An Artificial Neural Network Approach for Short-Term Electricity Prices Forecasting

Abstract

This paper presents an artificial neural network approach for short-term electricity prices forecasting. In the new deregulated framework, producers and consumers require short-term price forecasting to derive their bidding strategies to the electricity market. Accurate forecasting tools are required for producers to maximize their profits and for consumers to maximize their utilities. A three-layered feedforward artificial neural network, trained by the Levenberg-Marquardt algorithm, is used for forecasting the next 168 hour electricity prices. We evaluate the accuracy of the price forecasting attained with the proposed approach, reporting the numerical results from a real-world case study based on an electricity market.