杨玉锐,程杰,周刚,徐诒玥,吴伟健,吴佳
YANG Yurui,CHENG Jie,ZHOU Gang,XU Yiyue,WU Weiqun,WUJia

• 1:国网浙江平湖市供电公司

摘要(Abstract)：

为解决异常用电检测问题,提出一种基于果蝇算法的负荷模式分析新方法。在同区域相似电力用户负荷数据和用户历史负荷数据的基础上,应用果蝇算法提取负荷模式。根据用户用电负荷与相似用户用电负荷和用户历史用电负荷匹配的不同特点,采用不同的负荷数据预处理方式以及模式匹配评价方法。根据电力用户的实际数据,查出用户的异常用电情况,验证了算法的有效性。
In order to detect abnormal electricity utilization, this paper presents a new load model analysis method based on fruit fly algorithm. On the basis of load data and historic load data of the similar electricity users in the same area, fruit fly algorithm is adopted to extract load mode. According to different characteristics of the matching between load of electricity users or similar users and historic electricity load, different pre-process method of load data and evaluation method of mode matching. In line with the real data of electricity users, the abnormal electricity utilization of electricity users can be found out, effectiveness of the algorithm is verified through calculation.

关键词(KeyWords)： 用电检测;负荷模式;果蝇算法
electricity utilization detection;load mode;fruit fly algorithm

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 杨玉锐,程杰,周刚,徐诒玥,吴伟健,吴佳
YANG Yurui,CHENG Jie,ZHOU Gang,XU Yiyue,WU Weiqun,WUJia

DOI: 10.19585/j.zjdl.2014.09.004

参考文献(References)：

• [1]NIZAR A,DONG Z."Identification and detection of electricity customer behaviour irregularities[C].2009 IEEE PES Power Systems Conf Expo:1-10.
• [2]NIZAR A H,DONG Z Y,JALALUDDIN M,et al.Load profiling method in detecting non-technical loss activities in a power utility[C].2006 IEEE 1st Int Power and Energy Conf:82-87.
• [3]CABRAL J E,PINTO J O P,GONTIJO E M,et al.Fraud detection in electrical energy consumers using rough sets[C].2004 IEEE Int Conf.Systems,Man and Cybernetics:3625-3629.
• [4]NIZAR A H,DONG Z Y,ZHAO J H,et al.A data mining based NTL analysis method[C].2007 IEEE Power Eng Soc General Meeting:1-8.
• [5]MONEDERO I,BISCARRI F,BISCARRI J,et al.Detection of non-technical losses in electrical consumption using neural networks and statistical techniques[C].In Proceedings of the international conference on computational science and applications:3984.
• [6]NIZAR A H,DONG Z Y,JALALUDDIN M,et al.Load profiling method in detecting non-technical loss activities in a power utility[C].2006 IEEE 1st Int Power and Energy Conf:82-87.
• [7]NAGI J,MOHAMMAD A M,YAP K S,et al.Non-technical loss analysis for detection of electricity theft using support vector machines[C].2008 of the 2nd IEEE international power and energy conf:907-12.
• [8]RAMOS C C,SOUZA A N,PAPA J P,et al.A new approach for nontechnical losses detection based on opti mum-path forest[J].IEEE Trans Power Syst,2011(26):181.
• [9]NIZAR A H,DONG Z Y,WANG Y.Power utility nontechnical loss analysis with extreme learning machine method[J].IEEE Transactions on Power Systems,2008,23(3):946-55.
• [10]NAGI J,YAP K S,TIONG S K,et al.Improving SVMbased nontechnical loss detection in power utility using the fuzzy inference system[J].IEEE Transactions on power delivery,2011,26(2):1284-1285.
• [11]RAMOS C C,SOUZA A N,CHIACHIA G,et al.A novel algorithm for feature selection using Harmony Search and its application for non-technical losses detection[J].Computers and Electrical Engineering,2011(37):886-894.
• [12]PEREIRA L A M,AFONSO L C S,PAPA J P,et al.Mul tilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection[C].2013 IEEE Innovative Smart Grid Technologies Latin America(ISGT LA):1-6.
• [13]PAN W T.A new fruit fly optimization algorithm:taking the financial distress model as an example[J].KnowledgeBased Systems,2012,26(2):69-74.
• [14]ALLERA S V,HORSBURGH A G.Load profiling for the energy trading settlements in the UK electricity markets[C].in Presentation Report From Distribu-TECH Europe DA/DSM Conf,1998:27-29.
• [15]CHEN C S,KANG M S,WANG J C,et al.Implementation of the load survey system in Taipower[C].1999 IEEE Transmission and Distribution Conf.
• [16]NIZAR A H,DONG Z Y,ZHAO J H.Load profiling and data mining techniques in electricity deregulated market[C].2006 IEEE Power Engineering Society General Meeting:1-7.