Practical implementation of a hybrid fuzzy neural network for one-day-ahead load forecasting

The paper presents the development and practical implementation of a hybrid shortterm electrical load forecasting model for a power system control cen tre. This hybrid architecture incorporates a Kohonen self-organising featur e map with unsupervised learning for classification of daily load patterns, a supervised backpropagation neural network for mapping the temperature/lo ad relationship, and a fuzzy expert system for postprocessing of neural net work outputs. This load forecaster requires minimum operator intervention a nd can be trained adaptively on-line. The developed model has been tested e xtensively in the actual operating environment and has been shown to outper form the existing regression-based model.