Graph Neural Networks for Resource Allocation in Multi-Channel Wireless Networks

2025-06-04

AI Summary

In multi-channel wireless networks, severe interference and low efficiency of joint channel and power allocation (JCPA) hinder spectral utilization and scalability. Method: This paper proposes JCPGNN-M, a graph neural network (GNN)-driven framework for JCPA. It is the first to deeply integrate Lagrangian dual optimization with GNNs, enabling end-to-end learnable concurrent multi-channel access and spectrum reuse. Departing from conventional single-channel constraints, it supports scalable deployment in dense networks and cross-network generalization. Enhanced WMMSE initialization and iterative Lagrange multiplier updates are incorporated to improve convergence and solution quality. Results: Experiments demonstrate that JCPGNN-M achieves higher data rates than eWMMSE while significantly reducing inference latency. Moreover, it maintains strong generalization performance on larger-scale networks, validating its robustness and practicality for real-world multi-channel wireless systems.

Technology Category

• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

As the number of mobile devices continues to grow, interference has become a major bottleneck in improving data rates in wireless networks. Efficient joint channel and power allocation (JCPA) is crucial for managing interference. In this paper, we first propose an enhanced WMMSE (eWMMSE) algorithm to solve the JCPA problem in multi-channel wireless networks. To reduce the computational complexity of iterative optimization, we further introduce JCPGNN-M, a graph neural network-based solution that enables simultaneous multi-channel allocation for each user. We reformulate the problem as a Lagrangian function, which allows us to enforce the total power constraints systematically. Our solution involves combining this Lagrangian framework with GNNs and iteratively updating the Lagrange multipliers and resource allocation scheme. Unlike existing GNN-based methods that limit each user to a single channel, JCPGNN-M supports efficient spectrum reuse and scales well in dense network scenarios. Simulation results show that JCPGNN-M achieves better data rate compared to eWMMSE. Meanwhile, the inference time of JCPGNN-M is much lower than eWMMS, and it can generalize well to larger networks.

Problem

• Solving interference in multi-channel wireless networks
• Reducing computational complexity in resource allocation
• Enabling efficient multi-channel allocation for users

Innovation

• Enhanced WMMSE algorithm for JCPA optimization
• GNN-based multi-channel allocation solution
• Lagrangian framework with iterative updates