Joint Optimization of UAV Placement, User Association and Resource Allocation for Integrated TN-NTN via Multi-Agent DRL

Page view(s)
4
Checked on Sep 05, 2025
Joint Optimization of UAV Placement, User Association and Resource Allocation for Integrated TN-NTN via Multi-Agent DRL
Title:
Joint Optimization of UAV Placement, User Association and Resource Allocation for Integrated TN-NTN via Multi-Agent DRL
Journal Title:
IEEE Vehicular Technology Conference - Fall 2025
DOI:
Publication URL:
Keywords:
Publication Date:
22 October 2025
Citation:
J. Huang, S. Vignesh, and E. Kurniawan, "Joint Optimization of UAV Placement, User Association and Resource Allocation for Integrated TN-NTN via Multi-Agent DRL," IEEE VTC Fall 2025, Chengdu, China, In Proceedings, October 2025.
Abstract:
One of the key visions of the sixth generation (6G) network is to provide global coverage and ubiquitous connectivity. To support this vision, the design and optimization of integrated Terrestrial and Non-Terrestrial Networks (TN-NTN) is of great importance. The heterogeneous entities in integrated TN-NTN network pose great challenges in the design and optimization. This paper investigates the joint optimization of Unmanned Aerial Vehicle (UAV) base station (BS) placement, user association, and Resource Block (RB) allocation for integrated TN-NTN networks, with the objective to support more users while satisfying Quality of Service (QoS) requirements, and achieving fairness among users. More specifically, we proposed a Heterogeneous Multi-Agent Deep Reinforcement Learning (HeMADRL) framework with various types of agents to solve the problem. Simulation results show that the proposed algorithm outperforms benchmark algorithms.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation, and Infocomm Media Development Authority - Future Communications Programme
Grant Reference no. : FCP-ASTAR-IRC-2025-003
Description:
© 2025 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
ISSN:
1556-6080
Files uploaded:

File Size Format Action
2025-vtcfall-paper.pdf 481.88 KB PDF Request a copy