This paper presents an application of artificial neural networks for short-term times series electrical load
forecasting. An adaptive learning algorithm is derived from system stability to ensure the convergence of
training process. Historical data of hourly power load as well as hourly wind power generation are sourced from
European Open Power System Platform. The simulation demonstrates that errors steadily decrease in training
with the adaptive learning factor starting at different initial value and errors behave volatile with constant
learning factors with different values
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
An Application of Genetic Programming for Power System Planning and OperationIDES Editor
This work incorporates the identification of model
in functional form using curve fitting and genetic programming
technique which can forecast present and future load
requirement. Approximating an unknown function with
sample data is an important practical problem. In order to
forecast an unknown function using a finite set of sample
data, a function is constructed to fit sample data points. This
process is called curve fitting. There are several methods of
curve fitting. Interpolation is a special case of curve fitting
where an exact fit of the existing data points is expected.
Once a model is generated, acceptability of the model must be
tested. There are several measures to test the goodness of a
model. Sum of absolute difference, mean absolute error, mean
absolute percentage error, sum of squares due to error (SSE),
mean squared error and root mean squared errors can be used
to evaluate models. Minimizing the squares of vertical distance
of the points in a curve (SSE) is one of the most widely used
method .Two of the methods has been presented namely Curve
fitting technique & Genetic Programming and they have been
compared based on (SSE)sum of squares due to error.
Nano-satellites are key features for sharing the space data and scientific researches. They embed subsystems that are fed from solar panels and batteries. Power generated from these panels is subject to environmental conditions, most important of them are irradiance and temperature. Optimizing the usage of this power versus environmental variations is a primary task. Synchronous DC-DC buck converter is used to control the power transferred from PV panels to the subsystems while maintaining operation at maximal power. In this paper, artificial intelligence techniques: neural networks and adaptive neural fuzzy inference systems (ANFIS) are used to accomplish the tracking task. Simulation and experimental results demonstrate their efficiency, robustness and tracking quality.
International Journal of Computational Engineering Research(IJCER) is an intentional online Journal in English monthly publishing journal. This Journal publish original research work that contributes significantly to further the scientific knowledge in engineering and Technology
Prediction of Extreme Wind Speed Using Artificial Neural Network ApproachScientific Review SR
Prediction of an accurate wind speed of wind farms is necessary because of the intermittent nature
of wind for any region. Number of methods such as persistence, physical, statistical, spatial correlation, artificial
intelligence network and hybrid are generally available for prediction of wind speed. In this paper, ANN based
methods viz., Multi Layer Perceptron (MLP) and Radial Basis Function (RBF) neural networks are used. The
performance of the networks applied for prediction of wind speed is evaluated by model performance indicators
viz., Correlation Coefficient (CC), Model Efficiency (MEF) and Mean Absolute Percentage Error (MAPE).
Meteorological parameters such as maximum and minimum temperature, air pressure, solar radiation and
altitude are considered as input units for MLP and RBF networks to predict the extreme wind speed at Delhi.
The study shows the values of CC, MEF and MAPE between the observed and predicted wind speed (using
MLP) are computed as 0.992, 95.4% and 4.3% respectively while training the network data. For RBF network,
the values of CC, MEF and MAPE are computed as 0.992, 95.9% and 3.0% respectively. The model
performance analysis indicates the RBF is better suited network among two different networks studied for
prediction of extreme wind speed at Delhi.
Firefly Algorithm to Opmimal Distribution of Reactive Power Compensation Units IJECEIAES
The issue of electric power grid mode of optimization is one of the basic directions in power engineering research. Currently, methods other than classical optimization methods based on various bio-heuristic algorithms are applied. The problems of reactive power optimization in a power grid using bio-heuristic algorithms are considered. These algorithms allow obtaining more efficient solutions as well as taking into account several criteria. The Firefly algorithm is adapted to optimize the placement of reactive power sources as well as to select their values. A key feature of the proposed modification of the Firefly algorithm is the solution for the multi-objective optimization problem. Algorithms based on a bio-heuristic process can find a neighborhood of global extreme, so a local gradient descent in the neighborhood is applied for a more accurate solution of the problem. Comparison of gradient descent, Firefly algorithm and Firefly algorithm with gradient descent is carried out.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
An Application of Genetic Programming for Power System Planning and OperationIDES Editor
This work incorporates the identification of model
in functional form using curve fitting and genetic programming
technique which can forecast present and future load
requirement. Approximating an unknown function with
sample data is an important practical problem. In order to
forecast an unknown function using a finite set of sample
data, a function is constructed to fit sample data points. This
process is called curve fitting. There are several methods of
curve fitting. Interpolation is a special case of curve fitting
where an exact fit of the existing data points is expected.
Once a model is generated, acceptability of the model must be
tested. There are several measures to test the goodness of a
model. Sum of absolute difference, mean absolute error, mean
absolute percentage error, sum of squares due to error (SSE),
mean squared error and root mean squared errors can be used
to evaluate models. Minimizing the squares of vertical distance
of the points in a curve (SSE) is one of the most widely used
method .Two of the methods has been presented namely Curve
fitting technique & Genetic Programming and they have been
compared based on (SSE)sum of squares due to error.
Nano-satellites are key features for sharing the space data and scientific researches. They embed subsystems that are fed from solar panels and batteries. Power generated from these panels is subject to environmental conditions, most important of them are irradiance and temperature. Optimizing the usage of this power versus environmental variations is a primary task. Synchronous DC-DC buck converter is used to control the power transferred from PV panels to the subsystems while maintaining operation at maximal power. In this paper, artificial intelligence techniques: neural networks and adaptive neural fuzzy inference systems (ANFIS) are used to accomplish the tracking task. Simulation and experimental results demonstrate their efficiency, robustness and tracking quality.
International Journal of Computational Engineering Research(IJCER) is an intentional online Journal in English monthly publishing journal. This Journal publish original research work that contributes significantly to further the scientific knowledge in engineering and Technology
Prediction of Extreme Wind Speed Using Artificial Neural Network ApproachScientific Review SR
Prediction of an accurate wind speed of wind farms is necessary because of the intermittent nature
of wind for any region. Number of methods such as persistence, physical, statistical, spatial correlation, artificial
intelligence network and hybrid are generally available for prediction of wind speed. In this paper, ANN based
methods viz., Multi Layer Perceptron (MLP) and Radial Basis Function (RBF) neural networks are used. The
performance of the networks applied for prediction of wind speed is evaluated by model performance indicators
viz., Correlation Coefficient (CC), Model Efficiency (MEF) and Mean Absolute Percentage Error (MAPE).
Meteorological parameters such as maximum and minimum temperature, air pressure, solar radiation and
altitude are considered as input units for MLP and RBF networks to predict the extreme wind speed at Delhi.
The study shows the values of CC, MEF and MAPE between the observed and predicted wind speed (using
MLP) are computed as 0.992, 95.4% and 4.3% respectively while training the network data. For RBF network,
the values of CC, MEF and MAPE are computed as 0.992, 95.9% and 3.0% respectively. The model
performance analysis indicates the RBF is better suited network among two different networks studied for
prediction of extreme wind speed at Delhi.
Firefly Algorithm to Opmimal Distribution of Reactive Power Compensation Units IJECEIAES
The issue of electric power grid mode of optimization is one of the basic directions in power engineering research. Currently, methods other than classical optimization methods based on various bio-heuristic algorithms are applied. The problems of reactive power optimization in a power grid using bio-heuristic algorithms are considered. These algorithms allow obtaining more efficient solutions as well as taking into account several criteria. The Firefly algorithm is adapted to optimize the placement of reactive power sources as well as to select their values. A key feature of the proposed modification of the Firefly algorithm is the solution for the multi-objective optimization problem. Algorithms based on a bio-heuristic process can find a neighborhood of global extreme, so a local gradient descent in the neighborhood is applied for a more accurate solution of the problem. Comparison of gradient descent, Firefly algorithm and Firefly algorithm with gradient descent is carried out.
Short Term Load Forecasting: One Week (With & Without Weekend) Using Artifici...IJLT EMAS
This paper present for analysis of short term load forecasting: one week (with & without weekend) using ANN techniques for SLDC of Gujarat. In this paper short term electric load forecasting using neural network; based on historical load demand, The Levenberg-Marquardt optimization technique which has one of the best learning rates was used as a back propagation algorithm for the Multilayer Feed Forward ANN model using MATLAB.12 ANN tool box. Design a model for one week (with & w/o weekend) load pattern for STLF using the neural network have been input variables are (Min., Avg., & Max. load demands for previous week, Min., Avg., & Max. temperature for previous week & Min., Avg., & Max. humidity for previous week). And Nov-12 to Apr-13 (6 Months) historical load data from the SLDC, Gujarat are used for training, testing and showing the good performance. Using this ANN model computing the mean absolute error between the exact and predicted values, we were able to obtain an absolute mean error within specified limit and regression value close to one. This represents a high degree of accuracy.
Support Vector Machine for Wind Speed PredictionIJRST Journal
The energy is a vital input for the social and economic development of any nation. With increasing agricultural and industrial activities in the country, the demand for energy is also increasing. The increasing use of natural and renewable energy sources is needed to take the burden of our current dependency on fossil fuels. Development and analysis of renewable energy models helps utility in energy forecasting, planning, research and policy making. The wind power is a clean, inexhaustible, and almost a free source of energy. But the integration of wind parks with the power grid has resulted in many challenges for the utility in terms of commitment and control of power plants. As wind speed and wind direction fluctuate frequently, the accurate long-term and short-term forecasting of wind speed is important for ascertaining the wind power generation availability. To deal with wind speed forecasting, many methods have been developed such as physical method, which use lots of physical considerations to reach the best forecasting precision and other is the statistical method, which specializes in finding the relationship of the measured power data. Wind speed can be predicted by using time series analysis, artificial neural network, Kalman Filter method, linear prediction method, spatial correlation models and wavelet, also by using the support vector machines. In this paper, the SVM is used for day ahead prediction of wind speed using historical data of wind park. In this paper Support Vector Machine (SVM) results are compared with feedforward Backpropagation neural network. It is observed that the Mean Absolute Percentage Error (MAPE) by SVM method is around 7% and correlation coefficient is close to 1. This justifies the ability of SVM for wind speed prediction task than Backpropagation algorithm.
WIND SPEED & POWER FORECASTING USING ARTIFICIAL NEURAL NETWORK (NARX) FOR NEW...Journal For Research
Continuous Depleting conventional fuel reserves and its impact as increasing global warming concerns have diverted world attention towards non-conventional energy sources. Out of different non-conventional energy sources wind energy can be consider as one of the cleanest source with minimum possible pollution or harmful emissions and has the potential to decrease the relying on conventional energy sources. Today Wind energy can play a vital role to meet our energy demands; however, it faces various issues such as intermittent nature and frequency instability. To reduce such issues the knowledge of futuristic weather conditions and wind speed trend are required. This work mainly describes the implementation of NARX Artificial neural network for wind speed & power forecasting with the help of historical data available from wind farms.
Optimal design of adaptive power scheduling using modified ant colony optimi...IJECEIAES
For generating and distributing an economic load scheduling approach, artificial neural network (ANN) has been introduced, because power generation and power consumption are economically non-identical. An efficient load scheduling method is suggested in this paper. Normally the power generation system fails due to its instability at peak load time. Traditionally, load shedding process is used in which low priority loads are disconnected from sources. The proposed method handles this problem by scheduling the load based on the power requirements. In many countries the power systems are facing limitations of energy. An efficient optimization algorithm is used to periodically schedule the load demand and the generation. Ant colony optimization (ACO) based ANN is used for this optimal load scheduling process. The present work analyse the technical economical and time-dependent limitations. Also the works meets the demanded load with minimum cost of energy. Inorder to train ANN back propagation (BP) technics is used. A hybrid training process is described in this work. Global optimization algorithms are used to provide back propagation with good initial connection weights.
A Comparative study on Different ANN Techniques in Wind Speed Forecasting for...IOSRJEEE
There are several available renewable sources of energy, among which Wind Power is the one which is most uncertain in nature. This is because wind speed changes continuously with time leading to uncertainty in availability of amount of wind power generated. Hence, a short-term forecasting of wind speed will help in prior estimation of wind power generation availability for the grid and economic load dispatch.This paper present a comparative study of a Wind speed forecasting model using Artificial Neural Networks (ANN) with three different learning algorithms. ANN is used because it is a non-linear data driven, adaptive and very powerful tool for forecasting purposes. Here an attempt is made to forecast Wind Speed using ANN with Levenberg-Marquard (LM) algorithm, Scaled Conjugate Gradient (SCG) algorithm and Bayesian Regularization (BR) algorithm and their results are compared based on their convergence speed in training period and their performance in testing period on the basis of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Mean Square Error (MSE).A 48 hour ahead wind speed is forecasted in this work and it is compared with the measured values using all three algorithms and the best out of the three is selected based on minimum error.
Advance Data Mining - Analysis and forecasting of power factor for optimum el...Shrikant Samarth
Task: Execute a research project using data mining techniques
Approach: The topic chosen was ‘Analysis and Forecasting of Power Factor for Optimum Electric Consumption in a Household.’ Research question – What can be the best short term range of forecast for power factor patterns so that optimum energy consumption can be achieved for a household?
To answer the question, CRISM- DM method was used. The ARIMA machine learning model was developed using R.
Findings: The best short term range of forecasts for the power factor was achieved for 6 months and 12 months duration using the ARIMA model. The MAPE value for the ARIMA model was around 1.83.
Tools: Rstudio
Artificial Neural Network and Multi-Response Optimization in Reliability Meas...inventionjournals
Neural network is an important tool for reliability analysis, including estimation of reliability or utility function which are too complicated to be analytical expressed for large or complex system. It has been demonstrated the neural network has significant improvement in the parameter estimation accuracy over the traditional chi-square test. There are many parameters of a neural network that should be determined while training the dataset, since different setups of algorithm parameters affect the estimation performance in either accuracy or computation efficiency. In this paper, neural network training is used to estimate the utility function for the parallel-series redundancy allocation problem, and weighted principal component based multi-response optimization method is applied to find the optimal setting of neural network parameters so that the simultaneous minimizations of training error and computing time are achieved.
Available transfer capability computations in the indian southern e.h.v power...eSAT Journals
Abstract This paper presents three methods for computing the available transfer capability (ATC). One method is the conventional method known as continuation repeated power flow (CRPF) and other two are the intelligent techniques known as radial basis function neural network (RBFNN), basic adaptive neuro fuzzy inference system (ANFIS). In these two intelligent techniques, the basic ANFIS works with a multiple input single output (MISO) and it is modified as multiple input multiple output (MIMO) ANFIS using the proposed MIMO ANFIS. The main intension of this proposed method is to utilise the significant features of ANFIS with respect to the multiple outputs, as the basic ANFIS has been proved as the best intelligent techniques in the modelling of any application, but it has a disadvantage of single output and this drawback will be overcome using the proposed MIMO ANFIS. In this paper, the latest Indian southern region extra high voltage (SREHV) 72-bus system considered as test system to obtain the ATC computations using three methods. The ATC computations at desired buses are obtained with and without contingencies and compared the conventional ATC computations with the intelligent techniques. The obtained results are scrupulously verified with different test patterns and observed that the accuracy of proposed method is proved as the best as compared to the other methods for computing ATC. In this way, this paper shows a better way to compute ATC for the different open power market system Keywords— Available Transfer Capability, Total Transfer Capability, Open Power Markets, Repeated Power Flow, Radial Basis Function Neural Networks, Adaptive Neuro Fuzzy Inference System etc.
Optimal Load Shedding Using an Ensemble of Artifcial Neural NetworksKashif Mehmood
Optimal load shedding is a very critical issue in power systems. It plays a vital role, especially in third world countries.
A sudden increase in load can affect the important parameters of the power system like voltage, frequency and phase angle. This
paper presents a case study of Pakistan’s power system, where the generated power, the load demand, frequency deviation and load
shedding during a 24-hour period have been provided. An artifcial neural network ensemble is aimed for optimal load shedding.
The objective of this paper is to maintain power system frequency stability by shedding an accurate amount of load. Due to its fast
convergence and improved generalization ability, the proposed algorithm helps to deal with load shedding in an efcient manner.
Combination of Immune Genetic Particle Swarm Optimization algorithm with BP a...paperpublications3
Abstract:In this paper, merging Immune Genetic Particle Swarm Optimization algorithm (IGPSO) with BP algorithm to optimize BP Neural Network parameter i.e., BPIGPSO amalgamation to solve optimal reactive power dispatch algorithm. The basic perception is that first training BP neural network with IGPSO to find out a comparatively optimal solution, then take the network parameter at this time as the preliminary parameter of BP algorithm to carry out the training, finally searching the optimal solution. The proposed BPIGPSO has been tested on standard IEEE 57 bus test system and simulation results show clearly the better performance of the proposed algorithm in reducing the real power loss.
Keywords:BP neural network, Immune Genetic Particle Swarm Optimization algorithm, Optimal Reactive Power, Transmission loss.
The accurate prediction of solar irradiation has been
a leading problem for better energy scheduling approach.
Hence in this paper, an Artificial neural network based solar
irradiance is proposed for five days duration the data is
obtained from National Renewable Energy Laboratory, USA
and the simulation were performed using MATLAB 2013. It
was found that the neural model was able to predict the solar
irradiance with a mean square error of 0.0355.
Predict the Average Temperatures of Baghdad City by Used Artificial Neural Ne...IJERA Editor
This paper utilizes artificial neural networks (ANN) technique to improve temperature forecast performance of
Baghdad city. Our study based on Feed Forward Backpropagation Artificial Neural Networks (BPANN)
algorithm of which trained and tested by used a real world daily average temperatures of Bagdad city for ten
years past for months of January and July. Aimed at providing forecasts in a schedule, for all Days of the month
to help the meteorologist to foresee future weather temperature accurately and easily. Forecasts by ANN model
has been compared with the actual results and the realistic output (with IMOS). The results has been Compared
to the practical temperature prediction results, and shows that the BPANN forecasts have accuracy that gave
reasonably very good result and can be considered as a good method for temperature predicting..
A New Approach to Powerflow Management in Transmission System Using Interline...IJERA Editor
In this paper a new approach to power flow management in transmission system using interline Power Flow
Controller (IPFC) is proposed and model for IPFC is developed and simulate by MATLAB software. Interline
Power Flow Controller is a versatile device can be used to control power flows of a multi-line system or subnetworks
An Interline Power Flow Controller (IPFC) is a converter based FACTS controller for series
compensation with capability of controlling power flow among multi-lines within the same corridor of the
transmission line. It consists of two or more Voltage Source Converters (VSCs) with a common dc-link. Real
power can be transferred via the common dc-link between the VSCs and each VSC is capable of exchanging
reactive power with its own transmission system
Protons Relaxation and Temperature Dependence Due To Tunneling Methyl GroupIJERA Editor
Tunneling frequency and temperature dependence of proton spin lattice relaxation time T1, are depend upon the
height and the shape of the hindering barrier of methyl rotation and carry information on the group is molecular
environment are reported for some samples containing tertiary-butyl group.The temperature rang was 4-
300k.Data has been analyzed to provide estimates for the magnitude of the three fold potential barrier to
reorientation of all methyl groups in these materials. At low temperature the motion of the tertiary-butyl protons
can usually be neglected. All protons of the samples relax as a single system.In one or two cases tunneling is
observed for the first time in Tert-butyl. The T1 results are used to evaluate tunnel frequency in other cases. The
result suggest the importance of collective motion of methyl group in tert-butyl
Short Term Load Forecasting: One Week (With & Without Weekend) Using Artifici...IJLT EMAS
This paper present for analysis of short term load forecasting: one week (with & without weekend) using ANN techniques for SLDC of Gujarat. In this paper short term electric load forecasting using neural network; based on historical load demand, The Levenberg-Marquardt optimization technique which has one of the best learning rates was used as a back propagation algorithm for the Multilayer Feed Forward ANN model using MATLAB.12 ANN tool box. Design a model for one week (with & w/o weekend) load pattern for STLF using the neural network have been input variables are (Min., Avg., & Max. load demands for previous week, Min., Avg., & Max. temperature for previous week & Min., Avg., & Max. humidity for previous week). And Nov-12 to Apr-13 (6 Months) historical load data from the SLDC, Gujarat are used for training, testing and showing the good performance. Using this ANN model computing the mean absolute error between the exact and predicted values, we were able to obtain an absolute mean error within specified limit and regression value close to one. This represents a high degree of accuracy.
Support Vector Machine for Wind Speed PredictionIJRST Journal
The energy is a vital input for the social and economic development of any nation. With increasing agricultural and industrial activities in the country, the demand for energy is also increasing. The increasing use of natural and renewable energy sources is needed to take the burden of our current dependency on fossil fuels. Development and analysis of renewable energy models helps utility in energy forecasting, planning, research and policy making. The wind power is a clean, inexhaustible, and almost a free source of energy. But the integration of wind parks with the power grid has resulted in many challenges for the utility in terms of commitment and control of power plants. As wind speed and wind direction fluctuate frequently, the accurate long-term and short-term forecasting of wind speed is important for ascertaining the wind power generation availability. To deal with wind speed forecasting, many methods have been developed such as physical method, which use lots of physical considerations to reach the best forecasting precision and other is the statistical method, which specializes in finding the relationship of the measured power data. Wind speed can be predicted by using time series analysis, artificial neural network, Kalman Filter method, linear prediction method, spatial correlation models and wavelet, also by using the support vector machines. In this paper, the SVM is used for day ahead prediction of wind speed using historical data of wind park. In this paper Support Vector Machine (SVM) results are compared with feedforward Backpropagation neural network. It is observed that the Mean Absolute Percentage Error (MAPE) by SVM method is around 7% and correlation coefficient is close to 1. This justifies the ability of SVM for wind speed prediction task than Backpropagation algorithm.
WIND SPEED & POWER FORECASTING USING ARTIFICIAL NEURAL NETWORK (NARX) FOR NEW...Journal For Research
Continuous Depleting conventional fuel reserves and its impact as increasing global warming concerns have diverted world attention towards non-conventional energy sources. Out of different non-conventional energy sources wind energy can be consider as one of the cleanest source with minimum possible pollution or harmful emissions and has the potential to decrease the relying on conventional energy sources. Today Wind energy can play a vital role to meet our energy demands; however, it faces various issues such as intermittent nature and frequency instability. To reduce such issues the knowledge of futuristic weather conditions and wind speed trend are required. This work mainly describes the implementation of NARX Artificial neural network for wind speed & power forecasting with the help of historical data available from wind farms.
Optimal design of adaptive power scheduling using modified ant colony optimi...IJECEIAES
For generating and distributing an economic load scheduling approach, artificial neural network (ANN) has been introduced, because power generation and power consumption are economically non-identical. An efficient load scheduling method is suggested in this paper. Normally the power generation system fails due to its instability at peak load time. Traditionally, load shedding process is used in which low priority loads are disconnected from sources. The proposed method handles this problem by scheduling the load based on the power requirements. In many countries the power systems are facing limitations of energy. An efficient optimization algorithm is used to periodically schedule the load demand and the generation. Ant colony optimization (ACO) based ANN is used for this optimal load scheduling process. The present work analyse the technical economical and time-dependent limitations. Also the works meets the demanded load with minimum cost of energy. Inorder to train ANN back propagation (BP) technics is used. A hybrid training process is described in this work. Global optimization algorithms are used to provide back propagation with good initial connection weights.
A Comparative study on Different ANN Techniques in Wind Speed Forecasting for...IOSRJEEE
There are several available renewable sources of energy, among which Wind Power is the one which is most uncertain in nature. This is because wind speed changes continuously with time leading to uncertainty in availability of amount of wind power generated. Hence, a short-term forecasting of wind speed will help in prior estimation of wind power generation availability for the grid and economic load dispatch.This paper present a comparative study of a Wind speed forecasting model using Artificial Neural Networks (ANN) with three different learning algorithms. ANN is used because it is a non-linear data driven, adaptive and very powerful tool for forecasting purposes. Here an attempt is made to forecast Wind Speed using ANN with Levenberg-Marquard (LM) algorithm, Scaled Conjugate Gradient (SCG) algorithm and Bayesian Regularization (BR) algorithm and their results are compared based on their convergence speed in training period and their performance in testing period on the basis of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Mean Square Error (MSE).A 48 hour ahead wind speed is forecasted in this work and it is compared with the measured values using all three algorithms and the best out of the three is selected based on minimum error.
Advance Data Mining - Analysis and forecasting of power factor for optimum el...Shrikant Samarth
Task: Execute a research project using data mining techniques
Approach: The topic chosen was ‘Analysis and Forecasting of Power Factor for Optimum Electric Consumption in a Household.’ Research question – What can be the best short term range of forecast for power factor patterns so that optimum energy consumption can be achieved for a household?
To answer the question, CRISM- DM method was used. The ARIMA machine learning model was developed using R.
Findings: The best short term range of forecasts for the power factor was achieved for 6 months and 12 months duration using the ARIMA model. The MAPE value for the ARIMA model was around 1.83.
Tools: Rstudio
Artificial Neural Network and Multi-Response Optimization in Reliability Meas...inventionjournals
Neural network is an important tool for reliability analysis, including estimation of reliability or utility function which are too complicated to be analytical expressed for large or complex system. It has been demonstrated the neural network has significant improvement in the parameter estimation accuracy over the traditional chi-square test. There are many parameters of a neural network that should be determined while training the dataset, since different setups of algorithm parameters affect the estimation performance in either accuracy or computation efficiency. In this paper, neural network training is used to estimate the utility function for the parallel-series redundancy allocation problem, and weighted principal component based multi-response optimization method is applied to find the optimal setting of neural network parameters so that the simultaneous minimizations of training error and computing time are achieved.
Available transfer capability computations in the indian southern e.h.v power...eSAT Journals
Abstract This paper presents three methods for computing the available transfer capability (ATC). One method is the conventional method known as continuation repeated power flow (CRPF) and other two are the intelligent techniques known as radial basis function neural network (RBFNN), basic adaptive neuro fuzzy inference system (ANFIS). In these two intelligent techniques, the basic ANFIS works with a multiple input single output (MISO) and it is modified as multiple input multiple output (MIMO) ANFIS using the proposed MIMO ANFIS. The main intension of this proposed method is to utilise the significant features of ANFIS with respect to the multiple outputs, as the basic ANFIS has been proved as the best intelligent techniques in the modelling of any application, but it has a disadvantage of single output and this drawback will be overcome using the proposed MIMO ANFIS. In this paper, the latest Indian southern region extra high voltage (SREHV) 72-bus system considered as test system to obtain the ATC computations using three methods. The ATC computations at desired buses are obtained with and without contingencies and compared the conventional ATC computations with the intelligent techniques. The obtained results are scrupulously verified with different test patterns and observed that the accuracy of proposed method is proved as the best as compared to the other methods for computing ATC. In this way, this paper shows a better way to compute ATC for the different open power market system Keywords— Available Transfer Capability, Total Transfer Capability, Open Power Markets, Repeated Power Flow, Radial Basis Function Neural Networks, Adaptive Neuro Fuzzy Inference System etc.
Optimal Load Shedding Using an Ensemble of Artifcial Neural NetworksKashif Mehmood
Optimal load shedding is a very critical issue in power systems. It plays a vital role, especially in third world countries.
A sudden increase in load can affect the important parameters of the power system like voltage, frequency and phase angle. This
paper presents a case study of Pakistan’s power system, where the generated power, the load demand, frequency deviation and load
shedding during a 24-hour period have been provided. An artifcial neural network ensemble is aimed for optimal load shedding.
The objective of this paper is to maintain power system frequency stability by shedding an accurate amount of load. Due to its fast
convergence and improved generalization ability, the proposed algorithm helps to deal with load shedding in an efcient manner.
Combination of Immune Genetic Particle Swarm Optimization algorithm with BP a...paperpublications3
Abstract:In this paper, merging Immune Genetic Particle Swarm Optimization algorithm (IGPSO) with BP algorithm to optimize BP Neural Network parameter i.e., BPIGPSO amalgamation to solve optimal reactive power dispatch algorithm. The basic perception is that first training BP neural network with IGPSO to find out a comparatively optimal solution, then take the network parameter at this time as the preliminary parameter of BP algorithm to carry out the training, finally searching the optimal solution. The proposed BPIGPSO has been tested on standard IEEE 57 bus test system and simulation results show clearly the better performance of the proposed algorithm in reducing the real power loss.
Keywords:BP neural network, Immune Genetic Particle Swarm Optimization algorithm, Optimal Reactive Power, Transmission loss.
The accurate prediction of solar irradiation has been
a leading problem for better energy scheduling approach.
Hence in this paper, an Artificial neural network based solar
irradiance is proposed for five days duration the data is
obtained from National Renewable Energy Laboratory, USA
and the simulation were performed using MATLAB 2013. It
was found that the neural model was able to predict the solar
irradiance with a mean square error of 0.0355.
Predict the Average Temperatures of Baghdad City by Used Artificial Neural Ne...IJERA Editor
This paper utilizes artificial neural networks (ANN) technique to improve temperature forecast performance of
Baghdad city. Our study based on Feed Forward Backpropagation Artificial Neural Networks (BPANN)
algorithm of which trained and tested by used a real world daily average temperatures of Bagdad city for ten
years past for months of January and July. Aimed at providing forecasts in a schedule, for all Days of the month
to help the meteorologist to foresee future weather temperature accurately and easily. Forecasts by ANN model
has been compared with the actual results and the realistic output (with IMOS). The results has been Compared
to the practical temperature prediction results, and shows that the BPANN forecasts have accuracy that gave
reasonably very good result and can be considered as a good method for temperature predicting..
A New Approach to Powerflow Management in Transmission System Using Interline...IJERA Editor
In this paper a new approach to power flow management in transmission system using interline Power Flow
Controller (IPFC) is proposed and model for IPFC is developed and simulate by MATLAB software. Interline
Power Flow Controller is a versatile device can be used to control power flows of a multi-line system or subnetworks
An Interline Power Flow Controller (IPFC) is a converter based FACTS controller for series
compensation with capability of controlling power flow among multi-lines within the same corridor of the
transmission line. It consists of two or more Voltage Source Converters (VSCs) with a common dc-link. Real
power can be transferred via the common dc-link between the VSCs and each VSC is capable of exchanging
reactive power with its own transmission system
Protons Relaxation and Temperature Dependence Due To Tunneling Methyl GroupIJERA Editor
Tunneling frequency and temperature dependence of proton spin lattice relaxation time T1, are depend upon the
height and the shape of the hindering barrier of methyl rotation and carry information on the group is molecular
environment are reported for some samples containing tertiary-butyl group.The temperature rang was 4-
300k.Data has been analyzed to provide estimates for the magnitude of the three fold potential barrier to
reorientation of all methyl groups in these materials. At low temperature the motion of the tertiary-butyl protons
can usually be neglected. All protons of the samples relax as a single system.In one or two cases tunneling is
observed for the first time in Tert-butyl. The T1 results are used to evaluate tunnel frequency in other cases. The
result suggest the importance of collective motion of methyl group in tert-butyl
Design and Implementation of Low Power 3-Bit Flash ADC Using 180nm CMOS Techn...IJERA Editor
Analog-to-digital converter has become a very important device in today’s digitized world as they have a very
wide variety of applications. Among all the ADC’s available, the Flash ADC is the fastest one but a main
disadvantage of Flash ADC is its power consumption. So, this paper aims at implementing a low power high
speed Flash ADC. A 3-bit Flash ADC has been designed using CMOS technology. A two stage open loop
comparator and a priority encoder have been implemented using which the ADC has been designed. All the
circuits are simulated using 180nm technology in Tanner EDA environment. The supply voltage Vdd is
1.8v.Analog output of each comparator depending upon the comparison between the input and the reference
voltage is fed to the encoder and finally the compressed digital output is obtained. The power dissipation of
each circuit implemented is calculated individually including other parameters like are, resolution gain and
speed.
ANET: Technical and Future Challenges with a Real Time Vehicular Traffic Simu...IJERA Editor
VANET or Vehicular Ad-Hoc Network is a special type of MANET or Mobile Ad-Hoc Network that is
designed specifically for communications between vehicles or V2V and vehicles to infrastructure or V2I. There
is a lot of studies and research that has been dedicated to study this technology due to its importance and
necessity in our life. The fact that each and every module presented must be tested thoroughly before putting it
into action, as there will be severe consequences in case of a system malfunction especially if it's a vehicular
design problem. However, seeing VANETS coming into reality becomes very close with the advancement of
IEEE 802.11p standard that is being dedicated to the DSRC or dedicated short range communication [1]. This
paper will discuss this technology emphasizing some of its applications, current limitations and future challenges
plus simulating a real traffic using SUMO and OpenStreetMap
Motion Compensation With Prediction Error Using Ezw Wavelet CoefficientsIJERA Editor
The video compression technique is used to represent any video with minimal distortion. In the compression
techniques of image processing, DWT is more significant because of its multi-resolution properties. DCT used
in video coding often produces undesirability. The main objective of video coding is reduce spatial and temporal
redundancies. In this proposed work a new encoder is designed by exploiting the multi – resolution properties of
DWT to get the prediction error, using motion estimation technique to avoid the translation invariance.
SVM Based Identification of Psychological Personality Using Handwritten Text IJERA Editor
Identification of Personality is a complex process. To ease this process, a model is developed using cursive
handwriting. Area based, width based and height based thresholds are set for only character selection, word
selection and line selection. The rest is considered as noise. Followed by feature vector construction. Slope
feature using slope calculation, shape features and edge detection done using Sobel filter and direction
histogram is considered. Based on the direction of handwriting the analysis was done. Writing which rises to
the right shows optimism and cheerfulness. Sagging to the right shows physical or mental weariness. The lines
which are straight, reveals over-control to compensate for an inner fear of loss of control.The analysis was done
using single line and multiple lines. Simple techniques have provided good results. The results using single line
were 95% and multiple lines were 91%.The classification is done using SVM classifier.
An approach to the integration of knowledge mapsIJERA Editor
Knowledge plays more and more important role in the heavy competition environment. In order to facilitate the
inter-enterpriseknowledge sharing, the knowledge map in each enterprise needs to be integrated. In the paper, the
knowledge map integration approach is proposed. Firstly, the explicit knowledge is integrated. In the integration,
the documents in the original knowledge map are classified into the corresponding categories in the main
knowledge map according to the relevance. The unclassified documents are clustered to derive new categories.
Afterwards, experts, which are the owner of implicit knowledge, are classified based on the registered
documents or the documents in the original categories. Finally, the ranking of experts in each category are
determined. The illustrative example shows the proposed approach is feasible and performances well.
A Review on Experimental Investigation of Machining Parameters during CNC Mac...IJERA Editor
This review paper aims towards the optimization of CNC turning operation when used over an OHNS material.
The lathe machine was chosen because of its widespread availability and its ability to perform various tasks
without much change in its structure. Also using lathe machines is very cheap and hence it is beneficial from
economic point of view as well. The turning operation was specifically chosen because of the various
advantages that it offers. It can be used for machining a large variety of materials and it is cheaper than milling.
OHNS (Oil Hardened Non Shrinking) tool was chosen due to its hardness. These materials are used only for
dies so it was chosen so that its industrial usage could be exploited. To comprehend the usage, all the input and
output parameters that could affect the machining process, namely input parameters like feed, cutting
conditions, speed, etc. and output parameters like surface roughness, surface finish, material removal rate were
analyzed using the researches that had already been done on CNC turning. After careful study of a variety of
research papers on this topic, it was decided that several input as well as the output parameters would be
considered which included feed, depth of cut and cutting speed were taken as the input parameters whereas
Material Removal Rate (MRR) and surface finish were taken as the output parameters. From the results of the
research papers, it was concluded that feed, depth of cut and cutting speed could be chosen as input parameters
whereas MRR and surface finish would be the output parameters
Enhanced Anti-Weathering of Nanocomposite Coatings with Silanized Graphene Na...IJERA Editor
This article presents the development of a nanocomposite coating using nanographene platelets associated with
an epoxy primer to improve the coating resistance against corrosion and weathering. Based on the hypothesis
that coatings containing nanoadditives would provide strong resistance to degradation and that modified
graphene particles through silanization improve the stability of the graphene particles in the coatings, the
performance of the nanocomposite coatings was assessed by exposing them to ultraviolet (UV) light and salt fog
by placing specimens alternatively in two respective chambers for intervals of 24 hours for 20 days. Coating
performance analyses were carried out using atomic force microscopy (AFM), Fourier transform infrared
(FTIR) spectrometer thickness measurements, water contact angle, and electro impedance spectroscopy (EIS)
testing. Results show that a 17.15% reduction in coating thickness is observed for the coating containing
silanized graphene in contrast to a 20.60% reduction in thickness for the coating with unmodified graphene.
Furthermore, nanocomposite coatings containing unmodified graphene had a higher corrosion rate (38.71E-06
mpy) and a lower impedance value (75,040 ohms) than nanocomposite coatings containing silanized graphene,
boasting a corrosion rate of 12.11E-06 mpy and an impedance value of 140,000 ohms, which confirmed the
positive effects of graphene silanization
Moving Bed Biofilm Reactor -A New Perspective In Pulp And Paper Waste Water T...IJERA Editor
The pulp and paper mill effluent is one of the high polluting effluent amongst the effluents obtained
from polluting industries. All the available methods for treatment of pulp and paper mill effluent have certain
drawbacks. In this work, experiments were conducted to treat the pulp and paper mill effluent using moving bed
biofilm reactor (MBBR).The wastewater generated by these industries contains high COD, BOD, colour, organic
substances and toxic chemicals. This study was carried out on laboratory scale Moving Bed Biofilm Reactor with
proflex type biocarriers, where the biofilm grows on small, free floating plastic elements with a large surface area
and a density slightly less than 1.0 g/cm3
. The reactor was operated continuously at 50% percentages filling of
biocarriers. During the filling percentage, the removal efficiencies of COD & BOD were monitored at the time
period of 2h, 4h, 6h and 8h. The result showed that the maximum COD and BOD removal of 87% were achieved
for the 50 percent filling of biocarriers at the HRT of 8 h. From the experimental results, the moving bed biofilm
reactor could be used as an ideal and efficient option for the organic and inorganic removal from the wastewater
of pulp and paper industry
A Fuzzy Inventory Model with Perishable and Aging ItemsIJERA Editor
A parametric multi-period inventory model for perishable items considered in this paper. Each item in the stock
perishes in a given period of time with some uncertainty. A model derived for recursive unnormalized
conditional distributions of { } given the information accumulated about the inventory level- surviving items
processes.
Implementation of Huffman Decoder on FpgaIJERA Editor
Lossless data compression algorithm is most widely used algorithm in data transmission, reception and storage
systems in order to increase data rate, speed and save lots of space on storage devices. Now-a-days, different
algorithms are implemented in hardware to achieve benefits of hardware realizations. Hardware implementation
of algorithms, digital signal processing algorithms and filter realization is done on programmable devices i.e.
FPGA. In lossless data compression algorithms, Huffman algorithm is most widely used because of its variable
length coding features and many other benefits. Huffman algorithms are used in many applications in software
form, e.g. Zip and Unzip, communication, etc. In this paper, Huffman algorithm is implemented on Xilinx
Spartan 3E board. This FPGA is programmed by Xilinx tool, Xilinx ISE 8.2i. The program is written in VHDL
and text data is decoded by a Huffman algorithm on Hardware board which was previously encoded by
Huffman algorithm. In order to visualize the output clearly in waveforms, the same code is simulated on
ModelSim v6.4. Huffman decoder is also implemented in the MATLAB for verification of operation. The
FPGA is a configurable device which is more efficient in all aspects. Text application, image processing, video
streaming and in many other applications Huffman algorithms are implemented.
Equipment Inventory Management and Transaction Recording Using Bar Coding Sch...IJERA Editor
The aim of the study is to implement bar coding system developed through the VB6 and
Microsoft Access as mechanism for the PUP ECE Laboratory Transaction recording and monitoring. The study
was concerned on proper documenting and managing the daily transaction of the ECE Laboratory with the
AutoLab System.Results showed that the AutoLab System effectively automated the recording of transactions
merging the existing manual method into one recording mechanism. The Automated Laboratory coined as
AutoLab merged the ECE Room Utilization Log Book, ECE Borrower’s Slip and the ECE Transaction Log
Book into one complete package in terms of transaction recording and equipment inventory monitoring.
A Novel Timer-Based Hybrid Rerouting Algorithm for Improving Resource Utiliza...IJERA Editor
In this paper we investigate hybrid rerouting and minimization of incurred service disruption period due to
rerouting in Wavelength Division Multiplexed (WDM) transparent optical network. One limitation of such a
network is the wavelength continuity constraint which does not allow a circuit to be placed on a non
wavelength-continuous route. The impact of this constraint might have a severe consequence on the
performance of transparent optical networks especially in terms of rejection ratio ant it is especially severe when
traffic demands are unpredictable and characterized by random arrivals and departures. To alleviate the impact
of these constraints, either wavelength conversion or traffic rerouting can be used. Since, in the foreseeable
future, wavelength conversion is expected to remain an expensive technology, traffic rerouting is an attractive
alternative solution. Thus, we here propose to employ hybrid rerouting to improve the network performances.
Hybrid rerouting combines passive and active rerouting. Through simulation results, the performances of the
proposed algorithm in terms of rejection ratio are demonstrated to be promising while rerouting a small number
of already established lightpaths using Lightpath ReRouting (LRR). By rerouting a small number of existing
lightpaths using LRR, we hope that the incurred service disruption period due to rerouting is minimized.
Outlier Detection Using Unsupervised Learning on High Dimensional DataIJERA Editor
The outliers in data mining can be detected using semi-supervised and unsupervised methods. Outlier
detection in high dimensional data faces various challenges from curse of dimensionality. It means due
to the distance concentration the data becomes unobvious in high dimensional data. Using outlier
detection techniques, the distance base methods are used to detect outliers and label all the points as
good outliers. In high dimensional data to detect outliers effectively, we use unsupervised learning
methods like IQR, KNN with Anti hub.
Probable technologies behind the Vimanas described in RamayanaIJERA Editor
In Sanskrit literature there is a prominent place for Maharshi Valmiki‟s Ramayana. This is one of the very few
popular epics which are translated to multiple languages across the world. It has seven kaandas (books), five
hundred sargas (chapters) and twenty four thousand slokas (verses) in it. The vimanas are described in various
kaandas of Ramayana. It is said that Ravana had the vimana which could appear and disappear, travel long
distances with high speed based on the thought power of the master. A few years ago in the year 2013
researchers from the University of Minnesota have designed a model quadcopter which can be flown by the
human thought power. As per Prof Bin He from the University of Minnesota, for the first time humans are able
to control the flight of flying robots using just their thought sensed from non-invasive brain waves. German
scientists from the Technical University of Munich under the leadership of Professor Tim Fricke have simulated
the flight of aircraft using thought power of the pilots. This makes us think if such an aircraft with an advanced
technology like this existed once upon a time during the era of Ramayana. Carvings of Ravana‟s vimana in
Ellora cave temples help us in comparing it with that of modern Jetpack. Descriptions on seating capacity of
Pushpaka vimana help us in comparing the same with Airbus 380-800 which can accommodate 853 passengers.
Concepts of invisibility of aircrafts make us think of camouflaging techniques and stealth technology used in
modern military aircrafts. All these features help us in analyzing the probable technologies behind vimanas
described in Ramayana.
Through Lean Manufacturing Techniques Improvement InProduction of Cement PlantIJERA Editor
The production of cement is a process industry which is distinct from manufacturing and the main objective here
is to apply lean manufacturing technique to the eradicate waste to the processes and parameters which are
common between process and discrete manufacturing. Lean signifies a major advance over traditional mass
production methods. Value stream mapping is used first to identify different waste present in the current state.
This paper will describe work undertaken investigating the application of lean thinking to a continuous
production environment, in this instance exemplified by the cement industry. Implementation of lean helps
many organizations to improve their productivity and efficiency Cement plays a vital role in economic
development of any country. Having more than a hundred and fifty years history, it has been used extensively in
construction of anything, from a small building to a mammoth multi-purpose project. The need for improving
the efficiency of the cement production line is widely acknowledged in order to reduce the downtime rates, and
satisfy high levels of market demand where the demand for cement is mostly second substance behind water.
This paper articulates a methodology for data collection, knowledge extraction, model creation and
experimentation that combines the use of process mapping, computational simulation. A detailed description of
each step of the process is given and is illustrated by results from a case study undertaken during the research.
This paper describes work undertaken to implement lean practices in the continuous process sector as
represented by cement production. One of the major barriers to lean implementation is providing evidence of its
potential benefit to end-users. This work aims to overcome this obstacle by producing a tool which can be used
to easily visualize the benefits of adopting lean practices without requiring disruption to the production
environment.
Study of Earthquake Forces By Changing the Location of Lift CoreIJERA Editor
Lift core is an important element for strengthening of structure in earthquake prone area (Mw=6.5 or more).
This paper deals with use of lift cores to resist the seismic forces and its effect by changing the lift core location.
The study for G+5 and G+10 type frame buildings are taken under consideration. These buildings are further
subdivided as per soil strata i.e. hard, medium, and soft. Two locations of lift core considered for studies i.e.
centre core and corner core. Zone V is considered for all buildings which will cause maximum base shear to the
structure. Study is focused on comparative static and dynamic analysis which will show graphical
representation of G+5 and G+10 building along with soil type. Economy is studied in analysis.
In this paper, three beamforming design are considered for multi user MIMO system. First, transmit
beamformers are fixed and the receive (RX) beamformers are calculated. Transmit beamformer (TX-BF)is
projectedas a null space of appropriate channels. It reduces the interference for each user. Then the receiver
beamformer is determined which maximize the SNR. This beamforming design provides less computation time.
The second case is joint TX and RX beamformer for SNR maximization. In this transmitter and receiver
beamformer are calculated using extended alternating optimization (EAO) algorithm. The third one is joint
transmitter and receiver beamforming for SNR and SINR maximization using EAO algorithm. This algorithm
provides better error performance and sum rate performance. All the design cases are simulated by using
standard multipath channel model. Our simulation results illustrate that compared to the least square design and
zero forcing design, the joint TX and RX beamforming design using EAO algorithm provides faster
beamforming and improved error performance and sum rate.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Power system transient stability margin estimation using artificial neural ne...elelijjournal
This paper presents a methodology for estimating the normalized transient stability margin by using the multilayered perceptron (MLP) neural network. The complex relationship between the input variables and output variables is established by using the neural networks. The nonlinear mapping relation between the normalized transient stability margin and the operating conditions of the power system is established by using the MLP neural network. To obtain the training set of the neural network the potential energy boundary surface (PEBS) method along with time domain simulation method is used. The proposed method is applied on IEEE 9 bus system and the results shows that the proposed method provides fast and accurate tool to assess online transient stability.
AN IMPROVED METHOD FOR IDENTIFYING WELL-TEST INTERPRETATION MODEL BASED ON AG...IAEME Publication
This paper presents an approach based on applying an aggregated predictor formed by multiple versions of a multilayer neural network with a back-propagation optimization algorithm for helping the engineer to get a list of the most appropriate well-test interpretation models for a given set of pressure/ production data. The proposed method consists of three stages: (1) data decorrelation through principal component analysis to reduce the covariance between the variables and the dimension of the input layer in the artificial neural network, (2) bootstrap replicates of the learning set where the data is repeatedly sampled with a random split of the data into train sets and using these as new learning sets, and (3) automatic reservoir model identification through aggregated predictor formed by a plurality vote when predicting a new class. This method is described in detail to ensure successful replication of results. The required training and test dataset were generated by using analytical solution models. In our case, there were used 600 samples: 300 for training, 100 for cross-validation, and 200 for testing. Different network structures were tested during this study to arrive at optimum network design. We notice that the single net methodology always brings about confusion in selecting the correct model even though the training results for the constructed networks are close to 1. We notice also that the principal component analysis is an effective strategy in reducing the number of input features, simplifying the network structure, and lowering the training time of the ANN. The results obtained show that the proposed model provides better performance when predicting new data with a coefficient of correlation approximately equal to 95% Compared to a previous approach 80%, the combination of the PCA and ANN is more stable and determine the more accurate results with lesser computational complexity than was feasible previously. Clearly, the aggregated predictor is more stable and shows less bad classes compared to the previous approach.
Daily Peak Load Forecast Using Artificial Neural NetworkIJECEIAES
The paper presents an Artificial Neural Network (ANN) model for short-term load forecasting of daily peak load. A multi-layered feed forward neural network with Levenberg-Marquardt learning algorithm is used because of its good generalizing property and robustness in prediction. The input to the network is in terms of historical daily peak load data and corresponding daily peak temperature data. The network is trained to predict the load requirement ahead. The effectiveness of the proposed ANN approach to the short-term load forecasting problems is demonstrated by practical data from the Bangalore Electricity Supply Company Limited (BESCOM). The comparison between the proposed and the conventional methods is made in terms of percentage error and it is found that the proposed ANN model gives more accurate predictions with optimal number of neurons in the hidden layer.
Short Term Load Forecasting Using Bootstrap Aggregating Based Ensemble Artifi...Kashif Mehmood
Short Term Load Forecasting (STLF) can predict load from several minutes to week plays
the vital role to address challenges such as optimal generation, economic scheduling, dispatching and
contingency analysis. This paper uses Multi-Layer Perceptron (MLP) Artificial Neural Network
(ANN) technique to perform STFL but long training time and convergence issues caused by bias,
variance and less generalization ability, unable this algorithm to accurately predict future loads. This
issue can be resolved by various methods of Bootstraps Aggregating (Bagging) (like disjoint
partitions, small bags, replica small bags and disjoint bags) which helps in reducing variance and
increasing generalization ability of ANN. Moreover, it results in reducing error in the learning process
of ANN. Disjoint partition proves to be the most accurate Bagging method and combining outputs of
this method by taking mean improves the overall performance. This method of combining several
predictors known as Ensemble Artificial Neural Network (EANN) outperform the ANN and Bagging
method by further increasing the generalization ability and STLF accuracy.
Combination of Immune Genetic Particle Swarm Optimization algorithm with BP a...paperpublications3
Abstract:In this paper, merging Immune Genetic Particle Swarm Optimization algorithm (IGPSO) with BP algorithm to optimize BP Neural Network parameter i.e., BPIGPSO amalgamation to solve optimal reactive power dispatch algorithm. The basic perception is that first training BP neural network with IGPSO to find out a comparatively optimal solution, then take the network parameter at this time as the preliminary parameter of BP algorithm to carry out the training, finally searching the optimal solution. The proposed BPIGPSO has been tested on standard IEEE 57 bus test system and simulation results show clearly the better performance of the proposed algorithm in reducing the real power loss.
Short Term Load Forecasting Using Multi Layer Perceptron IJMER
Load forecasting is the method for prediction of Electrical load. Short term load forecasting is
one of the important concerns of power system and accurate load forecasting is essential for managing
supply and demand of electricity. The basic objective of STLF is to predict the near future load for example
next hour load prediction or next day load prediction etc….There are various factors which influence the
behaviour of the consumer load. The factors that we consider in this paper are Load,Temperature, humidity,
time. The ANN is used to learn the relationship among past, current and future parameters like load, temp. In
this paper we are using Multi parameter regression and comparing the results with the Artificial Neural
network output. Finally, outcomes of the approaches are evaluated and compared by means of the Mean
absolute Percentage error (MAPE).ANN outcomes are more fairly
accurate to the actual loads than those of conventional methods. So it can be considered as the suitable tool
to deal with STLF problems.
Saudi Arabia stands as a titan in the global energy landscape, renowned for its abundant oil and gas resources. It's the largest exporter of petroleum and holds some of the world's most significant reserves. Let's delve into the top 10 oil and gas projects shaping Saudi Arabia's energy future in 2024.
Welcome to WIPAC Monthly the magazine brought to you by the LinkedIn Group Water Industry Process Automation & Control.
In this month's edition, along with this month's industry news to celebrate the 13 years since the group was created we have articles including
A case study of the used of Advanced Process Control at the Wastewater Treatment works at Lleida in Spain
A look back on an article on smart wastewater networks in order to see how the industry has measured up in the interim around the adoption of Digital Transformation in the Water Industry.
Courier management system project report.pdfKamal Acharya
It is now-a-days very important for the people to send or receive articles like imported furniture, electronic items, gifts, business goods and the like. People depend vastly on different transport systems which mostly use the manual way of receiving and delivering the articles. There is no way to track the articles till they are received and there is no way to let the customer know what happened in transit, once he booked some articles. In such a situation, we need a system which completely computerizes the cargo activities including time to time tracking of the articles sent. This need is fulfilled by Courier Management System software which is online software for the cargo management people that enables them to receive the goods from a source and send them to a required destination and track their status from time to time.
Quality defects in TMT Bars, Possible causes and Potential Solutions.PrashantGoswami42
Maintaining high-quality standards in the production of TMT bars is crucial for ensuring structural integrity in construction. Addressing common defects through careful monitoring, standardized processes, and advanced technology can significantly improve the quality of TMT bars. Continuous training and adherence to quality control measures will also play a pivotal role in minimizing these defects.
Automobile Management System Project Report.pdfKamal Acharya
The proposed project is developed to manage the automobile in the automobile dealer company. The main module in this project is login, automobile management, customer management, sales, complaints and reports. The first module is the login. The automobile showroom owner should login to the project for usage. The username and password are verified and if it is correct, next form opens. If the username and password are not correct, it shows the error message.
When a customer search for a automobile, if the automobile is available, they will be taken to a page that shows the details of the automobile including automobile name, automobile ID, quantity, price etc. “Automobile Management System” is useful for maintaining automobiles, customers effectively and hence helps for establishing good relation between customer and automobile organization. It contains various customized modules for effectively maintaining automobiles and stock information accurately and safely.
When the automobile is sold to the customer, stock will be reduced automatically. When a new purchase is made, stock will be increased automatically. While selecting automobiles for sale, the proposed software will automatically check for total number of available stock of that particular item, if the total stock of that particular item is less than 5, software will notify the user to purchase the particular item.
Also when the user tries to sale items which are not in stock, the system will prompt the user that the stock is not enough. Customers of this system can search for a automobile; can purchase a automobile easily by selecting fast. On the other hand the stock of automobiles can be maintained perfectly by the automobile shop manager overcoming the drawbacks of existing system.
Final project report on grocery store management system..pdfKamal Acharya
In today’s fast-changing business environment, it’s extremely important to be able to respond to client needs in the most effective and timely manner. If your customers wish to see your business online and have instant access to your products or services.
Online Grocery Store is an e-commerce website, which retails various grocery products. This project allows viewing various products available enables registered users to purchase desired products instantly using Paytm, UPI payment processor (Instant Pay) and also can place order by using Cash on Delivery (Pay Later) option. This project provides an easy access to Administrators and Managers to view orders placed using Pay Later and Instant Pay options.
In order to develop an e-commerce website, a number of Technologies must be studied and understood. These include multi-tiered architecture, server and client-side scripting techniques, implementation technologies, programming language (such as PHP, HTML, CSS, JavaScript) and MySQL relational databases. This is a project with the objective to develop a basic website where a consumer is provided with a shopping cart website and also to know about the technologies used to develop such a website.
This document will discuss each of the underlying technologies to create and implement an e- commerce website.
Forklift Classes Overview by Intella PartsIntella Parts
Discover the different forklift classes and their specific applications. Learn how to choose the right forklift for your needs to ensure safety, efficiency, and compliance in your operations.
For more technical information, visit our website https://intellaparts.com
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdffxintegritypublishin
Advancements in technology unveil a myriad of electrical and electronic breakthroughs geared towards efficiently harnessing limited resources to meet human energy demands. The optimization of hybrid solar PV panels and pumped hydro energy supply systems plays a pivotal role in utilizing natural resources effectively. This initiative not only benefits humanity but also fosters environmental sustainability. The study investigated the design optimization of these hybrid systems, focusing on understanding solar radiation patterns, identifying geographical influences on solar radiation, formulating a mathematical model for system optimization, and determining the optimal configuration of PV panels and pumped hydro storage. Through a comparative analysis approach and eight weeks of data collection, the study addressed key research questions related to solar radiation patterns and optimal system design. The findings highlighted regions with heightened solar radiation levels, showcasing substantial potential for power generation and emphasizing the system's efficiency. Optimizing system design significantly boosted power generation, promoted renewable energy utilization, and enhanced energy storage capacity. The study underscored the benefits of optimizing hybrid solar PV panels and pumped hydro energy supply systems for sustainable energy usage. Optimizing the design of solar PV panels and pumped hydro energy supply systems as examined across diverse climatic conditions in a developing country, not only enhances power generation but also improves the integration of renewable energy sources and boosts energy storage capacities, particularly beneficial for less economically prosperous regions. Additionally, the study provides valuable insights for advancing energy research in economically viable areas. Recommendations included conducting site-specific assessments, utilizing advanced modeling tools, implementing regular maintenance protocols, and enhancing communication among system components.
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxR&R Consult
CFD analysis is incredibly effective at solving mysteries and improving the performance of complex systems!
Here's a great example: At a large natural gas-fired power plant, where they use waste heat to generate steam and energy, they were puzzled that their boiler wasn't producing as much steam as expected.
R&R and Tetra Engineering Group Inc. were asked to solve the issue with reduced steam production.
An inspection had shown that a significant amount of hot flue gas was bypassing the boiler tubes, where the heat was supposed to be transferred.
R&R Consult conducted a CFD analysis, which revealed that 6.3% of the flue gas was bypassing the boiler tubes without transferring heat. The analysis also showed that the flue gas was instead being directed along the sides of the boiler and between the modules that were supposed to capture the heat. This was the cause of the reduced performance.
Based on our results, Tetra Engineering installed covering plates to reduce the bypass flow. This improved the boiler's performance and increased electricity production.
It is always satisfying when we can help solve complex challenges like this. Do your systems also need a check-up or optimization? Give us a call!
Work done in cooperation with James Malloy and David Moelling from Tetra Engineering.
More examples of our work https://www.r-r-consult.dk/en/cases-en/
Democratizing Fuzzing at Scale by Abhishek Aryaabh.arya
Presented at NUS: Fuzzing and Software Security Summer School 2024
This keynote talks about the democratization of fuzzing at scale, highlighting the collaboration between open source communities, academia, and industry to advance the field of fuzzing. It delves into the history of fuzzing, the development of scalable fuzzing platforms, and the empowerment of community-driven research. The talk will further discuss recent advancements leveraging AI/ML and offer insights into the future evolution of the fuzzing landscape.
Vaccine management system project report documentation..pdfKamal Acharya
The Division of Vaccine and Immunization is facing increasing difficulty monitoring vaccines and other commodities distribution once they have been distributed from the national stores. With the introduction of new vaccines, more challenges have been anticipated with this additions posing serious threat to the already over strained vaccine supply chain system in Kenya.
Vaccine management system project report documentation..pdf
Short Term Electrical Load Forecasting by Artificial Neural Network
1. Hong Li. Int. Journal of Engineering Research and Application www.ijera.com
ISSN : 2248-9622, Vol. 6, Issue 7, ( Part -3) July 2016, pp.01-04
www.ijera.com 1 | P a g e
Short Term Electrical Load Forecasting by Artificial Neural
Network
Hong Li
Department of Computer Systems Technology, New York City College of Technology of the City University of
New York, USA
ABSTRACT
This paper presents an application of artificial neural networks for short-term times series electrical load
forecasting. An adaptive learning algorithm is derived from system stability to ensure the convergence of
training process. Historical data of hourly power load as well as hourly wind power generation are sourced from
European Open Power System Platform. The simulation demonstrates that errors steadily decrease in training
with the adaptive learning factor starting at different initial value and errors behave volatile with constant
learning factors with different values.
Keywords – Adaptive learning, neural network, short term load forecast, stability analysis
I. INTRODUCTION
The fundamental characteristic that makes
the electric power industry unique is the product,
electricity has limited storage capability. Electricity
energy cannot be stored as it should be generated as
soon as it is demanded. Since there is no “inventory”
or “buffer” from generation to end users
(customers), ideally, power systems have to be built
to meet the maximum demand, the so called peak
load, to insure that sufficient power can be delivered
to the customers whenever they need it. Therefore,
Electric Power Load Forecasting (EPLF) is a vital
process in the planning of electricity industry and the
operation of electric power systems. Accurate
forecasts lead to substantial savings in operating and
maintenance costs, increased reliability of power
supply and delivery system, and correct decisions for
future development. However, forecasting, by
nature, is a stochastic problem rather than
deterministic. Since the forecasters are dealing with
randomness, the output of a forecasting process is
supposed to be in a probabilistic form, such as a
forecast within error range under such value. Many
researches have been focusing on load forecasting
[1]. In work [2], a short term load forecasting was
presented using multi parameter regression. In work
[3], a scholastic method is investigated mainly based
on decomposition and fragmentation of time series.
A review of short term load forecasting using
artificial neural network (ANN) is given in [4]. It
concluded that the artificial intelligence based
forecasting algorithms are proved to be potential
techniques for this challenging job of nonlinear time
series prediction. This research uses an adaptive
learning algorithm which was proven to guarantee
the convergence of training process by updating the
learning factor at iteration. The simulation is based
on the historical data between 2010 – 2015 including
hourly electrical load and hourly wind power
generation. The data are sourced from Open Power
System Platform for European countries. In
following section, the artificial neural network and
an adaptive algorithm are described and simulation
results are presented.
II. AN ARTIFICIAL NEURAL
NETWORK MODEL
The ANN is a set of processing elements
(neurons or perceptrons) with a specific topology of
weighted interconnections between these elements
and a learning law for updating the weights of
interconnection between two neurons. In work [5],
the Lyapunov function [6,7] approach was used to
provide stability analysis of Backpropagation
training algorithm of such network. However, the
training process can be very sensitive to initial
condition such as number of neurons, number of
layers, and value of weights, and learning factors
which are often chosen by trial and error. The
Backpropgation algorithm is used for learning – that
is, weight adjusting.
The Least Square error function is defined
and verified satisfying the Lyapunov condition so
that it guarantees the stability of the system. In the
work [5], the analysis carries out a method that
defines a range for value of learning factor at
iteration which ensure the condition for stability are
satisfied. In simulation, instead of selecting a
learning factor by trial and error, author defines an
adaptive learning factor which satisfies the
convergence condition and adjust connection weight
accordingly.
RESEARCH ARTICLE OPEN ACCESS
2. Hong Li. Int. Journal of Engineering Research and Application www.ijera.com
ISSN : 2248-9622, Vol. 6, Issue 7, ( Part -3) July 2016, pp.01-04
www.ijera.com 2 | P a g e
The ANN model problem can be outlined
as follow: a set of data is collected from the system
including input data and corresponding output data
observed, or measured as target output of the ANN
model. The set is often called “training set”. An
ANN model with parameters, called weights, is
designed to simulate the system. When the output
from neural network is calculated, an error
representing the difference between target output
and calculated output from the system is generated.
The learning process of neural network is to modify
the network, the weights, to minimize the error.
Consider a system with N inputs
and M output units Y
= . A recurrent network combines
number of neurons, called nodes, feed forward to
next layer of nodes. Suppose is number of nodes
in lth layer, each output from the l-1th layer will be
used as input for next layer. A system of a single
layer with M outputs can be expressed in form of
(1)
where is called connection weight from input
to output ;vij is called connection weight of local
feedback at jth node with ith delay; is a
nonlinear sigmoid function
(2)
with constant coefficient , called slope; p = 1, …,
T, T is number of patterns, D is number of delay
used in local feedback.
The back-propagation algorithm has
become a common algorithm used for training feed-
forward multilayer perceptron. It is a generalized the
Least Mean Square algorithm that minimizes the
mean squared error between the target output and the
network output with respect to the weights. The
algorithm looks for the minimum of the error
function in weight space using the method of
gradient descent. The combination of weights which
minimizes the error function is considered to be a
solution of the learning problem. A proof of the
Back-propagation algorithm was presented in [11]
based on a graphical approach in which the
algorithm reduces to a graph labeling problem.
The total error E of the network over all
training set is defined as
where is the error associated with pth pattern
at the kth node of output layer,
where is the target at kth node and is
the output of network at the kth node. The learning
rule was chosen following gradient descent method
to update the network connection weights iteratively,
(5)
(6)
where
are weight vectors in jth node; µ is a constant called
learning factor.
From work [5], an extended and simplified
condition was derived such that the system defined
in (1) – (2) converges if the learning factor in (5) –
(6) satisfies the following conditions:
(7)
. (8)
III. SHORT TERM ELECTRICAL
LOAD FORECASTING
To The changing energy landscape requires
rigorous analysis to support robust investment and
policy decisions. Power systems are complex, hence
researchers and analysts often rely on large
numerical computer models for a variety of
purposes, ranging from price projections to policy
advice and system planning. Such models include
unit commitment, dispatch, and generation
expansion models. These models require a large
amount of input data, such as information about
existing power stations, interconnector capacity, and
yearly electricity consumption, and ancillary service
requirements, but also (hourly) time series of load,
wind and solar power generation, and heat demand.
Fortunately, most of these data are publicly
available, from sources such as transmission system
operators, regulators, or industry associations. The
Open Power System Data platforms provides free
and open data of the European power system with
restricted use for non-commercial applications. The
Open Power System Data is implemented by four
institutions, DIW Berlin, Europa-Universität
Flensburg, Technical University of Berlin, and Neon
Neue Energieökonomik and funded by the German
Federal Ministry for Economic Affairs and Energy.
This simulation used a data package which contains
time-series data relevant for power system modeling.
The data includes hourly electrical load of 36
European countries, wind and solar power
3. Hong Li. Int. Journal of Engineering Research and Application www.ijera.com
ISSN : 2248-9622, Vol. 6, Issue 7, ( Part -3) July 2016, pp.01-04
www.ijera.com 3 | P a g e
generation from German transmission system
operators. This simulation uses German electrical
load and wind power generation data available from
2010- 2015 for ANN training and mainly
demonstrates that the enhanced learning algorithm
may avoid many trial and error for selection of
learning factors.
In neural network training using Back
propagation algorithm, the initial weights are
randomly selected and the learning factor is
preselected. The performance of the learning can
sometime very volatile due to the selection of the
learning factor. To find the optimal fit, the trial and
error is common practice that runs the simulation
with different values of learning factors. In this
research, an upper boundary of learning factors (8) is
derived from the theory of convergence. At iteration
of network training, the norm of weights is
calculated and a learning factor is defined to satisfy
the convergence condition (8).
A three layer neural network structure was
selected with 13 inputs, 8 and 5 nodes in the hidden
layer, and one outputs. For every hour of electrical
load as output, the 13 inputs are defined as follows:
1 – 10: previous 10 hours electrical load
11: previous hour’s wind power generation
12: current hour wind power generation
13: next hours wind power generation
Data from 2010 to 2015 are used to train
the ANN model. 100 days data are used to setup
2400 patterns of the training set. Input and output
data are normalized to range from 0 to 1. After the
ANN model is trained, the 48 hours forecast of
electrical load are calculated from the model and
denormalized and then used to compare with the
actual electrical load. The following figures
demonstrates error behaviors of ANN training with
100 days data and 48 hours forecasting.
With the constant learning factor, after
number of trials with various values of learning
factor and slope, momentum term set as 0.1, and
random generated initial weights, the training
reached to absolute error 0.0198 after 100000
iterations with learning factor 0.02, slope 0.6. The
error behavior is sown in Fig. 1.
Figure 1. Error behavior of training with learning
factor 0.02 and slope 0.6
Fig. 2 and Fig. 3 demonstrate error
behavior of training with other randomly selected
learning factor and slope. It is observed that the error
stays around certain value and are not decreasing
after some iteration. Fig. 2 is error behavior of
training with learning factor 0.05 and slope 0.7,
whereas figure 3 is error behavior of training with
learning factor 0.4 and slope 0.6.
Figure 2. Error behavior of ANN training with
learning factor 0.05 and slope 0.7
Figure 3. Error behavior of ANN training with
learning factor 0.4 and slope 0.6
In comparison, the training process
with adaptive learning factor are experimented
with the same values of slope and initial
learning factor. The learning factor at each
iteration is calculated satisfying the
convergence condition given in (7).
From Fig. 4 – Fig. 6, it is observed that
error at iteration steadily decreases regardless of
initial values of learning factor.
Figure 4. Adaptive training with initial learning
factor 0.02 and slope 0.6
4. Hong Li. Int. Journal of Engineering Research and Application www.ijera.com
ISSN : 2248-9622, Vol. 6, Issue 7, ( Part -3) July 2016, pp.01-04
www.ijera.com 4 | P a g e
Figure 5. Error behavior of adaptive training with
initial learning factor 0.05 and slope 0.7
Figure 6. Error behavior of adaptive training with
initial factor 0.4 and slope 0.6
The following Fig. 7 shows the 48
hours load forecasting using the model trained
with adaptive learning comparing with the
actual electrical load.
Figure 7. Forty eight hours load forecasting
IV. CONCLUSION
This research applied artificial neural
network in short term forecasting of electrical load.
The historical data of time-series electrical load and
wind power generation are used for training the
model which successfully provide 48 hours
forecasting. The data of 36 European countries are
sourced from Open Power System platform. To
ensure the convergence of training and avoid
unstable phenomena, an adaptive learning factor are
calculated at iteration of training following the
analysis of convergence theory satisfying the
convergence condition. The analysis results in a
condition which provides an upper boundary of the
learning factor. Instead of selecting a constant
learning factor by trial and error, an adaptive
learning factor is calculated at iteration satisfying the
convergence condition. Furthermore, a more
simplified condition was used to provide a feasible
implementation of the adaptive learning factor. The
simulation result is based on the data of German
power plant. The error behaviors were demonstrated
for training with an adaptive learning factor as well
as with a selected constant learning factor. The
comparison demonstrated that a learning factor
arbitrarily chosen out of the predefined stability
domain leads to an unstable identification of the
considered system; however, an adaptive learning
factor satisfying the conditions chosen for this study
ensures the stability of the identification system. The
ANN network is trained with 100 days of data
including electrical load and wind power generation
and 48 hours forecasting is presented. Further work
may focus on analysis of evaluation of performance
of the model and the data selection for training.
REFERENCES
[1] J.P. Rothe, A.K. Wadhwani and S.
Wadhwani, Short term load forecasting
using multi parameter regression,
International Journal of Computer Science
and Information Security, Vol. 6, No. 2,
2009.
[2] H. Tao, D. Dickey, Electrical load
forecasting: Fundamentals and Best
Practices, Online open access eBook
https://www.otexts.org/book/elf
[3] E. Almeshaiei and H. Soltan, A
methodology for Electric Power Load
Forecasting, Alexandria Engineering
Journal (2011) 50, 137–144 Elsevier.
[4] A. Baliyan, K. Gaurav, and S.K. Mishra, A
Review of Short , Term Load Forecasting
using Artificial Neural Network Models,
International Conference on Intelligent
Computing, Communication &
Convergence, 2015
[5] Hong Li (2014). Adaptive Learning Factor
of Backpropagation in Feed Forward
Neural Networks, International Journal of
Modern Engineering, Vol. 14, No 2,
Spring/Summer 2014, pp 47 – 53.
[6] R. Rojas, Neural Networks, Springer-
Verlag, 1996
[7] Sontag, E.D., Mathematical Control
Theory, Springer-Verlag, New York