Short-Term Electricity Price Forecasting by Employing Ensemble Empirical Mode Decomposition and Extreme Learning Machine

Day-ahead electricity price forecasting plays a critical role in balancing energy consumption and generation, optimizing the decisions of market participants, formulating trading strategies, dispatching independent system operators. Despite fact that much research on has been published recent years, it remains difficult task because challenging nature prices includes seasonality, sharp fluctuations price, high volatility. This study presents three-stage short-term model by employing ensemble empirical mode decomposition (EEMD) extreme learning machine (ELM). In proposed model, EEMD is employed to decompose actual signals overcome non-linear non-stationary components data. Then, day-ahead performed using ELM model. We conduct several experiments real-time data obtained from three different states Australia, i.e., Queensland, New South Wales, Victoria. also implement various deep approaches as benchmark methods, recurrent neural network, multi-layer perception, support vector machine, ELM. order affirm performance our approaches, this performs evaluation metric, including Diebold–Mariano (DM) test. The results show productiveness developed (in terms higher accuracy) over its counterparts.