摘要
提出了一种基于模糊聚类分析和BP网络的短期负荷预测方法。考虑了温度、相对湿度以及日类型等影响负荷的因素,通过模糊聚类分析将负荷历史数据分成若干类,找出同预测日相符的预测类别,然后建立相应的BP网络模型,用附加动量和变学习速率的方法预测每小时的负荷。对于西安地区实际负荷的预测结果的分析表明该方法有较高的预测精度,取得了令人满意的结果。
A short-term load forecasting method based on fuzzy clustering analysis and BP neural network is presented. Some factors influencing load such as temperature, relative humidity and day type are considered. By means of dividing the historical load data into several categories by fuzzy clustering analysis and finding out the category coincident with that of the daily load to be forecasted, corresponding BP neural network model is built, then the additional momentum and diverse learning speed algorithm are employed to forecast hourly load. The actual load forecasting results for Xi'an district show that the proposed method possesses better forecasting accuracy and the forecasting is satisfactory.
出处
《电网技术》
EI
CSCD
北大核心
2005年第1期20-23,共4页
Power System Technology