基于联合优化的网络切片资源分配策略  

Network slicing resource allocation strategy based on joint optimization

作　　者：王再见[1,2] 谷慧敏 WANG Zaijian;GU Huimin(School of Physics and Electronic Information,Anhui Normal University,Wuhu 241002,China;Anhui Provincial Engineering Laboratory on Information Fusion and Control of Intelligent Robot,Wuhu 241002,China)

机构地区：[1]安徽师范大学物理与电子信息学院,安徽芜湖241002 [2]安徽省智能机器人信息融合与控制工程实验室,安徽芜湖241002

出　　处：《通信学报》2023年第5期234-245,共12页Journal on Communications

基　　金：安徽省自然科学基金资助项目(No.2008085MF222)。

摘　　要：为解决5G网络中各类应用差异性大对通信需求侧重点不同造成的网络资源利用率低的问题,提出一种基于联合优化的网络切片资源分配策略,旨在通过综合考虑切片间资源分配和切片内资源调度问题,最大化网络资源利用率和网络收益。首先,在切片间资源分配问题中定义一个切片用户平均满意度函数,基于切片用户数量、切片调度时延以及切片优先级等约束,提出基于用户服务质量(Qo S)的比例公平资源分配算法,以权衡各切片之间的公平性和用户需求。其次,在切片内资源调度问题中引入服务降级和资源迁移函数,针对拥塞和非拥塞2种情况为内部接入用户和外部接入用户分别建立价格模型。基于所提价格模型建立基站与用户之间的Stackelberg博弈,并采用一种低复杂度的全局搜索算法求解该博弈的最佳响应,使基站效用和用户效用最优。仿真结果表明,所提策略能够有效提高资源利用率和网络收益,并降低网络拥塞,较好地实现资源分配的公平性。To improve network resource utilization that was decreased by different applications with different requirements in 5G networks,a network slicing resource allocation strategy based on joint optimization was proposed,which was utilized to maximize both network resource utilization and network revenue by comprehensively considering in tra-slice and inter-slice resource schedule.Firstly,the user’s average satisfaction function was defined in the inter-slicing resource allocation problem.Furthermore,in terms of the number of users,slicing schedule delay and priority,a proportional fair resource allocation algorithm based on quality of service(QoS)was proposed,which was employed to achieve the best tradeoff between fairness and the users’requirements among slices.Secondly,after two functions(service degradation and resource migration)were introduced in the inter-slice resource schedule problem,two price models were established for internal access users and external access users respectively,where congestion and non-congestion conditions were analyzed.According to the proposed price models,a Stackelberg game between the base station and users was constructed,and a global search algorithm with low complexity was leveraged to obtain the best response of the game,where the best tradeoff between the base station revenue and user utility was obtained.Simulation results show that the proposed strategy can effectively improve resource utilization and network revenue while reducing network congestion.Therefore,it can better realize fairness in resource allocation.

关 键 词：资源分配 网络切片 比例公平 STACKELBERG博弈 

分 类 号：TN929.5[电子电信—通信与信息系统]