基于混合深度学习的电力用户窃电检测方法研究

吴栩峰; 区彦黛; 张思路; 庄婉铃; 魏华杰

吴栩峰,区彦黛,张思路,庄婉铃,魏华杰.基于混合深度学习的电力用户窃电检测方法研究[J].电测与仪表,2026,63(2):148-156.
WU Xufeng,OU Yandai,ZHANG Silu,ZHUANG Wanling,WEI Huajie.Research on electricity theft detection in distributed photovoltaic system based on hybrid deep learning[J].Electrical Measurement & Instrumentation,2026,63(2):148-156.

基于混合深度学习的电力用户窃电检测方法研究

Research on electricity theft detection in distributed photovoltaic system based on hybrid deep learning

DOI：10.19753/j.issn1001-1390.2026.02.016

中文关键词: 分布式光伏用户窃电检测半监督卷积神经网络模型 Transformer模型鲸鱼算法

英文关键词:photovoltaic system, theft detection, supervised, neural network model, Transformer model, optimization algorithm

基金项目:深圳供电局科技项目（项目编号：090000KK52222030）

作者中文名	作者英文名	单位
吴栩峰	WU Xufeng	深圳供电局有限公司
区彦黛	OU Yandai	深圳供电局有限公司
张思路	ZHANG Silu	云南电网有限责任公司昆明供电局
庄婉铃	ZHUANG Wanling	深圳供电局有限公司
魏华杰	WEI Huajie	深圳供电局有限公司

摘要点击次数: 468

中文摘要:

由于分布式光伏系统并网方式多样、运行模式灵活，窃电行为隐蔽性强，亟需高效检测方法。针对现有监督分类和无监督回归窃电检测模型泛化能力弱和检测精度低等问题，提出一种结合卷积神经网络和Transformer的混合半监督模型进行窃电检测。其中，卷积神经网络模型融合双向长短时记忆网络与注意力机制，并借助改进鲸鱼算法（融合Tent混沌映射、非线性收敛因子等优化策略）进行超参数寻优。Transformer模型通过多尺度感知层与线性映射层优化。实验结果表明，该模型在少量标注数据与大量未标注数据场景下，窃电检测准确率达96.67%，曲线下面积为99.05%，相比常规方法，所提方法的准确率分别提高了4.98%和0.44%，曲线下面积分别提高了3.12%和0.74%。研究为新型电力系统反窃电技术提供新思路，助力清洁能源可持续发展。

英文摘要:

Due to the diverse grid-connection methods and flexible operation modes of distributed photovoltaic system, electricity theft behaviors are highly covert, making it urgent to develop efficient detection methods. Aiming at the problems of weak generalization ability and low detection accuracy of existing supervised classification and unsupervised regression electricity theft detection models, a hybrid semi-supervised model combining convolutional neural network and Transformer is proposed for electricity theft detection. Specifically, the convolutional neural network (CNN) model integrates the bidirectional long short-term memory network and the attention mechanism, and employs an improved whale optimization algorithm (incorporating optimization strategies such as Tent chaotic mapping and nonlinear convergence factors) to search for optimal hyperparameters. The Transformer model is optimized through a multi-scale perception layer and a linear mapping layer. Experimental results demonstrate that, in scenarios with a small amount of labeled data and a large amount of unlabeled data. Compared with conventional methods, the accuracy of the proposed method is improved by 4.98% and 0.44%, respectively, and the area under the curve is increased by 3.12% and 0.74%, respectively. This research provides new ideas for anti-electricity theft technologies in power system and facilitates the sustainable development of clean energy.

查看全文查看/发表评论下载PDF阅读器

关闭