朱亮,支妍力,梅贱生,余萌,胡琛,徐超群
ZHU Liang,ZHI Yanli,MEI Jiansheng,YU Meng,HU Chen,XU Chaoqun

• 1:国网江西省电力有限公司供电服务管理中心
• 2:国网江西省电力有限公司
• 3:国网江西省电力有限公司抚州供电分公司
• 4:东南大学

摘要(Abstract)：

非介入式负荷辨识对于支撑负荷预测、需求响应等应用的开展具有重要意义。针对产线型工业负荷用户子设备独立分解困难的问题，依托产线内设备联动运行的特点，提出了以产线为分解单位的非介入式负荷辨识方案。基于GMM（高斯混合模型）的因子化隐马尔可夫算法，实现了产线级负荷的细粒度呈现。同时，依据工业产线负荷总体规律稳定的特点，提出状态转移概率时间分段的分解模型构建方法，进一步了提升负荷辨识精度。实验结果表明，文中所提模型分别在多状态建模和时间分段阶段取得了性能提升，部分产线上的负荷辨识误差指标最终达到了近20%的下降。
Non-intrusive load monitoring plays a significant role in supporting applications such as load forecasting and demand response. To address the challenge of independently decomposing sub-equipment in industrial load users with production lines, a non-intrusive load monitoring(NILM) scheme is proposed, using the production line as the decomposition unit, based on the interlinked operation of equipment within the line. A factorized hidden Markov model(FHMM), based on Gaussian mixture model(GMM), is employed to achieve a fine-grained representation of load at the production line level. Additionally, a time-segmented state transition probability decomposition model is developed, leveraging the stable overall load patterns of industrial production lines, to further enhance load monitoring accuracy. Experimental results demonstrate that the proposed model significantly improves performance in both multi-state modeling and time segmentation, with load monitoring error metrics on some production lines ultimately reduced by nearly 20%.

关键词(KeyWords)： 非介入式负荷辨识;工业产线;因子化隐马尔可夫模型;高斯混合模型;状态转移概率
non-intrusive load monitoring;industrial production line;FHMM;GMM;state transition probability

Abstract:

Keywords:

基金项目(Foundation): 国家电网有限公司科技项目（521852230006）

作者(Author): 朱亮,支妍力,梅贱生,余萌,胡琛,徐超群
ZHU Liang,ZHI Yanli,MEI Jiansheng,YU Meng,HU Chen,XU Chaoqun

DOI: 10.19585/j.zjdl.202412007

参考文献(References)：

• [1]王守相，孙智卿，孔繁钢，等.面向需求响应的建筑用能在线分解方法[J].电力自动化设备，2017,37(3):1-6.WANG Shouxiang,SUN Zhiqing,KONG Fangang,et al.Online building energy disaggregation orienting to demand response[J].Electric Power Automation Equipment,2017,37(3):1-6.
• [2]张路，陈军，南东亮，等.计及冶金负荷参与安全辅助服务的电网紧急负荷控制策略[J].电工电能新技术，2023,42(12):77-87.ZHANG Lu,CHEN Jun,NAN Dongliang,et al. Emergency load control strategy of power grid considering metallurgical load participation in safety auxiliary service[J].Advanced Technology of Electrical Engineering and Energy,2023,42(12):77-87.
• [3]宋玮琼，王立永，宋威，等.基于设备运行状态检测与能量回归同步评估的居民非介入式负荷辨识算法研究[J].电测与仪表，2023,60(12):182-188.SONG Weiqiong,WANG Liyong,SONG Wei,et al.Research on residential non-intrusive load identification algorithm based on equipment operation state detection and energy regression synchronous evaluation[J].Electrical Measurement&Instrumentation,2023,60(12):182-188.
• [4] SCHIRMER P A,MPORAS I.Non-intrusive load monitoring:a review[J]. IEEE Transactions on Smart Grid,2023,14(1):769-784.
• [5]林顺富，詹银枫，李毅，等.基于CNN-BiLSTM与DTW的非侵入式住宅负荷监测方法[J].电网技术，2022,46(5):1973-1981.LIN Shunfu,ZHAN Yinfeng,LI Yi,et al. Non-intrusive residential load monitoring method based on CNNBiLSTM and DTW[J].Power System Technology,2022,46(5):1973-1981.
• [6] MARI S,BUCCI G,CIANCETTA F,et al.An embedded deep learning NILM system:a year-long field study in real houses[J].IEEE Transactions on Instrumentation and Measurement,2023,72:1-15.
• [7]封钰，宋佑斌，金晟，等.基于随机森林算法和粗糙集理论的改进型深度学习短期负荷预测模型[J].发电技术，2023,44(6):889-895.FENG Yu,SONG Youbin,JIN Sheng,et al. Improved deep learning model for forecasting short-term load based on random forest algorithm and rough set theory[J].Power Generation Technology,2023,44(6):889-895.
• [8] LI D D,LI J F,ZENG X,et al.Transfer learning for multiobjective non-intrusive load monitoring in smart building[J].Applied Energy,2023,329:120223.
• [9] ZAOUALI K,AMMARI M L,BOUALLEGUE R.LSTM-based reinforcement Q learning model for Non intrusive load monitoring[M]//Lecture Notes in Networks and Systems. Cham:Springer International Publishing,2022:1-13.
• [10]赵志刚，冯忠义，王咏欣，等.基于小波随机森林的非侵入式工业负荷识别及其鲁棒性研究[J].水利水电技术，2022,53（增刊2）:265-270.ZHAO Zhigang,FENG Zhongyi,WANG Yongxin,et al.Non-intrusive industrial load identification and robustness research based on wavelet transform random forests[J].Water Resources and Hydropower Engineering,2022,53(S2):265-270.
• [11]段晶，李勇，张振宇，等.考虑辨识结果连续性的Type-Ⅲ型工商业负荷辨识方法[J].电力系统自动化，2021,45(24):65-72.DUAN Jing,LI Yong,ZHANG Zhenyu,et al.Identification method for type-Ⅲindustrial and commercial load considering identification result continuity[J].Automation of Electric Power Systems,2021,45(24):65-72.
• [12]余昊杨，武昕，郭一凡，等.基于事件感知的钢厂工业用户非侵入式负荷检测分解算法[J].南方电网技术，2022,16(11):29-36.YU Haoyang,WU Xin,GUO Yifan,et al. Non-intrusive load detection decomposition algorithm for industrial users of steel mill based on event perception[J].Southern Power System Technology,2022,16(11):29-36.
• [13]武昕，于金莹，彭林，等.基于用户边缘侧事件解析的工业电力负荷非侵入式感知辨识[J].电力系统自动化，2021,45(4):29-37.WU Xin,YU Jinying,PENG Lin,et al.Non-intrusive perception and identification of industrial power load based on analysis of event on user edge[J].Automation of Electric Power Systems,2021,45(4):29-37.
• [14]易姝慧，郭俊岑，刁新平，等.基于LSQR与系统距离聚类算法的专变用户非介入式负荷辨识[J].电测与仪表，2022,59(6):60-68.YI Shuhui,GUO Juncen,DIAO Xinping,et al. Nonintrusive load identification for special transformer users based on LSQR and system distance clustering algorithm[J].Electrical Measurement&Instrumentation,2022,59(6):60-68.
• [15] MAKONIN S,POPOWICH F,BAJIC I V,et al.Exploiting HMM sparsity to perform online real-time nonintrusive load monitoring[J]. IEEE Transactions on Smart Grid,2016,7(6):2575-2585.
• [16]杨东升，孔亮，胡博，等.基于多特征序列融合的负荷辨识方法[J].电力系统自动化，2017,41(22):66-73.YANG Dongsheng,KONG Liang,HU Bo,et al. Load identification method based on multi-feature sequence fusion[J].Automation of Electric Power Systems,2017,41(22):66-73.
• [17]苏晓，余涛，徐伟枫，等.基于隐马尔可夫模型的非侵入式负荷监测泛化性能改进[J].控制理论与应用，2022,39(4):691-700.SU Xiao,YU Tao,XU Weifeng,et al.Generalization performance improvement of non-intrusive load monitoring based on hidden Markov model[J].Control Theory&Applications,2022,39(4):691-700.
• [18] KUMAR P,ABHYANKAR A R.A time efficient factorial hidden Markov model-based approach for nonintrusive load monitoring[J].IEEE Transactions on Smart Grid,2023,14(5):3627-3639.
• [19]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 algorithms[J].Power System Technology,2022,46(11):4568-4579.
• [20] ANGELIS G F,TIMPLALEXIS C,KRINIDIS S,et al.NILM applications:Literature review of learning approaches, recent developments and challenges[J].Energy and Buildings,2022,261:111951.