Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Mechanical Wi-Fi Antenna Device for Automatic Orientation Tuning with Bayesian Optimization

Akihito Taya, Yuuki Nishiyama, Kaoru Sezaki

TL;DR

The paper addresses the sensitivity of indoor Wi‑Fi performance to antenna orientation, caused by polarization and multipath effects. It introduces a mechanical antenna device with dual‑axis yaw and roll control and real‑time channel‑capacity feedback, guided by Bayesian optimization to find near‑optimal orientations with few measurements. Key contributions include a hardware prototype, real‑time capacity‑based feedback, and demonstrated superiority of Bayesian optimization over random and Sobol baselines in identifying favorable orientations. Findings show orientation can yield up to approximately 70 Mbps throughput variation in LoS indoor conditions, and the system reliably aligns polarization to maximize throughput, enabling autonomous, practical adaptive optimization for residential and office deployments.

Abstract

Wi-Fi access points have been widely deployed in homes, offices, and public spaces. Some APs allow users to adjust the antenna orientation to improve communication performance by optimizing antenna polarization. However, it is difficult for non-expert users to determine the optimal orientation, and users often leave the antenna orientation in ineffective positions. To address this issue, we developed a mechanical Wi-Fi antenna device capable of automatically tuning its orientation. Experimental results show that antenna orientation could cause a throughput variation of approximately 70 Mbps under line-of-sight conditions. Furthermore, Bayesian optimization identified better configurations than random search, demonstrating its effectiveness for orientation tuning.

A Mechanical Wi-Fi Antenna Device for Automatic Orientation Tuning with Bayesian Optimization

TL;DR

The paper addresses the sensitivity of indoor Wi‑Fi performance to antenna orientation, caused by polarization and multipath effects. It introduces a mechanical antenna device with dual‑axis yaw and roll control and real‑time channel‑capacity feedback, guided by Bayesian optimization to find near‑optimal orientations with few measurements. Key contributions include a hardware prototype, real‑time capacity‑based feedback, and demonstrated superiority of Bayesian optimization over random and Sobol baselines in identifying favorable orientations. Findings show orientation can yield up to approximately 70 Mbps throughput variation in LoS indoor conditions, and the system reliably aligns polarization to maximize throughput, enabling autonomous, practical adaptive optimization for residential and office deployments.

Abstract

Wi-Fi access points have been widely deployed in homes, offices, and public spaces. Some APs allow users to adjust the antenna orientation to improve communication performance by optimizing antenna polarization. However, it is difficult for non-expert users to determine the optimal orientation, and users often leave the antenna orientation in ineffective positions. To address this issue, we developed a mechanical Wi-Fi antenna device capable of automatically tuning its orientation. Experimental results show that antenna orientation could cause a throughput variation of approximately 70 Mbps under line-of-sight conditions. Furthermore, Bayesian optimization identified better configurations than random search, demonstrating its effectiveness for orientation tuning.
Paper Structure (4 sections, 1 equation, 3 figures)

This paper contains 4 sections, 1 equation, 3 figures.

Table of Contents

  1. Introduction
  2. System Design
  3. Evaluations
  4. Conclusion

Figures (3)

  • Figure 1: Mechanical Wi-Fi antenna device and its control system. The device can automatically tune the antenna orientation using Bayesian optimization to improve communication performance by calculating channel capacity in real time.
  • Figure 2: TX antenna configurations and optimized results of RX antennas. RX antennas were adjusted to be parallel to TX antennas in both configurations.
  • Figure 3: Convergence of channel capacity optimization of vertical TX antenna configuration.