分布式系统监控资源多目标优化分配  

Optimal Multi-objective Monitoring Resources Allocation in Distributed Systems

作　　者：何盼[1] 袁月[1] 吴开贵[2] 

机构地区：[1]中国科学院重庆绿色智能技术研究院,重庆401122 [2]重庆大学计算机学院,重庆400044

出　　处：《计算机科学》2014年第5期64-67,77,共5页Computer Science

基　　金：重庆市科技攻关计划项目(cstc2011ggC40008);重庆市自然科学基金项目(CSTC2011BB2064)资助

摘　　要：针对分布式系统松耦合和动态配置的特点,提出采用监控资源分配进行组件监控周期的选择以达到可靠性保障和资源优化的目的。为了建立监控资源分配模型,首先采用马尔可夫链理论分析了监控策略下的系统可靠性模型;其次分析了监控机制的两种不同代价;再次选择了系统可靠性约束下的多目标监控资源分配模型,它通过最小化监控代价选择恰当的组件监控周期;最后应用遗传算法解决该优化模型。通过实验验证了监控资源分配的必要性和在可靠性优化中的作用,实验表明:监控资源分配能够达到资源优化和可靠性保障的目的;与单目标资源分配相比,多目标分配能够达到更好的优化效果。Against the loosely coupled and dynamic configuration features of distributed systems,multi-objective monitoring resources allocation oriented at optimal monitoring interval selection was studied to achieve the balance between resources optimization and reliability maintenance.To propose the allocation model,first of all,the Markov chain theory was employed to analyze the reliability of systems under monitoring mechanism.Secondly,two different kinds of monitoring resources cost models were analyzed.On the top of that,a multi-objective monitoring resources allocation model was built under the system reliability constraint.This model chooses the appropriate monitoring rate for each component through minimizing the monitoring cost.Finally,a genetic algorithm was used to solve the allocation and optimization model.Experimental studies results prove the necessity and impact of monitoring resources allocation in reliability optimization.The results also show that monitoring resources allocation can help to achieve resources optimization and reliability maintenance.Comparing with single-objective resources allocation,multi-objective resources allocation approaches can get better optimization results.

关 键 词：监控资源分配 分布式系统 可靠性优化 马尔可夫链 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]