A Hybrid Model of VMD-EMD-FFT, Similar Days Selection Method, Stepwise Regression, and Artificial Neural Network for Daily Electricity Peak Load Forecasting

Daily electricity peak load forecasting is important for generation capacity planning. Accurate leads to saving on excessive generating capacity, while maintaining the stability of power system. The main challenging tasks in this research field include improving accuracy and reducing computational time. This paper proposes a hybrid model involving variational mode decomposition (VMD), empirical (EMD), fast Fourier transform (FFT), stepwise regression, similar days selection (SD) method, artificial neural network (ANN) daily forecasting. Stepwise regression method are used input variable selection. VMD FFT applied data seasonality capturing, EMD employed determining an appropriate level VMD. constructed effectively forecast special holidays, which have different patterns from other normal weekdays weekends. performance tested with real provided by Electricity Generating Authority Thailand, leading utility state enterprise under Ministry Energy. Experimental results show that gives best computation time solving problems selection, decomposition, imbalance training process.