Simulation results examine power quality under different microgrid situations when integrating photovoltaics as a distributed resource.
A new smart approach of an efficient energy consumption management by using a...IJEECSIAES
Many consumers of electric power have excesses in their electric power consumptions that exceed the permissible limit by the electrical power distribution stations, and then we proposed a validation approach that works intelligently by applying machine learning (ML) technology to teach electrical consumers how to properly consume without wasting energy expended. The validation approach is one of a large combination of intelligent processes related to energy consumption which is called the efficient energy consumption management (EECM) approaches, and it connected with the internet of things (IoT) technology to be linked to Google Firebase Cloud where a utility center used to check whether the consumption of the efficient energy is satisfied. It divides the measured data for actual power (Ap) of the electrical model into two portions: the training portion is selected for different maximum actual powers, and the validation portion is determined based on the minimum output power consumption and then used for comparison with the actual required input power. Simulation results show the energy expenditure problem can be solved with good accuracy in energy consumption by reducing the maximum rate (Ap) in a given time (24) hours for a single house, as well as electricity’s bill cost, is reduced.
A new smart approach of an efficient energy consumption management by using a...nooriasukmaningtyas
This document proposes a new smart approach for efficient energy consumption management using machine learning techniques. It divides measured actual power data into training and validation portions to determine efficient energy consumption. Simulation results showed the approach can accurately reduce energy consumption and costs by lowering the maximum allowed power consumption over a 24-hour period for a single house. The approach connects to cloud services and uses Internet of Things technologies for real-time energy monitoring.
Integrated Energy System Modeling of China for 2020 by Incorporating Demand R...Kashif Mehmood
Electricity and heat energy carriers are mostly produced by the fossil fuel sources that are
conventionally operated independently, but these carriers have low efficiency due to heat losses. Moreover,
a high share of variable renewable energy sources disrupts the power system reliability and flexibility.
Therefore, the coupling of multiple energy carriers is underlined to address the above-mentioned issues that
are supported by the latest technologies, such as combined heat and power, heat pumps, demand response,
and energy storages. These coupling nodes in energy hubs stimulate the conversion of the electric power
system into the integrated energy system that proves to be cost-effective, flexible, and carbon-free. The
proposed work uses EnergyPLAN to model electricity, district, and individual heating integrated energy
system of China for the year 2020. Furthermore, the addition of heat pumps, thermal storage, and demand
response is analyzed in different scenarios to minimize the annual costs, fuel consumption, and CO2
emissions. Technical simulation strategy is conducted for optimal operation of production components that
result in the reduction of the above-mentioned prominent factors while calculating the critical and exportable
excess electricity production. The simulation results demonstrate that demand response and thermal storage
significantly enhance the share of variable renewable energy sources. In addition, it substantially reduces the
annual costs and fuel consumption, while heat pump increases the system efficiency
Achieving Energy Proportionality In Server ClustersCSCJournals
a great amount of interests in the past few years. Energy proportionality is a principal to ensure that energy consumption is proportional to the system workload. Energy proportional design can effectively improve energy efficiency of computing systems. In this paper, an energy proportional model is proposed based on queuing theory and service differentiation in server clusters, which can provide controllable and predictable quantitative control over power consumption with theoretically guaranteed service performance. Futher study for the transition overhead is carried out corresponding strategy is proposed to compensate the performance degradation caused by transition overhead. The model is evaluated via extensive simulations and is justified by the real workload data trace. The results show that our model can achieve satisfied service performance while still preserving energy efficiency in the system.
IRJET- Reducing electricity usage in Internet using transactional dataIRJET Journal
This document summarizes a research paper that proposes a method to reduce electricity usage and costs for internet services by optimizing how transactional data is mapped across geographically distributed data centers. It formulates the problem as a stochastic programming problem to maximize energy utilization within a cost budget. An efficient online algorithm is developed using Lyapunov optimization to map user requests to data centers based on changing factors like electricity prices and workload, with the goal of significantly reducing costs compared to baseline strategies. The system architecture involves front-end servers collecting user requests and dispatching them to appropriate back-end data centers for processing.
Reinforcement Learning for Building Energy Optimization Through Controlling o...Power System Operation
This paper presents a novel methodology to control HVAC system and minimize energy cost
on the premise of satisfying power system constraints. A multi-agent architecture based on game theory and
reinforcement learning is developed so as to reduce the cost and computational complexity of the microgrid.
The multi-agent architecture comprising agents, state variables, action variables, reward function and cost
game is formulated. The paper lls the gap between multi-agent HVAC systems control and power system
optimization and planning. The results and analysis indicate that the proposed algorithm is benecial to deal
with the problem of ``curse of dimensionality'' for multi-agent microgrid HVAC system control and speed
up learning of unknown power system conditions.
Data Science for Building Energy Management a reviewMigue.docxrandyburney60861
Data Science for Building Energy Management: a review
Miguel Molina-Solanaa,b, Maŕıa Rosa,∗, M. Dolores Ruiza, Juan Gómez-Romeroa, M.J. Martin-Bautistaa
aDepartment of Computer Science and Artificial Intelligence, Universidad de Granada
bData Science Institute, Imperial College London
Abstract
The energy consumption of residential and commercial buildings has risen steadily in recent years, an
increase largely due to their HVAC systems. Expected energy loads, transportation, and storage as well
as user behavior influence the quantity and quality of the energy consumed daily in buildings. However,
technology is now available that can accurately monitor, collect, and store the huge amount of data involved
in this process. Furthermore, this technology is capable of analyzing and exploiting such data in meaningful
ways. Not surprisingly, the use of data science techniques to increase energy efficiency is currently attracting
a great deal of attention and interest. This paper reviews how Data Science has been applied to address the
most difficult problems faced by practitioners in the field of Energy Management, especially in the building
sector. The work also discusses the challenges and opportunities that will arise with the advent of fully
connected devices and new computational technologies.
1. Introduction
There is a general consensus in the world today that human activities are having a negative impact
on the environment and have accelerated both global warming and climate change. These environmental
threats have been intensified by the emissions produced by the energy required for the lighting and HVAC
(heating, ventilation and air-conditioning) systems in building constructions. According to the International
Energy Agency (IEA), residential and commercial buildings are responsible for up to 32% of the total final
energy consumption. In fact, in most IEA countries, they account for approximately 40% of the primary
energy consumption. Similar statistics are given by the World Business Council for Sustainable Development
(WBCSD) within the framework of its Energy Efficiency in Buildings (EEB) project1. Also provided is a
comprehensive review [1] of the state of the art in building energy use (with a primary focus on energy
demand).
These data indicate that inefficient energy management in aging buildings combined with rising construc-
tion activity in developed countries will cause energy consumption to soar in the near future and heighten the
negative impacts associated with this consumption. Moreover, variable energy costs call for the implemen-
tation of more intelligent strategies to adapt and reduce energy consumption as well as to find alternative
and sustainable energy sources. The relevance of these issues is clearly reflected in the research priorities of
the European Union, as stated in its Horizon2020 Societal Challenge “Secure, Clean and Efficient Energy”.
This work program targets a significant reduction in energy consu.
IRJET- Impact and Control Study of LV Communication Networks with PV Pene...IRJET Journal
This document summarizes a study on the impact and control of low voltage communication networks with photovoltaic-integrated microgrids. The study designs a new smart microgrid system model using power line communication infrastructure. It contains distributed energy resources like photovoltaics and electric vehicles. The system is simulated in Matlab. Simulation results examine power quality under different microgrid situations when integrating photovoltaics as a distributed resource.
A new smart approach of an efficient energy consumption management by using a...IJEECSIAES
Many consumers of electric power have excesses in their electric power consumptions that exceed the permissible limit by the electrical power distribution stations, and then we proposed a validation approach that works intelligently by applying machine learning (ML) technology to teach electrical consumers how to properly consume without wasting energy expended. The validation approach is one of a large combination of intelligent processes related to energy consumption which is called the efficient energy consumption management (EECM) approaches, and it connected with the internet of things (IoT) technology to be linked to Google Firebase Cloud where a utility center used to check whether the consumption of the efficient energy is satisfied. It divides the measured data for actual power (Ap) of the electrical model into two portions: the training portion is selected for different maximum actual powers, and the validation portion is determined based on the minimum output power consumption and then used for comparison with the actual required input power. Simulation results show the energy expenditure problem can be solved with good accuracy in energy consumption by reducing the maximum rate (Ap) in a given time (24) hours for a single house, as well as electricity’s bill cost, is reduced.
A new smart approach of an efficient energy consumption management by using a...nooriasukmaningtyas
This document proposes a new smart approach for efficient energy consumption management using machine learning techniques. It divides measured actual power data into training and validation portions to determine efficient energy consumption. Simulation results showed the approach can accurately reduce energy consumption and costs by lowering the maximum allowed power consumption over a 24-hour period for a single house. The approach connects to cloud services and uses Internet of Things technologies for real-time energy monitoring.
Integrated Energy System Modeling of China for 2020 by Incorporating Demand R...Kashif Mehmood
Electricity and heat energy carriers are mostly produced by the fossil fuel sources that are
conventionally operated independently, but these carriers have low efficiency due to heat losses. Moreover,
a high share of variable renewable energy sources disrupts the power system reliability and flexibility.
Therefore, the coupling of multiple energy carriers is underlined to address the above-mentioned issues that
are supported by the latest technologies, such as combined heat and power, heat pumps, demand response,
and energy storages. These coupling nodes in energy hubs stimulate the conversion of the electric power
system into the integrated energy system that proves to be cost-effective, flexible, and carbon-free. The
proposed work uses EnergyPLAN to model electricity, district, and individual heating integrated energy
system of China for the year 2020. Furthermore, the addition of heat pumps, thermal storage, and demand
response is analyzed in different scenarios to minimize the annual costs, fuel consumption, and CO2
emissions. Technical simulation strategy is conducted for optimal operation of production components that
result in the reduction of the above-mentioned prominent factors while calculating the critical and exportable
excess electricity production. The simulation results demonstrate that demand response and thermal storage
significantly enhance the share of variable renewable energy sources. In addition, it substantially reduces the
annual costs and fuel consumption, while heat pump increases the system efficiency
Achieving Energy Proportionality In Server ClustersCSCJournals
a great amount of interests in the past few years. Energy proportionality is a principal to ensure that energy consumption is proportional to the system workload. Energy proportional design can effectively improve energy efficiency of computing systems. In this paper, an energy proportional model is proposed based on queuing theory and service differentiation in server clusters, which can provide controllable and predictable quantitative control over power consumption with theoretically guaranteed service performance. Futher study for the transition overhead is carried out corresponding strategy is proposed to compensate the performance degradation caused by transition overhead. The model is evaluated via extensive simulations and is justified by the real workload data trace. The results show that our model can achieve satisfied service performance while still preserving energy efficiency in the system.
IRJET- Reducing electricity usage in Internet using transactional dataIRJET Journal
This document summarizes a research paper that proposes a method to reduce electricity usage and costs for internet services by optimizing how transactional data is mapped across geographically distributed data centers. It formulates the problem as a stochastic programming problem to maximize energy utilization within a cost budget. An efficient online algorithm is developed using Lyapunov optimization to map user requests to data centers based on changing factors like electricity prices and workload, with the goal of significantly reducing costs compared to baseline strategies. The system architecture involves front-end servers collecting user requests and dispatching them to appropriate back-end data centers for processing.
Energy Efficient Technologies for Virtualized Cloud Data Center: A Systematic...IRJET Journal
This document summarizes a systematic mapping study and literature review of 74 peer-reviewed articles on energy efficient technologies for virtualized cloud data centers. The study aims to evaluate approaches that optimize power consumption in virtualized data centers. A characterization framework was proposed to classify the studies based on generic attributes, contribution type and evaluation method, technological attributes, and quality management. The results showed that virtualization, consolidation, and workload scheduling are widely used techniques. Around 60% of studies contributed solutions and validation methods through experiments or theoretical models. Dynamic voltage and frequency scaling-enabled scheduling and dynamic server consolidation were identified as important methods for saving energy. The study also identified a need for standardized benchmarking to help research progress and bridge industry-academia gaps
This document describes a research project that aims to develop a web-based system to automatically calculate and visualize large-scale energy performance maps of residential buildings in a city. The system would use existing data sources, an extended version of the TABULA/EPISCOPE project for calculating building energy parameters, and CityGML and WebGL standards for data storage and visualization. Preliminary results are presented for a service that assesses building energy performance at scale and visualizes the results in an intuitive 3D interface to help citizens, governments, and organizations analyze building energy efficiency across a city.
Data Driven Energy Economy Prediction for Electric City Buses Using Machine L...Shakas Technologies
Data Driven Energy Economy Prediction for Electric City Buses Using Machine Learning.
Shakas Technologies ( Galaxy of Knowledge)
#11/A 2nd East Main Road,
Gandhi Nagar,
Vellore - 632006.
Mobile : +91-9500218218 / 8220150373| land line- 0416- 3552723
Shakas Training & Development | Shakas Sales & Services | Shakas Educational Trust|IEEE projects | Research & Development | Journal Publication |
Email : info@shakastech.com | shakastech@gmail.com |
website: www.shakastech.com
Facebook: https://www.facebook.com/pages/Shakas-Technologies
An Overview of the Home Energy Management Systems Considering Different Types...IRJET Journal
This document provides an overview of home energy management systems (HEMS), including their architecture, components, and power scheduling strategies. It discusses how HEMS can optimize household appliance scheduling to reduce electricity costs and peak demand while maintaining user comfort. Various power scheduling techniques for HEMS are reviewed, such as optimization algorithms, fuzzy logic control, and mixed-integer nonlinear optimization. The document also compares different types of demand response programs that can be integrated with HEMS for dynamic energy management.
IRJET- An Energy Conservation Scheme based on Tariff ModerationIRJET Journal
This document discusses an energy conservation scheme based on tariff modification for domestic users. It proposes a new tariff rate structure that provides incentives for low consumption and penalties for high consumption. This aims to motivate consumers to reduce energy usage without causing losses for electric utilities. The existing structure provides 100 free units, which does not encourage conservation and causes losses. The proposed system calculates bills based on consumed units and compares to averages to determine incentives or penalties. The goal is to reduce residential energy usage through this modified tariff approach.
IRJET- Generation Planning using WASP SoftwareIRJET Journal
This document discusses determining the optimal power generation development plan for a power system over the next 15 years using the WASP software. It begins by estimating the system load over the planning period based on historical load data from the past 36 years. It then uses the WASP software to determine all possible supply combinations from the existing and planned generating units and selects the combination that minimizes costs and meets reliability criteria. The optimal plan is determined by changing the configuration and timing of added units each year to find the best objective function. Key steps include load forecasting, defining development units and constraints, using WASP modules to evaluate combinations and reliability, and selecting the optimal plan through dynamic programming.
An optimized cost-based data allocation model for heterogeneous distributed ...IJECEIAES
The document presents an optimized cost-based data allocation model for heterogeneous distributed computing systems. It aims to reduce the total system cost by optimizing how data is partitioned and allocated across different processors. The proposed approach uses an artificial bee colony algorithm to determine the allocation that minimizes the total cost, which is calculated by summing the costs of communication, computation, and network usage. Simulation results show the technique is able to efficiently lower the total system cost compared to existing methods and optimize the partitioned data allocation in heterogeneous distributed computing systems.
A modular framework to enable rapid evaluation and exploration of energy mana...Nancy Ideker
The document presents a modular transaction-level modeling framework for enabling rapid evaluation and exploration of energy management methods in smart home platforms. The framework allows designers to focus on specific sub-components without requiring detailed implementation across all levels. Two case studies are described where the framework is used to evaluate platform configurations given an energy usage model and integrate an energy optimization module to investigate rescheduling appliance usage times to lower costs.
The document discusses using machine learning techniques to predict power factor variations in an electrical power system of a cement plant factory. It aims to replace existing real-time monitoring techniques, which are costly, with machine learning models to predict power factor. This can help reduce errors, maintenance costs, and improve system reliability in a more cost-effective way. The document also reviews various literature on load forecasting and power demand prediction using techniques like neural networks and deep learning.
Characterization of electricity demand based on energy consumption data from ...IJECEIAES
The development of dynamic energy distribution grids to optimize energy resources has become very important at the international level in recent years. A very important step in this development is to be able to characterize the population based on their consumption behaviour. However, traditional consumption meters that report information at a monthly rate provide little information for in-depth analysis. In Colombia, this has changed in recent years due to the implementation and integration of advanced metering infrastructure (AMI). This infrastructure allows to record consumption values in small time intervals, and the available data then allows for the execution of many analysis mechanisms. In this paper we present an analysis of the electricity demand profile from a new dataset of energy consumption in Colombia. A characterization of the users demand profiles is presented using a k-means clustering procedure. Whit this customer segmentation technique we show that is possible identify customer consumption patterns and to identify anomalies in the system. In addition, this type of analysis also allows to assess changes in the consumption pattern of users due to social measures such as those resulting from the coronavirus disease (COVID-19) pandemic.
1) The document proposes a two-stage classification method for improving energy disaggregation accuracy during non-intrusive load monitoring.
2) The first stage uses multiple classification models in parallel to process the aggregated signal and produce a binary detection score for each device.
3) The second stage uses fusion regression models to estimate the power consumption for each electrical appliance based on the outputs of the first stage.
4) The method was tested on three public datasets and showed improvements in estimation accuracy up to 4.1% overall and 10.1% for some devices, particularly continuous and nonlinear appliances.
Stochastic control for optimal power flow in islanded microgridIJECEIAES
The problem of optimal power flow (OPF) in an islanded mircrogrid (MG) for hybrid power system is described. Clearly, it deals with a formulation of an analytical control model for OPF. The MG consists of wind turbine generator, photovoltaic generator, and diesel engine generator (DEG), and is in stochastic environment such as load change, wind power fluctuation, and sun irradiation power disturbance. In fact, the DEG fails and is repaired at random times so that the MG can significantly influence the power flow, and the power flow control faces the main difficulty that how to maintain the balance of power flow? The solution is that a DEG needs to be scheduled. The objective of the control problem is to find the DEG output power by minimizing the total cost of energy. Adopting the Rishel’s famework and using the Bellman principle, the optimality conditions obtained satisfy the Hamilton-Jacobi-Bellman equation. Finally, numerical examples and sensitivity analyses are included to illustrate the importance and effectiveness of the proposed model.
Energy Optimization of public and social housing buildings using ICT based se...CIMNE
The research will focus on two types of buildings: residential buildings and public buildings. The research plan covers the aspects of defining the ICT based energy management services to be offered, the architecture definition of the systems, definition of the methodology to evaluate energy savings and user behaviour changes and the analysis of the achieved outputs of pilot buildings in real operation conditions.
The document discusses methods for short-term forecasting of electric energy consumption in smart buildings. It compares statistical and machine learning approaches using data from 13 buildings on a university campus in Spain. The best performing methods were ensemble machine learning approaches like bagging and boosting, which were able to more accurately predict energy consumption over the next day compared to statistical models. The study also found that using over 7 days of historical data led to better predictions.
PVPF tool: an automated web application for real-time photovoltaic power fore...IJECEIAES
1) The document describes PVPF tool, a web application that provides 24-hour ahead forecasts of photovoltaic power production based on real-time weather data and a pre-trained machine learning system.
2) The tool imports temperature, solar irradiance, and PV production measurement data from the ASU weather station and a PV installation. This data is processed and fed into a neural network trained using the Bayesian Regularization algorithm.
3) Hourly power production forecasts for the next 24 hours are published in real-time on the renewable energy center's website as a power/time curve, along with actual measured production values once available.
A survey to harness an efficient energy in cloud computingijujournal
Cloud computing affords huge potential for dynamism, flexibility and cost-effective IT operations. Cloud computing requires many tasks to be executed by the provided resources to achieve good performance, shortest response time and high utilization of resources. To achieve these challenges there is a need to develop a new energy aware scheduling algorithm that outperform appropriate allocation map of task to
optimize energy consumption. This study accomplished with all the existing techniques mainly focus on reducing energy consumption.
A SURVEY: TO HARNESS AN EFFICIENT ENERGY IN CLOUD COMPUTINGijujournal
Cloud computing affords huge potential for dynamism, flexibility and cost-effective IT operations. Cloud computing requires many tasks to be executed by the provided resources to achieve good performance, shortest response time and high utilization of resources. To achieve these challenges there is a need to develop a new energy aware scheduling algorithm that outperform appropriate allocation map of task to optimize energy consumption. This study accomplished with all the existing techniques mainly focus on reducing energy consumption.
A SURVEY: TO HARNESS AN EFFICIENT ENERGY IN CLOUD COMPUTINGijujournal
This document summarizes various techniques for improving energy efficiency in cloud computing. It begins with an introduction to energy consumption problems in cloud computing such as energy sprawl and increased electricity costs. It then reviews 10 existing energy efficient models including workload consolidation, virtual machine power metering, renewable energy-aware migration, and energy-aware scheduling. Each model is evaluated based on the hardware/datasets used, tools, and parameters analyzed. The document concludes that while cloud computing can be more energy efficient, further technological solutions and enhanced frameworks are still needed to achieve optimal energy efficiency.
A SURVEY: TO HARNESS AN EFFICIENT ENERGY IN CLOUD COMPUTINGijujournal
Cloud computing affords huge potential for dynamism, flexibility and cost-effective IT operations. Cloud
computing requires many tasks to be executed by the provided resources to achieve good performance,
shortest response time and high utilization of resources. To achieve these challenges there is a need to
develop a new energy aware scheduling algorithm that outperform appropriate allocation map of task to
optimize energy consumption. This study accomplished with all the existing techniques mainly focus on
reducing energy consumption
A survey on energy efficient with task consolidation in the virtualized cloud...eSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
Energy Efficient Technologies for Virtualized Cloud Data Center: A Systematic...IRJET Journal
This document summarizes a systematic mapping study and literature review of 74 peer-reviewed articles on energy efficient technologies for virtualized cloud data centers. The study aims to evaluate approaches that optimize power consumption in virtualized data centers. A characterization framework was proposed to classify the studies based on generic attributes, contribution type and evaluation method, technological attributes, and quality management. The results showed that virtualization, consolidation, and workload scheduling are widely used techniques. Around 60% of studies contributed solutions and validation methods through experiments or theoretical models. Dynamic voltage and frequency scaling-enabled scheduling and dynamic server consolidation were identified as important methods for saving energy. The study also identified a need for standardized benchmarking to help research progress and bridge industry-academia gaps
This document describes a research project that aims to develop a web-based system to automatically calculate and visualize large-scale energy performance maps of residential buildings in a city. The system would use existing data sources, an extended version of the TABULA/EPISCOPE project for calculating building energy parameters, and CityGML and WebGL standards for data storage and visualization. Preliminary results are presented for a service that assesses building energy performance at scale and visualizes the results in an intuitive 3D interface to help citizens, governments, and organizations analyze building energy efficiency across a city.
Data Driven Energy Economy Prediction for Electric City Buses Using Machine L...Shakas Technologies
Data Driven Energy Economy Prediction for Electric City Buses Using Machine Learning.
Shakas Technologies ( Galaxy of Knowledge)
#11/A 2nd East Main Road,
Gandhi Nagar,
Vellore - 632006.
Mobile : +91-9500218218 / 8220150373| land line- 0416- 3552723
Shakas Training & Development | Shakas Sales & Services | Shakas Educational Trust|IEEE projects | Research & Development | Journal Publication |
Email : info@shakastech.com | shakastech@gmail.com |
website: www.shakastech.com
Facebook: https://www.facebook.com/pages/Shakas-Technologies
An Overview of the Home Energy Management Systems Considering Different Types...IRJET Journal
This document provides an overview of home energy management systems (HEMS), including their architecture, components, and power scheduling strategies. It discusses how HEMS can optimize household appliance scheduling to reduce electricity costs and peak demand while maintaining user comfort. Various power scheduling techniques for HEMS are reviewed, such as optimization algorithms, fuzzy logic control, and mixed-integer nonlinear optimization. The document also compares different types of demand response programs that can be integrated with HEMS for dynamic energy management.
IRJET- An Energy Conservation Scheme based on Tariff ModerationIRJET Journal
This document discusses an energy conservation scheme based on tariff modification for domestic users. It proposes a new tariff rate structure that provides incentives for low consumption and penalties for high consumption. This aims to motivate consumers to reduce energy usage without causing losses for electric utilities. The existing structure provides 100 free units, which does not encourage conservation and causes losses. The proposed system calculates bills based on consumed units and compares to averages to determine incentives or penalties. The goal is to reduce residential energy usage through this modified tariff approach.
IRJET- Generation Planning using WASP SoftwareIRJET Journal
This document discusses determining the optimal power generation development plan for a power system over the next 15 years using the WASP software. It begins by estimating the system load over the planning period based on historical load data from the past 36 years. It then uses the WASP software to determine all possible supply combinations from the existing and planned generating units and selects the combination that minimizes costs and meets reliability criteria. The optimal plan is determined by changing the configuration and timing of added units each year to find the best objective function. Key steps include load forecasting, defining development units and constraints, using WASP modules to evaluate combinations and reliability, and selecting the optimal plan through dynamic programming.
An optimized cost-based data allocation model for heterogeneous distributed ...IJECEIAES
The document presents an optimized cost-based data allocation model for heterogeneous distributed computing systems. It aims to reduce the total system cost by optimizing how data is partitioned and allocated across different processors. The proposed approach uses an artificial bee colony algorithm to determine the allocation that minimizes the total cost, which is calculated by summing the costs of communication, computation, and network usage. Simulation results show the technique is able to efficiently lower the total system cost compared to existing methods and optimize the partitioned data allocation in heterogeneous distributed computing systems.
A modular framework to enable rapid evaluation and exploration of energy mana...Nancy Ideker
The document presents a modular transaction-level modeling framework for enabling rapid evaluation and exploration of energy management methods in smart home platforms. The framework allows designers to focus on specific sub-components without requiring detailed implementation across all levels. Two case studies are described where the framework is used to evaluate platform configurations given an energy usage model and integrate an energy optimization module to investigate rescheduling appliance usage times to lower costs.
The document discusses using machine learning techniques to predict power factor variations in an electrical power system of a cement plant factory. It aims to replace existing real-time monitoring techniques, which are costly, with machine learning models to predict power factor. This can help reduce errors, maintenance costs, and improve system reliability in a more cost-effective way. The document also reviews various literature on load forecasting and power demand prediction using techniques like neural networks and deep learning.
Characterization of electricity demand based on energy consumption data from ...IJECEIAES
The development of dynamic energy distribution grids to optimize energy resources has become very important at the international level in recent years. A very important step in this development is to be able to characterize the population based on their consumption behaviour. However, traditional consumption meters that report information at a monthly rate provide little information for in-depth analysis. In Colombia, this has changed in recent years due to the implementation and integration of advanced metering infrastructure (AMI). This infrastructure allows to record consumption values in small time intervals, and the available data then allows for the execution of many analysis mechanisms. In this paper we present an analysis of the electricity demand profile from a new dataset of energy consumption in Colombia. A characterization of the users demand profiles is presented using a k-means clustering procedure. Whit this customer segmentation technique we show that is possible identify customer consumption patterns and to identify anomalies in the system. In addition, this type of analysis also allows to assess changes in the consumption pattern of users due to social measures such as those resulting from the coronavirus disease (COVID-19) pandemic.
1) The document proposes a two-stage classification method for improving energy disaggregation accuracy during non-intrusive load monitoring.
2) The first stage uses multiple classification models in parallel to process the aggregated signal and produce a binary detection score for each device.
3) The second stage uses fusion regression models to estimate the power consumption for each electrical appliance based on the outputs of the first stage.
4) The method was tested on three public datasets and showed improvements in estimation accuracy up to 4.1% overall and 10.1% for some devices, particularly continuous and nonlinear appliances.
Stochastic control for optimal power flow in islanded microgridIJECEIAES
The problem of optimal power flow (OPF) in an islanded mircrogrid (MG) for hybrid power system is described. Clearly, it deals with a formulation of an analytical control model for OPF. The MG consists of wind turbine generator, photovoltaic generator, and diesel engine generator (DEG), and is in stochastic environment such as load change, wind power fluctuation, and sun irradiation power disturbance. In fact, the DEG fails and is repaired at random times so that the MG can significantly influence the power flow, and the power flow control faces the main difficulty that how to maintain the balance of power flow? The solution is that a DEG needs to be scheduled. The objective of the control problem is to find the DEG output power by minimizing the total cost of energy. Adopting the Rishel’s famework and using the Bellman principle, the optimality conditions obtained satisfy the Hamilton-Jacobi-Bellman equation. Finally, numerical examples and sensitivity analyses are included to illustrate the importance and effectiveness of the proposed model.
Energy Optimization of public and social housing buildings using ICT based se...CIMNE
The research will focus on two types of buildings: residential buildings and public buildings. The research plan covers the aspects of defining the ICT based energy management services to be offered, the architecture definition of the systems, definition of the methodology to evaluate energy savings and user behaviour changes and the analysis of the achieved outputs of pilot buildings in real operation conditions.
The document discusses methods for short-term forecasting of electric energy consumption in smart buildings. It compares statistical and machine learning approaches using data from 13 buildings on a university campus in Spain. The best performing methods were ensemble machine learning approaches like bagging and boosting, which were able to more accurately predict energy consumption over the next day compared to statistical models. The study also found that using over 7 days of historical data led to better predictions.
PVPF tool: an automated web application for real-time photovoltaic power fore...IJECEIAES
1) The document describes PVPF tool, a web application that provides 24-hour ahead forecasts of photovoltaic power production based on real-time weather data and a pre-trained machine learning system.
2) The tool imports temperature, solar irradiance, and PV production measurement data from the ASU weather station and a PV installation. This data is processed and fed into a neural network trained using the Bayesian Regularization algorithm.
3) Hourly power production forecasts for the next 24 hours are published in real-time on the renewable energy center's website as a power/time curve, along with actual measured production values once available.
A survey to harness an efficient energy in cloud computingijujournal
Cloud computing affords huge potential for dynamism, flexibility and cost-effective IT operations. Cloud computing requires many tasks to be executed by the provided resources to achieve good performance, shortest response time and high utilization of resources. To achieve these challenges there is a need to develop a new energy aware scheduling algorithm that outperform appropriate allocation map of task to
optimize energy consumption. This study accomplished with all the existing techniques mainly focus on reducing energy consumption.
A SURVEY: TO HARNESS AN EFFICIENT ENERGY IN CLOUD COMPUTINGijujournal
Cloud computing affords huge potential for dynamism, flexibility and cost-effective IT operations. Cloud computing requires many tasks to be executed by the provided resources to achieve good performance, shortest response time and high utilization of resources. To achieve these challenges there is a need to develop a new energy aware scheduling algorithm that outperform appropriate allocation map of task to optimize energy consumption. This study accomplished with all the existing techniques mainly focus on reducing energy consumption.
A SURVEY: TO HARNESS AN EFFICIENT ENERGY IN CLOUD COMPUTINGijujournal
This document summarizes various techniques for improving energy efficiency in cloud computing. It begins with an introduction to energy consumption problems in cloud computing such as energy sprawl and increased electricity costs. It then reviews 10 existing energy efficient models including workload consolidation, virtual machine power metering, renewable energy-aware migration, and energy-aware scheduling. Each model is evaluated based on the hardware/datasets used, tools, and parameters analyzed. The document concludes that while cloud computing can be more energy efficient, further technological solutions and enhanced frameworks are still needed to achieve optimal energy efficiency.
A SURVEY: TO HARNESS AN EFFICIENT ENERGY IN CLOUD COMPUTINGijujournal
Cloud computing affords huge potential for dynamism, flexibility and cost-effective IT operations. Cloud
computing requires many tasks to be executed by the provided resources to achieve good performance,
shortest response time and high utilization of resources. To achieve these challenges there is a need to
develop a new energy aware scheduling algorithm that outperform appropriate allocation map of task to
optimize energy consumption. This study accomplished with all the existing techniques mainly focus on
reducing energy consumption
A survey on energy efficient with task consolidation in the virtualized cloud...eSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
Similar to Physical-data_Fusion_Modeling_Method_for_Energy_Co.pdf (20)
Implementing ELDs or Electronic Logging Devices is slowly but surely becoming the norm in fleet management. Why? Well, integrating ELDs and associated connected vehicle solutions like fleet tracking devices lets businesses and their in-house fleet managers reap several benefits. Check out the post below to learn more.
Understanding Catalytic Converter Theft:
What is a Catalytic Converter?: Learn about the function of catalytic converters in vehicles and why they are targeted by thieves.
Why are They Stolen?: Discover the valuable metals inside catalytic converters (such as platinum, palladium, and rhodium) that make them attractive to criminals.
Steps to Prevent Catalytic Converter Theft:
Parking Strategies: Tips on where and how to park your vehicle to reduce the risk of theft, such as parking in well-lit areas or secure garages.
Protective Devices: Overview of various anti-theft devices available, including catalytic converter locks, shields, and alarms.
Etching and Marking: The benefits of etching your vehicle’s VIN on the catalytic converter or using a catalytic converter marking kit to make it traceable and less appealing to thieves.
Surveillance and Monitoring: Recommendations for using security cameras and motion-sensor lights to deter thieves.
Statistics and Insights:
Theft Rates by Borough: Analysis of data to determine which borough in NYC experiences the highest rate of catalytic converter thefts.
Recent Trends: Current trends and patterns in catalytic converter thefts to help you stay aware of emerging hotspots and tactics used by thieves.
Benefits of This Presentation:
Awareness: Increase your awareness about catalytic converter theft and its impact on vehicle owners.
Practical Tips: Gain actionable insights and tips to effectively prevent catalytic converter theft.
Local Insights: Understand the specific risks in different NYC boroughs, helping you take targeted preventive measures.
This presentation aims to equip you with the knowledge and tools needed to protect your vehicle from catalytic converter theft, ensuring you are prepared and proactive in safeguarding your property.
Expanding Access to Affordable At-Home EV Charging by Vanessa WarheitForth
Vanessa Warheit, Co-Founder of EV Charging for All, gave this presentation at the Forth Addressing The Challenges of Charging at Multi-Family Housing webinar on June 11, 2024.
Charging and Fueling Infrastructure Grant: Round 2 by Brandt HertensteinForth
Brandt Hertenstein, Program Manager of the Electrification Coalition gave this presentation at the Forth and Electrification Coalition CFI Grant Program - Overview and Technical Assistance webinar on June 12, 2024.
Dahua provides a comprehensive guide on how to install their security camera systems. Learn about the different types of cameras and system components, as well as the installation process.
Charging Fueling & Infrastructure (CFI) Program Resources by Cat PleinForth
Cat Plein, Development & Communications Director of Forth, gave this presentation at the Forth and Electrification Coalition CFI Grant Program - Overview and Technical Assistance webinar on June 12, 2024.
Charging Fueling & Infrastructure (CFI) Program by Kevin MillerForth
Kevin Miller, Senior Advisor, Business Models of the Joint Office of Energy and Transportation gave this presentation at the Forth and Electrification Coalition CFI Grant Program - Overview and Technical Assistance webinar on June 12, 2024.
EV Charging at MFH Properties by Whitaker JamiesonForth
Whitaker Jamieson, Senior Specialist at Forth, gave this presentation at the Forth Addressing The Challenges of Charging at Multi-Family Housing webinar on June 11, 2024.
1. JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY, VOL. 10, NO. 2, March 2022
Physical-data Fusion Modeling Method for Energy
Consumption Analysis of Smart Building
Xiao Han, Chaohai Zhang, Yi Tang, and Yujian Ye
Abstract—
—The energy consumption of buildings accounts for
approximately 40% of total energy consumption. An accurate
energy consumption analysis of buildings can not only promise
significant energy savings but also help estimate the demand re‐
sponse potential more accurately, and consequently brings bene‐
fits to the upstream power grid. This paper proposes a novel
physical-data fusion modeling (PFM) method for modeling
smart buildings that can accurately assess energy consumption.
First, a thermal process model of buildings and an electrical
load model that focus on building heating, ventilation, and air
conditioning (HVAC) systems are presented to analyze the ther‐
mal-electrical conversion process of energy consumption of
buildings. Second, the PFM method is used to improve the accu‐
racy of the energy consumption analysis model for buildings by
modifying the parameters that are difficult to measure in the
physical model (i. e., it effectively modifies the electrical load
model based on the proposed PFM method). Finally, case stud‐
ies involving a real-world dataset recorded in a high-tech park
in Changzhou, China, demonstrate that the proposed method
exhibits superior performance with respect to the traditional
physical modeling (TPM) method and data-driven modeling
(DDM) method in terms of the achieved accuracy.
Index Terms—
—Smart building, physical-data fusion modeling
method, energy consumption, precision model, thermal-electri‐
cal conversion.
I. INTRODUCTION
WITH the continuous increase in urbanization and in‐
dustrial restructuring, the energy consumption of
buildings in urban cities has increased rapidly over the
world [1], [2]. According to [3], the energy consumption of
buildings accounts for 40% of total energy consumption, and
approximately 80% of energy consumption of buildings is at‐
tributed to heating, ventilation, and air conditioning (HVAC)
systems [3], [4]. Therefore, driven by the rapid development
and deployment of smart sensors, information, communica‐
tion, and artificial intelligence (AI) technologies [5], the en‐
ergy consumption of smart buildings can be analyzed and
evaluated more accurately to achieve energy conservation
[6], [7]. As a result, it promises a significant demand re‐
sponse potential to support the secure and economic opera‐
tion of power grids [8], [9].
With the advances in physical measurement tools and
monitoring systems for buildings, the energy consumption
can be measured more accurately [10]. Modeling methods
for energy consumption of buildings can be classified into
three types, i. e., physical modeling methods, data-driven
modeling (DDM) methods, and physical-data fusion model‐
ing (PFM) methods [11].
Physical modeling methods can be further subdivided into
simplified and precise physical models [12]. Simplified phys‐
ical models make certain assumptions and simplify the com‐
plex physical processes in building operations, such as the
interaction of internal areas, thermal processes, and air con‐
vection [13]. These modeling methods also neglect many
physical quantities that are difficult to be measured such as
the heat exchange coefficient and energy efficiency ratio
(EER) of HVAC systems. In addition, the simplified physi‐
cal models are not very scalable. Therefore, they pose con‐
siderable challenges in accurately accounting for the time-
varying thermal-electrical conversion process of a building,
which leads to poor generalization performances.
Precise modeling methods construct the models for ther‐
mal processes, fluids, and electrical equipment of buildings
and then combine them to build complex physical process
models. Therefore, a precise physical model is generally im‐
plemented using available commercial software such as
eQUEST, PowerDOE, DeST, and FloVENT [14], which par‐
tially consider certain complexities associated with the physi‐
cal models of buildings. However, these software programs
have certain limitations.
1) The time-varying characteristics of building informa‐
tion at multiple time scales are not properly considered in
these programs [15].
2) The energy consumption analysis of buildings may re‐
quire the use and coordination of multiple software pro‐
grams, which are assigned different tasks according to their
design features.
Reference [16] uses eQUEST to simulate the energy con‐
sumption of buildings and then uses FloVENT to simulate
the heat distribution in the internal area of buildings. Both
software programs are limited in their abilities to consider
Manuscript received: January 23, 2021; revised: June 1, 2021; accepted: No‐
vember 3, 2021. Date of Cross Check: November 3, 2021. Date of online publi‐
cation: February 4, 2022.
This work was supported in part by the National Natural Science Foundation
of China (No. 51877037).
This article is distributed under the terms of the Creative Commons Attribu‐
tion 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
X. Han and C. Zhang (corresponding author) are with the Jiangsu Key Labo‐
ratory of New Energy Generation and Power Conversion, Nanjing University of
Aeronautics and Astronautics, Nanjing 211106, China (e-mail: hanxiao0625@
163.com; zhangchaohai@nuaa.edu.cn).
Y. Tang is with the School of Electrical Engineering, Southeast University,
Nanjing 210096, China (e-mail: tangyi@seu.edu.cn).
Y. Ye is with the Department of Electrical and Electronic Engineering, Imperi‐
al College London, London, U.K. (e-mail: yujian.ye11@imperial.ac.uk).
DOI: 10.35833/MPCE.2021.000050
482
2. HAN et al.: PHYSICAL-DATA FUSION MODELING METHOD FOR ENERGY CONSUMPTION ANALYSIS OF SMART BUILDING
the effects of critical aspects such as the social and behavior‐
al factors of building residents on building modeling tasks.
DDM or statistical modeling methods are based on vari‐
ous statistical or machine learning methods to describe or
predict the energy consumption of buildings through exten‐
sive real-time and historical measurement data. These meth‐
ods do not rely on the accurate modeling of physical charac‐
teristics of buildings [17], [18]. The data collection is usual‐
ly implemented through real-time online monitoring systems
such as the building energy management system (BEMS)
[19]. Through the collection of a large amount of environ‐
mental and electrical data by the BEMS, DDM methods can
achieve relatively high accuracy through extensive training
on large-scale datasets [20]. However, the training accuracy
of DDM methods can be significantly affected by the poor
data quality of the samples [2], [4].
The results of DDM methods mostly depend on the quali‐
ty of historical data. However, historical data have many
problems such as poor data quality and low data density,
which result in a loss of information. Consequently, the sup‐
port from sophisticated algorithms is required [21]. In [21],
an energy consumption modeling method is proposed to
solve the problem of lacking the information about build‐
ings, and the accuracy of this method is verified through its
application to multiple buildings. These buildings may have
the equipment that is missing or damaged or have communi‐
cation problems. Simultaneously, other cases may occur in
special scenarios such as with equipment maintenance and
during holidays, which may lead to not only missing data
but also incorrect data. In [22], a modeling method of data
relevance is considered, and the comprehensiveness of the
model is improved by integrating external information such
as the external environment, social policies, and user behav‐
iors. However, this method has poor physical interpretation
and is difficult to understand. In addition, there may be dif‐
ferent situations of incomplete information collection in dif‐
ferent environments, which is not considered in the DDM
methods for buildings. Furthermore, the accuracy of measure‐
ment data significantly affects the accuracy of the model.
Moreover, the calculation algorithm plays a key role in im‐
proving the accuracy of the model. In [17], a bicubic interpo‐
lation algorithm and convolutional neural network are used
for the spatial prediction of energy consumption. In [18], the
evolutionary algorithms are discussed to solve the model for
energy consumption of buildings. However, a heavy compu‐
tational burden makes it difficult to apply AI algorithms to
online analysis on the energy consumption of buildings. In
other words, the simplified online DDM methods neglect the
physical characteristics and causality of buildings.
Therefore, the main contribution of this study is to estab‐
lish a detailed physical model for smart buildings and ensure
that the energy consumption analysis is more precise by
modifying the model through a PFM method. The energy
consumption analysis model of buildings is based on the
PFM method, which considers not only the interpretation
ability of the physical mechanism but also the incidence rela‐
tion of DDM methods. Physical methods can provide high-
entropy information for DDM methods. In addition, physical
methods can ensure that the parameters of physical model
are more targeted and can prevent the modeling method
from falling into a partial learning space. The critical factor
is that an accurate analysis model for energy consumption of
buildings based on the PFM method does not require exten‐
sive training data and can be run online. Finally, the PFM
method has a high initial training accuracy rate, which
means that this method is more scalable. Therefore, a de‐
tailed and accurate physical model needs to be constructed
using DDM methods to compensate for the loss of rules de‐
rived from the simplification of physical processes.
The remainder of this paper is organized as follows. Sec‐
tion II presents the thermal process model that considers the
structures and internal thermal-electrical conversion process‐
es of buildings. Section III investigates a solution for im‐
proving the accuracy of the model, namely, a PFM method,
which is used first to modify the key parameters in the phys‐
ical model and then to determine the accuracy of the power
load model while also providing a replacement strategy. The
results of case studies are presented in Section IV, and con‐
clusions are given in Section V.
II. PRECISE PHYSICAL MODELS OF BUILDINGS
A. Dataset Collection of Buildings
The premise of establishing a precise energy consumption
analysis model for buildings is to create a comprehensive
and high-quality dataset. The dataset should include structur‐
al, environmental, electrical, and behavioral data of build‐
ings, as shown in Fig. 1.
In addition, with a large amount of heterogeneous data, it
is necessary to consider multiple time-scale characteristics
and perform data preprocessing.
The structural data of buildings mainly include measure‐
ment parameters such as area and floor height, structural pa‐
rameters such as orientation and shape, material parameters
such as roof materials, wall materials, and vent types, and
empirical parameters such as heat transfer coefficients and
specific heat capacities. Because most of this information is
static data, the data processing is not necessary. However,
problems of inaccurate measurement data and empirical pa‐
rameters often arise and affect the accuracy of physical mod‐
el. Therefore, a PFM method needs to be employed to solve
these problems.
Correspondingly, the environmental information, electrical
data, and behavioral data are dynamic parameters. These da‐
tasets can be collected by monitoring equipment such as cir‐
cuit breakers and smart plugs, intelligent sensors, and envi‐
ronmental monitoring devices installed both inside and out‐
side the building. The environmental data are categorized in‐
to external and internal environmental data. These data main‐
ly include temperature, humidity, light intensity, and climate
data, etc. The acquisition of these data can also be divided
into fixed-period collection and trigger-mode collection. The
trigger-mode collection means that some data such as CO2
concentration do not change considerably over a short peri‐
od. We only needs to wait until a significant change is de‐
tected before collecting the data. Electrical data include the
voltage, current, frequency, active power, reactive power,
and accumulated electrical energy collected by each electri‐
483
3. JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY, VOL. 10, NO. 2, March 2022
cal device and each power node, EER, and coefficient of per‐
formance (COP), personal computer (PC) load, photovoltaic
(PV), etc. Based on different types of electrical equipment,
the collection period can be set to be seconds, minutes, or
hours. Finally, the behavioral data include status data and op‐
erational logs of electrical equipment, doors, windows, and
other vents as well as personnel data for each area, running
scenarios, and others. Most of these data are collected in trig‐
ger mode.
B. Structural Model of Buildings
To establish a refined physical model of a building, it is
necessary to perform a detailed model of several internal ar‐
eas such as rooms and aisles in the entire building. In this
manner, the effects of the external environment and internal
areas of the building can be fully considered. Simultaneous‐
ly, this can also improve the accuracy of the thermal process
and energy consumption analysis. Therefore, this study con‐
structs two matrices to describe the structural relationships
and corresponding parameters of each internal area of a
building. The first is the structural association matrix of the
building, which is given as:
A(m)
nect =
é
ë
ê
ê
ê
ê
ê
ê
ê
ê
0 bven01 bven0n
bcon10 a1 bven1n
bconn0 bconn1 an
ù
û
ú
ú
ú
ú
ú
ú
ú
ú
(1)
where A(m)
nect is the internal structural association matrix of the
mth
building; ai is the property of the ith
area, which includes
rooms, open areas, corridors, etc; bconij denotes whether one
or more enclosure structures exist between the ith
and jth
ar‐
eas of the building; bvenji denotes whether one or more vent
structures exist between the jth
and ith
areas of the building;
and n is the number of areas in the building.
Next, the structural parameter matrix of the building is
given as (2), which provides detailed information about the
internal areas.
A(m)
parm =
é
ë
ê
ê
ê
ê
ê
ê
ê
ê
0 dven01 dven0n
dcon10 c1 dven1n
dconn0 dconn1 cn
ù
û
ú
ú
ú
ú
ú
ú
ú
ú
(2)
where A(m)
parm is the structural parameter matrix of the mth
building; ci contains the volume of the ith
area inside the
building; dconij and dvenji are the parameter matrices of the
enclosure structures and vents between the ith
and jth
areas,
respectively, as given in (3) and (4).
dconij =
é
ë
ê
ê
ê
ê
ê
ê
ê
ê
s1
conij h1
conij o1
conij r1
conij
s2
conij h2
conij o2
conij r2
conij
svc
conij hvc
conij ovc
conij rvc
conij
ù
û
ú
ú
ú
ú
ú
ú
ú
ú
(3)
dvenji =
é
ë
ê
ê
ê
ê
ê
ê
ê
ê
s1
venji h1
venji o1
venji r1
venji
s2
venji h2
venji o2
venji r2
venji
svv
venji hvv
venji ovv
venji rvv
venji
ù
û
ú
ú
ú
ú
ú
ú
ú
ú
(4)
where the superscripts vc and vv are the numbers of enve‐
lope structures and vents between the ith
and jth
areas of the
building, respectively; sconij, hconij, oconij, and rconij are the
acreage, heat transfer coefficient, material type, and orienta‐
tion of the envelope structures between the ith
and jth
areas
of the building, respectively; and svenji, hvenji, ovenji, and rvenji
are the acreage, heat transfer coefficient, material type, and
orientation of the vents between the ith
and jth
areas of the
building, respectively.
C. Thermal Process Model of Buildings
A dynamic thermal process model of a building needs to
be established based on the structural model of building. Tak‐
ing a single area inside the building as an example, the dy‐
namic thermal process of a single area refers to the heat
transfer process of internal and external disturbances, as
shown in Fig. 2. The external heat transfer qEXT includes the
outdoor environment (e.g., ambient temperature and solar ra‐
diation) and external thermal conditions (e.g., thermal condi‐
tions in adjacent areas). The external heat transfer mainly af‐
fects the internal temperature of the room through the heat
? Electrical data
?HVAC load
?Light load
?PC load
?Teakettle load
?Smart breakers
?Smart plugs
?EER/COP
?Structural data
?Building orientation
?Floor quantity
?Building shape
?Area connectivity
?Floor material
?Wall material
?On/off state
?Temperature setting
?Load mode
?Operating record
?Contextual model
?Turnover rate
? Environmental data
?Dry-bulb temperature
?Wet-bulb temperature
?Illumination
?Relative humidity
?Longitude and latitude
?Sun angle
?Climate
Space
Height
Temperature
Electricity
power
Location
HVAC
Light
PV
PC
Smart breaker
State
On/off
lights
On/off door
On/off windows
Length
Width
Roof material
?Usable area
? Behavioral data
?Time-of-use (TOU)
…
…
…
…
Sun light
Fig. 1. Dataset collection system of building.
484
4. HAN et al.: PHYSICAL-DATA FUSION MODELING METHOD FOR ENERGY CONSUMPTION ANALYSIS OF SMART BUILDING
transfer through the wall and other enclosure structures or
through windows and other vents. Indoor air is affected by
heat convection and heat radiation. By contrast, internal heat
transfer qINT includes latent heat and sensible heat of furni‐
ture, equipment, and human bodies. The latent heat of hu‐
man bodies and equipment directly acts on the air in an ar‐
ea, which can immediately devalue the air in the area. The
sensible heat of HVAC, lights, computers, and other equip‐
ment is directly transferred to indoor air through thermal
convection.
To obtain a refined thermal process model for each area
in a building, it is important to solve the partial differential
equations for heat transfer of the enclosure structure in each
area. In addition, the connectivity between regions needs to
be considered. The model of dynamic thermal process for a
single area is given as:
dTi (t)
dt
=
1
Ci ρici
(qEXTi (t)+ qINTi (t)) (5)
where Ti (t) is the temperature of the ith
area inside the build‐
ing at time t; dTi (t)/dt is the change of temperature in the ith
area inside the building at time t; Ci is the specific heat ca‐
pacity of air in the ith
area; ρi is the air density in the ith
ar‐
ea; qEXTi (t) is the heat transferred by the external disturbance
heat process in the ith
area at time t; and qINTi (t) is the heat
transferred by the internal disturbance heat process in the ith
area at time t.
Based on (5) and Fig. 2, the heat obtained by the external
disturbance can be further calculated using (6) - (9). Heat
transferred by the external disturbance heat process in build‐
ings mainly includes heat transfer from the enclosure struc‐
ture, vents, and sun radiation.
qEXTi (t)= qconi (t)+ qveni (t)+ qsuni (t) (6)
qconi (t)=
ì
í
î
ï
ï
ï
ï
ï
ï
ï
ï
ï
ï
ï
ï
∑
j = 0
n
∑
k = 1
Anect ( ji)
DT(t)∏
μ = 1
2
dconji (kμ) i j
∑
j = i + 1
n
∑
k = 1
Anect (ij)
DT(t)∏
μ = 1
2
dconij (kμ) i j
(7)
DT(t)= Tj (t)- Ti (t) (8)
qveni (t)=
ì
í
î
ï
ï
ï
ï
ï
ï
ï
ï
ï
ï
ï
ï
∑
j = 0
n
∑
k = 1
Anect( ji)
DT(t)∏
μ = 1
2
dvenji (kμ) j i
∑
j = i + 1
n
∑
k = 1
Anect(ij)
DT(t)∏
μ = 1
2
dvenij (kμ) j i
(9)
where qconi (t), qveni (t), and qsuni (t) are the heat transferred
from the external area to the ith
area through the enclosure
structure, vent, and solar radiation at time t, respectively,
and qsuni (t) is calculated by measuring the intensity of light
[23], [24]; DT(t) is the temperature difference between the ith
and jth
areas; and Anect(ij) and Anect( ji) are the numbers of en‐
closure structures and vents between the ith
and jth
areas in‐
side the building, respectively.
The heat transferred by the internal disturbance heat pro‐
cess in buildings mainly includes heat transfer from HVAC,
lights, personnel, and other equipment, as shown in (10).
qINTi (t)= qHVACi (t)+ qlighti (t)+ qpersi (t)+ qequii (t) (10)
where qHVACi (t), qlighti (t), qpersi (t), and qequii (t) are the heat
transferred from the HVAC, lights, personnel [23], and other
equipment to the ith
area at time t, respectively, and
qHVACi (t), qlighti (t), and qequii (t) are calculated by measuring
or predicting the power of the corresponding equipment.
D. Thermal-electrical Conversion Model of Buildings
To analyze the energy consumption of buildings, a ther‐
mal-electrical conversion model of buildings is established.
First, the total power calculation model for a building is giv‐
en as:
P(t)= ∑
i = 0
n
(PHVACi (t)+ Plighti (t)+ Pequii (t))- PPVi (t) (11)
ì
í
î
ï
ï
ï
ï
ï
ï
ï
ï
PHVACi (t)= gHVAC (KNPLVi xwsi ηi )qHVACi
Plighti (t)= glight (Klighti xstlighti )qlighti
Pequii (t)= gequi (Kequii xstequii )qequii
(12)
where PHVACi (t), Plighti (t), Pequii (t), and PPVi (t) are the elec‐
tric power of HVAC, lights, other equipment, and PV genera‐
tion in the ith
area at time t; gHVAC (×), glight (×), and gequi (×) are
the thermal-electric conversion coefficient functions for
HVAC, lights, and other equipment, respectively; KNPLVi,
Klighti, and Kequii are the thermal-electric conversion coeffi‐
cients of HVAC, lights, and other equipment in the ith
area,
respectively; xwsi, xstlighti, and xstequii are the operating states
of the HVAC, lights, and other equipment in the ith
area, re‐
spectively; and ηi is the thermal-electric conversion efficien‐
cy.
xws ={xmode xst xspeed } (13)
gHVAC (KNPLV xws η)= KNPLV (xmode )(1 + η(xspeed )) (14)
where xmode is the operating mode of HVAC (refrigeration,
heating, air supply); xst is the operating switch status (on/off)
of HVAC; xspeed is the wind speed of HVAC; and KNPLV,
Klight, and Kequi are the EER corresponding to HVAC, lights,
and other equipment, respectively, which indicates the inher‐
ent energy efficiency of equipment. Under the specific cir‐
cumstances, the EERs of different devices are differently de‐
fined. The calculation methods for the energy consumption
qven,i(t)
qsun,i(t)
qsun,j(t)
qcon,i(t)
qcon,j(t)
hcon,j0
ocon,j0
rcon,j0
scon,j0,
qpers,j(t)
qequi,j(t)
qHVAC,i(t)
Ti(t)
qEXT
qINT
qlight,j(t)
The ith area
The jth area
Fig. 2. Dynamic thermal process model for a building.
485
5. JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY, VOL. 10, NO. 2, March 2022
and power of other electrical loads (e.g., lights, water boil‐
ers, PCs) in buildings are similar, and the formulas are
shown as:
I(Γ)= ∑
i = 0
n
(IHVACi (Γ)+ Ilighti (Γ)+ Iequii (Γ))- IPVi (Γ) (15)
ì
í
î
ï
ï
ï
ï
ï
ï
ï
ï
ï
ï
ï
ï
IHVACi (Γ)= ∫Γ
PHVACi (t)dt
Ilighti (Γ)= ∫Γ
Plighti (t)dt
Iequii (Γ)= ∫Γ
Pequii (t)dt
(16)
where Γ is the period required to calculate the energy con‐
sumption; and IHVACi (Γ), Ilighti (Γ), Iequii (Γ), and IPVi (Γ) are
the energy consumptions of HVAC, lights, other equipment,
and PV generation in the ith
area during time period Γ, re‐
spectively.
III. PFM METHOD
A. PFM Algorithm
The basis of the PFM method is the fusion mode. The
physical analysis method can provide high-entropy informa‐
tion, which helps improve the efficiency of the data model
analysis. In other words, the input features contain the target
features to be predicted, which can narrow the search space
and reduce the computational complexity when solving the
parameters of data model through the optimization process.
However, the PFM method can be used to construct a better
data model with high-entropy input features, achieving the
goal of building a data model. This also ensures that the
model parameter optimization is more targeted. To avoid fall‐
ing into local optimization, the PFM method improves the ra‐
tionality of the data model. This approach can compensate
for the loss of physical discipline rules in physical analysis
methods due to the model simplification.
This study proposes two PFM correction methods. One
(method 1) modifies the key parameters in the physical mod‐
el through the DDM method; the other (method 2) replaces
the submodels in the PFM method through the model modifi‐
cation. The process flow of method 1 is shown in Fig. 3.
Feedback
Modification
K1
K2
fP
x1(τ), x2(τ),…
+
+
+
+
+
v
+
u
Physical model
Measurement Output Y(τ+1)
Output Y (τ+1)
x1(τ)
x2(τ)
,
K1
K2
fH
x1(τ)
x2(τ)
,
PFM
(Ω)
(Ω)
y1(τ+1)
y2(τ+2)
y1(τ+1)
y2(τ+2)
'
'
'
…
DDM
…
…
…
…
…
K(Ω)=fD(X(τ), K, [Y(τ+1), Y'(τ+1)])
Fig. 3. Process flow of method 1.
The PFM method for energy consumption analysis of
smart buildings requires the configuration of model parame‐
ters. The parameters include the static parameters that are in‐
put when the model is built and the dynamic parameters ob‐
tained in real-time collection when the model is running. In
this paper, the parameters of thermal-electrical conversion
model for a smart building that need to be modified mainly
include the heat exchange coefficient and EER. Therefore,
the final PFM can be obtained by guiding and correcting a
simple physical model using the measurement data. The
methodology for correcting the key parameters in the physi‐
cal model through a DDM method is given as:
Y'(τ + 1)= fP (X(τ)K)+ u = fH (X(τ)K(Ω)
)+ v (17)
K(Ω)
= fD (X(τ)K[Y(τ + 1)Y'(τ + 1)]) (18)
where fP and fD are the functions of physical model and
DDM methods, respectively; fH is the function of PFM meth‐
od, which uses the same algorithm as fP; X(τ) is the input da‐
taset of the model at time τ; Y(τ + 1) and Y'(τ + 1) are the out‐
put datasets of the model at time τ + 1; K is the parameter
vector in the model; K(Ω)
is the parameter vector after DDM
correction; and u and v are the random errors. In this study,
K(Ω)
may include the parameters such as the heat exchange
coefficient and EER.
Figure 4 depicts the process flow for modifying the ther‐
mal-electrical conversion model of the building using the
PFM (method 2). The physical and statistical mapping mod‐
els are represented by (19) and (20), respectively.
Y'(τ + 1)= fP (X(τ)K)+ u = f (Ω)
H (X(τ)K)+ v (19)
f (Ω)
H = fD (X(τ) K[Y(τ + 1)Y'(τ + 1)]) (20)
where f (Ω)
H is the function set of the modified PFM, which is
obtained after replacing the submodels with DDM. The re‐
placement method and selection mechanism of submodels in
PFM are later analyzed in detail in conjunction with the
building.
B. Key Parameter Modification Based on PFM
Based on the PFM method, this study divides the process
for energy consumption analysis of the building into two
steps. The first step involves modifying the key parameters
in the precise physical model through DDM method. The
second step involves modifying some of the submodels in
the entire energy consumption analysis model and then build‐
ing a model selection mechanism to improve the accuracy of
PFM. The overall process is shown in Fig. 5.
In Section II, a precise physical model of the building is
established. Next, the key parameter modification in a physi‐
cal model using DDM method is discussed. The parameters
to be modified include the heat transfer coefficient of enclo‐
sure structures and vents and the conversion efficiency of
HVAC. These parameters are difficult to be measured or cal‐
culated. For example, the heat transfer coefficient can be af‐
fected by the wall material, shape, aging degree, and other
factors.
Feedback
Modification
K1
K2
fP
x1(τ), x2(τ), …
+
+
+
+
v
+
u
Physical model
Measurement Output Y(τ+1)
Output Y (τ+1)
x1(τ)
x2(τ)
,
PFM
y1(τ+1)
x2(τ+2)
y1(τ+1)
y2(τ+2)
'
'
'
…
(Ω)
fH
(Ω)
DDM
…
…
…
K1
K2
x1(τ)
x2(τ)
,
…
…
fH =fD(X(τ), K, [Y(τ+1),Y'(τ+1)])
Fig. 4. Process flow of method 2.
486
6. HAN et al.: PHYSICAL-DATA FUSION MODELING METHOD FOR ENERGY CONSUMPTION ANALYSIS OF SMART BUILDING
In this paper, a long short-term memory (LSTM) algo‐
rithm is used to modify the key parameters. LSTM has been
a popular machine learning algorithm in recent years [19].
Because of the temporal characteristics of the electrical, envi‐
ronmental, and behavioral data of buildings, LSTM is select‐
ed because it has advantages in dealing with time-sequenced
modeling. In addition, LSTM can be used to process global
sample datasets.
As a recurrent neural network, the input, output, and error
calculation forms of LSTM are explained in this study. The
input of the DDM method is a matrix. The horizontal axis
represents the characteristic quantity of sample datasets that
includes electrical, environmental, and behavioral informa‐
tion as well as key parameters that must be modified. The
vertical axis represents the time-sequenced values. In the
case studies, each sample dataset is selected for one day,
with an interval period of 5 min. The output of LSTM is di‐
vided into two data parts: thermal process data of various ar‐
eas in the building including the external and internal heat
exchange at various time, and power and status information
of different power loads in the building. The error is generat‐
ed between the output of each loop and the target measure‐
ment. The error is also calculated backwards, affecting every
gate in the output back to the input stage until this value is
filtered out.
C. Model Modification and Selection Mechanism
The second process involves modifying the submodels. In
the process of energy consumption analysis of an entire
building, problems may occur in which the physical model‐
ing of some links is inaccurate or the parameters are diffi‐
cult to modify. Therefore, this study proposes a model modi‐
fication mechanism. Other modeling methods can be used to
replace some of the modeling aspects in the energy analysis,
such as thermal process links, HVAC modeling, or other
electrical load modeling, as shown in Fig. 5.
The HVAC model is selected as a submodel for discus‐
sion. This study presents two typical HVAC algorithms and
provides a simple introduction. First, the modification and se‐
lection mechanism in this study are discussed through these
two typical models. Second, two models, i.e., the traditional
physical modeling (TPM) and DDM are used for compari‐
son purposes in the case studies to evaluate the effects of
the PFM proposed in this paper.
1) TPM
In [25], a classic HVAC model is proposed to evaluate the
HVAC energy consumption through three types of tempera‐
ture parameters, i. e., outdoor, indoor, and set temperatures,
combined with air conditioning power and cooling/heating
efficiency. The model also adds the users’ comfort limit on
the power consumption of HVAC, as shown in (21) and (22).
CHVAC
it = γi (θin
it - 1 - θref
it )2
(21)
θin
it = θin
it - 1 + αi (θout
it - θin
it - 1 )- βiqHVAC
it (22)
where CHVAC
it is the cost of HVAC considering the users’
comfort [25]; θin
it and θout
it are the indoor and outdoor temper‐
atures of building i at time t, respectively; γi is the environ‐
mental preferences (i.e., the temperature sensitivities) of the
occupants in the building i; αi is the thermal insulation; and
βi is the energy efficiency of HVAC.
In [22], an HVAC model could be dynamically adjusted
automatically by personnel according to their levels of com‐
fort. The model considers the effects of air temperature, aver‐
age radiant temperature, relative humidity, air speed, cloth‐
ing insulation, and metabolic rates on levels of comfort.
T in
t + 1 = εT in
t +(1 - ε)
( )
T out
t -
ηHVAC
A
et (23)
where T in
t and T out
t are the indoor and outdoor temperatures
of the building, respectively; ε, ηHVAC, and A are the conver‐
sion coefficients, and their specific meanings and values are
described in [22]; and et is the power of HVAC at time t.
2) DDM
In [19], the LSTM is also used to predict the energy con‐
sumption of residential buildings. The proposed approach in‐
tegrates preprocessing and data organization mechanisms to
refine the data and remove anomalies. A deep learning net‐
work is adopted to input refined sequence data into a convo‐
lutional neural network through a multi-layer bidirectional
LSTM network to learn sequence patterns effectively. Final‐
ly, a high-precision result is obtained in the evaluation of res‐
idential energy consumption of the buildings.
It should be noted that the role of the data-driven module
in PFM is to modify the key parameters and to select sub‐
models. However, the DDM mentioned above is an option in
the optional model list for the HVAC submodel. Further‐
more, an accuracy evaluation method needs to be established
to improve the model correction and selection mechanism.
This paper chooses the conventional average relative error to
measure the accuracy of the algorithm fitting. The algorithm
also calculates the average relative error from the two per‐
spectives of area temperature and total electricity consump‐
tion of the building.
Precise physical model
Environmental data
Behavioral data
Electrical data
Structural data
Thermal process
Thermal-electrical
conversion model
Parameter matrix
Structural matrix
Key parameter modification of PFM Model modification of DDM
Environmental
change
State change
Behavioral change
Key parameters
Process simulation
Value evaluation
Value table
Modification
Model list
TPM
DPM
Parameter
modification model
Model calculation
Output
Error evaluation
Model selection
Data flow; Method process; Loop iteration; Model set
Fig. 5. PFM process for energy consumption analysis of building.
487
7. JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY, VOL. 10, NO. 2, March 2022
IV. CASE STUDIES
A. Application and Data Introduction
In this case study, a high-tech park with multiple types of
buildings in Changzhou, China, is selected as an example.
The park covers an area of approximately 4 km2
in eastern
China, which locates in the geometric center of the Yangtze
River Delta. It has a subtropical monsoon climate with four
distinct levels. Approximately 40 buildings are located in the
park, which include office buildings, dormitories, factories,
and research institutes. Approximately 5000 employees work
in the park. Two 10 kV cables supply the power to the en‐
tire park, and the monthly electricity consumption of this
park is approximately 65 × 106
kWh. There are abundant
forms of energy supplies in the park such as distributed PV,
energy storage, and geothermal energy. Energy monitoring
systems have been installed for most of the buildings in the
park to achieve the data collection and the smart manage‐
ment and control.
In this study, a typical office building in the park is select‐
ed, which is an L-shaped structure with four floors and a to‐
tal area of approximately 11000 m2
. The envelope structure
of the building is mainly composed of a steel tube concrete
frame. The interior of the building can be divided into many
areas that include power distribution rooms, offices, laborato‐
ries, open office areas, corridors, and halls. The energy sup‐
ply form of the building is mainly composed of the power
grid and rooftop PV. The main energy load of the building
consists of HVAC, office computers, lights, and water boil‐
ers. The number of daily office and maintenance personnel
in the building is approximately 80. The time periods of per‐
sonnel activities are from 08: 00 to 20: 00 in summer and
from 08:30 to 19:00 in winter.
Both environmental energy monitoring system and BEMS
are installed in the building. Environmental monitoring out‐
side the building mainly relies on a miniature weather sta‐
tion installed on the roof. The weather station monitors the
environmental information, including temperature, humidity,
light intensity, carbon dioxide concentration, PM2.5, wind
speed, and rainfall. The monitoring period is 5 min. Similar‐
ly, the environmental monitoring inside the building is real‐
ized using numerous environmental monitoring sensors
throughout the building. The BEMS measures the amount of
distributed PV power generation and the power consumption
of various internal areas. The electricity consumption in the
internal areas inside the building is mainly composed of the
electricity consumption of HVAC, lights, office computers,
and other equipment. The collection period of the electrical
quantity is also 5 min. Simultaneously, the building is
equipped with a variety of smart sensing devices to monitor
the opening and closing statuses of doors, windows, and the
equipment, and the flow of people throughout the building.
Most of these information collection cycles are triggered.
The buildings selected in this study have a year-and-a-half’s
worth of sample data.
B. Performance Comparison of Three Modeling Methods
Typical days in summer and winter are selected as the cal‐
culation periods. Based on the two aspects of regional tem‐
perature and energy consumption of the building, the accura‐
cies of the PFM, TPM, and DDM methods are compared.
First, a refined physical model is established for the building
selected in the calculation example to analyze the energy
consumption. The LSTM algorithm is then used to modify
the key parameters in the refined physical model to obtain
the temperature and electric power of each area in the build‐
ing. The partial load model in the PFM is replaced with a
TPM method to obtain the TPM-based calculation results.
The partial load model in the PFM is replaced with a DDM,
and the DDM-based calculation results are obtained. Finally,
the results obtained by PFM and other two methods on a typ‐
ical day in summer are compared, as shown in Fig. 6.
It can be observed from Fig. 6 that the temperature and
power obtained based on the PFM method are more in line
with the actual values. Therefore, the accuracy rate is higher
than that of the TPM and DDM methods.
Figure 7 presents the box plot of accuracy comparison of
the PFM and other two methods on a typical day in summer.
The box is divided into three horizontal lines, which are the
upper quartile, median, and lower quartile of accuracy, re‐
spectively. The edges of the two vertical lines on the top and
00:00 04:00 08:00 12:00 16:00 20:00 24:00
24
26
28
30
32
34
36
38
40
Temperature
(°C)
Indoor (actual)
Indoor (PFM method)
Indoor (TPM method)
Indoor (DDM method)
Time
Time
0
50
100
150
200
250
300
350
400
Power
(kW)
Actual
PFM method
TPM method
DDM method
(a)
(b)
00:00 04:00 08:00 12:00 16:00 20:00 24:00
Outdoor
Fig. 6. Results of comparison between PFM and other two methods on a
typical day in summer. (a) Comparison of regional temperature. (b) Compar‐
ison of regional energy consumption.
488
8. HAN et al.: PHYSICAL-DATA FUSION MODELING METHOD FOR ENERGY CONSUMPTION ANALYSIS OF SMART BUILDING
bottom of the box indicate the top and bottom edges of accu‐
racy, respectively. Some discrete points can also be ob‐
served, which represent some outliers that occasionally ap‐
pear. In the calculation example, 100 sets of sample data are
used to verify the accuracy results. The accuracy of PFM
method is approximately 91.3% and clearly higher than that
of the other two methods, and it is relatively stable (revealed
by the fact that the height of the cabinet is relatively low).
The TPM method has the lowest accuracy and the worst
scalability. The DDM method has the medium calculation ac‐
curacy and scalability with a small amount (100 to 300
days) of sample data.
We then consider an example of a typical day in winter.
Three differences from the calculation examples on a typical
day in summer are observed. First, the working hours of em‐
ployees in winter are shorter than those in summer; there‐
fore, it is necessary to fully consider the behavioral parame‐
ters of employees in the building. Second, the working mode
of HVAC changes from cooling to heating; therefore, the op‐
erating status of HVAC varies, which makes HVAC have dif‐
ferent electrical characteristics. The third point is that in sum‐
mer, the main function of HVAC is cooling, but the solar ra‐
diation increases the temperature, which is the opposite of
air conditioning. However, in winter, the main function of
HVAC is heating, which is similar to solar radiation. The re‐
sults of comparison between the PFM and other two meth‐
ods on a typical day in winter are shown in Fig. 8.
It can be concluded that the temperature and power values
obtained based on the PFM method are more in line with
the actual values, and thus the accuracy rate is higher than
that of the TPM and DDM methods.
Figure 9 presents the box plot of accuracy comparison of
the PFM and other two methods on a typical day in winter.
In the calculation example, 100 sets of sample data are used
to verify the accuracy results. The accuracy of the PFM
method is approximately 92.6%, which is clearly higher than
that of the other two methods, and it is relatively stable. The
TPM method has the lowest accuracy and the worst scalabili‐
ty. The DDM method has the medium calculation accuracy
and scalability with a small amount (100 to 300 days) of
sample data.
Finally, we present the accuracy comparison of the PFM
and other two methods in the training process, as shown in
Fig. 10.
The PFM method has a higher training accuracy and a
higher starting point for training accuracy. This is because
the PFM method is based on an accurate physical model and
thus has a high training accuracy from the beginning. The fi‐
nal training accuracy of TPM method is low at only 70% to
80%. However, due to the inherent characteristics of the
physical model, the TPM methods could also have a certain
initial training accuracy. Because the DDM method is com‐
pletely based on data, the initial training accuracy is 0, but
the DDM method shows a good learning effect and thus the
final accuracy is basically the same as that of the PFM meth‐
od. However, because of its dependence on sample data, the
DDM method could not achieve high training accuracy
when the amount of training data is relatively small. As
shown by the dotted blue line, when the training accuracy of
PFM method reaches 90%, the accuracies of the TPM and
DDM methods are less than 70% and 80%, respectively.
65
70
75
80
85
90
95
100
No. 1 No. 2 No. 3 No. 4 No. 5 No. 6 No. 7 No. 8 No. 9 No. 10
Area
PFM method; DDM method
TPM method;
Accuracy
(%)
Fig. 7. Box plot of accuracy comparison between PFM and other two methods on a typical day in summer.
00:00 04:00 08:00 12:00 16:00 20:00 24:00
-5
0
5
10
15
20
25
30
Temperature
(°C)
Outdoor
Indoor (actual)
Indoor (PFM method)
Indoor (TPM method)
Indoor (DDM method)
Time
Time
0
50
100
150
200
250
300
350
400
Power
(kW)
Actual
PFM method
TPM method
DDM method
(a)
(b)
00:00 04:00 08:00 12:00 16:00 20:00 24:00
Fig. 8. Results of comparison between PFM and other two methods on a
typical day in winter. (a) Comparison of regional temperature. (b) Compari‐
son of regional energy consumption.
489
9. JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY, VOL. 10, NO. 2, March 2022
V. CONCLUSION
An office building in a high-tech park is used as an exam‐
ple to construct a precision physical model of the building.
A PFM method is proposed to correct the accuracy of the
model through the parameter and model correction. The rele‐
vant conclusions are as follows.
1) Existing studies on the architectures for energy con‐
sumption analysis have given little attention to precise physi‐
cal models. This paper constructs a refined physical model
for energy consumption analysis of buildings. This model de‐
scribes in detail the structural matrix and the thermal and
thermal-electric conversion processes of a building through
physical modeling. In particular, the interaction between the
interior areas of the building and behavioral information is
considered in the form of a structural matrix.
2) This paper proposes a method for analyzing energy con‐
sumption of building through the PFM method. The accura‐
cy of the energy consumption analysis could be improved by
modifying the parameters and model. The interactive mecha‐
nism of energy conversion in buildings could be retained
through a physical model, and the accuracy of the energy
consumption analysis could be improved by the DDM meth‐
od.
3) The energy consumption analysis based on the PFM
method proposed in this study can obtain higher accuracy
(over 90%) when the sample data volume is relatively small.
The problem that the DDM method for building energy con‐
sumption analysis of buildings requires a large amount of
sample data is solved.
REFERENCES
[1] J. Pan, R. Jain, S. Paul et al., “An internet of things framework for
smart energy in buildings: designs, prototype, and experiments,” IEEE
Internet of Things Journal, vol. 2, no. 6, pp. 527-537, Mar. 2016.
[2] H. Haider, O. See, and W. Elmenreich, “A review of residential de‐
mand response of smart grid,” Renewable and Sustainable Energy Re‐
views, vol. 59, pp. 166-178, Jun. 2016.
[3] D. Kolokotsa, “The role of smart grids in the building sector,” Energy
and Buildings, vol. 116, pp. 703-708, Mar. 2016.
[4] D. Zhang, S. Evangelisti, P. Lettieri et al., “Economic and environmen‐
tal scheduling of smart homes with microgrid: DER operation and
electrical tasks,” Energy Conversion and Management, vol. 110, pp.
113-124, Feb. 2016.
[5] A. F. Taha, N. Gatsis, B. Dong et al., “Buildings-to-grid integration
framework,” IEEE Transactions on Smart Grid, vol. 10, no. 2, pp.
1237-1249, Oct. 2017.
[6] X. Jin, J. Wu, Y. Mu et al., “Hierarchical microgrid energy manage‐
ment in an office building,” Applied Energy, vol. 208, pp. 480-494,
Dec. 2017.
[7] M. Razmara, M. Maasoumy, M. Shahbakhti et al., “Optimal exergy
control of building HVAC system,” Applied Energy, vol. 156, pp. 555-
565, Oct. 2015.
[8] M. Razmara, G. R. Bharati, D. Hanover et al., “Building-to-grid pre‐
dictive power flow control for demand response and demand flexibili‐
ty programs,” Applied Energy, vol. 203, pp. 128-141, Oct. 2017.
[9] W. Labeeuw, J. Stragier, and G. Deconinck, “Potential of active de‐
mand reduction with residential wet appliances: a case study for Bel‐
gium,” IEEE Transactions on Smart Grid, vol. 6, no. 1, pp. 315-323,
Jan. 2015.
[10] M. Brenna, M. C. Falvo, F. Foiadelli et al., “From virtual power plant
(VPP) to sustainable energy microsystem (SEM): an opportunity for
buildings energy management,” in Proceedings of 2015 IEEE Industry
Applications Society Annual Meeting, Addison, USA, Dec. 2015, pp.
1-8.
[11] X. Jin, Y. Mu, H. Jia et al., “Dynamic economic dispatch of a hybrid
energy microgrid considering building based virtual energy storage sys‐
tem,” Applied Energy, vol. 194, pp. 386-398, May 2017.
[12] T. Jiang, Z. Li, X. Jin et al., “Flexible operation of active distribution
network using integrated smart buildings with heating, ventilation and
air-conditioning systems,” Applied Energy, vol. 226, pp. 181-196,
Sept. 2018.
[13] X. Chen, J. Wang, J. Xie et al., “Demand response potential evalua‐
tion for residential air conditioning loads,” IET Generation, Transmis‐
sion Distribution, vol. 12, no. 19, pp. 4260-4268, Sept. 2018.
[14] C. Zhang, S. R. Kuppannagari, R. Kannan et al., “Building HVAC
scheduling using reinforcement learning via neural network based mod‐
el approximation,” in Proceedings of the 6th ACM International Con‐
ference on Systems for Energy-efficient Buildings, Cities, and Trans‐
portation, Zhuhai, China, Dec. 2019, pp. 287-296.
[15] X. Jin, J. Wu, Y. Mu et al., “Hierarchical microgrid energy manage‐
ment in an office building,” Applied Energy, vol. 208, pp. 480-494,
Dec. 2017.
[16] M. Razmara, G. R. Bharati, M. Shahbakhti et al., “Bilevel optimiza‐
tion framework for smart building-to-grid systems,” IEEE Transac‐
tions on Smart Grid, vol. 9, no. 2, pp. 582-593, Apr. 2016.
[17] Y. Ye, D. Qiu, X. Wu et al., “Model-free real-time autonomous con‐
trol for a residential multi-energy system using deep reinforcement
learning,” IEEE Transactions on Smart Grid, vol. 11, no. 4, pp. 3068-
3082, Feb. 2020.
[18] H. Nezamabadi and V. Vahidinasab, “Market bidding strategy of the
microgrids considering demand response and energy storage potential
flexibilities,” IET Generation, Transmission Distribution, vol. 13,
65
70
75
80
85
90
95
100
No. 1 No. 2 No. 3 No. 4 No. 5 No. 6 No. 7 No. 8 No. 9 No. 10
Area
PFM method; DDM method
TPM method;
Accuracy
(%)
Fig. 9. Box plot of accuracy comparison between PFM and other two methods on a typical day in winter.
0 50 100 150 200 250 300 350 400 450
No. of samples
10
20
30
40
50
60
70
80
90
100
Accuracy
(%)
PFM method
TPM method
DDM method
90%
80%
70%
Fig. 10. Accuracy comparison between PFM and other two methods in
training process.
490
10. HAN et al.: PHYSICAL-DATA FUSION MODELING METHOD FOR ENERGY CONSUMPTION ANALYSIS OF SMART BUILDING
no. 8, pp. 1346-1357, Jan. 2019.
[19] F. U. M. Ullah, A. Ullah, I. U. Haq et al., “Short-term prediction of
residential power energy consumption via CNN and multi-layer bi-di‐
rectional LSTM networks,” IEEE Access, vol. 8, pp. 123369-123380,
Dec. 2019.
[20] J. Song, G. Xue, Y. Ma et al., “An indoor temperature prediction
framework based on hierarchical attention gated recurrent unit model
for energy efficient buildings,” IEEE Access, vol. 7, pp. 157268-
157283, Oct. 2019.
[21] L. Yu, Y. Sun, Z. Xu et al., “Multi-agent deep reinforcement learning
for HVAC control in commercial buildings,” IEEE Transactions on
Smart Grid, vol. 12, no. 1, pp. 407-419, Jun. 2020.
[22] L. Yu, W. Xie, D. Xie et al., “Deep reinforcement learning for smart
home energy management,” IEEE Internet of Things Journal, vol. 7,
no. 4, pp. 2751-2762, Sept. 2019.
[23] S. Biao, B. L. Peter, Q. Jia et al., “Building energy management: inte‐
grated control of active and passive heating, cooling, lighting, shading,
and ventilation systems,” IEEE Transactions on Automation Science
and Engineering, vol. 10, no. 3, pp. 588-602, Jul. 2013.
[24] Z. Xiangyu, P. Manisa, C. Tao et al., “An IoT-based thermal model
learning framework for smart buildings,” IEEE Internet of Things
Journal, vol. 7, no. 1, pp. 518-527, Jan. 2020.
[25] S. Cui and J. Xiao, “Game-based peer-to-peer energy sharing manage‐
ment for a community of energy buildings,” International Journal of
Electrical Power Energy Systems, vol. 123, pp. 1-10, Dec. 2020.
Xiao Han received the B.S. degree in electrical engineering and automation
and the M.S. degree in electrical engineering from Nanjing Normal Univer‐
sity, Nanjing, China, in 2012 and 2015, respectively. He is now pursuing for
the Ph.D. degree in electrical engineering in Nanjing University of Aeronau‐
tics and Astronautics, Nanjing, China. His current research interest includes
smart energy system of buildings.
Chaohai Zhang received the B.A., M.S., and Ph.D. degrees from Harbin In‐
stitute of Technology (HIT), Harbin, China, in 1985, Navy Aeronautical En‐
gineering Academy, in 1997, and Hong Kong Polytechnic University, Hong
Kong, China, respectively. Currently, he is a Professor at Nanjing University
of Aeronautics and Astronautics, Nanjing, China. His research interests in‐
clude electrical discharges, plasma, electrical environment and condition
monitoring, and diagnosis of electric power equipment.
Yi Tang received the Ph.D. degree from the Harbin Institute of Technology,
Harbin, China, in 2006. He is currently a Professor with Southeast Universi‐
ty, Nanjing, China. His research interests include smart grid, power system
security, power system stability analysis, renewable energy system, and cy‐
ber-physical system.
Yujian Ye received the B.Eng. degree in Electrical and Electronic Engineer‐
ing from Northumbria University, Newcastle Upon Tyne, U.K., in 2011, the
M.Sc. and the Ph.D. degrees from Imperial College London, London, U.K.,
in 2013 and 2017, respectively. He is currently an Associate Professor at
Southeast University, Nanjing, China, and a Visiting Researcher at Imperial
College London. His current research interests include development and ap‐
plication of artificial intelligence techniques in modeling, analysis, and con‐
trol of power and energy system, and optimization of economics of power
system operation and planning.
491