Reliable Service Function Chain Deployment Algorithm Based on Edge-Cloud Collaboration
In response to the challenges of diverse requests and massive data in the Internet of Vehicle(IoV),the edge-cloud collaboration architecture supported by Software Defined Networking(SDN)and Network Function Virtualization(NFV)technologies has emerged as an effective solution to the Service Function Chain(SFC)deployment problem.However,ubiquitous electromagnetic interference renders the Virtual Network Functions(VNFs)that comprise the SFC highly vulnerable within the IoV.As VNFs are software-based,they are susceptible to failure,which compromises the reliability of the SFC deployment process.To ensure reliable deployment of vehicle requests at minimal cost,a reliable edge-cloud collaboration vehicle-computing architecture is built based on SDN/NFV,which trains deployment models using centralized training and distributed inference.Furthermore,the SFC reliability enhancement algorithm SFC-RA is designed to enhance SFC reliability by introducing a Backup Virtual Network Function(BVNF)that mirrors the functionality of the original VNF.Finally,an online SFC reliable deployment algorithm PG_RA is proposed based on the Policy Gradient(PG)approach,and a sequence-to-sequence model is employed as an agent to provide highly reliable and cost-efficient services while adhering to resource constraints.Simulation results demonstrate that,compared to other redundancy methods and deployment algorithms,the SFC-RA algorithm reduces the redundancy cost by 2.78 to 6.33 units,and the PG_RA algorithm enhances reliability by an average of 12.88 percentage points,and decreases average latency by approximately 6.7％.
Internet of Vehicle(IoV)edge-cloud collaborationreliabilityService Function Chain(SFC)Deep Reinforcement Learning(DRL)Network Function Virtualization(NFV)
万方数据
维普
