arXiv:2605.00457v3 Announce Type: replace-cross Abstract: The coexistence of NR-U and Wi-Fi in unlicensed spectrum introduces a challenging coexistence management problem, where heterogeneous channel access mechanisms lead to a significant imbalance in spectrum utilization and degraded Wi-Fi performance. To address this challenge, we propose a policy-driven deep reinforcement learning (DRL) framework for adaptive transmission opportunity (TXOP) control, in which the coexistence process is formulated as a Markov decision process (MDP) and a deep Q-network (DQN) learns control policies through o
The increasing density of wireless devices and the rollout of 5G technologies like NR-U are creating more complex spectrum sharing challenges, necessitating advanced coexistence solutions.
Efficient and fair coexistence of different wireless technologies in unlicensed spectrum is crucial for maintaining performance and preventing interference in common environments, impacting broad sectors from consumers to industrial IoT.
The application of DRL to optimize spectrum access for technologies like NR-U and Wi-Fi could lead to more robust and adaptive wireless communication systems, moving beyond static channel access protocols.
- · 5G NR-U deployments
- · Wi-Fi users in dense environments
- · Deep Reinforcement Learning researchers
- · IoT device manufacturers
- · Legacy spectrum management approaches
- · Systems unprepared for adaptive spectrum access
Improved network performance and reduced interference in congested unlicensed frequency bands.
Accelerated adoption of DRL-based solutions for managing complex resource allocation problems across various communication and computing systems.
Potential for new regulatory frameworks that accommodate dynamic, AI-driven spectrum sharing, influencing future wireless technology standards.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG