Article: Multi-agent deep reinforcement learning based resource management technique for vehicular networks in heterogeneous traffic Journal: International Journal of Mobile Communications (IJMC) 2026 Vol.28 No.2 pp.143 - 163 Abstract: Swift growth in vehicle to everything (V2X) communications has created new opportunities for advanced vehicular networking. Vehicle-to-vehicle communication plays a crucial role in supporting latency-critical and safety-related services under ultra-reliable low-latency communication (URLLC) requirements. However, the increasing number of vehicles and diverse quality-of-service demands make efficient resource management a challenging task. To address this, this work proposes a multi-agent deep reinforcement learning (DRL)-based resource allocation framework for joint channel and power optimisation in heterogeneous vehicular networks. Individual utility functions are designed for each vehicular user to capture heterogeneous traffic requirements. Unlike conventional single-agent DRL approaches, the proposed multi-agent deep deterministic policy gradient (MADDPG) method adopts centralised training with distributed execution, enabling better coordination among agents. Input and reward normalisation are applied to accelerate training convergence. Simulation results demonstrate that the proposed scheme outperforms duelling DQN, fixed power allocation, and other RL baselines, achieving up to 23% higher throughput and 15% fewer latency violations, validating its scalability and effectiveness for latency-sensitive V2X communications. Inderscience Publishers - linking academia, business and industry through research

Title: Multi-agent deep reinforcement learning based resource management technique for vehicular networks in heterogeneous traffic

Authors: N. Iswarya; R. Venkateswari

Addresses: Department of ECE, PSG Institute of Technology and Applied Research, Coimbatore, India ' Department of ECE, PSG College of Technology, Coimbatore, India

Abstract: Swift growth in vehicle to everything (V2X) communications has created new opportunities for advanced vehicular networking. Vehicle-to-vehicle communication plays a crucial role in supporting latency-critical and safety-related services under ultra-reliable low-latency communication (URLLC) requirements. However, the increasing number of vehicles and diverse quality-of-service demands make efficient resource management a challenging task. To address this, this work proposes a multi-agent deep reinforcement learning (DRL)-based resource allocation framework for joint channel and power optimisation in heterogeneous vehicular networks. Individual utility functions are designed for each vehicular user to capture heterogeneous traffic requirements. Unlike conventional single-agent DRL approaches, the proposed multi-agent deep deterministic policy gradient (MADDPG) method adopts centralised training with distributed execution, enabling better coordination among agents. Input and reward normalisation are applied to accelerate training convergence. Simulation results demonstrate that the proposed scheme outperforms duelling DQN, fixed power allocation, and other RL baselines, achieving up to 23% higher throughput and 15% fewer latency violations, validating its scalability and effectiveness for latency-sensitive V2X communications.

Keywords: resource management; heterogeneous network; multi-agent deep reinforcement learning; multi-agent deep deterministic policy gradient.

DOI: 10.1504/IJMC.2026.155420

International Journal of Mobile Communications, 2026 Vol.28 No.2, pp.143 - 163

Received: 12 Nov 2024
Accepted: 17 Oct 2025
Published online: 31 Jul 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Multi-agent deep reinforcement learning based resource management technique for vehicular networks in heterogeneous traffic

Keep up-to-date