Sample-and-score surrogate picks IEEE 802.11 coordinated spatial reuse
Original title: Sample-and-Score: Surrogate-Guided Coordinated Spatial Reuse in IEEE 802.11 Networks
On unseen topologies with 2–16 access points it recovers 52–77% of a perfect surrogate’s throughput.
The paper proposes sampling random coordinated spatial reuse configurations for IEEE 802.11bn, scoring them with an offline-trained surrogate, and deploying the best without online fine-tuning. The authors say it approaches multi-armed bandit and heuristic baselines that need extra interaction or measurements. On unseen topologies with 2–16 access points, the surrogate recovers 52–77% of a perfect surrogate’s throughput. A perfect sample-and-score run reaches 95% of the upper-bound throughput with 8192 candidates.
Unconfirmed: Throughput shares are the authors’ simulation results.
- The surrogate is trained offline and not fine-tuned online.
- Evaluation covers topologies with 2 to 16 access points.
- 8192 candidates reach 95% of the upper-bound throughput under a perfect scorer.
- The method targets IEEE 802.11bn coordinated spatial reuse.
From the original article
1 min read at arxiv.orgCoordinated spatial reuse (Co-SR) in IEEE 802. 11bn increases area throughput through simultaneous transmissions, yet the combinatorial configuration space makes real-time optimization challenging. We propose a sample-and-score approach: draw random Co-SR configurations, score each with a surrogate model, and select the best.
By Maksymilian Wojnar · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.