车载边缘计算中任务卸载和服务缓存的联合智能优化

针对车载环境下有限的网络资源和大量用户需求之间的矛盾,提出了智能驱动的车载边缘计算网络架构,以实现网络资源的全面协同和智能管理.基于该架构,设计了任务卸载和服务缓存的联合优化机制,对用户任务卸载以及计算和缓存资源的调度进行了建模.鉴于车载网络的动态、随机和时变的特性,利用异步分布式强化学习算法,给出了最优的卸载决策和资...

Joint intelligent optimization of task offloading and service caching for vehicular edge computing

Given the contradiction between limited network resources and massive user demands in Internet of vehicles,an intelligent vehicular edge computing network architecture was proposed to achieve the comprehensive cooperation and intelligent management of network resources.Based on this architecture,a joint optimization scheme of task offloading and service caching was furtherly devised,which formulated an optimization problem about how to offload tasks and allocate computation and cache resources.In view of the dynamics,randomness and time variation of vehicular networks,an asynchronous distributed reinforcement learning algorithm was employed to obtain the optimal task offloading and resource management policy.Simulation results demonstrate that the proposed algorithm achieves significant performance improvement in comparison with the other schemes.