Reinforcement Learning Based Computation Offloading in Vehicular Edge Computing

Qiaoxin chen

Keywords: edge computing, Internet of Vehicles, Deep Reinforcement Learning

Abstract: This paper designs a transmission model in VEC to improve the communication range of each vehicle, which considers the trust relationship and communication interference between edge servers. An offloading strategy based on a Deep Q-network algorithm is proposed, which can promote the convergence of the deep reinforcement learning algorithm. Simulation results show that the proposed scheme has the best convergence compared to other benchmark algorithms.

Submission Number: 6