【摘要】 为了提高短期负荷预测速度和精度,提出了将模糊聚类分析和神经网络代数算法相结合的短期负荷预测方法。综合考虑天气、日类型、历史负荷等对未来负荷变化的影响,通过模糊聚类分析选取学习样本,找出同预测日相符的预测类别,采用神经网络代数算法训练样本,对24小时负荷(24点)每点建立一个预测模型。该方法充分发挥了神经网络和模糊理论处理非线性问题的能力,提高了学习效能,而且克服了传统BP算法存在的缺点。算例分析结果表明该方法有较高的预测精度,取得了令人满意的结果。更多还原

【Abstract】 In order to improve the speed and accuracy of short-term load forecasting considering the combined influence of weather,day type and historical load data,a new short-term load forecasting method is proposed.The selection of learning samples is carried out by the fuzzy clustering method,and then based on finding out the category coincident with that of the daily load to be forecasted and using the neural network algebra algorithm,a forecasting model for each of the 24 points are established.In this method,the capacity of handling non-linear problems of neural network and fuzzy theory is made full use to improve the learning efficiency and overcome the shortcoming of the traditional BP algorithm.The case study results show that the proposed method has better performance with regards to forecasting accuracy.更多还原