摘要
在网络功能虚拟化的移动核心网中,提出了一种基于服务功能链(SFC)部署与计算资源分配联合算法.首先考虑SFC中虚拟网络功能(VNF)计算资源分配对处理时延的影响,建立SFC部署与计算资源分配联合优化问题,实现SFC的部署成本和端到端时延加权和的最小化.其次,为了求解所提优化问题,利用多智能体深度确定性策略梯度算法,从SFC各VNF的历史数据中学习策略指导即时的通用服务器节点选择和计算资源分配,提出了相应的SFC部署与计算资源分配联合算法.仿真结果表明,所提算法可以在保证SFC的服务质量需求的条件下实现部署成本和端到端时延的有效权衡.
In the mobile core networks,a service function chain (SFC) deployment and computation resource allocation joint algorithm for network function virtualization is proposed. Considering the impact of computation resource allocation of virtual network function (VNF) on processing delay in the SFC,a joint optimization problem of SFC deployment and computation resource allocation is established to minimize the weighted sum of deployment cost and end to end service delay of SFCs. To deal with the proposed problem,the multi-agent deep deterministic policy gradient algorithm is used to learn the strategy from the historical data of each VNF in the SFC to guide the immediate selection of general server nodes and computation resource allocation,based on which,a SFC deployment and computation resource allocation joint algorithm is proposed. Simulations show that the proposed algorithm can achieve an effective trade-off between deployment cost and end to end service delay while ensuring quality of service requirements of SFCs.
作者
张天魁
王筱斐
杨立伟
杨鼎成
ZHANG Tian-kui;WANG Xiao-fei;YANG Li-wei;YANG Ding-cheng(School of Information and Communication Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China;College of Information and Electrical Engineering,China Agricultural University,Beijing 100083,China;School of Information Engineering,Nanchang University,Nanchang 330031,China)
出处
《北京邮电大学学报》
EI
CAS
CSCD
北大核心
2021年第1期7-13,共7页
Journal of Beijing University of Posts and Telecommunications
基金
国家自然科学基金项目(61971060)。
关键词
移动核心网
服务功能链
计算资源
多智能体深度确定性策略梯度
mobile core network
service function chain
computation resource
multi-agent deep deterministic policy gradient