Development of a Hybrid Intelligent System for Electrical Load Forecasting

Ronaldo R. B. de AquinoAida A. FerreiraManoel A. CarvalhoMilde M. S. LiraGeane B. SilvaOtoni Nóbrega Neto

This paper presents a hybrid intelligent system for electrical load forecast. Artificial Neural Networks (ANN) were combined with Heuristic Rules to create the system. The study was based on load demand data of Energy Company of Pernambuco (CELPE), whose data contain the hourly load consumption in the period from January-2000 until December-2004. The data of hourly consumption of the holidays were eliminated from the file, as well as the data regarding the more critical period of the rationing in Brazil (from May until July 2001). The hybrid intelligent system presented an improvement in the load forecasts in relation to the results achieved by the ANN alone. The system was implemented in MATLAB.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: