Resource Allocation for Vehicle Platooning in 5G NR-V2X via Deep Reinforcement Learning

TL;DR

This paper proposes a deep reinforcement learning approach to resource allocation in vehicle platooning over 5G NR-V2X, significantly reducing collision probability compared to traditional random algorithms.

Contribution

The paper introduces a novel DRL-based resource allocation method for vehicle platooning in 5G V2X, improving collision avoidance over existing random selection schemes.

Findings

DRL algorithm reduces collision probability by up to 73%.

DRL outperforms random algorithms across various vehicle densities.

Analytical and simulation results validate the effectiveness of the proposed method.

Abstract

Vehicle platooning, one of the advanced services supported by 5G NR-V2X, improves traffic efficiency in the connected intelligent transportation systems (C-ITSs). However, the packet delivery ratio of platoon communication, especially in the out-of-coverage area, is significantly impacted by the random selection algorithms employed in the current resource allocation scheme. In this paper, we first analyze the collision probability via the random selection algorithm adopted in the current standard. Subsequently, we then investigate the deep reinforcement learning (DRL) algorithm that decreases the collision probability by letting the agent (vehicle) learn from the communication environment. Monte Carlo simulation is utilized to verify the results obtained in the analytical model and to compare the results between the two discussed algorithms. Numerical results show that the proposed DRL algorithm outperforms the random selection algorithm in terms of different vehicle density, which at least lowering the collision probability by 73% and 45% in low and high vehicle density respectively.