Power Allocation for Delay Optimization in Device-to-Device Networks: A Graph Reinforcement Learning Approach
- 6 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (11) , 17396-17412
Abstract
The pursuit of rate maximization in wireless communication frequently encounters substantial challenges associated with user fairness. This paper addresses these challenges by exploring a novel power allocation approach for delay optimization, utilizing graph neural networks (GNNs)-based reinforcement learning (RL) in device-to-device (D2D) communication. The proposed approach incorporates not only channel state information but also factors such as packet delay, the number of backlogged packets, and the number of transmitted packets into the components of the state information. We adopt a centralized RL method, where a central controller collects and processes the state information. The central controller functions as an agent trained using the proximal policy optimization (PPO) algorithm. To better utilize topology information in the communication network and enhance the generalization of the proposed method, we embed GNN layers into both the actor and critic networks of the PPO algorithm. This integration allows for efficient parameter updates of GNNs and enables the state information to be parameterized as a low-dimensional embedding, which is leveraged by the agent to optimize power allocation strategies. Simulation results demonstrate that the proposed method effectively reduces average delay while ensuring user fairness, outperforms baseline methods, and exhibits scalability and generalization capability.Keywords
All Related Versions
Funding Information
- National Key R&D Program of China (2024YFE0200700)
- National Natural Science Foundation of China (62201145, 62261160576)
- Basic and Applied Basic Research Foundation of Guangdong Province (2025A1515011948)
- Shenzhen University (2024TBZZJH003)
This publication has 43 references indexed in Scilit:
- Mutual-Interference-Aware Throughput Enhancement in Massive IoT: A Graph Reinforcement Learning FrameworkIEEE Internet of Things Journal, 2024
- SOQ: Structural Reinforcement Learning for Constrained Delay Minimization With Channel State InformationIEEE Internet of Things Journal, 2023
- On the Road to 6G: Visions, Requirements, Key Technologies, and TestbedsIEEE Communications Surveys & Tutorials, 2023
- Graph-Reinforcement-Learning-Based Task Offloading for Multiaccess Edge ComputingIEEE Internet of Things Journal, 2021
- Intelligent Delay-Aware Partial Computing Task Offloading for Multiuser Industrial Internet of Things Through Edge ComputingIEEE Internet of Things Journal, 2021
- Graph neural networks: A review of methods and applicationsAI Open, 2020
- A Comprehensive Survey on Mobility-Aware D2D Communications: Principles, Practice and ChallengesIEEE Communications Surveys & Tutorials, 2019
- Next Generation 5G Wireless Networks: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2016
- Optimal Delay-Power Tradeoff in Wireless Transmission with Fixed Modulation2007
- Learning representations by back-propagating errorsNature, 1986