Fuzzy short-term load forecasting models based on load curve-shaped prototype fuzzy clustering

Author

Papadakis, S.E. ; Theocharis, J.B. ; Bakirtzis, A.G.

Author_Institution

Dept. of Electr. & Comput. Eng., Aristotle Univ. of Thessaloniki, Thessaloniki, Greece

fYear

1999

fDate

Aug. 31 1999-Sept. 3 1999

Firstpage

2023

Lastpage

2028

Abstract

A modeling method is suggested in this paper which permits building fuzzy models for short-term load forecasting (STLF). The model building process is divided in two parts: a) the structure identification based on the fuzzy C-regression method and b) fine tuning which is achieved using a hybrid genetic/least squares algorithm. The method creates daily models that provide a physical insight of the forecast process. The simulation results demonstrate the efficiency of the suggested model.

Keywords

fuzzy set theory; genetic algorithms; least squares approximations; load forecasting; pattern clustering; power system simulation; regression analysis; splines (mathematics); B-spline; STLF; fine tuning; forecast process; fuzzy C-regression method; fuzzy clustering; fuzzy short-term load forecasting models; hybrid genetic/least squares algorithm; load curve-shaped prototype; model building process; modeling method; structure identification; Biological system modeling; Load forecasting; Load modeling; Predictive models; Prototypes; Splines (mathematics); Cubic B-splines; Fuzzy C-regression method; Fuzzy modeling; Short-term load forecasting;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (ECC), 1999 European

Conference_Location

Karlsruhe

Print_ISBN

978-3-9524173-5-5

Type

conf

Filename

7099615