FORECASTING WEEKLY ELECTRIC LOAD USING A HYBRID FUZZY-NEURAL NETWORK APPROACH

journal article - other

English

A hybrid approach utilizing a fuzzy system and artificial neural network (ANN) for short-term load forecasting of the Czech Electric Power Company (ČEZ) is proposed in this paper. Expert knowledge represented by fuzzy rules is used for preprocessing input data fed to a neural network. For training the neural network for one-week ahead load forecasting, fuzzy ‘If-Then’ rules are used, in addition to historical load and temperature data that are usually employed in conventional supervised training algorithms. The fuzzy-neural network is trained on real data for the years 1994 through 1998 and evaluated on the data for the year 1999 for forecasting next-week load profiles. A very good prediction performance is attained as shown in the simulation results, which verify the effectiveness and superiority of the modeling technique.

One-week ahead load forecasting, Multilayer neural networks and Hybrid fuzzy-neural networks (FNN)

KHAN, M., ŽÁK, L., ONDRŮŠEK, Č.

2004

26. 11. 2001

1210-2717

Inženýrská mechanika - Engineering Mechanics

2001

8

Czech Republic

44

98

55