A hybrid expert system assisting decision making for distribution system load forecasting.

Morsi, D.M.; Abbasy, N.H.; Abul Ella, M.S.

Abstract

This paper introduces a typically intelligent hybrid expert system (ES) for an annualized distribution system load forecasting. The proposed ES has the capability of predicting the annual distribution substation load growth, and patterns of subsequent load shifts, in the case of a substation overload. Also, possible expected system expansion plans are introduced. The parameters of the load growth model are estimated for each substation. The load transfer model is chosen to follow the Weibull distribution function and to simulate different factors affecting the transfer process. The ES is developed using an artificial intelligence language (PROLOG), and is applied to Alexandria city, 66/11 kV power distribution network.

Citation

MORSI, D.M., ABBASY, N.H. and ABUL ELLA, M.S. 1994. A hybrid expert system assisting decision making for distribution system load forecasting. In Proceedings of the 1994 Mediterranean electrotechnical conference (MELECON '94), 12-14 April 1994, Antalya, Turkey. Piscataway: IEEE [online], pages 893-896. Available from: https://doi.org/10.1109/MELCON.1994.380958

• Conference Name: 1994 Mediterranean electrotechnical conference (MELECON '94)
• Conference Location: Antalya, Turkey
• Start Date: Apr 12, 1994
• End Date: Apr 14, 1994
• Acceptance Date: Feb 28, 1994
• Online Publication Date: Apr 14, 1994
• Publication Date: Aug 6, 2002
• Deposit Date: Nov 10, 2022
• Publicly Available Date: Nov 10, 2022
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Book Title: Proceedings of the 1994 Mediterranean electrotechnical conference (MELECON '94), 12-14 April 1994, Antalya, Turkey
• ISBN: 0780317726
• DOI: https://doi.org/10.1109/melcon.1994.380958
• Keywords: Expert systems; Decision making; Substations; Load modeling; Power system modeling; Hybrid intelligent systems; Load forecasting; Weibull distribution; Artificial intelligence; Cities and towns
• Public URL: https://rgu-repository.worktribe.com/output/1805765