赵学明,王宏伟,吴宇彤,张军,史成豪,米东风
ZHAO Xueming,WANG Hongwei,WU Yutong,ZHANG Jun,SHI Chenghao,MI Dongfeng

• 1:国网天津市电力公司
• 2:天津大学电气自动化与信息工程学院

摘要(Abstract)：

准确检测事件的完整暂态过程可提升NILM（非侵入式负荷监测）的最终效果，然而现有的事件检测方法难以在多场景下维持其优良性能。为此，提出基于时域分析特征的非侵入式负荷事件检测方法。首先，对各功率采样点计算自适应阈值，并据此初步定位事件位置；随后，多次移动稳态搜索滑窗，定位事件前后的稳态时段以确定事件所处的时段，并通过变点检测确定事件的启止时间；然后，设计了后处理步骤，根据波形特征识别并移除波动事件；最后，在私有和公开的BLUED数据集上，将所提方法同其他3种检测方法进行对比实验，实验结果验证了所提方法的有效性。
Accurately detecting the complete transient process of an event can improve the performance of nonintrusive load monitoring(NILM). However, existing event detection methods struggle to maintain high performance across multiple scenarios. To address this issue, a non-intrusive load event detection method based on timedomain analysis features is proposed. First, adaptive thresholds are calculated for each power sampling point, which are then used to preliminarily locate event positions. Next, a sliding window search method is employed to repeatedly move through steady-state periods before and after the event, determining the time span of the event. The start and end times of the event are identified through change point detection(CPD). Subsequently, a post-processing step is designed to recognize and remove fluctuation events based on waveform characteristics. Finally, comparative experiments with three other detection methods are conducted using both private and publicly available BLUED datasets. The experimental results validate the effectiveness of the proposed method.

关键词(KeyWords)： 有功功率;非侵入式负荷监测;负荷事件检测;状态检测
active power;NILM;load event detection;state detection

Abstract:

Keywords:

基金项目(Foundation): 国网天津市电力公司科技项目（城东-研发2023-03）

作者(Author): 赵学明,王宏伟,吴宇彤,张军,史成豪,米东风
ZHAO Xueming,WANG Hongwei,WU Yutong,ZHANG Jun,SHI Chenghao,MI Dongfeng

DOI: 10.19585/j.zjdl.202503007

参考文献(References)：

• [1]余贻鑫.面向21世纪的智能电网[J].天津大学学报（自然科学与工程技术版），2020,53(6):551-556.YU Yixin.A brief description of the basics of the smart grid[J]. Journal of Tianjin University(Science and Technology),2020,53(6):551-556.
• [2]刘至纯，李华强，王俊翔，等.基于多时间尺度综合需求响应策略的综合能源系统优化运行[J].电力建设，2022,43(9):54-65.LIU Zhichun,LI Huaqiang,WANG Junxiang,et al.Optimal operation of integrated energy system based on multitime scale integrated demand response strategy[J]. Electric Power Construction,2022,43(9):54-65.
• [3]骆钊，刘德文，沈鑫，等.综合能源系统优化运行技术研究综述[J].电力建设，2022,43(12):3-14.LUO Zhao,LIU Dewen,SHEN Xin,et al.Review of research on optimal operation technology of integrated energy system[J]. Electric Power Construction,2022,43(12):3-14.
• [4] WU K L,GU J,MENG L,et al. An explainable framework for load forecasting of a regional integrated energy system based on coupled features and multi-task learning[J]. Protection and Control of Modern Power Systems,2022,7(1):24.
• [5]刘文杰，刘禾，王英男，等.基于完整自适应噪声集成经验模态分解的LSTM-Attention网络短期电力负荷预测方法[J].电力建设，2022,43(2):98-108.LIU Wenjie,LIU He,WANG Yingnan,et al.Short-term power load forecasting method based on CEEMDAN and LSTM-attention network[J]. Electric Power Construction,2022,43(2):98-108.
• [6] VINE D,BUYS L,MORRIS P.The effectiveness of energy feedback for conservation and peak demand:a literature review[J].Open Journal of Energy Efficiency,2013,2(1):7-15.
• [7] YI Z X,CHEN Z L,YIN K,et al.Sensing as the key to the safety and sustainability of new energy storage devices[J]. Protection and Control of Modern Power Systems,2023,8(1):27.
• [8] HOU J J,SONG G B,FAN Y F. Fault identification scheme for protection and adaptive reclosing in a hybrid multi-terminal HVDC system[J]. Protection and Control of Modern Power Systems,2023,8(2):1-17.
• [9]栾文鹏.高级量测体系[J].南方电网技术，2009,3(2):6-10.LUAN Wenpeng. Advanced metering infrastructure[J].Southern Power System Technology,2009,3(2):6-10.
• [10] HART G W.Nonintrusive appliance load monitoring[J].Proceedings of the IEEE,1992,80(12):1870-1891.
• [11]程祥，李林芝，吴浩，等.非侵入式负荷监测与分解研究综述[J].电网技术，2016,40(10):3108-3117.CHENG Xiang,LI Linzhi,WU Hao,et al.A survey of the research on non-intrusive load monitoring and disaggregation[J].Power System Technology,2016,40(10):3108-3117.
• [12] ZEIFMAN M,ROTH K. Nonintrusive appliance load monitoring:Review and outlook[J]. IEEE Transactions on Consumer Electronics,2011,57(1):76-84.
• [13] LIU B,ZHANG J F,LUAN W P,et al.Adaptive multitimescale event detection in nonintrusive load monitoring based on minimum description length principle[J]. IEEE Transactions on Instrumentation and Measurement,2024,73:2502514.
• [14]凌家源，彭勇刚.基于事件检测与CNN模型的非侵入式负荷识别方法及实现[J].电工电能新技术，2021,40(3):46-54.LING Jiayuan,PENG Yonggang. Implementation of a non-intrusive load identification method based on event detection and CNN model[J].Advanced Technology of Electrical Engineering and Energy,2021,40(3):46-54.
• [15] LUAN W P,LIU Z S,LIU B,et al. An adaptive twostage load event detection method for nonintrusive load monitoring[J].IEEE Transactions on Instrumentation and Measurement,2022,71:1-14
• [16] AZZINI H A D,TORQUATO R,DA SILVA L C P.Event detection methods for nonintrusive load monitoring[C]//2014 IEEE PES General Meeting|Conference&Exposition,July 27-31,2014,National Harbor,MD,USA.IEEE,2014:1-5.
• [17] GREEN D H,SHAW S R,LINDAHL P,et al.A MultiScale framework for nonintrusive load identification[J].IEEE Transactions on Industrial Informatics,2020,16(2):992-1002.
• [18] LU M Q,LI Z Y.A hybrid event detection approach for non-intrusive load monitoring[J]. IEEE Transactions on Smart Grid,2020,11(1):528-540.
• [19] CHEN M M,FANG K J,HUANG Q F,et al.A triplethreshold-based load event detection algorithm for nonintrusive load monitoring[J]. Journal of Physics:Conference Series,2021,2065(1):012011.
• [20] REHMAN A U,LIE T T,VALLèS B,et al. Eventdetection algorithms for low sampling nonintrusive load monitoring systems based on low complexity statistical features[J]. IEEE Transactions on Instrumentation and Measurement,2020,69(3):751-759.
• [21] ANDERSON K D,BERGES M E,OCNEANU A,et al.Event detection for Non Intrusive load monitoring[C]//IECON 2012-38th Annual Conference on IEEE Industrial Electronics Society. October 25-28,2012. Montreal,QC,Canada.IEEE,2012:10:3312-3317.
• [22] DE BAETS L,RUYSSINCK J,DEVELDER C,et al.Optimized statistical test for event detection in nonintrusive load monitoring[C]//2017 IEEE International Conference on Environment and Electrical Engineering and 2017 IEEE Industrial and Commercial Power Systems Europe(EEEIC/I&CPS Europe). June 6-9,2017,Milan,Italy.IEEE,2017:1-5.
• [23] ZHENG Z,CHEN H N,LUO X W.A supervised eventbased non-intrusive load monitoring for non-linear appliances[J].Sustainability,2018,10(4):1001.
• [24] KOTSILITIS S,KALLIGEROS E,MARCOULAKI E C,et al.An efficient lightweight event detection algorithm for on-site non-intrusive load monitoring[J].IEEE Transactions on Instrumentation and Measurement,2023,72:9000313.
• [25] LAZZARETTI A E,RENAUX D P B,LIMA C R E,et al. A multi-agent NILM architecture for event detection and load classification[J].Energies,2020,13(17):4396.
• [26] TANYER S G,OZER H.Voice activity detection in nonstationary noise[J].IEEE Transactions on Speech and Audio Processing,2000,8(4):478-482.
• [27] PEREIRA L,NUNES N.An experimental comparison of performance metrics for event detection algorithms in NILM[C]//Proceedings of NILM 2018. New York:ACM,2018:1-4.
• [28]栾文鹏，韦尊，刘博，等.非侵入式负荷监测算法的测试与评价方法[J].电网技术，2022,46(11):4568-4579.LUAN Wenpeng,WEI Zun,LIU Bo,et al. Testing and performance evaluation of nonintrusive load monitoring algorithmsh[J].Power System Technology,2022,46(11):4568-4579.
• [29] ANDERSON K,OCNEANU A F,BENITEZ D,et al.BLUED:a fully labeled public dataset for event-based nonintrusive load monitoring research[J]. Proceedings of the2nd KDD Workshop on Data Mining Applications in Sustainability(SustKDD),2012(October 2011):1-5.