Learning Load Balancing with GNN in MPTCP-Enabled Heterogeneous Networks

2024-10-22

arXiv.org

AI Summary

Existing load-balancing methods for LiFi/WiFi heterogeneous networks suffer from limited performance due to insufficient modeling capability for the dynamic, partially meshed topologies induced by Multipath TCP (MPTCP). To address this, we propose the first graph neural network (GNN)-based load-balancing framework for MPTCP-enabled heterogeneous networks. Our method models the network topology end-to-end, using channel states and rate demands as node features and load-balancing decisions as edge labels. It supports generalizable inference across arbitrary numbers of access points (APs) and user equipments (UEs), while ensuring both topological interpretability and model unification. Experimental results demonstrate that our approach achieves 98.5% of the optimal throughput—outperforming conventional deep neural networks (DNNs) by 21.7%—with comparable latency and a 10⁴× speedup in inference time.

Technology Category

• Machine Learning: Graph-based Machine Learning
• 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: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Hybrid light fidelity (LiFi) and wireless fidelity (WiFi) networks are a promising paradigm of heterogeneous network (HetNet), attributed to the complementary physical properties of optical spectra and radio frequency. However, the current development of such HetNets is mostly bottlenecked by the existing transmission control protocol (TCP), which restricts the user equipment (UE) to connecting one access point (AP) at a time. While the ongoing investigation on multipath TCP (MPTCP) can bring significant benefits, it complicates the network topology of HetNets, making the existing load balancing (LB) learning models less effective. Driven by this, we propose a graph neural network (GNN)-based model to tackle the LB problem for MPTCP-enabled HetNets, which results in a partial mesh topology. Such a topology can be modeled as a graph, with the channel state information and data rate requirement embedded as node features, while the LB solutions are deemed as edge labels. Compared to the conventional deep neural network (DNN), the proposed GNN-based model exhibits two key strengths: i) it can better interpret a complex network topology; and ii) it can handle various numbers of APs and UEs with a single trained model. Simulation results show that against the traditional optimisation method, the proposed learning model can achieve near-optimal throughput within a gap of 11.5%, while reducing the inference time by 4 orders of magnitude. In contrast to the DNN model, the new method can improve the network throughput by up to 21.7%, at a similar inference time level.

Problem

• Load balancing in MPTCP-enabled heterogeneous networks
• Graph neural network model for complex network topology
• Improving throughput and reducing inference time

Innovation

• GNN model for load balancing in MPTCP HetNets
• Graph representation with node and edge features
• Single model handles variable APs and UEs