基于灰色预测的分布式系统动态故障检测服务  

Grey prediction based dynamic failure detection service for distributed systems

作　　者：田东[1] 毛太平[1] 吴长泽[2] 

机构地区：[1]贵州省电子计算机软件开发中心,贵州贵阳550000 [2]重庆大学 计算机学院,重庆400044

出　　处：《计算机工程与设计》2007年第24期5915-5918,共4页Computer Engineering and Design

基　　金：贵州科技工业攻关计划基金项目(黔科合gy字(2006)3025)

摘　　要：针对已有故障检测服务不能有效满足分布式系统需求问题,设计了一种适用于分布式系统的动态故障检测服务。根据分布式系统的特点,在定义分布式系统模型的基础上,提出了动态故障检测服务架构。结合心跳策略和灰色预测方法,设计了一种动态心跳机制,并给出了预测模型和动态预测策略,提出了基于该动态心跳机制的分布式系统的故障检测算法。最后,仿真实验验证了该算法的正确性和有效性。Aimed at the problem that existing failure detection methods can not satisfy the requirements of distributedsystems, a dynamic failure detection service is presented. Firstly, according to the characteristics of distributed systems, a three-layer dynamic failure detection service architecture is iUustrated based on the definition of system model. Secondly, combining grey theory with heartbeat strategy, the GM （1,1） model for predicting the arrival time of heartbeat messages in real-time manner is constructed, as well as the dynamic prediction strategy is given, moreover, the failure detection algorithm is presented in detail. At last, simulation results demonstrate the effectiveness and correctness of the method.

关 键 词：分布式系统 故障检测 服务 灰色预测 心跳机制 

分 类 号：TP338.8[自动化与计算机技术—计算机系统结构]