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

Citation
D. Srinivasan et al., Practical implementation of a hybrid fuzzy neural network for one-day-ahead load forecasting, IEE P-GEN T, 145(6), 1998, pp. 687-692
Citations number
14
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
IEE PROCEEDINGS-GENERATION TRANSMISSION AND DISTRIBUTION
ISSN journal
13502360 → ACNP
Volume
145
Issue
6
Year of publication
1998
Pages
687 - 692
Database
ISI
SICI code
1350-2360(199811)145:6<687:PIOAHF>2.0.ZU;2-I
Abstract
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.