Self-Directed Spectrum Allocation Framework for Integrated TN-NTN 6G Networks
2026-07-20 • Networking and Internet Architecture
Networking and Internet Architecture
AI summaryⓘ
The authors developed a system that uses a type of machine learning called Q-learning to help wireless networks choose the best communication channels automatically. Their method watches how busy the network is and how much devices interfere with each other, then learns over time to balance speed, fairness among users, and reducing interference. They tested this approach through simulations and found it works well, improving average speeds and fairness while cutting down interference compared to random choices. This means the system can adapt to changing network traffic to make connections better for everyone.
Q-learningchannel assignmentMarkov decision processmulti-objective optimizationε-greedy strategysystem throughputuser fairnessinterference mitigationJain's fairness indexnetwork traffic dynamics
Authors
Vaskar Chakma, Wooyeol Choi
Abstract
This paper proposes a self-adaptive channel assignment framework based on Q-learning, where agents learn optimal policies by observing network load, interference conditions, and temporal traffic dynamics within a Markov decision process (MDP). A multi-objective reward function is designed to jointly optimize system throughput, user fairness, and interference mitigation, while an ε-greedy strategy is employed to facilitate effective exploration. Simulation results demonstrate stable convergence, achieving an average reward of 37.5 and an average throughput of 28.5 Mbps. Moreover, the proposed approach achieves a Jain's fairness index of 0.75 and reduces interference by 26.3% compared to random allocation by adaptively responding to dynamic traffic patterns.