基于孪生分支网络的非侵入式冲击负荷辨识方法

宋 磊; 徐永进; 刁瑞朋; 李亦龙; 陆春光; 王思奎

宋磊,徐永进,刁瑞朋,李亦龙,陆春光,王思奎.基于孪生分支网络的非侵入式冲击负荷辨识方法[J].电测与仪表,2022,59(11):96-104.
SONG Lei,xuyongjin,DIAO Ruipeng,LI Yilong,LU Chunguang,WANG Sikui.Non-intrusive impact load identification method based onsiamese-architecture network[J].Electrical Measurement & Instrumentation,2022,59(11):96-104.

基于孪生分支网络的非侵入式冲击负荷辨识方法

Non-intrusive impact load identification method based onsiamese-architecture network

DOI：10.19753/j.issn1001-1390.2022.11.013

中文关键词: 非侵入式负荷辨识 V-I轨迹孪生分支网络 ARM Cortex-M4

英文关键词:non-intrusive load identification, V-I trajectory, siamese-architecture network, ARM Cortex-M4

基金项目:基金项目:国网浙江省电力有限公司科技项目（5211DS19003K）

作者中文名	作者英文名	单位
宋磊	SONG Lei	国网浙江省电力有限公司营销服务中心
徐永进	xuyongjin	国网浙江省电力有限公司营销服务中心
刁瑞朋	DIAO Ruipeng	青岛鼎信通讯股份有限公司
李亦龙	LI Yilong	国网浙江省电力有限公司营销服务中心
陆春光	LU Chunguang	国网浙江省电力有限公司营销服务中心
王思奎	WANG Sikui	青岛鼎信通讯股份有限公司

摘要点击次数: 1136

中文摘要:

传统边缘侧电力设备无法有效检测出对电网影响较大的冲击性负荷的设备类别与功率启停信息。为此,提出一种基于孪生分支网络的非侵入式冲击负荷辨识方法。首先通过电力边缘设备入口处的高频采样数据提取波形的V-I轨迹特征和对角高斯谐波特征,接着利用卷积神经网络强大的学习能力,预设多种先验信息对不同设备冲击负荷特性进行训练,特别地,设计一种共享网络权重的孪生分支网络结构,利用不同的损失函数,智能监控与识别冲击负荷的发生分解其功率。使用非侵入式的方式并基于ARM Cortex-M4平台进行算法部署与识别测试,对比不同识别算法对冲击负荷的辨识能力,结果表明,当电网发生大功率冲击性波动时,孪生分支网络可更准确识别冲击负荷的设备类别并分解其功率,有效提高了对冲击负荷的辨识效果。

英文摘要:

Traditional electric equipment cannot effectively detect the type of equipment and power start-stop information of impact load which has a great influence on the power grid. Therefore, a non-intrusive identification method of impact load based on siamese-architecture network is proposed. Firstly, the V-I trajectory characteristics and diagonal Gaussian harmonic characteristics of the waveform are extracted from the high-frequency sampling data at the inlet of the power edge equipment. On this basis, using the strong learning ability of convolutional neural network, a variety of prior information is preset to train the impact load characteristics of different equipment. In particular, a siamese-architecture network structure with shared network weight is designed to intelligently monitor and identify the occurrence of impact load and decompose its power by using different loss functions. The algorithm is deployed and tested based on ARM Cortex-M4 platform in a non-invasive way, and the identification ability of different identification algorithms for impact load was compared. The results show that the siamese-architecture network can be more accurate when high-power impact fluctuations occur in the power grid, the siamese-architecture network can more accurately identify the equipment category of the impact load and decompose its power, which effectively improves the identification effect of the impact load.

查看全文查看/发表评论下载PDF阅读器

关闭