Long-term electrical energy consumption forecasting for developing and developed economies based on different optimized models and historical data types

• Development of optimized models for EEC (electrical energy consumption) forecasting.
• Types of historical data used include, (i) EEC and (ii) socio-economic indicators.
• Using socio-economic indicators data leads to more accurate EEC forecasting.
• IPSO (improved particle swarm optimization)–ANN (artificial neural networks) model MAPEs are 1.94 and 1.51% for Iran and the U.S., respectively.

The objectives of this study are (a) development of optimized regression and ANN (artificial neural network) models for EEC (electrical energy consumption) forecasting based on several optimization methodologies, (b) examination of the effects of different historical data types on accuracy of EEC forecasting, and (c) long-term EEC forecasting for Iran and the U.S. as developing and developed economies, respectively. For long-term EEC forecasting for 2010–2030, the two types of historical data used in this study include, (i) EEC and (ii) socio-economic indicators, namely, gross domestic product, energy imports, energy exports, and population, for 1967–2009 period. For both types of economies, the results demonstrate that using historical data of socio-economic indicators leads to more accurate EEC forecasting than those of EEC, when IPSO (improved particle swarm optimization) is used for optimal design of ANN for EEC forecasting. It is found that for developing and developed economies, forecasted EEC trends are significantly different, as expected, and IPSO–ANN model can be utilized to forecast long-term EEC up to 2030 with mean absolute percentage error of 1.94 and 1.51% for Iran and the U.S., respectively.