基于多尺度时序建模与估计的电力负荷数据恢复

doi:10.19595/j.cnki.1000-6753.tces.191664

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (3073 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要针对电力负荷数据缺损及失真问题,从时序数据特性分析及建模与估计的角度给出负荷数据补全与恢复的方法。运用马尔科夫链与序贯蒙特卡洛模拟联合法抽取负荷统计特性;基于电力负荷波动的年、月、周、日的多尺度时序特征分析,建立电力负荷的多尺度时序特征建模。引入B-spline基函数展开法解决负荷模型的非参、变系数问题,并给出负荷模型中关键参数的估计方法。采取误差多指标评判方法确定B-spline节点最优数量与样条最优次数。根据所得负荷恢复模型提出周尺度的电力负荷缺失数据恢复方法,并给出年度等长时段日负荷数据恢复思路。经实际算例验证,该文所提方法准确有效,具备工程应用价值。

	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
	张帅
	杨晶显
	刘继春
	刘俊勇
	林华珍

关键词 ：电力负荷恢复, 负荷统计特性抽取, 多尺度时序建模, 样条次数, 误差衡量指标

Abstract：Aiming at the defects and distortions of power load data, this paper presents a method of load data completion and recovery from the perspective of processing and characteristic analysis, modeling and estimation of time series data. Markov chain analysis and sequential Monte Carlo simulation methods were used to extract load statistics characteristics, then based on the power load fluctuation characteristics analysis of year, month, week and day, the multi-scale time-series characteristics of the load were modeled. B-spline basis function expansion method was introduced to solve the problems caused by non-parametric and variable coefficients characteristics of the load model, and an estimation method of the key parameters in the load model was provided. The optimal number of B-spline nodes and the optimal number of spline splines were determined by the multi-index error evaluation method. Based on the known load recovery model, a weekly lost power load recovery method is proposed, and the idea of daily load data recovery for the whole year or long duration is obtained. The method proposed in this paper is proved to be accurate and effective by practical examples and is of considerable engineering application value.

Key words： Power load recovery extraction of load statistics characteristics multi-scale time-series modeling degree of B-spline evaluating indicator of error

收稿日期: 2019-11-28

PACS:

TM74

基金资助:国家重点研发计划资助项目（2018YFB0905200）

通讯作者: 刘继春男,1975年生,博士,教授,研究方向为电力系统经济分析及电力市场。E-mail：jichunliu@scu.edu.cn

作者简介: 张帅男,1987年生,博士研究生,研究方向为可再生能源互补发电及电力市场。E-mail：shuaizhang@stu.scu.edu.cn

引用本文:

张帅, 杨晶显, 刘继春, 刘俊勇, 林华珍. 基于多尺度时序建模与估计的电力负荷数据恢复[J]. 电工技术学报, 2020, 35(13): 2736-2746. Zhang Shuai, Yang Jingxian, Liu Jichun, Liu Junyong, Lin Huazhen. Power Load Recovery Based on Multi-Scale Time-Series Modeling and Estimation. Transactions of China Electrotechnical Society, 2020, 35(13): 2736-2746.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.191664 https://dgjsxb.ces-transaction.com/CN/Y2020/V35/I13/2736

[1] 丁峰. 数据缺失条件下的电力负荷预测算法研究[D]. 武汉: 华中科技大学, 2016.
[2] 刘正超, 吴科成, 蔡珑, 等. 基于线性Bregman方法的缺失负荷数据低秩矩阵补全[J]. 广东电力, 2018, 31(5): 68-73.
Liu Zhengchao, Wu Kecheng, Cai Long, et al.Low rank matrix completion of missing load data based on linear Bregman[J]. Guangdong Electric Power, 2018, 31(5): 68-73.
[3] 毛李帆, 姚建刚, 金永顺, 等. 中长期负荷预测的异常数据辨识与缺失数据处理[J]. 电网技术, 2010, 34(7): 148-153.
Mao Lifan, Yao Jiangang, Jin Yongshun, et al.Abnormal data identification and missing data filling in medium-and long-term load forecasting[J]. Power System Technology, 2010, 34(7): 148-153.
[4] 李军, 李青. 基于CEEMDAN-排列熵和泄漏积分ESN的中期电力负荷预测研究[J]. 电机与控制学报, 2015, 19(8): 70-80.
Li Jun, Li Qing.Medium term electricity load forecasting based on CEEMDAN-permutation entropy and ESN with leaky integrator neurons[J]. Electric Machines and Control, 2015, 19(8): 70-80.
[5] 刁赢龙, 盛万兴, 刘科研, 等. 大规模配电网负荷数据在线清洗与修复方法研究[J]. 电网技术, 2015, 39(11): 3134-3140.
Diao Yinglong, Sheng Wanxing, Liu Keyan, et al.Research on online cleaning and repair methods of large-scale distribution network load data[J]. Power System Technology, 2015, 39(11): 3134-3140.
[6] 张晓英, 蒋拯, 丁宁, 等. 负荷裕度及其与典型参数的灵敏度计算[J]. 电机与控制学报, 2015, 19(8): 28-35.
Zhang Xiaoying, Jiang Zheng, Ding Ning, et al.Load margin and its sensitivity calculation with typical parameters[J]. Electric Machines and Control, 2015, 19(8): 28-35.
[7] 顾民, 葛良全, 熊文贤. 基于神经网络的电力负荷不良数据的清洗[J]. 微计算机信息, 2007(21): 265-267.
Gu Min, Ge Liangquan, Xiong Wenxian.Cleaning for bad electric load data based on neural network[J]. Microcomputer Information, 2007(21): 265-267.
[8] 韦钢, 王飞, 张永健, 等. 负荷预测中历史数据缺损处理[J]. 电力科学与工程, 2004(1): 16-19.
Wei Gang, Wang Fei, Zhang Yongjian, et al.Methods of processing shortage and damage of historical data in load forecasting[J]. Electric Power Science and Engineering, 2004(1): 16-19.
[9] 杨茂, 王金鑫, 都键. 基于极限学习机与格兰杰检验的风电功率缺失数据补齐[J]. 东北电力大学学报, 2019, 39(5): 9-16.
Yang Mao, Wang Jinxin, Du Jian.The complement of the missing data based on the extreme learning machine and Granger test in wind power[J]. Journal of Northeast Electric Power University, 2019, 39(5): 9-16.
[10] 杨茂, 孙涌, 穆钢, 等. 基于自适应神经模糊推理系统的风功率缺失数据补齐[J]. 电力系统自动化, 2014, 38(19): 16-21, 46.
Yang Mao, Sun Yong, Mu Gang, et al.Data completing of missing wind power data based on adaptive neuro-fuzzy inference system[J]. Automation of Electric Power Systems, 2014, 38(19): 16-21, 46.
[11] 吴润泽, 包正睿, 王文韬, 等. 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, et al.Short-term power load forecasting method based on pattern matching in Hadoop framework[J]. Transactions of China Electrotechnical Society, 2018, 33(7): 1542-1551.
[12] 徐春华, 陈克绪, 马建, 等. 基于深度置信网络的电力负荷识别[J]. 电工技术学报, 2019, 34(19): 4135-4142.
Xu Chunhua, Chen Kexu, Ma Jian, et al.Recognition of power loads based on deep belief network[J]. Transactions of China Electrotechnical Society, 2019, 34(19): 4135-4142.
[13] 王守相, 邓欣宇, 陈海文, 等. 采用可拓展交互式设计的负荷特性综合分析平台[J]. 电力系统自动化, 2019, 43(20): 176-189.
Wang Shouxiang, Deng Xinyu, Chen Haiwen, et al.Comprehensive analysis platform of load characteristics based on extendable and interactive design[J]. Automation of Electric Power Systems, 2019, 43(20): 176-189.
[14] 王志强, 王珊, 张馨月, 等. 计及用户响应行为差异性的区域电采暖负荷特性建模[J]. 电力系统自动化, 2019, 43(7): 67-79.
Wang Zhiqiang, Wang Shan, Zhang Xinyue, et al.Load characteristics modeling of regional electric heating system considering difference of users response behaviors[J]. Automation of Electric Power Systems, 2019, 43(7): 67-79.
[15] Billinton R, Allan R N.Reliability evaluation of engineering systems: concepts and techniques[M]. 2nd ed. New York and London: Plenum Press, 1992.
[16] 李文沅. 电力系统风险评估-模型、方法和应用[M].北京: 科学出版社, 2006.
[17] Shin J H, Yi B J, Kim Y I, et al.Spatiotemporal load-analysis model for electric power distribution facilities using consumer meter-reading data[J]. IEEE Transactions on Power Delivery, 2011, 26(2): 736-743.
[18] Liu Hanjie, Zhang Huajun, Huang Qinqin, et al.Power load forecasting based on data analysis and neural networks[C]//Chinese Automation Congress, Xi′an 2018: 744-748.
[19] 徐青山, 刘梦佳, 戴蔚莺, 等. 计及用户响应不确定性的可中断负荷储蓄机制[J]. 电工技术学报, 2019, 34(15): 3198-3208.
Xu Qingshan, Liu Mengjia, Dai Weiying, et al.Interruptible load based on deposit mechanism considering uncertainty of customer behavior[J]. Transactions of China Electrotechnical Society, 2019, 34(15): 3198-3208.
[20] Coughlin K, Murthi A, Eto J.Multi-scale analysis of wind power and load time series data[J]. Renewable Energy, 2014, 68: 494-504.
[21] Eilers P H C, Marx B D. Flexible smoothing with B-splines and penalties[J]. Statistical Science, 1996, 11(2): 89-102.
[22] Pereira L E S, Da Costa V M. Interval analysis applied to the maximum loading point of electric power systems considering load data uncertainties[J]. International Journal of Electrical Power & Energy Systems, 2014, 54: 334-340.
[23] 黄睿, 郭谋发, 陈永往. 基于径向基函数神经网络的配电网参数估计[J]. 电气技术, 2019, 20(4): 42-46.
Huang Rui, Guo Moufa, Chen Yongwang.Parameter estimation of distribution system based on radial basis neural network[J]. Electrical Engineering, 2019, 20(4): 42-46.
[24] 李春燕, 蔡文悦, 赵溶生, 等. 基于优化SAX和带权负荷特性指标的AP聚类用户用电行为分析[J]. 电工技术学报, 2019, 34(增刊1): 368-377.
Li Chunyan, Cai Wenyue, Zhao Rongsheng, et al.Customer behavior analysis based on affinity propagation algorithm with optimized sax and weighted load characteristic indices[J]. Transactions of China Electrotechnical Society, 2019, 34(S1): 368-377.
[25] Cheng B, Tong H.On residual sums of squares in nonparametric autoregression[J]. Stochastic Processes and Their Applications, 1993, 48(1): 157-174.
[26] Olatomiwa L, Mekhilef S, Shamshirband S, et al.A support vector machine fire fly algorithm-based model for global solar radiation prediction[J]. Solar Energy, 2015, 115: 632-644.
[27] 许珉, 刘玮. 加8项余弦窗插值FFT算法[J]. 电力系统保护与控制, 2015, 43(11): 27-32.
Xu Min, Liu Wei.An interpolation FFT algorithm based on 8-term cosine window[J]. Power System Protection and Control, 2015, 43(11): 27-32.
[28] 蒋泽甫, 谢开贵. 基于时序负荷的独立电网风/柴/储电源系统容量优化[J]. 电力系统保护与控制, 2012, 40(20): 119-124.
Jiang Zefu, Xie Kaigui.Capacity optimization of power supply system for the isolated grid containing WT/DU/ESS based on chronological loads[J]. Power System Protection and Control, 2012, 40(20): 119-124.
[29] 王毅, 张宁, 康重庆, 等.电力用户行为模型:基本概念与研究框架[J]. 电工技术学报, 2019, 34(10): 2056-2068.
Wang Yi, Zhang Ning, Kang Chongqing, et al.Electrical consumer behavior model: basic concept and research framework[J]. Transactions of China Electrotechnical Society, 2019, 34(10): 2056-2068.
[30] Mcloughlin F, Duffy A, Conlon M.A clustering approach to domestic electricity load profile characterisation using smart metering data[J]. Applied Energy, 2015, 141: 190-199.
[31] 王海燕, 任志超, 杜新伟, 等. 四川电网负荷特性分析预测[J]. 四川电力技术, 2013, 36(5): 37-40, 90.
Wang Haiyan, Ren Zhichao, Du Xinwei, et al.Load characteristics analysis and prediction of Sichuan power grid[J]. Sichuan Electric Power Technology, 2013, 36(5): 37-40, 90.
[32] 杨浩, 张磊, 何潜, 等. 基于自适应模糊C均值算法的电力负荷分类研究[J]. 电力系统保护与控制, 2010, 38(16): 111-115, 122.
Yang Hao, Zhang Lei, He Qian, et al.Study of power load classification based on adaptive fuzzy C means[J]. Power System Protection and Control, 2010, 38(16): 111-115, 122.