Short-term energy load forecasting using recurrent neural network

被引：0

作者：

Rashid, T ^{[1
]}

Kechadi, T ^{[1
]}

Huang, BQ ^{[1
]}

机构：

[1] Univ Coll Dublin, Dept Comp Sci, Dublin 4, Ireland

来源：

Proceedings of the Eighth IASTED International Conference on Artificial Intelligence and Soft Computing | 2004年

关键词：

short-term load forecasting; artificial neural networks; recurrent recurrent networks;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a study of an artificial recurrent neural network applied to the problem of the prediction of short term energy load. The idea is to predict a daily maximum load (DML) for a given month based on the previous years as the daily average temperature (DAT) is unknown. Two models were carried out to predict the DML. In the first model, the prediction is based on both weekday and weekend DML. The second model is based on the maximum load profile. A new recurrent network trained with back propagation is used for each model. The results for both models are compared and discussed.

引用

页码：276 / 281

页数：6