SDN下分布式负载均衡博弈算法研究  

Research on Distributed Load Balancing Game Algorithm under SDN

作　　者：张霖 ZHANG Lin(The Institute of Artificial Intelligence and Big Data,Sichuan University of Arts and Sciences,Dazhou,China,635000;Dazhou Intelligent Manufacturing Industry Technology Research Institute,Dazhou,China,635000)

机构地区：[1]四川文理学院人工智能与大数据学院,四川达州635000 [2]达州智能制造产业技术研究院,四川达州635000

出　　处：《福建电脑》2024年第12期27-31,共5页Journal of Fujian Computer

基　　金：达州智能制造产业技术研究院2022年度开放基金(No.ZNZZ2216)资助。

摘　　要：随着互联网产业中数据流量的不断增长,数据中心服务器的处理能力和内存访问速度也不断提高。为解决升级硬件层面成本高、可扩展性差的问题,本文提出了一个基于分布式马尔可夫博弈的自适应负载均衡系统。系统利用SDN的全局视图与动态控制能力,结合分布式马尔可夫博弈模型,实现多VNF实例的智能调度与资源优化。仿真结果表明,相比于传统的集中式负载均衡算法,本文提出的算法在提高网络可扩展性及降低网络能耗方面具有明显优势。With the continuous growth of data traffic in the Internet industry,the processing capacity and memory access speed of the data center server are also increasing.To address the issues of high cost and poor scalability in upgrading hardware,this paper proposes an adaptive load balancing system based on distributed Markov game theory.By utilizing the global view and dynamic control capabilities of SDN,combined with a distributed Markov game model,intelligent scheduling and resource optimization of multiple VNF instances can be achieved.The simulation results show that compared to traditional centralized load balancing algorithms,the algorithm proposed in this paper has significant advantages in improving network scalability and reducing network energy consumption.

关 键 词：软件定义网络 负载均衡 博弈算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]