基于数据融合技术的电能质量扰动关联分析
|
摘要
在复杂电网环境下,电能质量监测系统检测到的扰动事件与设备动作之间可能具有关联特性。现提出一种基于数据融合技术的电能质量扰动关联分析方法:首先,考虑电能质量扰动事件的时间关联特性,提出一种基于移动时间窗的扰动时段划分方法;其次,利用实体匹配技术融合同一扰动时段的电能质量数据和电网动作事件数据,鉴于融合数据的空间相似性,采用分布式关联规则分析方法挖掘了扰动事件特征与电网动作、事件成因之间的强关联规则,分析结果具备推广能力;最后,依据实际电网数据,验证了此方法的可行性和有效性。试验结果表明,所提出的方法能分析典型扰动事件特征与事件原因之间的关联特性。该特性对于指导未来电能质量成因分析具有重要意义。
In the complex power system,the disturbance events detected by the power quality monitoring system may be associated with device actions.This paper proposed a power quality disturbance association analysis method based on data fusion technology.First,a disturbance period partition method based on moving-window was proposed considering the temporal correlation of disturbance events.Then,the entity matching technology was used to integrate power quality data and power system equipment action data at the same disturbance period.The distributed association rules mining was utilized to obtain strong association rules among disturbance event features,equipment actions and event causes considering the spatial similarity of fused data.The analysis results have good generalization performance.Finally,the real grid data were taken as an example to verify the effectiveness and practicability of the proposed method.The test results show that the proposed method can analyze the relationship between the typical disturbance event features and event causes.This relationship is meaningful for analyzing power quality events causes in the future.
In the complex power system,the disturbance events detected by the power quality monitoring system may be associated with device actions.This paper proposed a power quality disturbance association analysis method based on data fusion technology.First,a disturbance period partition method based on moving-window was proposed considering the temporal correlation of disturbance events.Then,the entity matching technology was used to integrate power quality data and power system equipment action data at the same disturbance period.The distributed association rules mining was utilized to obtain strong association rules among disturbance event features,equipment actions and event causes considering the spatial similarity of fused data.The analysis results have good generalization performance.Finally,the real grid data were taken as an example to verify the effectiveness and practicability of the proposed method.The test results show that the proposed method can analyze the relationship between the typical disturbance event features and event causes.This relationship is meaningful for analyzing power quality events causes in the future.
引文
[1] 陈晓静,李开成,肖剑,等.一种实时电能质量扰动分类方法[J].电工技术学报,2017,32(3):45-55.
[2] 董海艳,贾清泉,崔志强,等.复杂电能质量扰动事件源定位方法[J].电工技术学报,2016,31(23):116-124.
[3] 何巨龙,王根平,刘丹,等.基于提升小波和改进BP神经网络的配电网系统电能质量扰动定位与识别[J].电力系统保护与控制,2017,45(10):69-76.
[4] YUAN R F,AI Q,HE X.Research on dynamic load modelling based on power quality monitoring system[J].IET Generation Transmission & Distribution,2013,7(1):46-51.
[5] 李玲玲,刘敬杰,凌跃胜,等.物元理论和证据理论相结合的电能质量综合评估[J].电工技术学报,2015,30(12):383-391.
[6] 曾君,徐冬冬,郭华芳,等.面向可再生能源的微电网电能质量特点分析与综合评价方法研究[J].电力系统保护与控制,2016,44(19):10-16.
[7] 董海艳,贾清泉,王宁,等.复杂电能质量关联扰动模式的可拓挖掘方法[J].中国电机工程学报,2016,36(5):1269-1278.
[8] 范译文,刘俊勇,刘友波,等.计及全路径关联概率的连锁故障风险评估模型[J].电力系统及其自动化学报,2016,28(5):15-22.
[9] 徐文远,雍静.电力扰动数据分析学:电能质量监测数据的新应用[J].中国电机工程学报,2013,33(19):93-101.
[10] HUANG Y H,ZHOU X X.Knowledge model for electric power big data based on ontology and semantic web[J].CSEE Journal of Power and Energy Systems,2015,1(1):19-27.
[11] 赵晨雪,陶顺,肖湘宁.基于电能质量检测系统电压暂降信息的故障定位估计方法[J].电网技术,2016,40(2):642-648.
[12] 徐彪,尹项根,张哲,等.基于拓扑图元信息融合的电网故障诊断模型[J].电工技术学报,2018,33(3):512-522.
[13] 杨健维,何正友,臧天磊.基于方向性加权模糊Petri网的电网故障诊断方法[J].中国电机工程学报,2010,30(34):42-49.
[14] MIN S,SOHN J,PARK J,et al.Adaptive fault section estimation using matrix representation with fuzzy relations[J].IEEE Transactions on Power Systems,2004,19(2):842-848.
[15] 林霞,李瑶,李强,等.基于多Agent的分层扩展电网故障信息融合处理系统[J].电力系统保护与控制,2016,44(21):129-137.
[16] CHEN W H.Online fault diagnosis for power transmission networks using fuzzy digraph models[J].IEEE Transactions on Power Delivery,2012,27(2):688-698.
[17] 宋杰,谢海宁,杨增辉,等.基于多源异构数据挖掘的配电网故障信息统计分析[J].电力系统保护与控制,2016,44(3):141-147.
[18] 樊峰峰,李战怀,陈群,等.一种基于离群点检测的自动实体匹配方法[J].计算机学报,2017,40(10):2197-2211.
[19] 莫文雄,许中,肖斐,等.基于随机矩阵理论的电力扰动事件时空关联[J].高电压技术,2017,43(7):2386-2393.
[20] HERNANDEZ M A,STOLFO S J.The merge/purge problem for large databases[J].ACM SIGMOD Record,1995,11(6):127-138.
[21] 徐永海,兰巧倩,孔祥雨,等.电压暂降特征值统计分析及暂降传播特性[J].电工技术学报,2016,31(11):165-175.
[22] 谢龙君,李黎,程勇,等.融合集对分析和关联规则的变压器故障诊断方法[J].中国电机工程学报,2015,35(2):277-286.
[23] 李智勇,陈志刚,徐政,等.中国全社会用电量增长主导因素辨识[J].电力系统自动化,2010,34(23):30-35.
[2] 董海艳,贾清泉,崔志强,等.复杂电能质量扰动事件源定位方法[J].电工技术学报,2016,31(23):116-124.
[3] 何巨龙,王根平,刘丹,等.基于提升小波和改进BP神经网络的配电网系统电能质量扰动定位与识别[J].电力系统保护与控制,2017,45(10):69-76.
[4] YUAN R F,AI Q,HE X.Research on dynamic load modelling based on power quality monitoring system[J].IET Generation Transmission & Distribution,2013,7(1):46-51.
[5] 李玲玲,刘敬杰,凌跃胜,等.物元理论和证据理论相结合的电能质量综合评估[J].电工技术学报,2015,30(12):383-391.
[6] 曾君,徐冬冬,郭华芳,等.面向可再生能源的微电网电能质量特点分析与综合评价方法研究[J].电力系统保护与控制,2016,44(19):10-16.
[7] 董海艳,贾清泉,王宁,等.复杂电能质量关联扰动模式的可拓挖掘方法[J].中国电机工程学报,2016,36(5):1269-1278.
[8] 范译文,刘俊勇,刘友波,等.计及全路径关联概率的连锁故障风险评估模型[J].电力系统及其自动化学报,2016,28(5):15-22.
[9] 徐文远,雍静.电力扰动数据分析学:电能质量监测数据的新应用[J].中国电机工程学报,2013,33(19):93-101.
[10] HUANG Y H,ZHOU X X.Knowledge model for electric power big data based on ontology and semantic web[J].CSEE Journal of Power and Energy Systems,2015,1(1):19-27.
[11] 赵晨雪,陶顺,肖湘宁.基于电能质量检测系统电压暂降信息的故障定位估计方法[J].电网技术,2016,40(2):642-648.
[12] 徐彪,尹项根,张哲,等.基于拓扑图元信息融合的电网故障诊断模型[J].电工技术学报,2018,33(3):512-522.
[13] 杨健维,何正友,臧天磊.基于方向性加权模糊Petri网的电网故障诊断方法[J].中国电机工程学报,2010,30(34):42-49.
[14] MIN S,SOHN J,PARK J,et al.Adaptive fault section estimation using matrix representation with fuzzy relations[J].IEEE Transactions on Power Systems,2004,19(2):842-848.
[15] 林霞,李瑶,李强,等.基于多Agent的分层扩展电网故障信息融合处理系统[J].电力系统保护与控制,2016,44(21):129-137.
[16] CHEN W H.Online fault diagnosis for power transmission networks using fuzzy digraph models[J].IEEE Transactions on Power Delivery,2012,27(2):688-698.
[17] 宋杰,谢海宁,杨增辉,等.基于多源异构数据挖掘的配电网故障信息统计分析[J].电力系统保护与控制,2016,44(3):141-147.
[18] 樊峰峰,李战怀,陈群,等.一种基于离群点检测的自动实体匹配方法[J].计算机学报,2017,40(10):2197-2211.
[19] 莫文雄,许中,肖斐,等.基于随机矩阵理论的电力扰动事件时空关联[J].高电压技术,2017,43(7):2386-2393.
[20] HERNANDEZ M A,STOLFO S J.The merge/purge problem for large databases[J].ACM SIGMOD Record,1995,11(6):127-138.
[21] 徐永海,兰巧倩,孔祥雨,等.电压暂降特征值统计分析及暂降传播特性[J].电工技术学报,2016,31(11):165-175.
[22] 谢龙君,李黎,程勇,等.融合集对分析和关联规则的变压器故障诊断方法[J].中国电机工程学报,2015,35(2):277-286.
[23] 李智勇,陈志刚,徐政,等.中国全社会用电量增长主导因素辨识[J].电力系统自动化,2010,34(23):30-35.