State estimation plays a vital role in the stable operation of modern power systems,but it is vulnerable to cyber attacks.False data injection attacks(FDIA),one of the most common cyber attacks,can tamper with measure...State estimation plays a vital role in the stable operation of modern power systems,but it is vulnerable to cyber attacks.False data injection attacks(FDIA),one of the most common cyber attacks,can tamper with measure-ment data and bypass the bad data detection(BDD)mechanism,leading to incorrect results of power system state estimation(PSSE).This paper presents a detection framework of FDIA for PSSE based on graph edge-conditioned convolutional networks(GECCN),which use topology information,node features and edge features.Through deep graph architecture,the correlation of sample data is effectively mined to establish the mapping relationship between the estimated values of measurements and the actual states of power systems.In addition,the edge-conditioned convolution operation allows processing data sets with different graph structures.Case studies are undertaken on the IEEE 14-bus system under different attack intensities and degrees to evaluate the performance of GECCN.Simulation results show that GECCN has better detection performance than convolutional neural networks,deep neural net-works and support vector machine.Moreover,the satisfactory detection performance obtained with the data sets of the IEEE 14-bus,30-bus and 118-bus systems verifies the effective scalability of GECCN.展开更多
信息通信技术的发展和智能设备的引入使电力系统逐渐演变为电力信息物理系统,而信息层与物理层之间的深度耦合也加剧了电力系统遭受网络攻击的风险。虚假数据注入攻击(false data injection attack,FDIA)作为一种兼具隐蔽性、灵活性和...信息通信技术的发展和智能设备的引入使电力系统逐渐演变为电力信息物理系统,而信息层与物理层之间的深度耦合也加剧了电力系统遭受网络攻击的风险。虚假数据注入攻击(false data injection attack,FDIA)作为一种兼具隐蔽性、灵活性和攻击导向性的网络攻击方式,对电力数据采集与监控(supervisory control and data acquisition,SCADA)系统的安全稳定构成很大威胁。为应对这一威胁挑战,学者们研究了各种各样的FDIA检测方法。该文对面向电力SCADA系统的FDIA检测方法进行综述,首先介绍了FDIA的攻击原理及构建方法,梳理了FDIA检测算法的发展历程,并按照模型驱动和数据驱动对算法进行了分类整理,针对模型驱动中的基于状态估计、图论、物理特性等检测方法和数据驱动中的有监督学习、无监督学习、半监督学习、对抗博弈学习和强化学习等检测方法分别进行了机理分析;然后对比分析了相关算法的检测性能、优缺点及其适用场景;最后,对FDIA检测防御的后续研究方向进行了展望。展开更多
虚假数据注入攻击(false data injection attack,FDIA)是智能电网安全与稳定运行面临的严重威胁。文中针对FDIA检测中存在的有标签数据稀少、正常和攻击样本极不平衡的问题,提出了融合无监督和有监督学习的FDIA检测算法。首先引入对比...虚假数据注入攻击(false data injection attack,FDIA)是智能电网安全与稳定运行面临的严重威胁。文中针对FDIA检测中存在的有标签数据稀少、正常和攻击样本极不平衡的问题,提出了融合无监督和有监督学习的FDIA检测算法。首先引入对比学习捕获少量攻击数据特征,生成新的攻击样本实现数据扩充;然后利用多种无监督检测算法对海量的无标签样本进行特征自学习,解决有标签样本稀缺的问题;最后将无监督算法提取的特征与历史特征集进行融合,在新的特征空间上构建有监督XGBoost分类器进行识别,输出正常或异常的检测结果。在IEEE 30节点系统上的算例分析表明,与其他FDIA检测算法相比,文中方法增强了FDIA检测模型在有标签样本稀少和数据不平衡情况下的稳定性,提升了FDIA的识别精度并降低了误报率。展开更多
基金supported in part by the Key-Area Research and Development Program of Guangdong Province under Grant 2020B010166004in part by the Guangdong Basic and Applied Basic Research Foundation under Grant 2020A1515111100+1 种基金in part by the National Natural Science Foundation of China under Grant 52207106in part by the Open Fund of State Key Laboratory of Operation and Control of Renewable Energy&Storage Systems(China Electric Power Research Institute)under Grant KJ80-21-001.
文摘State estimation plays a vital role in the stable operation of modern power systems,but it is vulnerable to cyber attacks.False data injection attacks(FDIA),one of the most common cyber attacks,can tamper with measure-ment data and bypass the bad data detection(BDD)mechanism,leading to incorrect results of power system state estimation(PSSE).This paper presents a detection framework of FDIA for PSSE based on graph edge-conditioned convolutional networks(GECCN),which use topology information,node features and edge features.Through deep graph architecture,the correlation of sample data is effectively mined to establish the mapping relationship between the estimated values of measurements and the actual states of power systems.In addition,the edge-conditioned convolution operation allows processing data sets with different graph structures.Case studies are undertaken on the IEEE 14-bus system under different attack intensities and degrees to evaluate the performance of GECCN.Simulation results show that GECCN has better detection performance than convolutional neural networks,deep neural net-works and support vector machine.Moreover,the satisfactory detection performance obtained with the data sets of the IEEE 14-bus,30-bus and 118-bus systems verifies the effective scalability of GECCN.
文摘信息通信技术的发展和智能设备的引入使电力系统逐渐演变为电力信息物理系统,而信息层与物理层之间的深度耦合也加剧了电力系统遭受网络攻击的风险。虚假数据注入攻击(false data injection attack,FDIA)作为一种兼具隐蔽性、灵活性和攻击导向性的网络攻击方式,对电力数据采集与监控(supervisory control and data acquisition,SCADA)系统的安全稳定构成很大威胁。为应对这一威胁挑战,学者们研究了各种各样的FDIA检测方法。该文对面向电力SCADA系统的FDIA检测方法进行综述,首先介绍了FDIA的攻击原理及构建方法,梳理了FDIA检测算法的发展历程,并按照模型驱动和数据驱动对算法进行了分类整理,针对模型驱动中的基于状态估计、图论、物理特性等检测方法和数据驱动中的有监督学习、无监督学习、半监督学习、对抗博弈学习和强化学习等检测方法分别进行了机理分析;然后对比分析了相关算法的检测性能、优缺点及其适用场景;最后,对FDIA检测防御的后续研究方向进行了展望。
文摘虚假数据注入攻击(false data injection attack,FDIA)是智能电网安全与稳定运行面临的严重威胁。文中针对FDIA检测中存在的有标签数据稀少、正常和攻击样本极不平衡的问题,提出了融合无监督和有监督学习的FDIA检测算法。首先引入对比学习捕获少量攻击数据特征,生成新的攻击样本实现数据扩充;然后利用多种无监督检测算法对海量的无标签样本进行特征自学习,解决有标签样本稀缺的问题;最后将无监督算法提取的特征与历史特征集进行融合,在新的特征空间上构建有监督XGBoost分类器进行识别,输出正常或异常的检测结果。在IEEE 30节点系统上的算例分析表明,与其他FDIA检测算法相比,文中方法增强了FDIA检测模型在有标签样本稀少和数据不平衡情况下的稳定性,提升了FDIA的识别精度并降低了误报率。
