Forecasting India's electricity demand using Artificial Neural Network

Power System planning starts with Electric load (demand) forecasting. Accurate electricity load forecasting is one of the most important challenges in managing supply and demand of the electricity, since the electricity is volatile in nature; it cannot be stored and has to be consumed immediately. Artificial Neural Network (ANN) is applied to predict the annual electricity consumption in India for the period of 10 years from 2011 to 2020. Population and Per Capita Gross Domestic Product (GDP) are taken as the input variables and the electricity consumption is the predicted output variable. 27 years of data are used for training and 4 years of data is used for testing the ANN. Comparison has been made with Regression Analysis (RA) using Mean Absolute Percentage Error (MAPE) to measure the accuracy of test data. The results obtained with ANN method is encouraging.