An efficient framework for short-term electricity price forecasting in deregulated power market

It is widely acknowledged that electricity price forecasting become an essential factor in operational activities, planning, and scheduling for the participant price-setting market, nowadays. Nevertheless, became a complex signal due to its non-stationary, non-linearity, time-variant behavior. Consequently, variety of artificial intelligence techniques are proposed provide efficient method short-term forecasting. BSA as recent augmentation optimization technique, yield potential searching closed-form solution mathematical modeling with higher probability, obviating necessity comprehend correlations between variables. Concurrently, this study also developed feature selection select input variables subsets have substantial implication on price, based combination mutual information (MI) SVM. For verification simulation results, actual data sets from Ontario energy market year 2020 covering various weather seasons acquired. Finally, obtained results demonstrate feasibility strategy through improved preciseness comparison distinctive methods.