VNF-FG design and VNF placement for 5G mobile networks

作     者：Jiuyue CAO Yan ZHANG Wei AN Xin CHEN Jiyan SUN Yanni HAN 

作者机构：State Key Laboratory of Information Security Institute of Information EngineeringChinese Academy of Sciences 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2017年第60卷第4期

页      面：17-31页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported in part by National Science Foundation of China (Grant Nos. 61303250, 61302031) Strategic Pilot Project of Chinese Academy of Sciences (Grant No. XDA06010306) Scientific Research Foundation of the Institute of Information Engineering, Chinese Academy of Sciences (Grant No. Y6Z0011105) 

主　　题：network function virtualization VNF-FG design VNF placement multi-objective optimization genetic algorithm 

摘      要：Network function virtualization(NFV) is envisioned as one of the critical technologies in 5thGeneration(5G) mobile networks. This paper investigates the virtual network function forwarding graph(VNFFG) design and virtual network function(VNF) placement for 5G mobile networks. We first propose a two-step method composed of flow designing and flow combining for generating VNF-FGs according to network service requests. For mapping VNFs in the generated VNF-FG to physical resources, we then modify the hybrid NFV environment with introducing more types of physical nodes and mapping modes for the sake of completeness and practicality, and formulate the VNF placement optimization problem for achieving lower bandwidth consumption and lower maximum link utilization simultaneously. To resolve this problem, four genetic algorithms are proposed on the basis of the frameworks of two existing algorithms(multiple objective genetic algorithm and improved non-dominated sorting genetic algorithm). Simulation results show that Greedy-NSGA-II achieves the best performance among our four algorithms. Compared with three non-genetic algorithms(random, backtracking mapping and service chains deployment with affiliation-aware), Greedy-NSGA-II reduces 97.04%, 87.76% and88.42% of the average total bandwidth consumption, respectively, and achieves only 13.81%, 25.04% and 25.41%of the average maximum link utilization, respectively. Moreover, using our VNF-FG design method and GreedyNSGA-II together can also reduce the total bandwidth consumption remarkably.