SlideShare a Scribd company logo
1 of 36
Power Rangers
Carla Coulson, Dominique Hinton, Roman Villoria
Carla Coulson
carla.k.coulson.civ@mail.mil
carlacoulson@comcast.net
Roman Villoria
LinkedIn
romanvilloria@hotmail.com
Dominique Hinton
LinkedIn
dominiquealexandriahinton7@gmail.com
Contributors
Project Abstract
● The Energy Section is key
contributor to climate change
● The city has placed an
emphasis on becoming
carbon neutral and more
green in the future.
● The group aims to provide
the city and building owners
with more information to help
optimize resources.
Initial Hypotheses
1. The best performing buildings are those most recently constructed and with higher ES ratings.
2. Buildings with improving ES ratings over time exhibit reduced energy and water consumption and GHG
emissions.
3. Water usage is correlated to overall energy usage.
4. Increases in energy and water usage are associated with extreme weather evidenced by climate change.
5. Changes in energy usage due to the COVID pandemic have resulted in decreases in energy and water usage.
6. Given energy usage data for buildings over 50,000 Gross Square Feet in the District of Columbia, as well as
facility Energy Star (ES) ratings and weather data, we can predict future energy usage in a manner that may
generate savings for building owners (or operators).
Primary Hypothesis
Can we predict DC large commercial buildings’ energy usage based on their historical electricity and
natural gas consumption and weather patterns?
Open Data DC
Project Architecture
National Climatic
Data Center -
NOAA
Building_Energy_
Benchmarks
CSV File PostgreSQL
Hosted on
Amazon Web
Services
Regression
Scikit- Learn
Yellowbrick
Features
Building
Characteristics
● Type
● Area
● Year Built
● NG
Heating
Monthly Data
● Electricity
● Natural
Gas
Data Ingestion
Data Munging and
Wrangling
Data Computation and
Analysis
Data Modeling and
Application
Data Reporting and
Visualization
Weather Month
Data for DC.
Data Cleaning
Pandas
Jupyter
Notebook
● Can we predict energy
usage based on
historical buildings'
electricity & natural gas
consumption, and
weather patterns?
EDA
Matplotlab
Numpy
Pandas
Seaborn
Data Product
Visualization
Plotly
https://opendata.dc.gov/datasets/
building-energy-benchmarkshttps://www.ncdc.noaa.gov/
Data Sources
● Relational Database
● Selected for WORM
capabilities
● Integrates well with
AWS
● Ensure all group
members had access
to an updated copy of
the database at all
times
● Jupyter Notebooks was used
to easily run code using the
repl
● Pandas was used to do initial
transformations and
exploration of the data
Data Storage and Initial Analysis
Instances by Building Type Heat MapMap Violin Plot
Data Cleaning and Wrangling Tools and
Initial Visualizations
Data Cleaning and Wrangling
● Removed columns that are not relevant
● Removed instances that did not have 12 months of valid data
● Removed duplicates
● Calculated energy intensity (kbtu/sqft)
● Used Pandas Melt function to pivot usage columns to rows
● Met with data owners, the DC Department of Energy and Environment
● Merged property types from 40 to 19
● Eliminated annual data e.g. - water usage, GHG emissions
● Removed renewable energy as a potential feature because of sparsity of
data
● Investigated whether Energy Star scores contributed to energy usage
Instances (building month) by Building Type
Dominant building types are lodging/residential and office
Most lodging/residential and offices are in Ward 2
Ward 2 also has the highest average energy intensity across all building types
EDA Correlation Heatmap
● Yellowbrick was used to visualize different
models and to help with feature selection
● Models were tested on all buildings and
then on individual building types
● Global model received relatively good R2
and MSE scores but larger individual
models also received good scores
Feature Importance of Features (RandomForetsRegressor) with ES Score
Back
Some definitions:
● Energy Usage in kBtu (1,000 British Thermal Units)
● Intensity = Energy Usage / Square Footage
● CLDD: Cooling Degree Days
● HTDD: Heating Degree Days
Additional EDA And Feature Engineering
Cyclic Encoding
EDA Led Us To Focus The Analysis On Electricity Usage
And Take Into Account Seasonal Patterns
Natural Gas usage requires different
considerations for modeling (dropped)
tavg
After Feature Engineering, We Decided To Use CLDD And
HTDD Instead Of Tavg
cldd
htdd
kbtu intensity
Global Model Versus Models By Building Type
● Lodging/Residential and Office
buildings: ~80% of the dataset
● Started with simple Linear Regression
based on EDA findings
● Energy Usage or Intensity as the target
variable?
● Explored different combinations of
features
Lodging/Residential
GLOBAL
All Building
Types
Banks
Education
Entertainment
Food Sales
Food Services
Healthcare Industrial
Mixed Use
Others
Parking
Public Services
Religious
Utilities
Services
Tech
Retail
Storage
Office
We Made Some Decisions on Target Variables And
Some Features, Based on Modeling
DOEE recommended using: reported floor area and 2018-2019 usage data
Monthly energy usage
for years 2010 - 2019
vs.
Monthly energy usage
for years 2018 - 2019
One Hot Encoded Foreign
Keys, one at the time
vs.
All Foreign Keys (One
Hot) Encoded
Tax Record Floor Area vs. Reported Floor Area
Target Variable: Intensity
vs.
Target Variable: Energy Usage
● All years
● Tax record area
● One Hot: ‘Ward’
R2 = 0.11
Coefficient R2 Increases When One Hot Encoding Both ‘Ward’ And ‘Year Built’
Global Model, LinearRegression
● All years
● Tax record area
● One Hot: ‘Year Built’
R2 = 0.09
● All years
● Tax record area
● One Hot: ‘Ward’, ‘Year Built’
R2 = 0.16
1) Effect of different foreign keys as features:
● Years 2018-2019
● Reported area
● Target: ‘Intensity’
R2 = 0.36
● Years 2018-2019
● Reported area
● Target: ‘Energy Usage’
R2 = 0.73
2) Target variable (with One Hot -- ‘Ward’, ‘Year Built’):
Also, ‘reported area’ is a better predictor
of Energy Usage in commercial buildings
Preparation For Modeling
● Built a separate Jupyter notebooks for each model attempt
● Pipeline
○ ColumnTransformer
○ FeatureUnion
○ OneHotEncoder
● Cross validation
○ Time Series Split with 12 folds
○ Returned Coefficient of Determination (R2) and mean squared error (mse) of the regressor,
along with the final fitted model, fitted on all of the data
Algorithm Selection
Global Model:
● LinearRegression
● SGDRegressor, PolynomialFeatures (quad, cub)
● LinearRegression, PolynomialFeatures (quad, cub)
● Random Forest
Models by Building Type:
● Ensemble: LinearRegression, RandomForest, VotingRegressor
Results
Average Usage (MBtu) - All Buildings:
Mean
R2
Std. Dev.
R2
Mean
RMSE
Std. Dev
RMSE
LinearRegression 0.72 0.04 891 445
RandomForest 0.82 0.04 718 365
LR-PolyFeat(2) 0.84 0.12 681 614
LR-PolyFeat(3) 0.65 0.23 992 811
P25 P50 P75
174 400 900
Average Usage (MBtu) - Lodg./Res.:
Ensemble 0.84 0.04 261 148 174 400 900
Global Model:
Lodging/Residential:
Average Usage (MBtu) - Office:
Ensemble 0.89 0.02 331 129 455 862 1,465
Office:
A Global Model Does OK, Per-Building Models
Excel At Predicting Energy Usage
● Ensemble models for both Lodging/Residential and Office buildings enhance
weaker models such as the Linear Regression, therefore are more predictive
● Linear Regression model with second order polynomial features performs
better than third order polynomial
● Global model’s RMSE is considerably high compared to buildings energy
usage interquartile ranges
Conclusions
● It is possible to accurately predict energy used by DC large commercial
buildings with this type of data
● Owner reported (versus tax reported) square footage is the most important
driver of energy usage in buildings larger that 50,000 square feet in DC
● Using the methodology presented in this study, DOEE will have a good
picture of how large commercial buildings consume energy
● Also, once new data is available, DOEE will have a better understanding of
the effects of COVID-19 on energy consumption profiles
Next Steps
● Update study once 2020 data is available
● Contribute to the DC Open Data Repo
● Work further with DOEE
● Explore additional features in models
● Look more closely at the importance of building location
● Dominique becomes a TA and later an instructor at G-town and then a Super
Star!!!!
Questions?
Thank You
ADDITIONAL SLIDES
Cyclic Encoder And Extraction Pipeline
Regularization Methods Attempted On Global
Model To Eliminate Multicollinearity
Algorithm R2
Lasso 0.69
Ridge 0.71
ElasticNet 0.68
Joint Plots
Year Built vs. Ward: Area Year vs. Built:
Yellowbrick Feature Importance - Global Model
Global - Lasso Global - Random Forest
Yellowbrick Feature Importance - L/R. Model
Lodging/Res. - Lasso Lodging/Res. - Random Forest
Yellowbrick Feature Importance - Office Model
Office - Lasso Office - Random Forest

More Related Content

What's hot

Modelling Circular Economy in TIMES
Modelling Circular Economy in TIMESModelling Circular Economy in TIMES
Modelling Circular Economy in TIMESIEA-ETSAP
 
spatial_load_analysis
spatial_load_analysisspatial_load_analysis
spatial_load_analysisDavid Hollema
 
Techno-Economic Modelling of Cogeneration Options for the South African Sugar...
Techno-Economic Modelling of Cogeneration Options for the South African Sugar...Techno-Economic Modelling of Cogeneration Options for the South African Sugar...
Techno-Economic Modelling of Cogeneration Options for the South African Sugar...IEA-ETSAP
 
Impacts of green hydrogen on the Italian power system by 2030
Impacts of green hydrogen on the Italian power system by 2030Impacts of green hydrogen on the Italian power system by 2030
Impacts of green hydrogen on the Italian power system by 2030IEA-ETSAP
 
Short-term Production planning for district heating networks with JMODelica.org
Short-term Production planning for district heating networkswith JMODelica.orgShort-term Production planning for district heating networkswith JMODelica.org
Short-term Production planning for district heating networks with JMODelica.orgModelon
 
How do changes to future technology and fuel developments affect the optimal ...
How do changes to future technology and fuel developments affect the optimal ...How do changes to future technology and fuel developments affect the optimal ...
How do changes to future technology and fuel developments affect the optimal ...IEA-ETSAP
 
ICEEE Poster_YoannGuinard
ICEEE Poster_YoannGuinardICEEE Poster_YoannGuinard
ICEEE Poster_YoannGuinardYoann Guinard
 
Modelling different Thermal Energy Storage (TES) options in a TIMES model
Modelling different Thermal Energy Storage (TES) options in a TIMES modelModelling different Thermal Energy Storage (TES) options in a TIMES model
Modelling different Thermal Energy Storage (TES) options in a TIMES modelIEA-ETSAP
 
Working with TIMES and Monte Carlo in a Policy Setting
Working with TIMES and Monte Carlo in a Policy SettingWorking with TIMES and Monte Carlo in a Policy Setting
Working with TIMES and Monte Carlo in a Policy SettingIEA-ETSAP
 
Decarbonization of industry - impact on energy
Decarbonization of industry - impact on energyDecarbonization of industry - impact on energy
Decarbonization of industry - impact on energyBig Data Value Association
 
R callaghan DT774 Energy and Retrofit Presentation
R callaghan DT774 Energy and Retrofit PresentationR callaghan DT774 Energy and Retrofit Presentation
R callaghan DT774 Energy and Retrofit Presentationrichcie
 
Comparación entre consumo energético teórico y real en viviendas sociales
Comparación entre consumo energético teórico y real en viviendas socialesComparación entre consumo energético teórico y real en viviendas sociales
Comparación entre consumo energético teórico y real en viviendas socialesCluster Construction Eraikune
 
Jure Čižman, Jožef Stefan Institute, Ljubljana, Slovenia.
Jure Čižman, Jožef Stefan Institute, Ljubljana, Slovenia.Jure Čižman, Jožef Stefan Institute, Ljubljana, Slovenia.
Jure Čižman, Jožef Stefan Institute, Ljubljana, Slovenia.ARC research group
 
Chapter 6 : Smart District heating/cooling, Summer Course, AUST 2015
Chapter 6 : Smart District heating/cooling, Summer Course, AUST 2015Chapter 6 : Smart District heating/cooling, Summer Course, AUST 2015
Chapter 6 : Smart District heating/cooling, Summer Course, AUST 2015Isam Shahrour
 
TIMES-CGE-SD model coupling and data exchange mechanism for the LEDS developm...
TIMES-CGE-SD model coupling and data exchange mechanism for the LEDS developm...TIMES-CGE-SD model coupling and data exchange mechanism for the LEDS developm...
TIMES-CGE-SD model coupling and data exchange mechanism for the LEDS developm...IEA-ETSAP
 
Smart Grids, Energy Efficiency and Renewable Energy Sources in urban areas: t...
Smart Grids, Energy Efficiency and Renewable Energy Sources in urban areas: t...Smart Grids, Energy Efficiency and Renewable Energy Sources in urban areas: t...
Smart Grids, Energy Efficiency and Renewable Energy Sources in urban areas: t...Community Protection Forum
 
eni_Rossi Gianmarco - Energy Management System for the Optimization of the Up...
eni_Rossi Gianmarco - Energy Management System for the Optimization of the Up...eni_Rossi Gianmarco - Energy Management System for the Optimization of the Up...
eni_Rossi Gianmarco - Energy Management System for the Optimization of the Up...Gianmarco Rossi
 
Numerical simulation of Hybrid Generation System: a case study
Numerical simulation of Hybrid Generation System: a case studyNumerical simulation of Hybrid Generation System: a case study
Numerical simulation of Hybrid Generation System: a case studyIRJET Journal
 

What's hot (20)

Modelling Circular Economy in TIMES
Modelling Circular Economy in TIMESModelling Circular Economy in TIMES
Modelling Circular Economy in TIMES
 
spatial_load_analysis
spatial_load_analysisspatial_load_analysis
spatial_load_analysis
 
Techno-Economic Modelling of Cogeneration Options for the South African Sugar...
Techno-Economic Modelling of Cogeneration Options for the South African Sugar...Techno-Economic Modelling of Cogeneration Options for the South African Sugar...
Techno-Economic Modelling of Cogeneration Options for the South African Sugar...
 
Impacts of green hydrogen on the Italian power system by 2030
Impacts of green hydrogen on the Italian power system by 2030Impacts of green hydrogen on the Italian power system by 2030
Impacts of green hydrogen on the Italian power system by 2030
 
Short-term Production planning for district heating networks with JMODelica.org
Short-term Production planning for district heating networkswith JMODelica.orgShort-term Production planning for district heating networkswith JMODelica.org
Short-term Production planning for district heating networks with JMODelica.org
 
How do changes to future technology and fuel developments affect the optimal ...
How do changes to future technology and fuel developments affect the optimal ...How do changes to future technology and fuel developments affect the optimal ...
How do changes to future technology and fuel developments affect the optimal ...
 
ICEEE Poster_YoannGuinard
ICEEE Poster_YoannGuinardICEEE Poster_YoannGuinard
ICEEE Poster_YoannGuinard
 
Modelling different Thermal Energy Storage (TES) options in a TIMES model
Modelling different Thermal Energy Storage (TES) options in a TIMES modelModelling different Thermal Energy Storage (TES) options in a TIMES model
Modelling different Thermal Energy Storage (TES) options in a TIMES model
 
Working with TIMES and Monte Carlo in a Policy Setting
Working with TIMES and Monte Carlo in a Policy SettingWorking with TIMES and Monte Carlo in a Policy Setting
Working with TIMES and Monte Carlo in a Policy Setting
 
Decarbonization of industry - impact on energy
Decarbonization of industry - impact on energyDecarbonization of industry - impact on energy
Decarbonization of industry - impact on energy
 
R callaghan DT774 Energy and Retrofit Presentation
R callaghan DT774 Energy and Retrofit PresentationR callaghan DT774 Energy and Retrofit Presentation
R callaghan DT774 Energy and Retrofit Presentation
 
Aci home-mpg-sam nutter-csg
Aci home-mpg-sam nutter-csgAci home-mpg-sam nutter-csg
Aci home-mpg-sam nutter-csg
 
Comparación entre consumo energético teórico y real en viviendas sociales
Comparación entre consumo energético teórico y real en viviendas socialesComparación entre consumo energético teórico y real en viviendas sociales
Comparación entre consumo energético teórico y real en viviendas sociales
 
Jure Čižman, Jožef Stefan Institute, Ljubljana, Slovenia.
Jure Čižman, Jožef Stefan Institute, Ljubljana, Slovenia.Jure Čižman, Jožef Stefan Institute, Ljubljana, Slovenia.
Jure Čižman, Jožef Stefan Institute, Ljubljana, Slovenia.
 
Chapter 6 : Smart District heating/cooling, Summer Course, AUST 2015
Chapter 6 : Smart District heating/cooling, Summer Course, AUST 2015Chapter 6 : Smart District heating/cooling, Summer Course, AUST 2015
Chapter 6 : Smart District heating/cooling, Summer Course, AUST 2015
 
TIMES-CGE-SD model coupling and data exchange mechanism for the LEDS developm...
TIMES-CGE-SD model coupling and data exchange mechanism for the LEDS developm...TIMES-CGE-SD model coupling and data exchange mechanism for the LEDS developm...
TIMES-CGE-SD model coupling and data exchange mechanism for the LEDS developm...
 
Smart Grids, Energy Efficiency and Renewable Energy Sources in urban areas: t...
Smart Grids, Energy Efficiency and Renewable Energy Sources in urban areas: t...Smart Grids, Energy Efficiency and Renewable Energy Sources in urban areas: t...
Smart Grids, Energy Efficiency and Renewable Energy Sources in urban areas: t...
 
Developing an effective strategic heating/cooling plan: What key success fact...
Developing an effective strategic heating/cooling plan: What key success fact...Developing an effective strategic heating/cooling plan: What key success fact...
Developing an effective strategic heating/cooling plan: What key success fact...
 
eni_Rossi Gianmarco - Energy Management System for the Optimization of the Up...
eni_Rossi Gianmarco - Energy Management System for the Optimization of the Up...eni_Rossi Gianmarco - Energy Management System for the Optimization of the Up...
eni_Rossi Gianmarco - Energy Management System for the Optimization of the Up...
 
Numerical simulation of Hybrid Generation System: a case study
Numerical simulation of Hybrid Generation System: a case studyNumerical simulation of Hybrid Generation System: a case study
Numerical simulation of Hybrid Generation System: a case study
 

Similar to Predict DC Building Energy Usage

Deep Learning Based Integrated Energy Efficiency Optimization for Smart Building
Deep Learning Based Integrated Energy Efficiency Optimization for Smart BuildingDeep Learning Based Integrated Energy Efficiency Optimization for Smart Building
Deep Learning Based Integrated Energy Efficiency Optimization for Smart Buildingeliyart
 
Introduction to School Energy Management
Introduction to School Energy ManagementIntroduction to School Energy Management
Introduction to School Energy ManagementMeg Thompson
 
Reframed Tech Series: Solar panels & deep retrofits
Reframed Tech Series: Solar panels & deep retrofitsReframed Tech Series: Solar panels & deep retrofits
Reframed Tech Series: Solar panels & deep retrofitsPembina Institute
 
Optimized Energy Management and planning tools for the Iron and Steel Industr...
Optimized Energy Management and planning tools for the Iron and Steel Industr...Optimized Energy Management and planning tools for the Iron and Steel Industr...
Optimized Energy Management and planning tools for the Iron and Steel Industr...Schneider Electric
 
REBNY NYC Benchmarking Seminar: EnergyStar Portfolio Managerr
REBNY NYC Benchmarking Seminar: EnergyStar Portfolio ManagerrREBNY NYC Benchmarking Seminar: EnergyStar Portfolio Managerr
REBNY NYC Benchmarking Seminar: EnergyStar Portfolio ManagerrREBNY
 
2011 expo-smart grn-energy
2011 expo-smart grn-energy2011 expo-smart grn-energy
2011 expo-smart grn-energyEllieNowels
 
NZEB Interm Specification by Sean Armstrong
NZEB Interm Specification by Sean ArmstrongNZEB Interm Specification by Sean Armstrong
NZEB Interm Specification by Sean ArmstrongSustainableEnergyAut
 
How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?IES VE
 
Lessons Learned from Meter Calibrated Energy Simulations of Multi-Unit Reside...
Lessons Learned from Meter Calibrated Energy Simulations of Multi-Unit Reside...Lessons Learned from Meter Calibrated Energy Simulations of Multi-Unit Reside...
Lessons Learned from Meter Calibrated Energy Simulations of Multi-Unit Reside...RDH Building Science
 
Energy Efficiency Workshop - Powering Sydney
Energy Efficiency Workshop - Powering SydneyEnergy Efficiency Workshop - Powering Sydney
Energy Efficiency Workshop - Powering SydneyTransGrid AU
 
COHEAT @ BEIS May 2017
COHEAT @ BEIS May 2017COHEAT @ BEIS May 2017
COHEAT @ BEIS May 2017Marko Cosic
 
COSTMODEL_IDETC_2010_Jie
COSTMODEL_IDETC_2010_JieCOSTMODEL_IDETC_2010_Jie
COSTMODEL_IDETC_2010_JieMDO_Lab
 
Metering and Regulating the Electricity Grid
Metering and Regulating the Electricity GridMetering and Regulating the Electricity Grid
Metering and Regulating the Electricity GridAnirudh Ramesh
 
Importance of Data Driven Decision Making in Enterprise Energy Management | D...
Importance of Data Driven Decision Making in Enterprise Energy Management | D...Importance of Data Driven Decision Making in Enterprise Energy Management | D...
Importance of Data Driven Decision Making in Enterprise Energy Management | D...Cairn India Limited
 
Towards a new model of Energy Development
Towards a new model of Energy DevelopmentTowards a new model of Energy Development
Towards a new model of Energy DevelopmentRCREEE
 
IES Faculty - Big Data in Building Services
IES Faculty - Big Data in Building ServicesIES Faculty - Big Data in Building Services
IES Faculty - Big Data in Building ServicesIES VE
 
2012 Critical Issues Summit Energy Panel, Part I
2012 Critical Issues Summit Energy Panel, Part I2012 Critical Issues Summit Energy Panel, Part I
2012 Critical Issues Summit Energy Panel, Part ISFMI
 
ZERO ENERGY BUILDING; DESIGN AND SIMULATION
ZERO ENERGY BUILDING; DESIGN AND SIMULATIONZERO ENERGY BUILDING; DESIGN AND SIMULATION
ZERO ENERGY BUILDING; DESIGN AND SIMULATIONIRJET Journal
 

Similar to Predict DC Building Energy Usage (20)

Deep Learning Based Integrated Energy Efficiency Optimization for Smart Building
Deep Learning Based Integrated Energy Efficiency Optimization for Smart BuildingDeep Learning Based Integrated Energy Efficiency Optimization for Smart Building
Deep Learning Based Integrated Energy Efficiency Optimization for Smart Building
 
Introduction to School Energy Management
Introduction to School Energy ManagementIntroduction to School Energy Management
Introduction to School Energy Management
 
Reframed Tech Series: Solar panels & deep retrofits
Reframed Tech Series: Solar panels & deep retrofitsReframed Tech Series: Solar panels & deep retrofits
Reframed Tech Series: Solar panels & deep retrofits
 
Bl36378381
Bl36378381Bl36378381
Bl36378381
 
Optimized Energy Management and planning tools for the Iron and Steel Industr...
Optimized Energy Management and planning tools for the Iron and Steel Industr...Optimized Energy Management and planning tools for the Iron and Steel Industr...
Optimized Energy Management and planning tools for the Iron and Steel Industr...
 
REBNY NYC Benchmarking Seminar: EnergyStar Portfolio Managerr
REBNY NYC Benchmarking Seminar: EnergyStar Portfolio ManagerrREBNY NYC Benchmarking Seminar: EnergyStar Portfolio Managerr
REBNY NYC Benchmarking Seminar: EnergyStar Portfolio Managerr
 
2011 expo-smart grn-energy
2011 expo-smart grn-energy2011 expo-smart grn-energy
2011 expo-smart grn-energy
 
NZEB Interm Specification by Sean Armstrong
NZEB Interm Specification by Sean ArmstrongNZEB Interm Specification by Sean Armstrong
NZEB Interm Specification by Sean Armstrong
 
How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?
 
Lessons Learned from Meter Calibrated Energy Simulations of Multi-Unit Reside...
Lessons Learned from Meter Calibrated Energy Simulations of Multi-Unit Reside...Lessons Learned from Meter Calibrated Energy Simulations of Multi-Unit Reside...
Lessons Learned from Meter Calibrated Energy Simulations of Multi-Unit Reside...
 
Energy Efficiency Workshop - Powering Sydney
Energy Efficiency Workshop - Powering SydneyEnergy Efficiency Workshop - Powering Sydney
Energy Efficiency Workshop - Powering Sydney
 
COHEAT @ BEIS May 2017
COHEAT @ BEIS May 2017COHEAT @ BEIS May 2017
COHEAT @ BEIS May 2017
 
presentation
presentationpresentation
presentation
 
COSTMODEL_IDETC_2010_Jie
COSTMODEL_IDETC_2010_JieCOSTMODEL_IDETC_2010_Jie
COSTMODEL_IDETC_2010_Jie
 
Metering and Regulating the Electricity Grid
Metering and Regulating the Electricity GridMetering and Regulating the Electricity Grid
Metering and Regulating the Electricity Grid
 
Importance of Data Driven Decision Making in Enterprise Energy Management | D...
Importance of Data Driven Decision Making in Enterprise Energy Management | D...Importance of Data Driven Decision Making in Enterprise Energy Management | D...
Importance of Data Driven Decision Making in Enterprise Energy Management | D...
 
Towards a new model of Energy Development
Towards a new model of Energy DevelopmentTowards a new model of Energy Development
Towards a new model of Energy Development
 
IES Faculty - Big Data in Building Services
IES Faculty - Big Data in Building ServicesIES Faculty - Big Data in Building Services
IES Faculty - Big Data in Building Services
 
2012 Critical Issues Summit Energy Panel, Part I
2012 Critical Issues Summit Energy Panel, Part I2012 Critical Issues Summit Energy Panel, Part I
2012 Critical Issues Summit Energy Panel, Part I
 
ZERO ENERGY BUILDING; DESIGN AND SIMULATION
ZERO ENERGY BUILDING; DESIGN AND SIMULATIONZERO ENERGY BUILDING; DESIGN AND SIMULATION
ZERO ENERGY BUILDING; DESIGN AND SIMULATION
 

Recently uploaded

POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxSayali Powar
 
Painted Grey Ware.pptx, PGW Culture of India
Painted Grey Ware.pptx, PGW Culture of IndiaPainted Grey Ware.pptx, PGW Culture of India
Painted Grey Ware.pptx, PGW Culture of IndiaVirag Sontakke
 
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxiammrhaywood
 
Full Stack Web Development Course for Beginners
Full Stack Web Development Course  for BeginnersFull Stack Web Development Course  for Beginners
Full Stack Web Development Course for BeginnersSabitha Banu
 
Difference Between Search & Browse Methods in Odoo 17
Difference Between Search & Browse Methods in Odoo 17Difference Between Search & Browse Methods in Odoo 17
Difference Between Search & Browse Methods in Odoo 17Celine George
 
AmericanHighSchoolsprezentacijaoskolama.
AmericanHighSchoolsprezentacijaoskolama.AmericanHighSchoolsprezentacijaoskolama.
AmericanHighSchoolsprezentacijaoskolama.arsicmarija21
 
MICROBIOLOGY biochemical test detailed.pptx
MICROBIOLOGY biochemical test detailed.pptxMICROBIOLOGY biochemical test detailed.pptx
MICROBIOLOGY biochemical test detailed.pptxabhijeetpadhi001
 
What is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPWhat is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPCeline George
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxmanuelaromero2013
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...Marc Dusseiller Dusjagr
 
Roles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in PharmacovigilanceRoles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in PharmacovigilanceSamikshaHamane
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon AUnboundStockton
 
Gas measurement O2,Co2,& ph) 04/2024.pptx
Gas measurement O2,Co2,& ph) 04/2024.pptxGas measurement O2,Co2,& ph) 04/2024.pptx
Gas measurement O2,Co2,& ph) 04/2024.pptxDr.Ibrahim Hassaan
 
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdf
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdfFraming an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdf
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdfUjwalaBharambe
 
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdfssuser54595a
 
MARGINALIZATION (Different learners in Marginalized Group
MARGINALIZATION (Different learners in Marginalized GroupMARGINALIZATION (Different learners in Marginalized Group
MARGINALIZATION (Different learners in Marginalized GroupJonathanParaisoCruz
 
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfLike-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfMr Bounab Samir
 

Recently uploaded (20)

POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
 
Painted Grey Ware.pptx, PGW Culture of India
Painted Grey Ware.pptx, PGW Culture of IndiaPainted Grey Ware.pptx, PGW Culture of India
Painted Grey Ware.pptx, PGW Culture of India
 
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
 
Full Stack Web Development Course for Beginners
Full Stack Web Development Course  for BeginnersFull Stack Web Development Course  for Beginners
Full Stack Web Development Course for Beginners
 
Difference Between Search & Browse Methods in Odoo 17
Difference Between Search & Browse Methods in Odoo 17Difference Between Search & Browse Methods in Odoo 17
Difference Between Search & Browse Methods in Odoo 17
 
AmericanHighSchoolsprezentacijaoskolama.
AmericanHighSchoolsprezentacijaoskolama.AmericanHighSchoolsprezentacijaoskolama.
AmericanHighSchoolsprezentacijaoskolama.
 
MICROBIOLOGY biochemical test detailed.pptx
MICROBIOLOGY biochemical test detailed.pptxMICROBIOLOGY biochemical test detailed.pptx
MICROBIOLOGY biochemical test detailed.pptx
 
What is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPWhat is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERP
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptx
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
 
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
 
Roles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in PharmacovigilanceRoles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in Pharmacovigilance
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon A
 
Gas measurement O2,Co2,& ph) 04/2024.pptx
Gas measurement O2,Co2,& ph) 04/2024.pptxGas measurement O2,Co2,& ph) 04/2024.pptx
Gas measurement O2,Co2,& ph) 04/2024.pptx
 
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdf
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdfFraming an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdf
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdf
 
ESSENTIAL of (CS/IT/IS) class 06 (database)
ESSENTIAL of (CS/IT/IS) class 06 (database)ESSENTIAL of (CS/IT/IS) class 06 (database)
ESSENTIAL of (CS/IT/IS) class 06 (database)
 
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdfTataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
 
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
 
MARGINALIZATION (Different learners in Marginalized Group
MARGINALIZATION (Different learners in Marginalized GroupMARGINALIZATION (Different learners in Marginalized Group
MARGINALIZATION (Different learners in Marginalized Group
 
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfLike-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
 

Predict DC Building Energy Usage

  • 1. Power Rangers Carla Coulson, Dominique Hinton, Roman Villoria
  • 3. Project Abstract ● The Energy Section is key contributor to climate change ● The city has placed an emphasis on becoming carbon neutral and more green in the future. ● The group aims to provide the city and building owners with more information to help optimize resources.
  • 4. Initial Hypotheses 1. The best performing buildings are those most recently constructed and with higher ES ratings. 2. Buildings with improving ES ratings over time exhibit reduced energy and water consumption and GHG emissions. 3. Water usage is correlated to overall energy usage. 4. Increases in energy and water usage are associated with extreme weather evidenced by climate change. 5. Changes in energy usage due to the COVID pandemic have resulted in decreases in energy and water usage. 6. Given energy usage data for buildings over 50,000 Gross Square Feet in the District of Columbia, as well as facility Energy Star (ES) ratings and weather data, we can predict future energy usage in a manner that may generate savings for building owners (or operators). Primary Hypothesis Can we predict DC large commercial buildings’ energy usage based on their historical electricity and natural gas consumption and weather patterns?
  • 5. Open Data DC Project Architecture National Climatic Data Center - NOAA Building_Energy_ Benchmarks CSV File PostgreSQL Hosted on Amazon Web Services Regression Scikit- Learn Yellowbrick Features Building Characteristics ● Type ● Area ● Year Built ● NG Heating Monthly Data ● Electricity ● Natural Gas Data Ingestion Data Munging and Wrangling Data Computation and Analysis Data Modeling and Application Data Reporting and Visualization Weather Month Data for DC. Data Cleaning Pandas Jupyter Notebook ● Can we predict energy usage based on historical buildings' electricity & natural gas consumption, and weather patterns? EDA Matplotlab Numpy Pandas Seaborn Data Product Visualization Plotly
  • 7. ● Relational Database ● Selected for WORM capabilities ● Integrates well with AWS ● Ensure all group members had access to an updated copy of the database at all times ● Jupyter Notebooks was used to easily run code using the repl ● Pandas was used to do initial transformations and exploration of the data Data Storage and Initial Analysis
  • 8. Instances by Building Type Heat MapMap Violin Plot Data Cleaning and Wrangling Tools and Initial Visualizations
  • 9. Data Cleaning and Wrangling ● Removed columns that are not relevant ● Removed instances that did not have 12 months of valid data ● Removed duplicates ● Calculated energy intensity (kbtu/sqft) ● Used Pandas Melt function to pivot usage columns to rows ● Met with data owners, the DC Department of Energy and Environment ● Merged property types from 40 to 19 ● Eliminated annual data e.g. - water usage, GHG emissions ● Removed renewable energy as a potential feature because of sparsity of data ● Investigated whether Energy Star scores contributed to energy usage
  • 10. Instances (building month) by Building Type Dominant building types are lodging/residential and office
  • 11. Most lodging/residential and offices are in Ward 2
  • 12. Ward 2 also has the highest average energy intensity across all building types
  • 14. ● Yellowbrick was used to visualize different models and to help with feature selection ● Models were tested on all buildings and then on individual building types ● Global model received relatively good R2 and MSE scores but larger individual models also received good scores
  • 15. Feature Importance of Features (RandomForetsRegressor) with ES Score
  • 16.
  • 17. Back Some definitions: ● Energy Usage in kBtu (1,000 British Thermal Units) ● Intensity = Energy Usage / Square Footage ● CLDD: Cooling Degree Days ● HTDD: Heating Degree Days Additional EDA And Feature Engineering
  • 18. Cyclic Encoding EDA Led Us To Focus The Analysis On Electricity Usage And Take Into Account Seasonal Patterns Natural Gas usage requires different considerations for modeling (dropped)
  • 19. tavg After Feature Engineering, We Decided To Use CLDD And HTDD Instead Of Tavg cldd htdd kbtu intensity
  • 20. Global Model Versus Models By Building Type ● Lodging/Residential and Office buildings: ~80% of the dataset ● Started with simple Linear Regression based on EDA findings ● Energy Usage or Intensity as the target variable? ● Explored different combinations of features Lodging/Residential GLOBAL All Building Types Banks Education Entertainment Food Sales Food Services Healthcare Industrial Mixed Use Others Parking Public Services Religious Utilities Services Tech Retail Storage Office
  • 21. We Made Some Decisions on Target Variables And Some Features, Based on Modeling DOEE recommended using: reported floor area and 2018-2019 usage data Monthly energy usage for years 2010 - 2019 vs. Monthly energy usage for years 2018 - 2019 One Hot Encoded Foreign Keys, one at the time vs. All Foreign Keys (One Hot) Encoded Tax Record Floor Area vs. Reported Floor Area Target Variable: Intensity vs. Target Variable: Energy Usage
  • 22. ● All years ● Tax record area ● One Hot: ‘Ward’ R2 = 0.11 Coefficient R2 Increases When One Hot Encoding Both ‘Ward’ And ‘Year Built’ Global Model, LinearRegression ● All years ● Tax record area ● One Hot: ‘Year Built’ R2 = 0.09 ● All years ● Tax record area ● One Hot: ‘Ward’, ‘Year Built’ R2 = 0.16 1) Effect of different foreign keys as features: ● Years 2018-2019 ● Reported area ● Target: ‘Intensity’ R2 = 0.36 ● Years 2018-2019 ● Reported area ● Target: ‘Energy Usage’ R2 = 0.73 2) Target variable (with One Hot -- ‘Ward’, ‘Year Built’): Also, ‘reported area’ is a better predictor of Energy Usage in commercial buildings
  • 23. Preparation For Modeling ● Built a separate Jupyter notebooks for each model attempt ● Pipeline ○ ColumnTransformer ○ FeatureUnion ○ OneHotEncoder ● Cross validation ○ Time Series Split with 12 folds ○ Returned Coefficient of Determination (R2) and mean squared error (mse) of the regressor, along with the final fitted model, fitted on all of the data
  • 24. Algorithm Selection Global Model: ● LinearRegression ● SGDRegressor, PolynomialFeatures (quad, cub) ● LinearRegression, PolynomialFeatures (quad, cub) ● Random Forest Models by Building Type: ● Ensemble: LinearRegression, RandomForest, VotingRegressor
  • 25. Results Average Usage (MBtu) - All Buildings: Mean R2 Std. Dev. R2 Mean RMSE Std. Dev RMSE LinearRegression 0.72 0.04 891 445 RandomForest 0.82 0.04 718 365 LR-PolyFeat(2) 0.84 0.12 681 614 LR-PolyFeat(3) 0.65 0.23 992 811 P25 P50 P75 174 400 900 Average Usage (MBtu) - Lodg./Res.: Ensemble 0.84 0.04 261 148 174 400 900 Global Model: Lodging/Residential: Average Usage (MBtu) - Office: Ensemble 0.89 0.02 331 129 455 862 1,465 Office:
  • 26. A Global Model Does OK, Per-Building Models Excel At Predicting Energy Usage ● Ensemble models for both Lodging/Residential and Office buildings enhance weaker models such as the Linear Regression, therefore are more predictive ● Linear Regression model with second order polynomial features performs better than third order polynomial ● Global model’s RMSE is considerably high compared to buildings energy usage interquartile ranges
  • 27. Conclusions ● It is possible to accurately predict energy used by DC large commercial buildings with this type of data ● Owner reported (versus tax reported) square footage is the most important driver of energy usage in buildings larger that 50,000 square feet in DC ● Using the methodology presented in this study, DOEE will have a good picture of how large commercial buildings consume energy ● Also, once new data is available, DOEE will have a better understanding of the effects of COVID-19 on energy consumption profiles
  • 28. Next Steps ● Update study once 2020 data is available ● Contribute to the DC Open Data Repo ● Work further with DOEE ● Explore additional features in models ● Look more closely at the importance of building location ● Dominique becomes a TA and later an instructor at G-town and then a Super Star!!!!
  • 31. Cyclic Encoder And Extraction Pipeline
  • 32. Regularization Methods Attempted On Global Model To Eliminate Multicollinearity Algorithm R2 Lasso 0.69 Ridge 0.71 ElasticNet 0.68
  • 33. Joint Plots Year Built vs. Ward: Area Year vs. Built:
  • 34. Yellowbrick Feature Importance - Global Model Global - Lasso Global - Random Forest
  • 35. Yellowbrick Feature Importance - L/R. Model Lodging/Res. - Lasso Lodging/Res. - Random Forest
  • 36. Yellowbrick Feature Importance - Office Model Office - Lasso Office - Random Forest