基于遗传算法的SDN网络装箱问题研究  

Research on SDN Packing Problem Based on Genetic Algorithm

作　　者：何利文[1] 张幸宁 HE Liwen;ZHANG Xingning(Nanjing University of Posts and Telecommunications,Nanjing 210023)

机构地区：[1]南京邮电大学,南京210023

出　　处：《计算机与数字工程》2020年第3期633-637,共5页Computer & Digital Engineering

摘　　要：随着网络规模愈加庞大和复杂,运营商正处于逐渐从传统IP网络向SDN网络架构发展阶段。论文以SDN架构下的网络为研究对象,建立以最大带宽利用率最小化和新增业务后全局网络扰动最小为目标的网络模型,提出基于改进的遗传算法对复杂网络环境下的装箱问题进行求解。利用Java编写并模拟仿真当前运营商主流网络场景IPRAN,分析遗传算法和其他启发式算法,如粒子群,模拟退火算法在装箱问题的优化效果,验证所提出的改进遗传算法对于解决网络装箱问题的有效性。The size of internet has been undergoing the urgent swelling and the network applications have emerged diversity.The telecom operators are gradually evolving from traditional IP networks to SDN network architectures. On the basis of establishing the optimizing internet model on the aim of minimizing maximum bandwidth utilization and minimizing global network disturbances after adding new services,this paper presents an improved genetic algorithm for solving packing problem in a complex network environment. In addition,this paper designes the main internet environment of telecom operators by Java to verify the feasibility of the proposed algorithm. The simulation results show that the improved GA is effective,which improves the business loading and load balance compared with other algorithms,such as PSO and SA.

关 键 词：SDN网络 负载均衡 多目标遗传算法 网络业务装箱 

分 类 号：TP3-0[自动化与计算机技术—计算机科学与技术]