Global Load Demand Forecasting of Spain using a MLP Neural Network Model

C. Senabre, S. Valero, A. Gabaldon, and M. Ortiz (Spain)

Keywords

Shortterm load forecasting, MLP neural networks, electricity market, load estimation.

Abstract

The load forecasting is very important for the operation of power systems and is necessary for the daily scheduling of power plants. A precise short term electrical load forecasting avoids unnecessary costs and risky operational conditions, allowing utilities to commit their production resources to optimize energy prices and exchange with vendors and clients. This research uses neural networks as a short-term forecasting method for the global load demand curve of Spain. After analyzing the results of several neural networks for load forecasting in previous researchs, the Multilayer Perceptron (MLP) was chosen. The data used was obtained from the Spanish electric system operator. The results allowed to obtain the global demand curve for 24 hour periods (hour to hour). In order to validate the model, several error indices were assigned through the comparison of the results with the real known curves. Summing up, the research establishes a tool that helps in the decision making forecasting the short-term global electric load demand curve.

Important Links:



Go Back