Short-Term Price Forecasting by Using ANN Algorithms

Abstract

With deregulation much attention is given to electricity price forecasting. Some of the factors which affect forecast are day of the week, weather, season, hour of the day, year, and special days. In general, the main factor which drives the electricity price is power demand. Here, ANN algorithms i.e. Bayesian Regularization, Levenberg Marquardt back propagation & Scaled Conjugate Gradient algorithms has been applied in short-term price forecasting that is, the one hour-ahead forecast of the electricity price using MATLAB R14a. The simulation results have shown accurate one hour ahead forecasts.