Non-invasive Household Load Decomposition Based on GRNN and Attention Mechanism Model
-
摘要: 为了提高识别精度,提出一种基于GRNN与注意力机制模型的非侵入式家用负荷分解方法。采用批标准化来减少神经网络层与层之间的耦合,利用GRNN强大的时间序列特征表示能力,来提取电力负荷入口处测得的总用电信息与各电器能耗之间的关系,同时利用注意力机制来减少模型的权重参数。最后通过算例验证了算法的可行性与优越性。Abstract: In order to improve identification accuracy,the paper proposes a non-invasive household load decomposition method based on GRNN and attention mechanism model. Batch standardization is adopted to reduce the coupling between the layers of neural network,and GRNN’s powerful time series feature representation ability is used to extract the relationship between the total electricity consumption measured at power load access point and the power consumption of each electrical appliance. Meanwhile,the attention mechanism is used to reduce the weight parameters of the model. Finally,a numerical example is provided to verify the feasibility and superiority of the algorithm.
-
[1] 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):1-5. YU Yixin,LIU Bo,LUAN Wenpeng. Nonintrusive residential loadmonitoring and decomposition technology[J].Southern PowerSystem Technology,2013,7(4):1-5.
[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. Review of non-invasiveload monitoring and decomposition[J]. Power System Technology,2016,40(10):3108-3117.
[3] 郭陆阳,王守相,陈海文,等.基于双向GRNN与时间序列翻译模型的非侵入式负荷分解算法[J].供用电,2019,36(10):9-15,86. GUO Luyang, WANG Shouxiang, CHEN Haiwen, et al.Noninvasive load decomposition algorithm based on bidirectionalGRNN and time series translation model[J]. Distribution&Utilization,2019,4(10):9-15,86.
[4] 崔亮节,孙毅,刘耀先.考虑分时段状态行为的非侵入式负荷分解方法[J].电力系统自动化,2020,44(5):215-222. CUI Liangjie,SUN Yi,LIU Yaoxian. A non-intrusive loaddecomposition method considering time-divided state behavior[J].Automation of Electric Power Systems,2020,44(5):215-222.
[5] 程江洲,谢诗雨,张赟宁,等.基于聚类加权随机森林的非侵入式负荷识别[J].智慧电力,2020,48(8):123-129. CHEN Jiangzhou,XIE Shiyu,ZHANG Yunning,et al. Clusteringweighted random forest based non-invasive load identification[J].Smart Power,2020,48(8):123-129.
[6] 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. Non-intrusive multi-objective decomposition framework of power load[J]. Power SystemProtection and Control,2020,48(6):100-107.
[7] 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):103-111. WANG Shouxiang,GUO Luyang,CHEN Haiwen,et al. Non-intrusive load identification algorithm based on feature fusion anddeep learning[J]. Automation of Electric Power Systems,2020,44(9):103-111.
[8] 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 convolutionalneural network[J]. Power System Technology,2020,44(6):2038-2044.
[9] 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):4185-4193. MOU Kuiyi,YANG Honggeng. Non-intrusive load monitoringmethod based on PLA-GTTW support vector machine[J]. PowerSystem Technology,2019,43(11):4185-4193.
[10] 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. On-lineevaluation of aggregate load demand response capability based onnon-intrusive load identification[J]. Electric Power EngineeringTechnology,2020,39(6):19-25,65.
[11] 周东国,张恒,周洪.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. Noninvasive loadevent detection method based on state feature clustering[J].Transactions of China Electrotechnical Society,2020,35(21):4565-4575.
[12] 乔适苏,蔡慧,谢岳.基于小波变换的非侵入负荷事件检测算法研究[J].中国计量大学学报,2020,31(4):421-429. QIAO Shisu,CAI Hui,XIE Yue. Research on Non-intrusive loadevent detection algorithm based on wavelet transform[J]. Journal ofChina University of Metrology,2020,31(4):421-429.
[13] 赵会茹,赵一航,郭森.基于互补集合经验模态分解和长短期记忆神经网络的短期电力负荷预测[J].中国电力,2020,53(6):48-55. ZHAO Huiru,ZHAO Yihang,GUO Sen. Short-term power loadprediction based on empirical mode decomposition ofcomplementary sets and long and short memory neural network[J].Electric Power,2020,53(6):48-55.
[14] 庞传军,张波,余建明.基于LSTM循环神经网络的短期电力负荷预测[J].电力工程技术,2021,40(1):175-180,194. PANG Chuanjun,ZHANG Bo,YU Jianming. Short-term powerload prediction based on LSTM cyclic neural network[J]. ElectricPower Engineering Technology,2021,40(1):175-180,194.
[15] 杨秀,曹泽棋,张美霞,等.基于Attention-LSTM的商业建筑负荷分解研究[J].智慧电力,2020,48(9):89-95. YANG Xiu,CAO Zeqi,ZHANG Meixia,et al. Research on load decomposition of commercial buildings based on attention-LSTM[J].Smart Power,2020,48(9):89-95.
[16] 孙庆凯,王小君,张义志,等.基于LSTM和多任务学习的综合能源系统多元负荷预测[J].电力系统自动化,2021,45(5):63-70. SUN Qingkai,WANG Xiaojun,ZHANG Yizhi,et al. Multivariateload prediction of integrated energy system based on LSTM andmulti-task learning[J]. Automation of Electric Power Systems,201,45(5):63-70.
[17] 唐子卓,刘洋,许立雄,等.基于负荷数据频域特征和LSTM网络的类别不平衡负荷典型用电模式提取方法[J].电力建设,2020,41(8):17-24. TANG Zizhuo,LIU Yang,XU Lixiong,et al. Extraction method oftypical power consumption patterns of unbalanced load based onload data frequency domain characteristics and LSTM network[J].Electric Power Construction,2020,41(8):17-24.
[18] 王志建,张炜健,刘士杰.基于EMD-GRU循环神经网络的转向交通流量组合预测[J].工业控制计算机,2020,33(12):73-76. WANG Zhijian, ZHANG Weijian, LIU Shijie. Integratedprediction of steering traffic flow based on EMD-GRU cyclicneural network[J]. Industrial Control Computer,2020,33(12):73-76.
[19] ASSIS MARCOS V O,CARVALHO LUIZ F. A GRU deep learningsystem against attacks in software defined networks[J]. Journal ofNetwork and Computer Applications,2020,177.
[20] 宋旭东,王雪,伊卫国.基于小波变换和GRU神经网络的系泊缆力预测[J].大连交通大学学报,2020,41(6):91-94. SONG Xudong,WANG Xue,YI Weiguo. Prediction of mooringcable force based on wavelet transform and GRU neural network[J].Journal of Dalian Jiaotong University,2020,41(6):91-94.
[21] 谢谦,董立红,厍向阳.基于Attention-GRU的短期电价预测[J].电力系统保护与控制,2020,48(23):154-160. XIE Qian,DONG Lihong,KU Xiangyang. Short-term electricityprice prediction based on attention-GRU[J]. Power SystemProtection and Control,2020,48(23):154-160.
[22] 杨震,何通海.一种基于非负矩阵分解的智能电网数据分解方法[P].北京:CN108197425B,2019-09-03. [23] 吴争,李瑶虹,杨晓梅,等.基于HMM的无线充电系统PFC装置故障检测[J].电力工程技术,2020,39(6):166-171. WU Zheng,LI Yaohong,YANG Xiaomei,et al. Fault detection ofPFC device in wireless charging system based on HMM[J]. ElectricPower Engineering Technology,2020,39(6):166-171.
[24] 蒋正锋,黄勇萍.基于多参数融合优化的隐马尔科夫模型的设计[J].现代计算机,2020(18):28-32. JIANG Zhengfeng,HUANG Yongping. Design of hidden markovmodel based on multi-parameter fusion optimization[J]. ModernComputer,2020(18):28-32.
[25] 刘晓波,孔屹刚,李涛,等.采煤机调高泵隐半马尔可夫模型磨损故障预测[J].科学技术与工程,2020,20(29):11980-11986. LIU Xiaobo,KONG Yigang,LI Tao,et al. Wear fault predictionof shearer height-adjusting pump using hidden semi-markov model[J]. Science Technology and Engineering,2020,20(29):11980-11986.
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
下载:
