Decision Algorithm for Vehicle Task Offloading Based on Improved SMDP
Aimed at the overload problem of edge servers,the virtualization technology can be applied to integrate idle vehicles on the roadside and mobile vehicles into a resource pool to provide elastic services for delay-sensitive tasks.Therefore,a packet transmis-sion communication system model is established.In order to reduce the probability of channel collision in the binary exponential back-off algorithm(BEB),the minimum competition window is adjusted appropriately based on the number of vehicle nodes in the net-work.Considered the timing characteristics of resource allocation,a computational offloading strategy is proposed for vehicle edge computing(VEC)system based on the improved semi-Markov decision process(SMDP).With the optimal strategy of system action developed,the nonlinear weight factor with cosine term is introduced to dynamically weight the immediate reward and future expected reward.The iterative algorithm based on Bellman equation is utilized to achieve the maximum long-term reward.Simulation results show that the proposed strategy can effectively reduce the offloading delay,increase the throughput,and significantly improve the long-term reward of the system.
NETL
NSTL
万方数据
