Short-Term Load Forecasting Using Radial Basis Function Neural Network (RBFN) in PJM Electricity Market

A precise short-term load forecasting technique is required for the economic and reliable operation of power system. Modern load forecasting techniques especially ANN methods are attractive as they have the ability to handle the non-linear relationships between load, weather temperature and the factors affecting it directly. In this paper, an investigation on the use of ANN for short term load forecasting has been conducted using hour and day indicators and pricing signal as inputs. Generalized Regression Neural Network (GRNN), a type of Radial Basis Function Network (RBFN) has been used and tested on publicly available data of PJM electricity market. The test results show that GRNN method is very promising in forecasting the short-term load with satisfactory mean absolute percentage error (MAPE).