Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.13701 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- With the rapid advancement of next-generation satellite networks, addressing clustering tasks, user grouping, and efficient link management has become increasingly critical to optimize network performance and reduce interference. In this paper, we provide a comprehensive overview of modern clustering approaches based on machine learning and heuristic algorithms. The experimental results indicate that improved machine learning techniques and graph theory-based methods deliver significantly better performance and scalability than conventional clustering methods, such as the pure clustering algorithm examined in previous research. These advantages are especially evident in large-scale satellite network scenarios. Furthermore, the paper outlines potential research directions and discusses integrated, multi-dimensional solutions to enhance adaptability and efficiency in future satellite communication.