翟玮星
ZHAI Weixing

• 1:国网浙江省电力公司宁波供电公司

摘要(Abstract)：

提出了一种短期负荷多步预测的修正方法。首先采用BP神经网络法建立短期负荷的分时多步预测模型,对于每一个初始预测值,采用卡尔曼滤波模型进行修正,以减少模型的累积误差,提高多步预测的效果。算例结果证明了所提方法不仅能够提高单步预测的预测效果,而且能够有效降低多步预测的误差,对于实现连续日短期负荷预测具有现实意义。
This paper proposes a modified method for multi-step forecasting of short-term load. Firstly, the BP neural network method is adopted to establish time-sharing and multi-step forecasting model of short-term load; then Kalman filter model is utilized to modify each initial forecast value to reduce the cumulative error of the model and improve multi-step forecasting. The calculation example result demonstrates that the proposed method can not only improve forecasting of single-step forecasting but effectively reduce multi-step forecasting errors; it is of operation significance for consecutive daily short-term load forecasting.

关键词(KeyWords)： 卡尔曼滤波;短期负荷;多步预测;累积误差;BP神经网络
Kalman filter;short-term load;multi-step forecasting;cumulative error;BP neural network

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 翟玮星
ZHAI Weixing

DOI: 10.19585/j.zjdl.2014.07.005

参考文献(References)：

• [1]牛东晓,曹树华,卢建昌,等.电力负荷预测技术及其应用[M].北京:中国电力出版社,2009.
• [2]康重庆,夏清,刘梅.电力系统负荷预测[M].北京:中国电力出版社,2007.
• [3]HONG TZER YANG,CHAO MING HUANG.A new short-term load forecasting approach using self-organizing fuzzy ARMAX models[J].IEEE Transactions on Power Systems,1998,13(1):217-225.
• [4]李林川,王立成.应用人工神经网络进行短期负荷预测[J].电力系统及其自动化学报,1994,6(3):33-41.
• [5]李云飞,黄彦全,蒋功连.基于PCA-SVM的电力系统短期负荷预测[J].电力系统及其自动化学报,2007,19(5):66-70.
• [6]陈伟.电力系统短期负荷预测组合模型研究[D].武汉:华中科技大学电气学院,2007.
• [7]赵攀,戴义平,夏俊荣,等.卡尔曼滤波修正的风电场短期功率预测模型[J].西安交通大学学报,2011,45(5):47-51.
• [8]李明干,孙健利,刘沛.基于卡尔曼滤波的电力系统短期负荷预测[J].继电器,2004,32(4):9-12.