针对分布式系统的特点,提出了一种基于网格空间的测度属性关联度计算方法,并以此建立了网络模型来刻画分布式系统测度属性的关系;提出了基于隐马尔可夫模型的测度属性关系网络划分方法;利用最新监测的属性关联度信息,设计了基于测度属性关系网络划分的分布式系统异常检测算法;对多种攻击进行异常检测实验,从而验证了提出方法的有效性. In view of the characteristics of distributed system, this paper proposes a method to calculate the degree of relevance of measurement attributes based on grid space, and establishes a network model to describe the relationship between the measured attributes of distributed systems. A measure based on hidden Markov model Attribute relational network partitioning method. Based on the newly monitored attribute relational degree information, a distributed system anomaly detection algorithm based on measurement attribute relational network partitioning is designed. Anomaly detection experiments on a variety of attacks are carried out to verify the effectiveness of the proposed method.