基于反馈的改进动态负载均衡策略  

Improved Dynamic Load Balancing Strategy Based on Feedback

作　　者：陈超[1] 赵跃龙[1] 王文丰[2] 潘敏[1] 

机构地区：[1]华南理工大学计算机科学与工程学院,广州510640 [2]南昌工程学院计算机科学与技术系,南昌330099

出　　处：《计算机工程》2010年第14期34-36,39,共4页Computer Engineering

基　　金：国家自然科学基金资助项目(60573145);广州市科技计划基金资助项目(2007J1-C0401);高等学校博士点专项科研基金资助项目(200805610019)

摘　　要：针对集群系统中的负载均衡问题,提出一种基于反馈的改进动态负载均衡策略。该策略结合周期反馈原理,将更新间隔分为若干个相等的子时间间隔,在每一个子时间间隔内引入一定的随机性来分发请求,同时利用排队论对集群系统的工作过程进行建模,获得该模型下系统性能的计算公式。仿真结果表明,与AggressiveLI策略相比,该策略能够以较小的计算开销获得与之相当的系统性能,且实现复杂度较小。For the load balancing problem of cluster system,an improved dynamic load balancing strategy based on feedback is introduced.Combined with periodic feedback theory,the strategy divides update interval into several equal subintervals,and adopts a random mechanism to distribute requests in each subinterval.The model of the process of cluster system is founded based on queuing theory and the formula for calculating the system performance is obtained.Simulation results show that,compared with Aggressive LI strategy,this strategy can attain equivalent performance at the expense of smaller cost,and has small complexity of implementation.

关 键 词：负载均衡 反馈 分时 集群 排队论 

分 类 号：N945[自然科学总论—系统科学]