An intelligent neural network-based short-term wind power forecasting in PJM Electricity Market

Due to the rapid growth of wind power generation in the recent years, accurate wind power prediction is necessary for reliable power system operation. This paper proposes a novel forecasting algorithm for day-ahead wind power forecasting. In the presented model, instead of relying on the gradient-descent approach, a meta-heuristic optimization method called shuffled frog leaping algorithm (SFLA) is developed to determine the parameters of a feedforward artificial neural network (ANN). The trained ANN by SFLA will be employed in the next step to forecast the day-ahead wind power data. The performance of the proposed model is demonstrated on the wind power data of PJM Electricity Market for 2015.