Hadoop架构下基于模式匹配的短期电力负荷预测方法

doi:10.19595/j.cnki.1000-6753.tces.170121

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (14484 KB)
输出: BibTeX | EndNote (RIS)

摘要大数据处理技术充分利用海量动态数据,能有效提升电力负荷预测精度及计算效率。采用Hadoop架构提出了一种基于模式匹配的短期电力负荷预测方法,通过度量日负荷序列相似性挖掘得出典型日负荷模式,辨识出关键影响因素构建基于并行随机森林的决策树群从而建立模式匹配规则,实现待测日负荷模式的快速准确匹配;在典型负荷模式下建立多时刻点预测模型,采用MapReduce计算框架进行负荷计算与预测分析,从而建立大量样本下的负荷预测模型。以某地市电网全年负荷数据为例进行负荷预测分析,并通过平均误差和方均根误差等指标对比局部加权线性回归（LWLR）算法的预测效果。仿真结果表明该方法用于短期负荷预测时具有更高的预测准确性和计算效率。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	吴润泽
	包正睿
	王文韬
	邓伟
	唐良瑞

关键词 ： Hadoop架构, 负荷预测, 影响因素, 决策树群, 模式匹配

Abstract：Big data processing technologies make full use of massive dynamic data, which can improve the accuracy and efficiency of power load forecasting. To this end, realize the short-term load forecasting based on load pattern matching combined with Hadoop framework. Typical day-load patterns are deduced from the similarity of the daily load sequences, and the decision trees are built by identifying the important influence factors based on the parallel random forest to achieve the fast and accurate matching of the daily load pattern. The forecasting model of multiple time point for each typical load pattern is constructed in MapReduce computing framework for load prediction and analysis to get the prediction results of the following day load using a large number of samples. The simulation analysis used the whole-year load data in a city power grid and compared with locally weighted linear regression (LWLR) algorithm by the mean error, root mean square error and other indices. The results show that the method can provide higher prediction accuracy and computational efficiencyin short-term load forecasting.

Key words： Hadoop framework load forecasting influence factor decision trees pattern matching

收稿日期: 2017-02-08 出版日期: 2018-04-12

PACS:

TM714

基金资助:国家自然科学基金重点项目（51507063）和国家电网公司科技项目（B34681150152）资助

通讯作者: 包正睿男,1992年生,硕士研究生,研究方向为面向智能电网应用的大数据关键技术和电力负荷预测。E-mail：baozr_ncepu@163.com

作者简介: 吴润泽女,1975年生,博士,副教授,研究方向为电力通信网可靠性分析评估与规划。E-mail：wurz@ncepu.edu.cn

引用本文:

吴润泽, 包正睿, 王文韬, 邓伟, 唐良瑞. Hadoop架构下基于模式匹配的短期电力负荷预测方法[J]. 电工技术学报, 2018, 33(7): 1542-1551. Wu Runze, Bao Zhengrui, Wang Wentao, Deng Wei, Tang Liangrui. Short-Term Power Load Forecasting Method Based on Pattern Matching in Hadoop Framework. Transactions of China Electrotechnical Society, 2018, 33(7): 1542-1551.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.170121 https://dgjsxb.ces-transaction.com/CN/Y2018/V33/I7/1542

[1] 丁杰, 奚后玮, 韩海韵, 等. 面向智能电网的数据密集型云存储策略[J]. 电力系统自动化, 2012, 36(12): 66-70.
Ding Jie, Xi Houwei, Han Haiyun, et al.A smart grid-oriented data placement strategy for data-intensive cloud environment[J]. Automation of Electric Power Systems, 2012, 36(12): 66-70.
[2] Amjady N.Short-term hourly load forecasting using time series modeling with peak load estimation capability[J].IEEE Transactions on Power Systems, 2001, 16(4): 798-805.
[3] 马坤隆. 基于大数据的分布式短期负荷预测方法[D].长沙: 湖南大学, 2014.
[4] 李龙, 魏靖, 黎灿兵, 等. 基于人工神经网络的负荷预测模型[J]. 电工技术学报, 2015, 30(8): 225-230.
Li Long, Wei Jing, Li Canbing, et al.Prediction of load model based on artificial neural network[J]. Transactions of China Electrotechnical Society, 2015, 30(8): 225-230.
[5] 刘念, 张清鑫, 刘海涛. 基于核函数极限学习机的微电网短期负荷预测方法[J]. 电工技术学报, 2015, 30(8): 218-224.
Liu Nian, Zhang Qingxin, Liu Haitao.Online short-term load forecasting based on ELM with Kernel algorithm in micro-grid environment[J]. Transactions of China Electrotechnical Society, 2015, 30(8): 218-224.
[6] 陈亚, 李萍. 基于神经网络的短期电力负荷预测仿真研究[J]. 电气技术, 2017, 18(1): 26-29.
Chen Ya, Li Ping.Research on simulation of short-term power load forecasting based on neural network[J]. Electrical Engineering, 2017, 18(1): 26-29.
[7] 王贺, 胡志坚, 张翌晖, 等. 基于聚类经验模态分解和最小二乘支持向量机的短期风速组合预测[J]. 电工技术学报, 2014, 29(4): 237-245.
Wang He, Hu Zhijian, Zhang Yihui, et al.A hybrid model for short-term wind speed forecasting based on ensemble empirical mode decomposition and least squares support vector machines[J]. Transactions of China Electrotechnical Society, 2014, 29(4): 237-245.
[8] 田中大, 李树江, 王艳红, 等. 基于小波变换的风电场短期风速组合预测[J]. 电工技术学报, 2015, 30(9): 112-120.
Tian Zhongda, Li Shujiang, Wang Yanhong, et al.Short-term wind speed combined prediction for wind farms based on wavelet transform[J]. Transactions of China Electrotechnical Society, 2015, 30(9): 112-120.
[9] 虞尚智. 机器学习算法在短期电力负荷预测中的应用[J]. 科学技术与工程, 2013, 13(8): 2231-2234.
Yu Shangzhi.Application of machine learning in short-term load prediction[J]. Science Technology and Engineering, 2013, 13(8): 2231-2234.
[10] 赵莉, 候兴哲, 胡君, 等. 基于改进k-means算法的海量智能用电数据分析[J]. 电网技术, 2014, 38(10): 2715-2720.
Zhao Li, Hou Xingzhe, Hu Jun, et al.Improved k-means algorithm based analysis on massive data of intelligent power utilization[J]. Power System Technology, 2014, 38(10): 2715-2720.
[11] 董新华, 李瑞轩, 周湾湾, 等. Hadoop系统性能优化与功能增强综述[J]. 计算机研究与发展, 2013, 50(增刊2): 1-15.
Dong Xinhua, Li Ruixuan, Zhou Wanwan, et al.Performance optimization and feature enhancements of hadoop system[J]. Journal of Computer Research and Development, 2013, 50(S2): 1-15.
[12] 陈曦, 陈华钧, 顾珮嵚, 等. 一种基于Hadoop 的语义大数据分布式推理框架[J]. 计算机研究与发展, 2013, 50(增刊2): 103-113.
Chen Xi, Chen Huajun, Gu Peiqin, et al.A distributed reasoning framework for big semantic data based on hadoop[J]. Journal of Computer Research and Development, 2013, 50(S2): 103-113.
[13] 宋亚奇, 周国亮, 朱永利. 智能电网大数据处理技术现状与挑战[J]. 电网技术, 2013, 37(4): 927-935.
Song Yaqi, Zhou Guoliang, Zhu Yongli.Present status and challenges of big data processing in smart grid[J]. Power System Technology, 2013, 37(4): 927-935.
[14] 罗滇生, 王新坤. 基于云计算的智能电网负荷预测平台架构研究[J]. 湖南大学学报(自然科学版), 2016, 43(2): 101-108.
Luo Diansheng, Wang Xinkun.Research on the framework of smart grid load forecasting platform based on cloud computing[J]. Journal of Hunan University(Natural Sciences), 2016, 43(2): 101-108.
[15] 王德文, 孙志伟. 电力用户侧大数据分析与并行负荷预测[J]. 中国电机工程学报, 2015, 35(3): 527-537.
Wang Dewen, Sun Zhiwei.Big data analysis and parallel load forecasting of electric power user side[J]. Proceedings of the CSEE, 2015, 35(3): 527-537.
[16] 张素香, 赵丙镇, 王风雨, 等. 海量数据下的电力负荷短期预测[J]. 中国电机工程学报, 2015, 35(1): 37-42.
Zhang Suxiang, Zhao Bingzhen, Wang Fengyu, et al.Short-term power load forecasting based on big data[J]. Proceedings of the CSEE, 2015, 35(1): 37-42.
[17] 毛力, 王运涛, 刘兴阳, 等. 基于改进极限学习机的短期电力负荷预测方法[J]. 电力系统保护与控制, 2012, 40(20): 140-144.
Mao Li, Wang Yuntao, Liu Xingyang, et al.Short-term power load forecasting method based on improved extreme learning machine[J]. Power System Protection and Contol, 2012, 40(20): 140-144.
[18] Breiman L.Random forests[J].Machine Learning, 2001, 45(1): 5-32.
[19] 刘敏, 郎荣玲, 曹永斌. 随机森林中树的数量[J]. 计算机工程与应用, 2015, 51(5): 126-131.
Liu Min, Lang Rongling, Cao Yongbin.Number of trees in random forest[J]. Computer Engineering and Applications, 2015, 51(5): 126-131.
[20] 张光亚, 方柏山. 基于氨基酸组成分布的嗜热和嗜冷蛋白随机森林分类模型[J]. 生物工程学报, 2008, 24(2): 302-308.
Zhang Guangya, Fang Baishan.Random forest for classification of thermophilic and psychrophilic proteinsbased on amino acid composition distribution[J]. Chinese Journal of Biotechnology, 2008, 24(2): 302-308.