An overview of energy demand forecasting methods published in 2005–2015

Abstract

The importance of energy demand management has been more vital in recent decades as the resources are getting less, emission is getting more and developments in applying renewable and clean energies has not been globally applied. Demand forecasting plays a vital role in energy supply-demand management for both governments and private companies. Therefore, using models to accurately forecast the future energy consumption trends—specifically with nonlinear data—is an important issue for the power production and distribution systems. Several techniques have been developed over the last few decades to accurately predict the future in energy consumption. This paper reviews various energy demand-forecasting methods that have been published as research articles between 2005 and 2015. The scope of forecasting applications and techniques is quite large, and this article focuses on the methods which are used to predict energy consumption. The applications of traditional techniques such as econometric and time series models along with soft computing methods such as neural networks, fuzzy logic and other models are reviewed in the current work. The most cited studies applied neural networks to forecast the energy consumption and approved the notable performance of the models, but computation time is much more than many other methods based on its sophisticated structure. Another field of future research includes the development of hybrid methods. The literature shows that the classical methods cannot result in dominant outputs anymore.