基于多视角低秩分析的电力状态不良数据检测  

An Approach for Detecting Band Data in Smart Grid Based on Low-Rank Multi-View Analysis

作　　者：李永攀 彭伟伦 门锟 吴俊阳 LI Yong-pan;PENG Wei-lun;MEN Kun;WU Jun-yang(Shenzhen Power Supply Co.,Ltd. Shenzhen Guangdong 518001;Sichuan Energy Internet Research Institute,Tsinghua University Chengdu 610213)

机构地区：[1]深圳供电局有限公司,广东深圳518001 [2]清华四川能源互联网研究院,成都610213

出　　处：《电子科技大学学报》2019年第3期361-365,共5页Journal of University of Electronic Science and Technology of China

摘　　要：随着信息化技术在智能电网的应用逐步深入,在智能电网的运维中能及时自动检测到不良数据,如网络攻击数据和设备故障数据,对电网的稳定和持续运行有着重要意义。该文提出一种基于多视角低秩分析的电力状态不良数据检测算法。该算法使用来自多个观测源的观测数据综合估计电力系统的状态,算法使用低秩模型挖掘出来自多个观测源数据间的共享本真数据,同时使用稀疏模型对不良数据建模。针对所提出的目标方程,给出了一种基于交叉迭代的优化算法。最后,在IEEE多个节点测试系统上的实验证明了该算法相对于已有算法的先进性。With the widely deployment of information techniques in smart grid, it is quite important to automatically detect the bad data, e.g., malicious injection data and unfunctional sensor data, from daily observations. In this paper, we propose a novel approach for bad data detection in smart grid based on multi-view low-rank analysis. Specifically, the proposed method estimates the grid state by analyzing the data collected from multiple sources. A low-rank function is learned to unveil the shared true data from observations, and the sparsity of data is applied to formulate bad data. Furthermore, an iterative optimization algorithm is proposed to solve the objective function. At last, extensive experiments on several IEEE bus systems verify the superiority of the proposed method.

关 键 词：网络空间安全 低秩表示 多视角学习 电力状态估计 

分 类 号：TM769[电气工程—电力系统及自动化]