基于维特比算法改进的稳暂态混合非侵入式负荷识别方法

doi:10.19595/j.cnki.1000-6753.tces.220566

Abstract
Figure/Table
References (0)
Related Citation (5)

Download: PDF (535 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract

Non-intrusive load monitoring (NILM) is the most commonly used method to achieve load state identification, which is an important technology to realize power grid panoramic perception and support the carbon peaking and carbon neutrality goals. Depending on the detection object, NILM can be divided into two categories, i.e., steady-state signature based NILM and transient-state signature based NILM. Various studies have been conducted on both fields respectively, but the internal relationships between different states are rarely discussed. To explore the potential of associating the sequential states in load disaggregation problem, this paper thoroughly investigates the sequential logics between the load states in adjacent steady-state process and transient-state process, and makes use of them to improve the NILM performance.
Firstly, considering the switching states of appliances, steady-state signature based NILM is solved by discrete particle swarm optimization (DPSO) algorithm. Secondly, transient-state signature based NILM is addressed by dynamic time warping (DTW) approach, to deal with the complex event characteristics. Then, a probability evaluation system is applied for decision-making, where multiple identification results with high confidence are selected to construct the candidate sets of independent identification results. Lastly, the candidate sets of adjacent steady-state and transient-state are associated together, and Viterbi algorithm is utilized to establish the probabilistic sequential model and optimize the load identification results.
The proposed method is analyzed and validated on load consumption data from both Low Voltage Network Simulator (LVNS) and UK-DALE dataset. Four metrics, including F1 measure (F1), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Normalized Mean Square Error (NMSE), are utilized to evaluate the load disaggregation performance. The results show that the proposed method can effectively improve the overall load identification accuracy, especially for these appliances with high rated power. In the simulation-based case, the disaggregation performance for the incandescent light bulb rated at 40W is unsatisfactory by the proposed method, due to the similarity of the rated power and frequent fluctuating power values. However, such results for low-power appliances do not affect the overall performance, while the global NILM is greatly enhanced by integrating the different states together. In the measurement dataset-based case, all appliances, including the 85W fridge, are accurately identified by the proposed method, along with a significant improvement compared with independent steady-state signature based NILM. Besides, the disaggregation results for dishwasher, the appliance with complex operation states, are remarkably promoted by the proposed method, indicating the superiority and applicability of this study. Finally, two conventional NILM approaches, i.e., Combinatorial Optimization (CO) and Factor Hidden Markov Model (FHMM), are also tested and compared in the cases. Although CO and FHMM outperform DPSO under traditional framework, by integrating the proposed strategy, the DPSO based NILM is largely enhanced from all metrics, generating a better NILM solution.
The following conclusions can be drawn from the verification analysis: (1) By utilizing the sequential logics between adjacent load states, the load disaggregation performance could be largely enhanced compared with independent steady-state signature based NILM, as well as transient-state signature based NILM. Bedside, the proposed framework has a good compatibility with diverse independent NILM approaches. (2) Compared with CO and FHMM, the proposed model has definite physical significance. In addition, the proposed method shows remarkable enhancement in load disaggregation, even if the basic steady-state signature based NILM algorithm performs poorly. (3) The proposed model and method are flexible in time scalability, which is promising in load perception and prediction under the dynamic rolling mechanism.

Key words： Non-intrusive load monitoring discrete particle swarm optimization algorithm dynamic time warping Viterbi algorithm steady- and transient-state

Received: 14 April 2022

PACS:

TM714

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Liu Yu
	Liu Congxiao
	Zhao Xin
	Gao Shan
	Huang Xueliang

Cite this article:

Liu Yu,Liu Congxiao,Zhao Xin等. An Improved Steady- and Transient-State Mixed Non-Intrusive Load Monitoring Using Viterbi Algorithm[J]. Transactions of China Electrotechnical Society, 0, (): 230602-230602.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.220566 OR https://dgjsxb.ces-transaction.com/EN/Y0/V/I/230602

[1] 徐明杰, 赵健, 王小宇, 等. 基于多任务联合模型的居民用电模式分类方法[J]. 电工技术学报, 2022, 37(21): 5490-5502.
Xu Mingjie, Zhao Jian, Wang Xiaoyu, et al.Residential electricity consumption pattern classification method based on multi-task joint model[J]. Transactions of China Electrotechnical Society, 2022, 37(21): 5490-5502.
[2] 范睿, 孙润稼, 刘玉田. 考虑空调负荷需求响应的负荷恢复量削减方法[J]. 电工技术学报, 2022, 37(11): 2869-2877.
Fan Rui, Sun Runjia, Liu Yutian.A load restoration amount reduction method considering demand response of air conditioning loads[J]. Transactions of China Electrotechnical Society, 2022, 37(11): 2869-2877.
[3] 金国彬, 潘狄, 陈庆, 等. 考虑源荷不确定性的直流配电网模糊随机日前优化调度[J]. 电工技术学报, 2021, 36(21): 4517-4528.
Jin Guobin, Pan Di, Chen Qing, et al.Fuzzy random day-ahead optimal dispatch of DC distribution network considering the uncertainty of source-load[J]. Transactions of China Electrotechnical Society, 2021, 36(21): 4517-4528.
[4] 张潼, 于鹤洋, 田江, 等. 基于非侵入式负荷辨识的聚合负荷需求响应能力在线评估[J]. 电力工程技术, 2020, 39(6): 19-25, 65.
Zhang Tong, Yu Heyang, Tian Jiang, et al.Online aggregation monitoring of low-voltage power load demand response capability based on non-intrusive load identification[J]. Jiangsu Electrical Engineering, 2020, 39(6): 19-25, 65.
[4] 张潼, 于鹤洋, 田江, 等. 基于非侵入式负荷辨识的聚合负荷需求响应能力在线评估[J]. 电力工程技术, 2020(6):19-25,65.
Zhang Tong, Yu Heyang, Tian Jiang, et al.Online aggregation monitoring of low-voltage power load demand responsecapability based on non-intrusive load identification[J]. Electric Power Engineering Technology, 2020(6):19-25,65.
[5] 雷怡琴, 孙兆龙, 叶志浩, 等. 电力系统负荷非侵入式监测方法研究[J]. 电工技术学报, 2021, 36(11): 2288-2297.
Lei Yiqin, Sun Zhaolong, Ye Zhihao, et al.Research on non-invasive load monitoring method in power system[J]. Transactions of China Electrotechnical Society, 2021, 36(11): 2288-2297.
[6] Hart G W.Nonintrusive appliance load monitoring[J]. Proceedings of the IEEE, 1992, 80(12): 1870-1891.
[7] 余贻鑫, 刘博, 栾文鹏. 非侵入式居民电力负荷监测与分解技术[J]. 南方电网技术, 2013, 7(4): 49-51.
Yu Yixin, Liu Bo, Luan Wenpeng.Nonintrusive residential load monitoring and decomposition technology[J]. Southern Power System Technology, 2013, 7(4): 49-51.
[8] Liang Jian, Ng S K K, Kendall G, et al. Load signature study—part I: basic concept, structure, and methodology[J]. IEEE Transactions on Power Delivery, 2010, 25(2): 551-560.
[9] 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.
[10] 徐青山, 娄藕蝶, 郑爱霞, 等. 基于近邻传播聚类和遗传优化的非侵入式负荷分解方法[J]. 电工技术学报, 2018, 33(16): 3868-3878.
Xu Qingshan, Lou Oudie, Zheng Aixia, et al.A non-intrusive load decomposition method based on affinity propagation and genetic algorithm optimization[J]. Transactions of China Electrotechnical Society, 2018, 33(16): 3868-3878.
[11] 尹立亚. 非侵入式负荷特征提取与识别算法的研究[D]. 北京: 华北电力大学.
[12] 孙毅, 张璐, 赵洪磊, 等. 基于动态自适应粒子群算法的非侵入式家居负荷分解方法[J]. 电网技术, 2018, 42(6): 1819-1826.
Sun Yi, Zhang Lu, Zhao Honglei, et al.A non-intrusive household load monitoring method based on dynamic adaptive particle swarm optimization algorithm[J]. Power System Technology, 2018, 42(6): 1819-1826.
[13] 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 CNN-BiLSTM and DTW[J]. Power System Technology, 2022, 46(5): 1973-1981.
[14] Buddhahai B, Wongseree W, Rakkwamsuk P.A non-intrusive load monitoring system using multi-label classification approach[J]. Sustainable Cities and Society, 2018, 39: 621-630.
[15] Tabatabaei S M, Dick S, Xu W.Toward non-intrusive load monitoring via multi-label classification[J]. IEEE Transactions on Smart Grid, 2017, 8(1): 26-40.
[16] Liu Yu, Liu Congxiao, Shen Yiwen, et al.Non-intrusive energy estimation using random forest based multi-label classification and integer linear programming[J]. Energy Reports, 2021, 7: 283-291.
[17] Li Ding, Sawyer K, Dick S.Disaggregating household loads via semi-supervised multi-label classification[C]//2015 Annual Conference of the North American Fuzzy Information Processing Society (NAFIPS) held jointly with 2015 5th World Conference on Soft Computing (WConSC), Redmond, WA, USA, 2015: 1-5.
[18] 周东国, 张恒, 周洪, 等. 基于状态特征聚类的非侵入式负荷事件检测方法[J]. 电工技术学报, 2020, 35(21): 4565-4575.
Zhou Dongguo, Zhang Heng, Zhou Hong, et al.Non-intrusive load event detection method based on state feature clustering[J]. Transactions of China Electrotechnical Society, 2020, 35(21): 4565-4575.
[19] 张致强, 周步祥, 张冰, 等. 计及小波设计和半监督机器学习的非侵入式负载识别[J]. 电力系统及其自动化学报, 2020, 32(5): 143-150.
Zhang Zhiqiang, Zhou Buxiang, Zhang Bing, et al.Wavelet design and semi-supervised machine learning for non-intrusive load identification[J]. Proceedings of the CSU-EPSA, 2020, 32(5): 143-150.
[20] Le T T H, Heo S, Kim H. Toward load identification based on the Hilbert transform and sequence to sequence long short-term memory[J]. IEEE Transactions on Smart Grid, 2021, 12(4): 3252-3264.
[21] 牟魁翌, 杨洪耕. 基于PLA-GDTW支持向量机的非侵入式负荷监测方法[J]. 电网技术, 2019, 43(11): 4185-4192.
Mu Kuiyi, Yang Honggeng.Non-intrusive load identification method based on PLA-GDTW support vector machine[J]. Power System Technology, 2019, 43(11): 4185-4192.
[22] 赵文清, 张诗满, 李刚. 基于聚类和关联分析的居民用户非侵入式负荷分解[J]. 电力自动化设备, 2020, 40(6): 8-14.
Zhao Wenqing, Zhang Shiman, Li Gang.Non-intrusive load decomposition of residential users based on cluster and association analysis[J]. Electric Power Automation Equipment, 2020, 40(6): 8-14.
[23] Yang Dongsheng, Gao Xiaoting, Kong Liang, et al.An event-driven convolutional neural architecture for non-intrusive load monitoring of residential appliance[J]. IEEE Transactions on Consumer Electronics, 2020, 66(2): 173-182.
[24] 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.
[25] Liu Yu, Liu Congxiao, Wang Wen, et al.A robust non-intrusive load disaggregation method with roof-top photovoltaics[J]. Electric Power Systems Research, 2022, 208: 107887.
[26] Liu Yu, Liu Congxiao, Ling Qicheng, et al.Toward smart distributed renewable generation via multi-uncertainty featured non-intrusive interactive energy monitoring[J]. Applied Energy, 2021, 303: 117689.
[27] 牛卢璐, 贾宏杰. 一种适用于非侵入式负荷监测的暂态事件检测算法[J]. 电力系统自动化, 2011, 35(9): 30-35.
Niu Lulu, Jia Hongjie.Transient event detection algorithm for non-intrusive load monitoring[J]. Automation of Electric Power Systems, 2011, 35(9): 30-35.
[28] Torquato R, Shi Qingxin, Xu W, et al.A Monte Carlo simulation platform for studying low voltage residential networks[J]. IEEE Transactions on Smart Grid, 2014, 5(6): 2766-2776.
[29] Kelly J, Knottenbelt W.The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes[J]. Scientific Data, 2015, 2(1): 1-14.
[30] 冯人海, 袁万琦, 葛磊蛟. 基于图信号交替优化的居民用户非侵入式负荷监测方法[J]. 中国电机工程学报, 2022, 42(4): 1355-1364.
Feng Renhai, Yuan Wanqi, Ge Leijiao.Non-intrusive load monitoring method for resident users based on alternating optimization in graph signal[J]. Proceedings of the CSEE, 2022, 42(4): 1355-1364.
[31] Song J, Lee Yonggu, Hwang E.Time-frequency mask estimation based on deep neural network for flexible load disaggregation in buildings[J]. IEEE Transactions on Smart Grid, 2021, 12(4): 3242-3251.
[32] Batra N, Kelly J, Parson O, et al.NILMTK: an open source toolkit for non-intrusive load monitoring[C]//Proceedings of the 5th international conference on Future energy systems, Cambridge, United Kingdom, 2014: 265-276.