基于深度自编码器的智能电网窃电网络攻击异常检测
电子技术应用
黄燕1,李金灿1,杨霞琴2,李佩2,李梓3
1.广西电网有限责任公司,广西 南宁 530023;2.广西电网有限责任公司南宁供电局,广西 南宁 530000; 3.广西电网有限责任公司梧州供电局,广西 梧州 543002
摘要: 现有AMIs中的异常检测器存在浅层架构,难以捕获时间相关性以及电力消耗数据中存在的复杂模式,从而影响检测性能。提出基于长短期记忆(LSTM)的序列对序列(seq2seq)结构的深度(堆栈)自编码器。自动编码器结构的深度有助于捕获数据的复杂模式,seq2seq LSTM模型可以利用数据的时间序列特性。研究了简单自编码器、变分自编码器和注意自编码器(AEA)的性能,得出在这3种自编码器采用seq2seq结构时检测性能优于全连接结构。仿真结果表明,带有注意力机制的检测器(AEA)检出率和虚警率分别比现有性能最好的检测器高4%~21%和4%~13%。
中圖分類號:TM28 文獻標(biāo)志碼:A DOI: 10.16157/j.issn.0258-7998.234395
中文引用格式: 黃燕,李金燦,楊霞琴,等. 基于深度自編碼器的智能電網(wǎng)竊電網(wǎng)絡(luò)攻擊異常檢測[J]. 電子技術(shù)應(yīng)用,2024,50(2):76-82.
英文引用格式: Huang Yan,Li Jincan,Yang Xiaqin,et al. Anomaly detection of smart grid stealing network attacks based on deep autoencoder[J]. Application of Electronic Technique,2024,50(2):76-82.
中文引用格式: 黃燕,李金燦,楊霞琴,等. 基于深度自編碼器的智能電網(wǎng)竊電網(wǎng)絡(luò)攻擊異常檢測[J]. 電子技術(shù)應(yīng)用,2024,50(2):76-82.
英文引用格式: Huang Yan,Li Jincan,Yang Xiaqin,et al. Anomaly detection of smart grid stealing network attacks based on deep autoencoder[J]. Application of Electronic Technique,2024,50(2):76-82.
Anomaly detection of smart grid stealing network attacks based on deep autoencoder
Huang Yan1,Li Jincan1,Yang Xiaqin2,Li Pei2,Li Zi3
1.State Grid Guangxi Power Supply Company,Nanning 530023, China;2.State Grid Nanning Power Supply Company,Nanning 530000, China;3.State Grid Wuzhou Power Supply Company,Wuzhou 543002, China
Abstract: Existing anomaly detectors in AMIs suffer from shallow architectures, which impede their ability to capture temporal correlations and complex patterns in electricity consumption data, thus impact detection performance adversely. A deep (stacked) autoencoder structure based on Long Short-Term Memory (LSTM) with a sequence-to-sequence (seq2seq) configuration is proposed. The depth of the autoencoder architecture is beneficial for capturing complex data patterns, and the seq2seq LSTM model effectively utilizes the temporal sequential characteristics of the data. The performance of simple autoencoders, variational autoencoders, and Attention Enhanced Autoencoders (AEA) was studied, revealing that using the seq2seq structure in these three types of autoencoders results in superior detection performance compared to fully connected architectures. Simulation results demonstrate that the detector with an attention mechanism (AEA) achieves a 4%~21% higher detection rate and a 4%~13% lower false alarm rate compared to the best-performing existing detectors.
Key words : autoencoder;deep machine learning;power stealing;hyperparameter optimization;sequence-to-sequence
引言
電力盜竊不僅會使電網(wǎng)過載,還會對電網(wǎng)的穩(wěn)定性和效率產(chǎn)生負面影響。因此提出了使用機器學(xué)習(xí)模型來識別電力盜竊[1-2]?;跈C器學(xué)習(xí)的檢測器包括監(jiān)督分類器和異常檢測器。監(jiān)督分類器包括淺層機器學(xué)習(xí)分類器,如樸素貝葉斯[3]和支持向量機(SVM)[4],還有基于決策樹和SVM的兩步檢測器[5]。雖然上述分類器檢測準(zhǔn)確率高,但過于依賴于客戶耗電數(shù)據(jù)的良性和惡意樣本的可用性,只能檢測到已經(jīng)訓(xùn)練過的攻擊類型。
本文詳細內(nèi)容請下載:
http://m.ihrv.cn/resource/share/2000005859
作者信息:
黃燕1,李金燦1,楊霞琴2,李佩2,李梓3
1.廣西電網(wǎng)有限責(zé)任公司,廣西 南寧 530023;2.廣西電網(wǎng)有限責(zé)任公司南寧供電局,廣西 南寧 530000; 3.廣西電網(wǎng)有限責(zé)任公司梧州供電局,廣西 梧州 543002

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。
