A hierarchical neural model in short-term load forecasting.

Carpinteiro, Otávio Augusto SalgadoReis, Agnaldo José da RochaSilva, Alexandre Pinto Alves da2012-06-192012-06-192004CARPINTEIRO, O. A. S.; REIS, A. J. R.; SILVA, A, P. A. A hierarchical neural model in short-term load forecasting. Applied Soft Computing, v. 4, n. 4, p. 405-412, set. 2004. Disponível em: <https://www.sciencedirect.com/science/article/pii/S156849460400050X>. Acesso em: 19 jun. 2012.15684946http://www.repositorio.ufop.br/handle/123456789/877This paper proposes a novel neural model to the problem of short-term load forecasting (STLF). The neural model is made up of two self-organizing map (SOM) nets—one on top of the other. It has been successfully applied to domains in which the context information given by former events plays a primary role. The model was trained on load data extracted from a Brazilian electric utility, and compared to a multilayer perceptron (MLP) load forecaster. It was required to predict once every hour the electric load during the next 24 h. The paper presents the results, the conclusions, and points out some directions for future work.en-USShort-term load forecastingSelf-organizing mapNeural networkA hierarchical neural model in short-term load forecasting.Artigo publicado em periodicoO Periódico Applied Soft Computing concede permissão para depósito do artigo no Repositório Institucional da UFOP. Número da licença: 3291280500461.