Research on dynamic orchestration of service function chain based on deep reinforcement learning in mobile edge computing scenarios
Mobile edge computing(MEC)is one of the key technologies of the fifth generation of mobile communication technol-ogy(5G)to provide low-latency network services on the side close to the user.In order to solve the problem of difficult network service delivery due to physical resource constraints of edge devices and time-varying network resources in mobile edge compu-ting scenarios,a service function chain orchestration architecture for constrained physical networks was proposed for service function chain(SFC)orchestration,and a general model of service function chain orchestration was constructed by comprehen-sively considering the performance constraints of the network and the computational and storage resource constraints of the edge devices.A dynamic service function chaining algorithm based on deep reinforcement learning(DRL)algorithm was proposed.The simulation results showed that the proposed algorithm reduced end-to-end latency by 18％and reduced the occupancy of computing and storage resources while satisfying constraint conditions.
mobile edge computingsoftware-defined networkingnetwork function virtualizationservice function chainingdeep reinforcement learning
NETL
NSTL
万方数据
