Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GCN-Based Throughput-Oriented Handover Management in Dense 5G Vehicular Networks

Nazanin Mehregan, Robson E. De Grande

TL;DR

This work addresses handover instability in dense 5G vehicular networks, focusing on minimizing ping-pong handovers while maximizing throughput and SINR. It introduces TH-GCN, a throughput-oriented, spatiotemporal graph neural network that models vehicles and base stations as a dynamic graph with edge-aware weights and uses triplet loss to learn embeddings for tower ranking. The approach integrates both UE and BS perspectives, enabling real-time, edge-deployable handover decisions and multi-stakeholder optimization that balances load and network-wide throughput. Evaluations on a realistic Cologne urban scenario show TH-GCN achieving up to 78% fewer handovers and around 10% SINR improvements, alongside enhanced throughput and reliability, highlighting its potential for scalable deployment in dense 5G vehicular networks.

Abstract

The rapid advancement of 5G has transformed vehicular networks, offering high bandwidth, low latency, and fast data rates essential for real-time applications in smart cities and vehicles. These improvements enhance traffic safety and entertainment services. However, the limited coverage and frequent handovers in 5G networks cause network instability, especially in high-mobility environments due to the ping-pong effect. This paper presents TH-GCN (Throughput-oriented Graph Convolutional Network), a novel approach for optimizing handover management in dense 5G networks. Using graph neural networks (GNNs), TH-GCN models vehicles and base stations as nodes in a dynamic graph enriched with features such as signal quality, throughput, vehicle speed, and base station load. By integrating both user equipment and base station perspectives, this dual-centric approach enables adaptive, real-time handover decisions that improve network stability. Simulation results show that TH-GCN reduces handovers by up to 78 percent and improves signal quality by 10 percent, outperforming existing methods.

GCN-Based Throughput-Oriented Handover Management in Dense 5G Vehicular Networks

TL;DR

This work addresses handover instability in dense 5G vehicular networks, focusing on minimizing ping-pong handovers while maximizing throughput and SINR. It introduces TH-GCN, a throughput-oriented, spatiotemporal graph neural network that models vehicles and base stations as a dynamic graph with edge-aware weights and uses triplet loss to learn embeddings for tower ranking. The approach integrates both UE and BS perspectives, enabling real-time, edge-deployable handover decisions and multi-stakeholder optimization that balances load and network-wide throughput. Evaluations on a realistic Cologne urban scenario show TH-GCN achieving up to 78% fewer handovers and around 10% SINR improvements, alongside enhanced throughput and reliability, highlighting its potential for scalable deployment in dense 5G vehicular networks.

Abstract

The rapid advancement of 5G has transformed vehicular networks, offering high bandwidth, low latency, and fast data rates essential for real-time applications in smart cities and vehicles. These improvements enhance traffic safety and entertainment services. However, the limited coverage and frequent handovers in 5G networks cause network instability, especially in high-mobility environments due to the ping-pong effect. This paper presents TH-GCN (Throughput-oriented Graph Convolutional Network), a novel approach for optimizing handover management in dense 5G networks. Using graph neural networks (GNNs), TH-GCN models vehicles and base stations as nodes in a dynamic graph enriched with features such as signal quality, throughput, vehicle speed, and base station load. By integrating both user equipment and base station perspectives, this dual-centric approach enables adaptive, real-time handover decisions that improve network stability. Simulation results show that TH-GCN reduces handovers by up to 78 percent and improves signal quality by 10 percent, outperforming existing methods.
Paper Structure (28 sections, 4 equations, 3 figures, 1 table, 1 algorithm)

This paper contains 28 sections, 4 equations, 3 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. TH-GCN Model
  4. Dataset Collection
  5. Graph Construction and Structure
  6. Node and Edge Features
  7. Graph Representation
  8. Graph Neural Network (GNN) Architecture
  9. Message Passing and Node Embedding
  10. Embedding Space and Optimization
  11. Model Training
  12. Initialization and Incremental Training
  13. Triplet Loss Optimization
  14. Edge-Weighted Aggregation
  15. Training Pipeline
  16. ...and 13 more sections

Figures (3)

  • Figure 1: Overview of the TH-GCN pipeline for optimizing handover decisions in dense 5G vehicular networks.
  • Figure 2: Simulation Scenario of Cologne, Germany.
  • Figure 3: Comparison of Evaluation Metrics across various vehicle densities.