Short-term electrical load forecasting using hybrid ANN–DE and wavelet transforms approach

This paper proposes a hybrid artificial neural networks–differential evolution (ANN–DE) and wavelet transforms (WTs)-based approach to forecast the short-term electrical load demand data. The input data ranging from 1 h to several days have a significant effect on the accuracy of short-term load forecasting (STLF). Different forecasting methods with good accuracy are developed for solving the STLF problem based on time series analysis and artificial intelligence system. However, there are several disadvantages of ANNs such as falling in trap of local minima during its parameter optimization process. Therefore, to avoid this problem, in this paper, a hybrid approach is developed by combining the ANNs, WTs and evolutionary-based DE algorithm. Here, the ANNs are used to model the nonlinear and complex behavior of electrical load demand. WTs are used to improve the forecasting ability by decreasing the ill-behaved load demand series into a more stable series. The chance of falling into local optimum can be overcome by using the evolutionary-based DE algorithm. In order to show the effectiveness and suitability of the proposed hybrid approach, the load demand data are taken from California Independent System Operator Web site.