Forecasting the energy demand of Turkey with a NN based on an improved Particle Swarm Optimization

Abstract

Forecasting the future energy demand accurately is a critical issue, especially for countries like Turkey where the energy dependency ratio is high. This paper presents a neural network based on the particle swarm optimization algorithm with mutation (PSOM-NN) to enhance the prediction accuracy of the energy demand of Turkey. Unlike some studies in the field which are using all the observed data for training purpose, the proposed network used only a part of these data for training. Approximately 63 % and 37 % of the mentioned data are used for the training and test, respectively. Detrending is applied to the data to avoid nonlinear transfer functions that constrain the model to the input range values. The analysis of the results revealed that PSOM-NN produced better forecasts of energy demand compared to the earlier studies in terms of root-meansquare error, mean absolute percentage error and mean absolute deviation. Finally, future projections under different scenarios are also employed and discussed. It is believed that the proposed model could be applied to any country that needs accurate forecasts of the energy demand for sustainable energy policies.