Learning Based Channel Allocation and Task Offloading in Temporary UAV-Assisted Vehicular Edge Computing Networks
Chao Yang, Baichuan Liu, Haoyu Li, Bo Li, Kan Xie, Shengli Xie
Abstract
High-level autonomous decision making system is one of the key technologies in intelligent transportation networks, it requires the traffic information within a certain range of vehicles in real time. When the traffic roads become congested or the roadside units (RSUs) are unaccessed beyond the communication range, the unmanned aerial vehicle (UAV)-assisted vehicular edge computing network (VECN) is considered as a potential solution. In this paper, we propose a learning based channel allocation and task offloading strategy in temporary UAV-assisted VECNs from a user perspective, in which the UAV passing temporarily can serve as the relay and edge computing node to support the decision making system. However, the limited available computation resources and time-varying communication channel states make it critical to process the received computing tasks. To address the above mentioned challenges, we design an efficient data transmission strategy combined the long-term evolution vehicle-to-everything (LTE-V2X) and time-division multiple access (TDMA) technologies firstly, then, we propose a multi-option task processing scheme, a service cost minimization problem is proposed where the integral decisions of channel allocation and task processing mode selection are jointly optimized. Under dynamic computing resources and the current data transmission conditions, the UAV selects an optimal task processing service model based on deep reinforcement learning (DRL) algorithm. Simulation results show the proposed strategy greatly improves the data transmission efficiency.