Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Beam-aware Kernelized Contextual Bandits for User Association and Beamforming in mmWave Vehicular Networks

Xiaoyang He, Manabu Tsukada

Abstract

Timely channel information is necessary for vehicles to determine both the serving base station (BS) and the beamforming vector, but frequent estimation of fast-fading mmWave channels incurs significant overhead. To address this challenge, we propose a Beam-aware Kernelized Contextual Upper Confidence Bound (BKC-UCB) algorithm that estimates instantaneous transmission rates without additional channel measurements by exploiting historical contexts such as vehicle location and velocity, together with past observed transmission rates. Specifically, BKC-UCB leverages kernel methods to capture the nonlinear relationship between context and transmission rate by mapping contexts into a reproducing kernel Hilbert space (RKHS), where linear learning becomes feasible. Rather than treating each beam as an independent arm, the beam index is embedded into the context, enabling BKC-UCB to exploit correlations among beams to accelerate convergence. Furthermore, an event-triggered information sharing mechanism is incorporated into BKC-UCB, enabling information exchange only when significant explorations are conducted to improve learning efficiency with limited communication overhead.

Beam-aware Kernelized Contextual Bandits for User Association and Beamforming in mmWave Vehicular Networks

Abstract

Timely channel information is necessary for vehicles to determine both the serving base station (BS) and the beamforming vector, but frequent estimation of fast-fading mmWave channels incurs significant overhead. To address this challenge, we propose a Beam-aware Kernelized Contextual Upper Confidence Bound (BKC-UCB) algorithm that estimates instantaneous transmission rates without additional channel measurements by exploiting historical contexts such as vehicle location and velocity, together with past observed transmission rates. Specifically, BKC-UCB leverages kernel methods to capture the nonlinear relationship between context and transmission rate by mapping contexts into a reproducing kernel Hilbert space (RKHS), where linear learning becomes feasible. Rather than treating each beam as an independent arm, the beam index is embedded into the context, enabling BKC-UCB to exploit correlations among beams to accelerate convergence. Furthermore, an event-triggered information sharing mechanism is incorporated into BKC-UCB, enabling information exchange only when significant explorations are conducted to improve learning efficiency with limited communication overhead.
Paper Structure (10 sections, 22 equations, 4 figures, 1 algorithm)

This paper contains 10 sections, 22 equations, 4 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. beam-aware kernelized upper confidence bound Algorithm
  4. Framework of BKC-UCB Algorithm
  5. User Association Decision
  6. Beam Tracking
  7. Synchronization
  8. Regret Analysis
  9. Numerical Results
  10. Conclusion

Figures (4)

  • Figure 1: Architecture of the BKC-UCB algorithm during periods $[\bar{t}, \bar{t} + N_A - 1]$.
  • Figure 2: Cumulative external regret to time horizon $\mathbb{E}[\mathcal{R}_i(T)] / T$ (ERT).
  • Figure 3: Average transmission rate (Avg. Rate) per vehicle and synchronization rate (Syn. Rate) against the transmit power.
  • Figure 4: Average transmission rate per vehicle (Avg. Rate) against period $T$.