arXiv：cs.LG· Po-Heng Chou, Yi-Fang Yu, Shou-Yu Chen, Chiapin Wang·· 13 小时前
面向 NR-U/Wi-Fi 共存的公平性引导 DQN TXOP 控制
Fairness-Guided DQN-Based TXOP Control for NR-U/Wi-Fi Coexistence
AI 导读
一项研究提出公平性引导的 DQN，根据观测到的单节点吞吐量比例调整 NR-U 的 TXOP，以缓解 NR-U 与 Wi-Fi 的共存失衡。两种奖励设计 Q1 与 Q2 呈现互补特性：Q1 追求严格的单节点吞吐量均衡，Q2 允许更宽的跨接入技术公平区间并奖励中间公平带内的吞吐量提升。
正文
Abstract:New Radio operating in unlicensed spectrum (NR-U) and Wi-Fi employ different contention parameters and channel-occupancy durations, which can produce severe coexistence imbalance. This correspondence develops a fairness-guided deep Q-network (DQN) that adjusts the NR-U transmission opportunity (TXOP) using the observed per-node throughput ratio. Two reward designs, Q1 and Q2, expose complementary operating regimes. Q1 promotes strict per-node throughput balance, whereas Q2 admits a broader inter-radio-access-technology fairness region and rewards throughput improvement in an intermediate fairness band. The policies are compared with the default Third Generation Partnership Project (3GPP) listen-before-talk (LBT), an adapted multi-armed-bandit method, a utility-fairness-based tabular Q-learning comparator, and a default-referenced fixed-TXOP baseline. Experiments across four priority classes and asymmetric populations report aggregate throughput, user-level Jain fairness, and concave throughput utility over 20 independent trials. The results characterize the cost of strict fairness, efficiency recovery under moderate relaxation, and transfer from symmetric to asymmetric deployments.
| Comments: | 5 pages, 2 figures, 1 table. Submitted to IEEE Transactions on Vehicular Technology |
| Subjects: | Networking and Internet Architecture (cs.NI); Machine Learning (cs.LG); Systems and Control (eess.SY) |
| MSC classes: | 68T05, 90B18 |
| ACM classes: | C.2.1; I.2.6; C.4 |
| Cite as: | arXiv:2605.00457 [cs.NI] |
| (or arXiv:2605.00457v5 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.00457 arXiv-issued DOI via DataCite |
Submission history
From: Po-Heng Chou [view email]
[v1]
Fri, 1 May 2026 06:43:09 UTC (1,786 KB)
[v2]
Wed, 6 May 2026 14:52:21 UTC (1,807 KB)
[v3]
Wed, 27 May 2026 09:12:34 UTC (1,787 KB)
[v4]
Thu, 18 Jun 2026 07:24:07 UTC (1,787 KB)
[v5]
Fri, 9 Oct 2026 06:02:21 UTC (199 KB)
来源：arXiv：cs.LG · arxiv.org