A hybrid wavelet transform and ANFIS model for short term electric load prediction

Abstract

A novel approach, combining wavelet transform and adaptive neuro-fuzzy inference system is proposed in this study for short-term electric load consumption prediction. The use of wavelet techniques is to overcome the discontinuities and a non periodicity in the change on the load curve and to increase the accuracy of time series load prediction. However, the original time series data are decomposed into number of wavelet coefficient signals then used as an input vectors to ANFIS. The outputs from the ANFIS are recombined using the same wavelet technique to predict electric load. Load demand information from a real-world case study based in electricity market of mainland France is used for model development. The results obtained with the proposed model, showed that the mean absolute error in short term electric load prediction of 1.6288% was achieved.