EdgeSAC: Graph Neural Soft Actor-Critic for Hierarchical IoV Resource Management
- 7 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-13
Abstract
Intelligent Transportation Systems (ITS) rely on the Internet of Vehicles (IoV) to sustain high data rates and low latency under dynamic and heterogeneous conditions. Joint power and spectrum control across macro and micro tiers remains challenging due to mobility, interference coupling, and large continuous action spaces. EdgeSAC is a graph-aware Soft Actor Critic (SAC) framework executed at the edge for power control in hierarchical Fifth-Generation New Radio (5G NR) Multiple-Input Multiple-Output (MIMO) networks. A permutation-equivariant Graph Neural Network (GNN) with edge updates encodes co-channel interference among Base Stations (BSs) and outputs node-level power fractions under tier budgets. An on-demand scheduler activates fixed-size channels and assigns at most one macro and one micro resource per user to realize dual connectivity. Signal-to-Interference-plus-Noise Ratio (SINR) is mapped to rate using a Shannon with gap model with rank adaptive MIMO, enabling tier aggregation without action discretization. In simulation with Third Generation Partnership Project (3GPP) TR 38.901 path loss and Manhattan mobility, EdgeSAC increases throughput over SAC and Proximal Policy Optimization (PPO) and reduces power relative to Twin Delayed Deep Deterministic Policy Gradient (TD3), which raises energy efficiency and fairness. The findings indicate that interference-aware graph embeddings combined with entropy regularized continuous control provide a scalable and power-efficient solution for hierarchical IoV resource management.Keywords
Funding Information
- National Natural Science Foundation of China (62372307)
- Science, Technology and Innovation Commission of Shenzhen Municipality (KCXFZ20230731094001003)
- Basic and Applied Basic Research Foundation of Guangdong Province (2024A1515011691)
- Shenzhen Science and Technology Program (RCYX20231211090129039)
- Shenzhen Science and Technology Foundation (JCYJ20230808105906014)
- Key research and development program in Xinjiang Uygur Autonomous Region (2025B04019-001)
- Guangdong Provincial Key Laboratory of Integrated Communication
- Sensing and Computation for Ubiquitous IoT (2023B1212010007)
- Project of DEGP (2023KCXTD042)
- Hospital IoT Branch of China Association of Medical Equipment
- Annual Hospital IoT Innovation and Development Project (YYWLW2026ZD-010)
- Intelligent Computing Center of Shenzhen University
This publication has 32 references indexed in Scilit:
- Fair Resource Allocation for Hierarchical Federated Edge Learning in Space-Air-Ground Integrated Networks via Deep Reinforcement Learning With Hybrid ControlIEEE Journal on Selected Areas in Communications, 2024
- Joint Computation Offloading and Multidimensional Resource Allocation in Air–Ground Integrated Vehicular Edge Computing NetworkIEEE Internet of Things Journal, 2024
- Cooperative Hierarchical Deep Reinforcement Learning-Based Joint Sleep and Power Control in RIS-Aided Energy-Efficient RANIEEE Transactions on Cognitive Communications and Networking, 2024
- Implementing Graph Neural Networks Over Wireless Networks via Over-the-Air Computing: A Joint Communication and Computation FrameworkIEEE Wireless Communications, 2023
- Joint Sensing and Communications for Deep Reinforcement Learning-based Beam Management in 6G2022
- Decentralized Power Allocation for MIMO-NOMA Vehicular Edge Computing Based on Deep Reinforcement LearningIEEE Internet of Things Journal, 2021
- A DRL Agent for Jointly Optimizing Computation Offloading and Resource Allocation in MECIEEE Internet of Things Journal, 2021
- Multi-Agent Reinforcement Learning Based Resource Management in MEC- and UAV-Assisted Vehicular NetworksIEEE Journal on Selected Areas in Communications, 2020
- Understanding Failures of Deterministic Actor-Critic with Continuous Action Spaces and Sparse Rewards2020
- Decentralized Deep Reinforcement Learning for Delay-Power Tradeoff in Vehicular Communications2019