Daily peak electricity demand forecasting based on an adaptive hybrid two-stage methodology

• We present a novel model for daily peak load forecasting.
• The model combines five techniques to produce an adaptive hybrid two-stage methodology.
• We use data from the Algerian power system.
• The hybrid model improves the forecasting accuracy in both normal and special days.

This paper describes daily peak load forecasting using an adaptive hybrid two-stage methodology. Because the time series of electricity consumption is mainly influenced by seasonal effects, the double seasonal Holt–Winters exponential smoothing method is firstly used for next-day peak electricity demand forecasting. In the second stage, the secondary forecasting model is applied taking into account the benefits of Fuzzy c-means clustering; K-nearest neighbors algorithm; Wavelet packet decomposition; and Adaptive Neuro-Fuzzy Inference System, for further improvement in forecasting accuracy. The whole architecture of the proposed model will be presented and the results will be compared with neural networks and stand-alone adaptive neuro-fuzzy inference system based approaches by using a gathered data from the Algerian power system. The results show that: (1) the proposed methodology is the best among all the considered schemes, (2) the FKW-ANFIS has satisfactory performance in both normal and special daily conditions.