丁健,陈鉴祥,刘旺朋,丁一帆,王谱宇
DING Jian,CHEN Jianxiang,LIU Wangpeng,DING Yifan,WANG Puyu

• 1:南京理工大学自动化学院

摘要(Abstract)：

现有基于V-I轨迹的非侵入式负荷监测研究，存在对于轨迹相似的电器设备识别准确率较低、网络较复杂的问题。针对该问题提出了一种基于改进型颜色编码与密集连接网络的非侵入式负荷监测方法。首先，分析了基于滑动窗的事件检测算法的原理；其次，提出了一种改进型颜色编码V-I轨迹的绘制方法，以解决小功率区间电器种类繁多的问题，提高V-I轨迹的区分度；然后，将所绘制的V-I轨迹用于自建密集连接网络的训练，得到了一个适用于低分辨率V-I轨迹的识别模型；最后，在PLAID与WHITED数据集上进行验证，结果表明：所提方法具有更高的准确率和识别效率。
Current research on non-intrusive load monitoring(NILM) based on V-I trajectories faces challenges such as low recognition accuracy for appliances with similar trajectories and complex network structures. To address these issues, the paper proposes a non-intrusive load monitoring method based on improved color coding and dense convolutional network(DenseNet). First, the paper analyzes the principles of the event detection algorithm based on a sliding window. Then, it introduces an improved color coding algorithm for plotting V-I trajectories to address the problem of diverse appliance types in low-power ranges and to enhance the differentiation of V-I trajectories.Next, the plotted V-I trajectories are used to train the dense convolutional network, resulting in a recognition model suitable for low-resolution V-I trajectories. Finally, validation on the PLAID and WHITED demonstrates that the proposed method achieves higher accuracy and recognition efficiency.

关键词(KeyWords)： 非侵入式负荷监测;V-I轨迹;图像识别;密集连接网络;家用电器
NILM;V-I trajectory;image recognition;DenseNet;household appliance

Abstract:

Keywords:

基金项目(Foundation): 江苏省自然科学基金（BK20242048）

作者(Author): 丁健,陈鉴祥,刘旺朋,丁一帆,王谱宇
DING Jian,CHEN Jianxiang,LIU Wangpeng,DING Yifan,WANG Puyu

DOI: 10.19585/j.zjdl.202502001

参考文献(References)：

• [1]武昕，严萌，郭一凡，等.基于结构化特征图谱的组合支持向量机非侵入式负荷辨识[J].电力系统自动化，2022,46(12):210-219.WU Xin,YAN Meng,GUO Yifan,et al. Non-intrusive load identification by combined support vector machine based on structured characteristic spectrum[J]. Automation of Electric Power Systems,2022,46(12):210-219.
• [2]许烽，陶远超，陆翌，等.基于源荷预测的含多能储能区域电热系统的优化调度[J].浙江电力，2023,42(9):17-26.XU Feng,TAO Yuanchao,LU Yi,et al.Optimal dispatch of regional electricity-thermal system with multi-energy storage based on source and load forecasting[J].Zhejiang Electric Power,2023,42(9):17-26.
• [3]向颖，严慧峰，余旭阳，等.基于特征优选及改进自组织神经网络的非侵入式负荷辨识[J].中国电机工程学报，2022,42（增刊1）:106-114.XIANG Ying,YAN Huifeng,YU Xuyang,et al. Noninvasive load identification based on feature optimization and improved self-organizing neural network[J].Proceedings of the CSEE,2022,42(S1):106-114.
• [4]张玉天，邓春宇，刘沅昆，等.基于卷积神经网络的非侵入负荷辨识算法[J].电网技术，2020,44(6):2038-2044.ZHANG Yutian,DENG Chunyu,LIU Yuankun,et al.Non-intrusive load identification algorithm based on convolution neural network[J]. Power System Technology,2020,44(6):2038-2044.
• [5]周晨轶，闫娇娇，刘晨阳.基于贝叶斯准则的非侵入式负荷监测方法[J].浙江电力，2018,37(5):7-11.ZHOU Chenyi,YAN Jiaojiao,LIU Chenyang. Nonintrusive load monitoring based on Bayes criterion[J].Zhejiang Electric Power,2018,37(5):7-11.
• [6]王异成，罗华峰，马骏超，等.一种小微负荷智能监测与聚合分析系统研究[J].浙江电力，2021,40(12):37-45.WANG Yicheng,LUO Huafeng,MA Junchao,et al.Research on smart monitoring and aggregate analysis system for small and micro loads[J]. Zhejiang Electric Power,2021,40(12):37-45.
• [7]邓晓平，张桂青，魏庆来，等.非侵入式负荷监测综述[J].自动化学报，2022,48(3):644-663.DENG Xiaoping,ZHANG Guiqing,WEI Qinglai,et al.A survey on the non-intrusive load monitoring[J].Acta Automatica Sinica,2022,48(3):644-663.
• [8]张继东，陈雪薇，徐述，等.非侵入式负荷辨识技术研究及应用[J].机电信息，2021(23):1-4.ZHANG Jidong,CHEN Xuewei,XU Shu,et al.Research and application of non-invasive load identification technology[J].Mechanical and Electrical Information,2021(23):1-4.
• [9]杨秀，李安，孙改平，等.基于改进GMM-CNN-GRU混合的非侵入式负荷监测方法研究[J].电力系统保护与控制，2022,50(14):65-75.YANG Xiu,LI An,SUN Gaiping,et al.Non-invasive load monitoring based on an improved GMM-CNN-GRU combination[J].Power System Protection and Control,2022,50(14):65-75.
• [10]陈飞.面向住宅用户的非侵入式负荷监测方法研究[D].贵阳：贵州大学，2022.CHEN Fei. Research on non-invasive load monitoring method for residential users[D].Guiyang:Guizhou University,2022.
• [11]班昭.面向家居负荷的非侵入式负荷辨识方法研究[D].石家庄：河北科技大学，2023.BAN Zhao. Research on non-invasive load identification method for household load[D]. Shijiazhuang:Hebei University of Science and Technology,2023.
• [12] YU Z W,ZHAO R F,LIU B,et al.Deep co-training for semi-supervised non-intrusive load monitoring based on VI trajectory[C]//2023 8th Asia Conference on Power and Electrical Engineering(ACPEE). Tianjin,China. IEEE,2023:1458-1463.
• [13] GAO J K,KARA E C,GIRI S,et al.A feasibility study of automated plug-load identification from high-frequency measurements[C]//2015 IEEE Global Conference on Signal and Information Processing(GlobalSIP).Orlando,FL,USA.IEEE,2015:220-224.
• [14] LAM H Y,FUNG G S K,LEE W K.A novel method to construct taxonomy electrical appliances based on load signaturesof[J]. IEEE Transactions on Consumer Electronics,2007,53(2):653-660.
• [15] DE BAETS L,DHAENE T,DESCHRIJVER D,et al.VI-based appliance classification using aggregated power consumption data[C]//2018 IEEE International Conference on Smart Computing(SMARTCOMP).Taormina,Italy.IEEE,2018:179-186.
• [16] LIU Y C,WANG X,YOU W.Non-intrusive load monitoring by voltage-current trajectory enabled transfer learning[J].IEEE Transactions on Smart Grid,2019,10(5):5609-5619.
• [17] SHI Z L,YIN B.An improved Non-intrusive load identification method for V-I trajectory based on amplitude to pixel value[C]//2021 IEEE 5th Information Technology,Networking,Electronic and Automation Control Conference(ITNEC).Xi’an,China.IEEE,2021:1510-1516.
• [18] WANG S X,CHEN H W,GUO L Y,et al.Non-intrusive load identification based on the improved voltage-current trajectory with discrete color encoding background and deep-forest classifier[J].Energy and Buildings,2021,244:111043.
• [19]解洋，梅飞，郑建勇，等.基于V-I轨迹颜色编码的非侵入式负荷识别方法[J].电力系统自动化，2022,46(4):93-102.XIE Yang,MEI Fei,ZHENG Jianyong,et al. Nonintrusive load monitoring method based on V-I trajectory color coding[J].Automation of Electric Power Systems,2022,46(4):93-102.
• [20]崔昊杨，蔡杰，陈磊，等.基于颜色编码的非侵入式负荷细粒度识别方法[J].电网技术，2022,46(4):1557-1567.CUI Haoyang,CAI Jie,CHEN Lei,et al. Non-intrusive load fine-grained identification based on color encoding[J].Power System Technology,2022,46(4):1557-1567.
• [21]宰州鹏，赵升，朱翔鸥，等.基于颜色编码与谐波特征融合的非侵入式负荷识别方法[J].电气技术，2022,23(12):9-16.ZAI Zhoupeng,ZHAO Sheng,ZHU Xiang’ou,et al.Nonintrusive load monitoring based on color coding and harmonic feature fusion[J]. Electrical Engineering,2022,23(12):9-16.
• [22]杨苗，游文霞，刘玥，等.基于颜色编码和残差神经网络的非侵入式负荷识别[J].电工材料，2024(2):94-99.YANG Miao,YOU Wenxia,LIU Yue,et al. Nonintrusive load identification based on binary V-I trajectory color coding and residual neural network[J].Electrical Engineering Materials,2024(2):94-99.
• [23]张鲁昊.基于人工神经网络的非侵入式负荷识别算法研究[D].杭州：浙江大学，2022.ZHANG Luhao.Research on non-invasive load identification algorithm based on artificial neural network[D].Hangzhou:Zhejiang University,2022.
• [24]王丙楠.基于小样本学习的非侵入式负荷监测方法[D].杭州：浙江大学，2022.WANG Bingnan. Non-intrusive load monitoring methods based on few-shot learning[D].Hangzhou:Zhejiang University,2022.
• [25]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.
• [26]钟韬，刘刚，黄蕾，等.基于决策树的非入侵式负荷分解算法的研究[J].计算机应用研究，2020,37（增刊1）:163-165.ZHONG Tao,LIU Gang,HUANG Lei,et al.Research on non-invasive load decomposition algorithm based on decision tree[J].Application Research of Computers,2020,37(S1):163-165.
• [27]郇嘉嘉，汪超群，洪海峰，等.基于图像编码与深度学习的非侵入式负荷识别方法[J].科学技术与工程，2021,21(21):8901-8908.HUAN Jiajia,WANG Chaoqun,HONG Haifeng,et al.Non-intrusive load monitoring method based on color encoding and deep learning[J].Science Technology and Engineering,2021,21(21):8901-8908.
• [28]王守相，郭陆阳，陈海文，等.基于特征融合与深度学习的非侵入式负荷辨识算法[J].电力系统自动化，2020,44(9):103-110.WANG Shouxiang,GUO Luyang,CHEN Haiwen,et al.Non-intrusive load identification algorithm based on feature fusion and deep learning[J]. Automation of Electric Power Systems,2020,44(9):103-110.
• [29]裘星，尹仕红，张之涵，等.基于V-I轨迹与高次谐波特征的非侵入式负荷识别方法[J].电力工程技术，2021,40(6):34-42.QIU Xing,YIN Shihong,ZHANG Zhihan,et al. Nonintrusive load identification method based on V-I trajectory and high-order harmonic feature[J]. Electric Power Engineering Technology,2021,40(6):34-42.
• [30] LI W,DONG T X,WANG Y S, et al.Research on load recognition algorithms based on current distortion and harmonic content[C]//2019 IEEE Symposium Series on Computational Intelligence(SSCI).Xiamen,China.IEEE,2019:2753-2758.
• [31]周任飞，汤鹏飞，刘三丰，等.基于卷积神经网络的非侵入式负荷识别研究[J].信息技术与网络安全，2019,38(8):64-68.ZHOU Renfei,TANG Pengfei,LIU Sanfeng,et al. Research of non-intrusive load identification based on convolutional neural network[J]. Information Technology and Network Security,2019,38(8):64-68.
• [32] HUANG G,LIU Z,VAN DER MAATEN L,et al.Densely connected convolutional networks[C]//2017IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu,HI,USA. IEEE,2017:2261-2269.
• [33]武昕，焦点，高宇辰.基于非侵入式用电数据分解的自适应特征库构建与负荷辨识[J].电力系统自动化，2020,44(4):101-109.WU Xin,JIAO Dian,GAO Yuchen.Construction of adaptive feature library and load identification based on decomposition of non-intrusive power consumption data[J].Automation of Electric Power Systems,2020,44(4):101-109.
• [34]王谱宇，丁一帆，陈鉴祥，等.基于动态谐波导纳参数的非侵入式负荷监测数据模拟生成方法[J/OL].中国电机工程学报，2024:1-14.WANG Puyu,DING Yifan,CHEN Jianxiang,et al.Simulation method of non-intrusive load monitoring data generation based on dynamic harmonic admittance parameters[J/OL].Proceedings of the CSEE,2024:1-14.
• [35] KAHL M,HAQ A U,KRIECHBAUMER T,et al.Whited-A worldwide household and industry transient energy data set[C]//3rd International Workshop NonIntrusive Load Monitoring,Vancouver,BC,Canada,2016:1-5.