Resource Allocation based on Graph Neural Networks in Vehicular Communications
Authors:
- 1 December 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
In this article, we investigate spectrum allocation in vehicle-to-everything (V2X) network. We first express the V2X network into a graph, where each vehicle-to-vehicle (V2V) link is a node in the graph. We apply a graph neural network (GNN) to learn the low-dimensional feature of each node based on the graph information. According to the learned feature, multi-agent reinforcement learning (RL) is used to make spectrum allocation. Deep Q-network is utilized to learn to optimize the sum capacity of the V2X network. Simulation results show that the proposed allocation scheme can achieve near-optimal performance.Keywords
Funding Information
- National Science Foundation (1815637,1731017)
This publication has 14 references indexed in Scilit:
- Vehicular Communications: A Network Layer PerspectiveIEEE Transactions on Vehicular Technology, 2018
- Machine Learning for Vehicular Networks: Recent Advances and Application ExamplesIEEE Vehicular Technology Magazine, 2018
- Graph-Based Resource Sharing in Vehicular CommunicationIEEE Transactions on Wireless Communications, 2018
- Integrated Networking, Caching, and Computing for Connected Vehicles: A Deep Reinforcement Learning ApproachIEEE Transactions on Vehicular Technology, 2017
- Vehicular Communications: A Physical Layer PerspectiveIEEE Transactions on Vehicular Technology, 2017
- Resource Allocation for D2D-Enabled Vehicular CommunicationsIEEE Transactions on Communications, 2017
- Resource Management with Deep Reinforcement Learning2016
- Radio Resource Management for D2D-Based V2V CommunicationIEEE Transactions on Vehicular Technology, 2015
- LTE for vehicular networking: a surveyIEEE Communications Magazine, 2013
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008