scholarly journals Short Term Electric Load Forecasting of Kathmandu Valley of Nepal using Artificial Neural Network

2018 ◽  
Vol 1 (1) ◽  
pp. 43-48
Author(s):  
Binod Bhandari ◽  
Shree Raj Shakya ◽  
Ajay Kumar Jha
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Load Flow ◽  
Kathmandu Valley ◽  
Electric Load ◽  
Short Term ◽  
Load Demand ◽  
The Neural Network ◽  
Artificial Neural

Decision making in the energy sector has to be based on accurate forecasts of the load demand. Short-term forecasting, which forms the focus of this paper, gives a day ahead hourly forecast of electric load. This forecast can help to make important decisions in the field of scheduling, contingency analysis, load flow analysis, preventing imbalance in the power generation and load demand, load switching strategies, thus leading to greater network reliability and power quality. A method called Artificial Neural Network is used to anticipate the future load of Kathmandu Valley of Nepal. The Neural Network is build, trained with historical data along with seven different input variables and used for prediction of day ahead 24 hours load. The output is validated with the real Load collected from NEA. In addition, forecasting is performed by some other time series methods as well, and whose output are compared with that of neural network. The range of Mean Absolute Deviation for four different time series models lied between 1.50-2.59. When the errors were calculated in terms of MSE and MAPE the range of these values were found to be in between 2.59-7.78, and 1.61- 5.07 respectively. The Artificial Neural Network proved to be the more accurate forecast method when the results are compared in terms of error measurements with a MAD having 1.23, MSE having 1.79 and MAPE having 1.17. The Neural Network proved to be more accurate method comparatively with satisfactory minimum error.

scholarly journals NEURAL NETWORK FORECASTING OF ENERGY CONSUMPTION OF A METALLURGICAL ENTERPRISE

2021 ◽  
pp. 14-22
Author(s):  
Anna Bakurova ◽  
Olesia Yuskiv ◽  
Dima Shyrokorad ◽  
Anton Riabenko ◽  
Elina Tereschenko
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Artificial Neural Networks ◽  
Energy Consumption ◽  
Short Term ◽  
Metallurgical Enterprise ◽  
Input Information ◽  
The Neural Network ◽  
Artificial Neural

The subject of the research is the methods of constructing and training neural networks as a nonlinear modeling apparatus for solving the problem of predicting the energy consumption of metallurgical enterprises. The purpose of this work is to develop a model for forecasting the consumption of the power system of a metallurgical enterprise and its experimental testing on the data available for research of PJSC "Dneprospetsstal". The following tasks have been solved: analysis of the time series of power consumption; building a model with the help of which data on electricity consumption for a historical period is processed; building the most accurate forecast of the actual amount of electricity for the day ahead; assessment of the forecast quality. Methods used: time series analysis, neural network modeling, short-term forecasting of energy consumption in the metallurgical industry. The results obtained: to develop a model for predicting the energy consumption of a metallurgical enterprise based on artificial neural networks, the MATLAB complex with the Neural Network Toolbox was chosen. When conducting experiments, based on the available statistical data of a metallurgical enterprise, a selection of architectures and algorithms for learning neural networks was carried out. The best results were shown by the feedforward and backpropagation network, architecture with nonlinear autoregressive and learning algorithms: Levenberg-Marquard nonlinear optimization, Bayesian Regularization method and conjugate gradient method. Another approach, deep learning, is also considered, namely the neural network with long short-term memory LSTM and the adam learning algorithm. Such a deep neural network allows you to process large amounts of input information in a short time and build dependencies with uninformative input information. The LSTM network turned out to be the most effective among the considered neural networks, for which the indicator of the maximum prediction error had the minimum value. Conclusions: analysis of forecasting results using the developed models showed that the chosen approach with experimentally selected architectures and learning algorithms meets the necessary requirements for forecast accuracy when developing a forecasting model based on artificial neural networks. The use of models will allow automating high-precision operational hourly forecasting of energy consumption in market conditions. Keywords: energy consumption; forecasting; artificial neural network; time series.

Sign in / Sign up

Export Citation Format

Share Document