Dynamic Orchestration of Service Function Chain Based on Reinforcement Learning

Network Function Virtualization (NFV) technology decoupled Network functions from hardware resources to create more flexible Network services and support more flexible Network resource allocation. By matching and linking different virtual network functions (VNF) to form the Service Function Chain (SFC), NFV technology can provide users with end-to-end network services in a more flexible and rapid manner, and support the expansion and development of new services. In order to maintain the stability of network performance during the dynamic change of network demand, scaling is a basic task in SFC deployment. The key of the NFC scaling is the high accuracy of the time and scale quantity, which can avoid unnecessary resource provisioning and releasing process while maintaining network performance. In this paper, we propose a scaling mechanism based on Reinforcement Learning, which can make better decisions for managing network performance changes in dynamic workloads. Resource utilization is also introduced into the mechanism to avoid the idle waste of network resources. The simulation implements the scaling mechanism in a virtualized EPC network and the result proves that the proposed scaling mechanism has high accuracy in managing network performance and advantages in efficient utilization of network resources.