Intelligent Computation Offloading for MEC-Based Cooperative Vehicle Infrastructure System: A Deep Reinforcement Learning Approach

In the cooperative vehicle infrastructure system, the road side unit (RSU) equipped with a mobile edge computing (MEC) server and sensors could provide vehicle infrastructure cooperation services for vehicles, such as optimization and cooperative driving, enhanced visibility, and so on. In view of this, the MEC server needs to fuse the sensing information from sensors on the vehicles and RSU, respectively. In the case of bad channel conditions, uploading the raw sensing information from the vehicles results in high uplink transmission latency. To deal with it, the vehicles can process the information locally and just deliver the results to the RSU. However, due to the limited computing resources on the vehicles, the processing accuracy of the raw information on the vehicles is lower than that on the MEC server. Besides, processing locally leads to higher vehicle energy consumption. Thus, in this paper, we aim to jointly optimize execution latency, processing accuracy, and energy consumption of the MEC-based cooperative vehicle infrastructure system. Firstly, we design the terminal machine learning task model and the edge machine learning task model on the vehicle side and RSU side, respectively. Then, we formulate a long-term multi-objective optimization problem. Owing to the stochastic traffic and time-varying communication conditions, we reformulate it as a Markov decision process and propose a two-stage deep reinforcement learning-based offloading and resource allocation (TDORA) strategy to determine the task offloading and the transmit power of each vehicle. Simulation results demonstrate the efficacy of the proposed strategy.

Automated summary

This paper investigates the optimization of execution latency, processing accuracy, and energy consumption in the MEC-based cooperative vehicle infrastructure system. By designing machine learning task models for the vehicle side and RSU side, and employing a two-stage deep reinforcement learning strategy, the problem of task offloading and resource allocation is effectively addressed.