智能电网中的隐匿虚假数据入侵(False data injection,FDI)攻击能够绕过坏数据检测机制,导致控制中心做出错误的状态估计,进而干扰电力系统的正常运行.由于电网系统具有复杂的拓扑结构,故基于传统机器学习的攻击信号检测方法存在维度过...智能电网中的隐匿虚假数据入侵(False data injection,FDI)攻击能够绕过坏数据检测机制,导致控制中心做出错误的状态估计,进而干扰电力系统的正常运行.由于电网系统具有复杂的拓扑结构,故基于传统机器学习的攻击信号检测方法存在维度过高带来的过拟合问题,而深度学习检测方法则存在训练时间长、占用大量计算资源的问题.为此,针对智能电网中的隐匿FDI攻击信号,提出了基于拉普拉斯特征映射降维的神经网络检测学习算法,不仅降低了陷入过拟合的风险,同时也提高了隐匿FDI攻击检测学习算法的泛化能力.最后,在IEEE57-Bus电力系统模型中验证了所提方法的优点和有效性.展开更多
Affinity propagation(AP)is a classic clustering algorithm.To improve the classical AP algorithms,we propose a clustering algorithm namely,adaptive spectral affinity propagation(AdaSAP).In particular,we discuss why AP ...Affinity propagation(AP)is a classic clustering algorithm.To improve the classical AP algorithms,we propose a clustering algorithm namely,adaptive spectral affinity propagation(AdaSAP).In particular,we discuss why AP is not suitable for non-spherical clusters and present a unifying view of nine famous arbitrary-shaped clustering algorithms.We propose a strategy of extending AP in non-spherical clustering by constructing category similarity of objects.Leveraging the monotonicity that the clusters’number increases with the self-similarity in AP,we propose a model selection procedure that can determine the number of clusters adaptively.For the parameters introduced by extending AP in non-spherical clustering,we provide a grid-evolving strategy to optimize them automatically.The effectiveness of AdaSAP is evaluated by experiments on both synthetic datasets and real-world clustering tasks.Experimental results validate that the superiority of AdaSAP over benchmark algorithms like the classical AP and spectral clustering algorithms.展开更多
文摘智能电网中的隐匿虚假数据入侵(False data injection,FDI)攻击能够绕过坏数据检测机制,导致控制中心做出错误的状态估计,进而干扰电力系统的正常运行.由于电网系统具有复杂的拓扑结构,故基于传统机器学习的攻击信号检测方法存在维度过高带来的过拟合问题,而深度学习检测方法则存在训练时间长、占用大量计算资源的问题.为此,针对智能电网中的隐匿FDI攻击信号,提出了基于拉普拉斯特征映射降维的神经网络检测学习算法,不仅降低了陷入过拟合的风险,同时也提高了隐匿FDI攻击检测学习算法的泛化能力.最后,在IEEE57-Bus电力系统模型中验证了所提方法的优点和有效性.
基金This work was supported by the National Natural Science Foundation of China(71771034,71901011,71971039)the Scientific and Technological Innovation Foundation of Dalian(2018J11CY009).
文摘Affinity propagation(AP)is a classic clustering algorithm.To improve the classical AP algorithms,we propose a clustering algorithm namely,adaptive spectral affinity propagation(AdaSAP).In particular,we discuss why AP is not suitable for non-spherical clusters and present a unifying view of nine famous arbitrary-shaped clustering algorithms.We propose a strategy of extending AP in non-spherical clustering by constructing category similarity of objects.Leveraging the monotonicity that the clusters’number increases with the self-similarity in AP,we propose a model selection procedure that can determine the number of clusters adaptively.For the parameters introduced by extending AP in non-spherical clustering,we provide a grid-evolving strategy to optimize them automatically.The effectiveness of AdaSAP is evaluated by experiments on both synthetic datasets and real-world clustering tasks.Experimental results validate that the superiority of AdaSAP over benchmark algorithms like the classical AP and spectral clustering algorithms.
