Parallel neural network-fuzzy expert system strategy for short-term load forecasting : System implementation and performance evaluation

Abstract

The on-line implementation and results from a hybrid short-term electrical load forecaster that Is being evaluated by a power utility are documented in this paper. Tills forecaster employs a new approach involving a parallel neural-fuzzy expert system, whereby Kohonen's selforganizing feature map with unsupervised learning, is used to classify daily load patterns. Post-processing of the neural network outputs is performed with a fuzzy expert system which successfully corrects the load deviations caused by the effects of weather and holiday activity. Being highly automated, little human interference is required during the process of load forecasting. A comparison made between this model and a regression-based model currently being used in the Control Centre has shown a marked improvement in load forecasting results. © 1997 IEEE.