基于KL变换和KL散度的电网数据特征提取与分类
|
摘要
智能电网用户行为特征的分析在电力营销策略中扮演者重要的角色。文中结合KL变换和KL散度的方法,提取与分类用电数据信息的特征,实现不同类型的用电数据划分。同时通过综合分析所有用户的日负荷曲线,提取不同类型用户的典型日负荷曲线。研究结果表明:基于KL变换的方法,通过对原始数据的压缩和主要特征的保留,大大降低了智能电网数据提取与分类的计算量,提高了时间效率;基于KL散度的方法,通过对k-means算法中的k值和初始聚类中心的选择进行优化,提高了聚类效果的准确率;实例中电网用户正常数据为38组,可分为3类典型用户,迎峰用电型、错峰用电型、部分迎峰用电型。该研究结果可以更加有效地对电网用户用电行为进行分类,从而为售电公司进行业务拓展提供技术基础。
The analysis of behavior feature in smart grid users plays an important role in power marketing strategy. Based on KL-divergence and KL transform,this paper completed feature extraction and classification in smart grid data,which achieved grid data division of different types. Moreover,based on the overall analysis of the daily load profile in all users,it is extracted that the typical daily load profile in different types of users. The research results prove that it is greatly reduced that calculation of extraction and classification in smart grid users by means of KL transform,it increases the time efficiency by the compression of raw data and the retention of main feature,it is optimized that the selection of initial clustering center and cluster number by means of KL-divergence,so the accuracy of clustering is improved; the normal data of grid users in this instance is 38 groups,the users are divided into 3 categories of peak electricity type,peak avoidance electricity type and part meeting peak electricity type. The results can be used to classify behavior feature of smart grid users more effectively,it will provide a technical basis for business expansion of electric power company.
The analysis of behavior feature in smart grid users plays an important role in power marketing strategy. Based on KL-divergence and KL transform,this paper completed feature extraction and classification in smart grid data,which achieved grid data division of different types. Moreover,based on the overall analysis of the daily load profile in all users,it is extracted that the typical daily load profile in different types of users. The research results prove that it is greatly reduced that calculation of extraction and classification in smart grid users by means of KL transform,it increases the time efficiency by the compression of raw data and the retention of main feature,it is optimized that the selection of initial clustering center and cluster number by means of KL-divergence,so the accuracy of clustering is improved; the normal data of grid users in this instance is 38 groups,the users are divided into 3 categories of peak electricity type,peak avoidance electricity type and part meeting peak electricity type. The results can be used to classify behavior feature of smart grid users more effectively,it will provide a technical basis for business expansion of electric power company.
引文
[1]林弘宇,田世明.智能电网条件下的智能小区关键技术[J].电网技术,2011,35(12):1-7.LinHongyu,Tian Shiming.Research on key technologies for smart residential community[J].Power System Technology,2011,35(12):1-7.
[2]周海明,刘广一,刘超群.能源互联网技术框架研究[J].中国电力,2014,47(11):140-144.
[3]何永秀,王冰,熊威,等.基于模糊综合评价的居民智能用电行为分析与互动机制设计[J].电网技术,2012,36(10):247-252.He Yongxiu,Wang Bing,Xiong Wei,et al.Analysis of residents’smart electricity consumption behavior based on fuzzy synthetic evaluation and the design of interactive mechanism[J].Power System Technology,2012,36(10):247-252.
[4]黄梅,贺仁睦,杨少兵,等.东北电网负荷模型的分类与应用[J].电力系统自动化,2005,29(4):85-87.Huang Mei,He Renmu,Yang Shaobing,et al.Application of load model classification in northeast power network[J].Automation of Electric Power System,2005,29(4):85-87.
[5]和敬涵,卢育梓,陆金耀,等.基于“进化”主成分分析法的用户分类及其应用[J].电力建设,2017,38(3):101-105.He Jinghan,Lu Yuzi,Lu Jinyao,et al.User Classification Method Based on‘Evolution’PCA and Its Application[J].Electric Power Construction,2017,38(3):101-105.
[6]杨丽君,李健强,李学平,闫鹏达.考虑需求响应的含风电电力系统日前经济调度[J].电工电能新技术,2015,34(11):29-36.
[7]李欣然,姜学皎,钱军,等.基于用户日负荷曲线的用电行业分类与综合方法[J].电力系统自动化,2010,34(10):56-60.Li Xinran,Jiang Xuejiao,Qian Jun,et al.A Classifying and Synthesizing Method of Power Consumer Industry Based on the Daily Load Profile[J].Automation of Electric Power System,2010,34(10):56-60.
[8]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.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.
[9]刘丽轻.电力用户负荷模式识别系统研究与设计[D].保定:华北电力大学,2012.Liu Liqing.Research and design on recognition system of electricity customer load pattern[D].Baoding:North China Electric Power University,2012.
[10]Zeng Feng,Zhang Xiaoning.Application of cluster analysis to preventive maintenance scheme design of pavement[J].Journal of Harbin Institute of Technology,2009,16(4):581-586.
[11]郑晓雨,马进,贺仁睦,等.基于模型激励响应的负荷分类与泛化能力[J].电工技术学报,2009,24(2):132-138.Zheng Xiaoyu,Ma Jin,He Renmu,et al.Classification and generalization of the load model based on model dynamic responses[J].Transactions of China Elect rotechni cal Society,2009,24(2):132-138.
[12]Kalogridis G,Denic S Z.Data mining and privacy of personal behaviour types in smart grid[A].IEEE International Conference on Data Mining Workshops(ICDMW)[C].2011:636-642.
[13]江辉,张清联,彭建春.基于改进云物元模型的风电场电能质量评价[J].电网技术,2014,38(1):205-210.Jiang Hui,Zhang Qinglian,Peng Jianchun.An improved cloud matter element model based wind farm power quality evaluation[J].Power System Technology,2014,38(1):205-210.
[14]蒋正阳.基于电量预测及客户行为分析的电网系统的设计与实现[D].广州:中山大学,2013.
[15]殷桂梁,伍麒伊.基于UKF和IGG改进聚类算法的特高压交流输电线路参数辨识[J].电工电能新技术,2017,36(6):69-75.
[16]杨海学,张继业,张晗.基于改进Sage-Husa的自适应无迹卡尔曼滤波的锂离子电池SOC估计[J].电工电能新技术,2016,35(1):30-35.
[17]张素香,刘建明,赵丙镇,等.基于云计算的居民用电行为分析模型研究[J].电网技术,2013,37(6):1542-1546.Zhang Suxiang,Liu Jianming,Zhao Bingzhen,et al.Cloud computingbased analysis on residential electricity consumption behavior[J].Power System Technology,2013,37(6):1542-1546.
[18]程艳柳.基于云计算的智能电网数据挖掘的研究[D].保定:华北电力大学,2013.
[19]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.
[20]张宜浩,金澎,孙锐,等.基于改进k-means算法的中文词义归纳[J].计算机应用,2012,32(5):1332-1334.Zhang Yihao,Jin Peng,Sun Rui,et al.Chinese word sense induction based on improved k-means algorithm[J].Journal of Computer Applications,2012,32(5):1332-1334.
[21]Rajaraman A,Ullman J D.大数据:互联网大规模数据挖掘与分布式处理[M].北京:人民邮电出版社,2012.
[22]Jackson J E.A user's guide to principal components.1991[J].John Willey&Sons,New York.
[2]周海明,刘广一,刘超群.能源互联网技术框架研究[J].中国电力,2014,47(11):140-144.
[3]何永秀,王冰,熊威,等.基于模糊综合评价的居民智能用电行为分析与互动机制设计[J].电网技术,2012,36(10):247-252.He Yongxiu,Wang Bing,Xiong Wei,et al.Analysis of residents’smart electricity consumption behavior based on fuzzy synthetic evaluation and the design of interactive mechanism[J].Power System Technology,2012,36(10):247-252.
[4]黄梅,贺仁睦,杨少兵,等.东北电网负荷模型的分类与应用[J].电力系统自动化,2005,29(4):85-87.Huang Mei,He Renmu,Yang Shaobing,et al.Application of load model classification in northeast power network[J].Automation of Electric Power System,2005,29(4):85-87.
[5]和敬涵,卢育梓,陆金耀,等.基于“进化”主成分分析法的用户分类及其应用[J].电力建设,2017,38(3):101-105.He Jinghan,Lu Yuzi,Lu Jinyao,et al.User Classification Method Based on‘Evolution’PCA and Its Application[J].Electric Power Construction,2017,38(3):101-105.
[6]杨丽君,李健强,李学平,闫鹏达.考虑需求响应的含风电电力系统日前经济调度[J].电工电能新技术,2015,34(11):29-36.
[7]李欣然,姜学皎,钱军,等.基于用户日负荷曲线的用电行业分类与综合方法[J].电力系统自动化,2010,34(10):56-60.Li Xinran,Jiang Xuejiao,Qian Jun,et al.A Classifying and Synthesizing Method of Power Consumer Industry Based on the Daily Load Profile[J].Automation of Electric Power System,2010,34(10):56-60.
[8]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.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.
[9]刘丽轻.电力用户负荷模式识别系统研究与设计[D].保定:华北电力大学,2012.Liu Liqing.Research and design on recognition system of electricity customer load pattern[D].Baoding:North China Electric Power University,2012.
[10]Zeng Feng,Zhang Xiaoning.Application of cluster analysis to preventive maintenance scheme design of pavement[J].Journal of Harbin Institute of Technology,2009,16(4):581-586.
[11]郑晓雨,马进,贺仁睦,等.基于模型激励响应的负荷分类与泛化能力[J].电工技术学报,2009,24(2):132-138.Zheng Xiaoyu,Ma Jin,He Renmu,et al.Classification and generalization of the load model based on model dynamic responses[J].Transactions of China Elect rotechni cal Society,2009,24(2):132-138.
[12]Kalogridis G,Denic S Z.Data mining and privacy of personal behaviour types in smart grid[A].IEEE International Conference on Data Mining Workshops(ICDMW)[C].2011:636-642.
[13]江辉,张清联,彭建春.基于改进云物元模型的风电场电能质量评价[J].电网技术,2014,38(1):205-210.Jiang Hui,Zhang Qinglian,Peng Jianchun.An improved cloud matter element model based wind farm power quality evaluation[J].Power System Technology,2014,38(1):205-210.
[14]蒋正阳.基于电量预测及客户行为分析的电网系统的设计与实现[D].广州:中山大学,2013.
[15]殷桂梁,伍麒伊.基于UKF和IGG改进聚类算法的特高压交流输电线路参数辨识[J].电工电能新技术,2017,36(6):69-75.
[16]杨海学,张继业,张晗.基于改进Sage-Husa的自适应无迹卡尔曼滤波的锂离子电池SOC估计[J].电工电能新技术,2016,35(1):30-35.
[17]张素香,刘建明,赵丙镇,等.基于云计算的居民用电行为分析模型研究[J].电网技术,2013,37(6):1542-1546.Zhang Suxiang,Liu Jianming,Zhao Bingzhen,et al.Cloud computingbased analysis on residential electricity consumption behavior[J].Power System Technology,2013,37(6):1542-1546.
[18]程艳柳.基于云计算的智能电网数据挖掘的研究[D].保定:华北电力大学,2013.
[19]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.
[20]张宜浩,金澎,孙锐,等.基于改进k-means算法的中文词义归纳[J].计算机应用,2012,32(5):1332-1334.Zhang Yihao,Jin Peng,Sun Rui,et al.Chinese word sense induction based on improved k-means algorithm[J].Journal of Computer Applications,2012,32(5):1332-1334.
[21]Rajaraman A,Ullman J D.大数据:互联网大规模数据挖掘与分布式处理[M].北京:人民邮电出版社,2012.
[22]Jackson J E.A user's guide to principal components.1991[J].John Willey&Sons,New York.