| 摘要: |
| 为解决移动边缘计算中面向用户的服务功能链（Service Function Chain,SFC）部署成本开销过大、时延过长问题，提出了针对SFC的支出成本与时延联合自适应优化的部署策略。首先，在虚拟网络功能（Virtualized Network Function,VNF）节点选取阶段，考虑路径损耗这一无线信道衰落问题，根据有线用户与无线用户的位置情况，选择当前最佳节点以降低SFC的响应时延。其次，在服务节点配置阶段，根据用户请求处理的数据内容的新鲜度记录，自适应动态增加和删减相应的缓存，利用资源感知算法在保证数据传递可靠性的同时，减少服务节点的配置个数，降低配置开销。最后，在SFC部署阶段，利用基于KSP（K-shortest Paths）的功耗感知算法确定最佳节点映射排序与通信链路，在减少通信链路重映射的同时还能保证部署的SFC的低成本与低时延。实验仿真结果表明，相比于已有方案，该方法能够有效降低部署成本与时延，并能对不同用户的SFC部署做到自适应优化，提高了SFC的部署成功率。 |
| 关键词: 移动边缘计算(MEC) 服务功能链(SFC) 虚拟网络功能(VNF) 自适应优化部署 |
| DOI：10.20079/j.issn.1001-893x.220719005 |
|
| 基金项目:国家自然科学基金资助项目(61761007) |
|
| Adaptive Optimal Deployment Strategy for Service Functional Chain in Mobile Edge Computing |
| XIONG Zekai,WANG Suhong,WANG Jingjun,ZHU Changhong,QIN Tuanfa |
| (a.School of Computer and Electronic Information;b.Guangxi Key Laboratory of Multimedia Communication and Network Technology,Guangxi University,Nanning 530004,China) |
| Abstract: |
| In order to solve the problems of high cost and long delay of service function chain(SFC) deployment in mobile edge computing,a joint adaptive optimization strategy for SFC cost and delay is proposed.First,on the mode of selecting virtualized network function(VNF) nodes,the optimal mode is selected to reduce the response delay of the SFC according to the locations of wired and wireless users.Second,in the stage of service node configuration,according to the freshness record of the data content processed by users,the corresponding cache is dynamically increased and deleted adaptively,and the resource-aware algorithm is used to reduce the number of service node configuration and the configuration cost while ensuring the reliability of data transmission.Finally,in SFC deployment phase,the optimal node mapping sequence and communication link are determined by using K-Shortest Paths(KSP) power sensing algorithm,which not only reduces the remapping of communication link,but also ensures the low cost and low delay of deployed SFC.Experimental simulation results show that compared with the existing schemes,the proposed method can effectively reduce deployment cost and delay,achieve adaptive optimization of SFC deployment for different users,and improve the success rate of SFC deployment. |
| Key words: mobile edge computing(MEC) service function chain(SFC) virtual network function(VNF) adaptive optimization |
《电讯技术》编辑部 