zbMATH — the first resource for mathematics

Multilayer neuro-fuzzy network for short term electric load forecasting. (English) Zbl 1142.68468
Hirsch, Edward A. (ed.) et al., Computer science – theory and applications. Third international computer science symposium in Russia, CSR 2008 Moscow, Russia, June 7–12, 2008. Proceedings. Berlin: Springer (ISBN 978-3-540-79708-1/pbk). Lecture Notes in Computer Science 5010, 339-348 (2008).
Summary: The problem of short term electric load forecasting is considered in the case when a part of input variables is given in a nonnumeric form. Novel neuro-fuzzy network architecture and learning algorithms are proposed, which enable high-rate processing of information given in different measurements scales (quantitative, ordinal, and nominal). Types and parameters of the employed membership functions may be determined by the amount of available explicit prior knowledge. Experimental comparison to a traditional neural network confirms superiority of the proposed approach.
For the entire collection see [Zbl 1136.68005].
68T05 Learning and adaptive systems in artificial intelligence
90B99 Operations research and management science
PDF BibTeX Cite
Full Text: DOI