Key points are not available for this paper at this time.
A hybrid approach utilizing a fuzzy system and artificial neural network for bus load forecasting is proposed in this paper. This approach models the behavior of load on those areas where it is primarily a function of temperature. Load sequences were broken down into a nonweather sensitive, normal load sequence and a pure weather sensitive load sequence. It has been shown that normal load has a stationary characteristic and can be modeled by back propagation neural networks. The weather sensitive load has been modeled by a set of three fuzzy logic systems trained by least square estimation of an optimal fuzzy basis function coefficient. The model was tested with 1994 historical data from the town of Hinton, West Virginia (part of the Appalachian Power Company). The results show an average MAPE (mean absolute percentage error) of 2%, which is comparable with system load forecasting methods reported in the literature.
Kassaei et al. (Sat,) studied this question.