基于人工神经网络的鲁棒短期负荷预测方法

提出一种用神经网络设计提前一天的短期负荷预测系统的方法.在对神经网络进行训练前,先通过一种简单的方法对数据进行了预处理,以使设计的系统具有处理由于突发事件等因素引起负荷突然变化的能力.用山东省电网2003年的负荷数据进行试验,试验结果表明方法的适用性.

A robust short-term load forecasting method using neural network

In this paper, we proposed a neural network approach for next day load curve forecastting.Before the data were fed into the neural network, they were preprocessed through a simple way. The proposed method has the advantage of dealing with load curve which is influenced by special cases.The suitability of the proposed approach was illustrated through an application to actual load data of Shan Dong Electric Power Company.