作者: Otávio A. S. Carpinteiro , Isaías Lima , Rafael C. Leme , Antonio C. Zambroni de Souza , Edmilson M. Moreira
DOI: 10.1007/S00521-006-0072-8
关键词: Search engine 、 Multilayer perceptron 、 Perceptron 、 Artificial neural network 、 Term (time) 、 Data mining 、 Computer science 、 Time series 、 Electrical load
摘要: A novel hierarchical hybrid neural model to the problem of long-term electrical load forecasting is proposed in this paper. The made up two self-organizing map nets: one on top other, and a single-layer perceptron. It has application into domains which require time series analysis. compared multilayer Both perceptron models are endowed with windows their input layers. They trained assessed data extracted from North-American electric utility. required predict once every week peak-load mean-load for next 2 years. results presented evaluated