Non-invasive load monitoring based on an improved GMM-CNN-GRU combination
-
摘要: 为挖掘用户侧节能减排潜力，对用户用电行为进行精细化分析和管理，提升电能利用效率，提出了一种基于高斯混合模型聚类和深度神经网络相结合的非侵入式负荷监测方法。首先，针对同一电器常出现功率相近但运行状态不一致问题，利用高斯混合模型聚类算法中“软分类”和类簇灵活的优势，对负荷工作状态进行精细分类，形成负荷用电设备实际运行情况的负荷状态特征库。其次，针对常见的应用于非侵入式负荷监测模型的深度神经网络在多标签分类时存在识别精度低等问题，提出卷积神经网络与门控循环单元混合的深度神经网络模型。最后，综合考虑外部环境数据对家庭用户用能习惯的影响，在AMPds2数据集上开展验证分析，并与其他模型进行对比。结果表明，所提的非侵入式负荷监测模型具有较高的准确性。
-
关键词:
- 非侵入式负荷监测与分解 /
- 高斯混合模型聚类 /
- 卷积神经网络 /
- 门控循环单元 /
- 深度学习
Abstract: A non-intrusive load monitoring method based on Gaussian mixture model clustering combined with a deep neural network is proposed to explore the potential of energy saving and emission reduction at the customer side.It also fine-tunes the analysis and management of customer electricity consumption behavior,and improves the efficiency of electricity use.First,we tackle the problem that the same electrical appliance often has similar power but inconsistent operating status.In order to classify the load working status in fine manner,the advantages of"soft classification"and flexible clustering in the Gaussian mixture model clustering algorithm can be used to form a load status feature library that conforms to the actual operating conditions of electrical equipment.Secondly,note that in the common deep neural networks applied to non-invasive load monitoring models,there are problems such as low recognition accuracy in multi-label classification.Thus a deep neural network model with a mixture of convolutional neural networks and gated recurrent units is proposed.Finally,the validation analysis is carried out on the AMPds2 dataset by considering the influence of external environmental data on the energy consumption habits of household users,and the results are compared with other models.The results show that the proposed non-invasive load monitoring model has high accuracy. -
[1] 张永生,巢清尘,陈迎,等.中国碳中和:引领全球气候治理和绿色转型[J].国际经济评论, 2021(3):1-18. ZHANG Yongsheng, CHAO Qingchen, CHEN Ying, et al.China's carbon neutrality:leading in global climate governance and green transition[J]. International Economic Review, 2021(3):1-18.
[2] 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.
[3] 李叶茂,李雨桐,郝斌,等.低碳发展背景下的建筑“光储直柔”配用电系统关键技术分析[J].供用电,2021, 38(1):32-38. LI Yemao, LI Yutong, HAO Bin, et al. Key technologies of building power supply and distribution system towards carbon neutral development[J]. Distribution&Utilization,2021, 38(1):32-38.
[4] 盛四清,吴昊,顾清,等.含碳捕集装置的电气综合能源系统低碳经济运行[J].电测与仪表, 2021, 58(6):82-90. SHENG Siqing, WU Hao, GU Qing, et al. Low-carbon economic operation of integrated electricity and natural gas system with carbon capture devices[J]. Electrical Measurement&Instrumentation, 2021, 58(6):82-90.
[5] 白云,贾燕冰,陈浩,等.计及供气充裕性的电-气互联综合能源系统低碳经济调度[J].电测与仪表, 2021,58(11):32-38. BAI Yun, JIA Yanbing, CHEN Hao, et al. Low-carbon economic dispatch of electric-gas interconnection systems considering gas supply adequacy[J]. Electrical Measurement&Instrumentation, 2021, 58(11):32-38.
[6] HART G W. Nonintrusive appliance load monitoring[J].Proceedings of the IEEE, 1992, 80(12):1870-1891.
[7] 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.
[8] BOZORG M, BRACALE A, CARAMIA P, et al. Bayesian bootstrap quantile regression for probabilistic photovoltaic power forecasting[J]. Protection and Control of Modern Power Systems, 2020, 5(3):218-229.
[9] MADHIARASAN M. Accurate prediction of different forecast horizons wind speed using a recursive radial basis function neural network[J]. Protection and Control of Modern Power Systems, 2020, 5(3):230-238.
[10] 陈弘川,蔡旭,孙国歧,等.基于智能优化方法的相似日短期负荷预测[J].电力系统保护与控制, 2021,49(13):121-127. CHEN Hongchuan, CAI Xu, SUN Guoqi, et al. Similar day short-term load forecasting based on intelligent optimization method[J]. Power System Protection and Control, 2021, 49(13):121-127.
[11] 刘云,吴家宏.计及电动汽车渗透率的台区负荷预测研究[J].电网与清洁能源, 2020, 36(1):72-78. LIU Yun, WU Jiahong. Research on forecasting of transformer area load considering the permeability of electric vehicles[J]. Power System and Clean Energy,2020, 36(1):72-78.
[12] 仝新宇,张宇泽,张长生,等.基于广义回归神经网络的有源配电网网供负荷预测方法[J].供用电, 2020,37(12):40-45. TONG Xinyu, ZHANG Yuze, ZHANG Changsheng, et al.Load forecasting method of active distribution network based on generalized regression neural network[J].Distribution&Utilization, 2020, 37(12):40-45.
[13] 李强,赵健,王磊,等.配电网馈线负荷预测及风险评估预警分析方法[J].供用电, 2020, 37(5):50-55. LI Qiang, ZHAO Jian, WANG Lei, et al. Distribution network feeder load forecasting and risk assessment warning analysis method[J]. Distribution&Utilization,2020, 37(5):50-55.
[14] 杨立余,陈昊,黎明,等.非侵入式电力负荷多目标分解框架[J].电力系统保护与控制, 2020, 48(6):100-107. YANG Liyu, CHEN Hao, LI Ming, et al. A framework for non-intrusive load monitoring using multi-objective evolutionary algorithms[J]. Power System Protection and Control, 2020, 48(6):100-107.
[15] 张安安,庄景泰,郭红鼎,等.结合图半监督与广义回归神经网络的非侵入式海洋平台负荷监测[J].电力系统保护与控制, 2020, 48(7):85-91. ZHANG An'an, ZHUANG Jingtai, GUO Hongding, et al.Non-intrusive offshore platform load monitoring based on graph-based semi-supervised learning and generalized regression neural networks[J]. Power System Protection and Control, 2020, 48(7):85-91.
[16] 朱永灿,张鹏,田毅,等.变电设备在线监测技术中的同步采集触发方法对比分析[J].中国电力, 2022, 55(3):64-73. HU Yongcan, ZHANG Peng, TIAN Yi, et al. Comparison of synchronous acquisition trigger methods in on-line monitoring technology of transformer equipment[J].Electric Power, 2022, 55(3):64-73.
[17] 许易经,韩学山,杨明,等.基于设备在线监测的电网状态检修决策模型[J].电力系统自动化, 2020, 44(23):72-81. XU Yijing, HAN Xueshan, YANG Ming, et al.Decision-making model of condition-based maintenance for power grid with equipment on-line monitoring[J].Automation of Electric Power Systems, 2020, 44(23):72-81.
[18] KELLY J, KNOTTENBELT W J. Neural NILM:deep neural networks applied to energy disaggregation[M].Springer International Publishing, 2015.
[19] VERMA S, SINGH S, MAJUMDAR A. Multi-label LSTM autoencoder for non-intrusive appliance load monitoring[J]. Electric Power Systems Research, 2021,199.
[20] 王轲,钟海旺,余南鹏,等.基于seq2seq和Attention机制的居民用户非侵入式负荷分解[J].中国电机工程学报, 2019, 39(1):75-83. WANG Ke, ZHONG Haiwang, YU Nanpeng, et al.Nonintrusive load monitoring based on sequence-tosequence model with Attention mechanism[J]. Proceedings of the CSEE, 2019, 39(1):75-83.
[21] ZHOU X, FENG J, LI Y. Non-intrusive load decomposition based on CNN–LSTM hybrid deep learning model[J].Energy Reports, 2021, 7:5762-5771.
[22] 燕续峰,翟少鹏,王治华,等.深度神经网络在非侵入式负荷分解中的应用[J].电力系统自动化, 2019, 43(1):126-132. YAN Xufeng, ZHAI Shaopeng, WANG Zhihua, et al.Application of deep neural network in non-intrusive load disaggregation[J]. Automation of Electric Power Systems,2019, 43(1):126-132.
[23] LI Kehua, MA Zhenjun, ROBINSON D, et a1. Identification of typical building daily electricity usage profiles using Gaussian mixture model-based clustering and hierarchical clustering[J]. Applied Energy, 2018, 231:331-342.
[24] Model-based clustering and Gaussian mixture model[EB/OL].[2017-01-02]. https://en.proft.me/2017/02/1/model-based-clustering-r/.
[25] 张美霞,李丽,杨秀,等.基于高斯混合模型聚类和多维尺度分析的负荷分类方法[J].电网技术, 2020,44(11):4283-4296. ZHANG Meixia, LI Li, YANG Xiu, et al. A load classification method based on gaussian mixture model clustering and multi-dimensional scaling analysis[J].Power System Technology, 2020, 44(11):4283-4296.
[26] KIM Y. Convolutional neural networks for sentence classification[Z]. 2014.
[27] LIU S, YOU S, ZENG C, et al. Data source authentication of synchrophasor measurement devices based on1D-CNN and GRU[J]. Electric Power Systems Research,2021, 196:107-207.
[28] MAKONIN S, ELLERT B, BAJIC I V, et al. Electricity,water, and natural gas consumption of a residential house in Canada from 2012 to 2014[J]. Scientific Data, 2016, 3:1-12.
[29] 周志华.机器学习[M].北京:清华大学出版社, 2016. [30] 何敏瑶.非侵入式家庭用户负荷监测算法研究[D].西安:西安理工大学, 2021.HE Minyao. Research on household non-invasive load monitoring algorithm[D]. Xi’an:Xi’an University of Technology, 2021. [31] MENGISTU M A, GIRMAY A A, CAMARDA C, et al. A cloud-based on-line disaggregation algorithm for home appliance loads[J]. IEEE Transactions on Smart Grid,2019, 10(3):3430-3439.
[32] MOON T K. The expectation-maximization algorithm[J].IEEE Signal Processing Magazine, 1996, 13(6):47-60.
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
下载:
