论文信息 - Artificial neural network for forecasting daily loads of a Canadian electric utility

Artificial neural network for forecasting daily loads of a Canadian electric utility

This paper describes the application of an artificial neural network to short term load forecasting. One of the most popular artificial neural network models, the 3-layer backpropagation model, is used to learn the relationship between 86 inputs, which are believed to have significant effects on the loads, and 24 outputs: one for each hourly load of the day. Historical data collected over a period of 2 years (e.g. calendar years 1989 and 1990) is used to train the proposed ANN network. The results of the proposed ANN networks have been compared to those of the present system (multiple linear regression) and show an improved forecast capability.<<ETX>>

[1] Chuen-Sheng Cheng,et al. Identification of seasonal short-term load forecasting models using statistical decision functions , 1990 .

[2] Robert J. Marks,et al. Electric load forecasting using an artificial neural network , 1991 .

[3] Mo-Shing Chen,et al. An Application of State Estimation to Short-Term Load Forecasting, Part I: Forecasting Modeling , 1970 .

[4] George G. Karady,et al. Advancement in the application of neural networks for short-term load forecasting , 1992 .

[5] G. Fronza,et al. Role of weather inputs in short-term forecasting of electric load , 1986 .

[6] Saifur Rahman,et al. An expert system based algorithm for short term load forecast , 1988 .