PREDICTING INDIA?S DOMESTIC SECTOR ELECTRICITY CONSUMPTION A COMPARISON OF GENETIC ALGORITHM AND DIFFERENTIAL EVOLUTION

摘要

The main objective of the present study is to apply the meta-heuristic techniques such as Genetic Algorithm (GA) and Differential evolution (DE) to estimate the electricity consumption (EC) of domestic sector (DS) in India. Population, per capita GDP and Electricity production were selected as independent variables. The models are developed in exponential form is proposed to forecast the DS-EC of India. Results of the comparison showed that the performance values of the DE method are better than the performance values of the GA. According to obtained results, Mean Absolute Percentage Error (MAPE) of the DE model provides better-fit solutions. DS-EC of India is forecasted up to the year 2025. According to the DE model, India?s DS-EC will increase to a value of 440931.68 Giga Watt hour (GWh).