摘要
虚拟计算环境R-Net的监测系统RNMS(R-Net monitoring system)把侵扰控制作为研究的一项重要内容,RNMS试图从多个方面来进行侵扰控制,并把重点放在监测数据采集阶段的侵扰控制上.基于自主元素的概念,介绍了主机传感器侵扰的自主控制机制及主要思想,在此基础上实现了自适应算法及多种控制策略.通过实际测试,介绍了传感器自主控制机制及算法策略的使用背景,并通过模拟测试,对不同策略和不同配置参数下的监测精度和开销进行了对比.与固定采样间隔策略相比,在保证精度的前提下,自适应策略下能够有效地降低侵扰.
RNMS （R-Net monitoring system）, the monitoring infrastructure of R-Net virtual computing environment, takes intrusiveness control as an important research objective. RNMS tries to control the intrusiveness in many aspects. Of them, RNMS focuses on intrusiveness control in the procedure of monitoring data acquisition. Based on the concept of autonomic element, autonomic host sensors intrusiveness control mechanism and main control thought are introduced, and adaptive sensor control algorithm and policies are implemented. By practical testing, the usage background of adaptive algorithm and policies are described. Then, the monitoring accuracy and overhead are compared in different policies and configuration parameters by simulating. Comparing with the non-control policy, on the precondition of ensuring the monitoring accuracy, the monitoring with the adaptive policies can effectively reduce intrusiveness.
出处
《软件学报》
EI
CSCD
北大核心
2007年第8期1987-2001,共15页
Journal of Software
基金
the National Natural Science Foundation of China under Grant No.90412001 (国家自然科学基金)
the National Basic Research Program of China under Grant No.2005CB321806 (国家重点基础研究发展计划(973))
