Deep Reinforcement Learning-Based V2V Partial Computation Offloading in Vehicular Fog Computing

Vehicular fog computing (VFC) has been expected as a promising paradigm that can improve the computational capability of vehicles, where vehicles can share their idle computing resource among each other. Considering the limited computational capability of a single vehicle and the short vehicle-to-vehicle (V2V) link duration, binary task offloading may suffer from the long execution time and the V2V link interruption, which may not be appropriate for some computation-intensive tasks. V2V partial computation offloading is expected to be a promising solution where tasks are divided into several parts and executed in multiple neighboring vehicles. However, due to the high-dynamic vehicular environment, it is challenging to design a scheme that can determine the service vehicles and the computing resource allocation both in local on-board CPU and in service vehicles for offloading tasks. To deal with these problems above, this paper develops a novel V2V partial computation offloading scheme and evaluates the service availability of neighboring vehicles in terms of their idle computing resource and the vehicle mobility. Moreover, the V2V partial offloading problem is formulated as a sequential decision making problem and solved by our proposed algorithm based on deep reinforcement learning (DRL). Finally, simulation results validate the effectiveness of our proposed mechanism.