基于Fuzzy的负载调度算法在CDN中的应用研究  

Load Scheduling Algorithm for CDN Using Fuzzy Reasoning

作　　者：梁凯 LIANG Kai(Luoyang Institute of Science and Technology,Luoyang 471023,China)

机构地区：[1]洛阳理工学院现代教育技术中心,河南洛阳471023

出　　处：《洛阳理工学院学报（自然科学版）》2018年第3期61-65,共5页Journal of Luoyang Institute of Science and Technology：Natural Science Edition

摘　　要：针对负载调度中请求延时期间的负载波动情况自适应性较差、平均响应时间分布不均等问题,提出了一种基于模糊逻辑的自适应算法,以服务器队列长度、服务时间、响应时间等模糊变量为输入,应用27种推理规则,得到模糊输出集。仿真实验结果表明,能够根据节点服务器负载的动态变化实现自我调整,降低各服务器的最小响应时间,实现服务器集群的负载均衡。In order to solve the problem of poor adaptability and unequal distribution of average response time for load fluctuation during request delay in load scheduling, an adaptive algorithm based on fuzzy logic is proposed. It takes fuzzy variables such as server queue length, service time, response time, ete. for input, applying 27 inference rules to obtain a fuzzy output set. The simulation results show that it can self-adjust according to the dynamic changes of the node server load, minimize response time of each server and a- chieve server cluster load balancing.

关 键 词：负载均衡 模糊推理 镜像服务器 内容分发网络 

分 类 号：TP331[自动化与计算机技术—计算机系统结构]