Collaborative optimization of Edge-Cloud Computation Offloading in Internet of Vehicles

Recently, as the traffic flow in the internet of vehicles increases, the conflict between the huge number of computing tasks and limited computation resources needs to be solved urgently. For the above situation, Mobile Cloud Computing (MCC) and Mobile Edge Computing (MEC) can usually serve as effective solutions. In this paper, we first develop a hierarchical edge computing model for time-varying mobile IoV-edge-cloud environment. Then we formulate a collaborative optimization problem to minimize the system cost by jointly optimizing offloading decision, the allocation of computation resource and bandwidth. Based on Reinforcement Learning (RL) method, we develop a Q-learning based algorithm to accomplish computation offloading and resource allocation. Numerical simulations verify the effectiveness of our proposed scheme by comparing with typical algorithms.