Constrained MARL for Coexisting TN-NTN Resource Allocation: Scalability and Flexibility

2026-01-20

AI Summary

This work addresses the challenge of joint constrained resource allocation in large-scale, highly dynamic coexistence scenarios between terrestrial and non-terrestrial networks. To tackle this problem, the authors propose a cross-segment interference-aware decomposition mechanism and develop a sequential multi-agent reinforcement learning framework. By incorporating randomized training environments to model system dynamics, the approach significantly enhances the adaptability and robustness of the learned policies in real-world conditions. Extensive experiments across various configurations under a full 20 MHz bandwidth demonstrate the superiority of the proposed method: it achieves substantially improved scalability compared to existing solutions and maintains stable performance even in highly dynamic user environments.

Technology Category

• Multiagent Systems: Multiagent Learning
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

This paper considers the joint TN-NTN constrained resource allocation, where terrestrial base stations and non-terrestrial base stations coexist in the spectrum. We focus on large-scale and practical scenarios characterized by large numbers of transmission channels and users, alongside highly dynamic user behaviors. As common learning solutions fail to address these challenges, we propose a decomposition solution based on the special properties of the cross-segment interference, and then tackle the original problem via solving subproblems in a sequential learning manner. Furthermore, to enhance the flexibility of the learned policies, we design a stochastic training environment that captures the key characteristics of real-world systems. Simulation results tested on the full 20MHz bandwidth with various numerologies show that our solution significantly improves scalability compared to existing solutions and remains robust in highly dynamic scenarios.

Problem

• Constrained MARL
• TN-NTN coexistence
• resource allocation
• scalability
• dynamic user behavior

Innovation

• Constrained MARL
• TN-NTN Coexistence
• Scalable Resource Allocation
• Sequential Learning
• Stochastic Training Environment