含有历史不良数据的电力负荷预测研究

杨慧霞; 邓迎君; 刘志斌; 姚睿

引用本文:	杨慧霞,邓迎君,刘志斌,等.含有历史不良数据的电力负荷预测研究[J].电力系统保护与控制,2017,45(15):62-68.
	YANG Huixia,DENG Yingjun,LIU Zhibin,et al.Study on electric load forecasting with historical bad data[J].Power System Protection and Control,2017,45(15):62-68

【打印本页】【下载PDF全文】【查看/发表评论】【EndNote】【RefMan】【BibTex】

←前一篇|后一篇→

过刊浏览高级检索

本文已被：浏览 5020次下载 2085次	码上扫一扫！
分享到：微信更多字体:加大+\|默认\|缩小-
含有历史不良数据的电力负荷预测研究
杨慧霞^1,2,邓迎君³,刘志斌⁴,姚睿⁵
(1.许昌开普电气研究院，河南许昌 461000;2.河南省继电保护及自动化重点实验室，河南许昌 461000; 3.许继集团有限公司，河南许昌 461000;4.上海电力学院，上海 200090; 5.北京四方继保自动化股份有限公司，北京 100085)

摘要:

传统负荷预测算法在历史负荷序列无不良数据的条件下已能对短期负荷做出较为理想的预测。由于实际负荷数据在监测、集抄、存储过程中难免会产生错误或有所误差，此时仍依靠传统预测算法进行负荷预测，可能在某些时间节点会引起较大误差。为了解决此问题，提出含有历史负荷序列不良数据辨识与修正能力且能对负荷进行相似度预测及负荷偏差纠正的预测模型。通过运用实际电力负荷数据进行验证，该模型能较好地避免了不良数据的干扰，有效地提高了含有不良数据的历史负荷序列的预测精度。

关键词: 短期负荷预测不良数据辨识相似度神经网络

DOI：10.7667/PSPC162122

分类号:

基金项目:国家自然科学基金(61602295);上海市自然科学基金(16ZR1413100)

Study on electric load forecasting with historical bad data

YANG Huixia^1,2,DENG Yingjun³,LIU Zhibin⁴,YAO Rui⁵

(1. Xuchang Ketop Electric Research Institute, Xuchang 461000, China;2. Henan Key Laboratory of Relay Protection and Automation, Xuchang 461000, China;3. XJ Group Corporation, Xuchang 461000, China;4. Shanghai University of Electric Power, Shanghai 200090, China;5. Beijing Sifang Automation Co., Ltd., Beijing 100085, China)

Abstract:

Traditional load forecasting algorithm can predict short-term load when there is no bad data in historical load sequence. Actual load data will inevitably produce errors during the process of monitoring, collecting and storing, if the traditional prediction algorithm is still used for load forecasting, it may cause large errors at some time nodes. In order to solve this problem, this paper proposes a prediction model which can not only identify and correct the bad data of historical load sequence and but also predict the load similarity and correct the load deviation. By using the actual load data to verify the model, the model can better avoid the interference of bad data, and effectively improve the prediction accuracy of the historical load sequence with bad data. This work is supported by National Natural Science Foundation of China (No. 61602295) and Natural Science Foundation of Shanghai (No. 16ZR1413100).

Key words: short-term load forecasting bad data identification similarity neural networks

X关闭