摘要
对传统方法调度大象流时容易造成数据中心网络拥塞等问题进行研究,提出一种基于蚁群优化的动态负载均衡(Dynamic Load Balancing based on Ant Colony Optimization,DLB-ACO)算法。该算法通过计算一个周期的链路负载方差,降低瞬时负载极值对负载均衡度的影响,避免资源浪费,再对蚁群算法的路径选择概率引入混沌策略和分段调节挥发因子,使算法具有较强的全局搜索能力和较高的收敛速度,从而提高全局最优路径计算的概率。实验结果表明,与等价多径路由(Equal Cost Multi Path,ECMP)算法和全局优先匹配流量调度(Global First Fit,GFF)算法对比,所提算法提高了网络的链路利用率和吞吐量,并且降低了时延。
For the problem that the traditional method of scheduling elephant flow easily causes network congestion in data center,a dynamic load balancing algorithm based on ant colony optimization is proposed.By introducing cycle time to load balance degree,the influence of instantaneous load extreme value on load balance degree is reduced,and the waste of resources is avoided.Chaos strategy and piecewise volatile factor are introduced into the path selection probability of ant colony algorithm,which makes the algorithm have strong global search ability and high convergence speed,and can calculate the global optimal path.Experiment results show that compared with equal-cost multi-path routing(ECMP)and the global first fit(GFF)traffic scheduling algorithms,the proposed algorithm improves the link utilization and throughput of the network,and reduces the delay.
作者
朱国晖
史思潮
翟鹏宇
ZHU Guohui;SHI Sichao;ZHAI Pengyu(School of Communications and Information Engineering,Xi’an University of Posts and Telecommunications,Xi’an 710121,China)
出处
《西安邮电大学学报》
2022年第5期11-17,共7页
Journal of Xi’an University of Posts and Telecommunications
基金
国家自然科学基金项目(61371087)。
关键词
数据中心网络
大象流
负载均衡度
蚁群优化算法
data center networks
scheduling elephant
load balance degree
ant colony optimization algorithm
