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

TL;DR

This paper introduces BKC-UCB, a kernelized contextual bandit algorithm that efficiently estimates transmission rates in mmWave vehicular networks by leveraging historical data and beam correlations, reducing measurement overhead.

Contribution

The paper proposes a novel beam-aware kernelized contextual bandit algorithm that exploits context-beam correlations and event-triggered communication to improve learning efficiency in vehicular networks.

Findings

BKC-UCB accurately estimates transmission rates without additional channel measurements.

The algorithm exploits beam correlations to accelerate convergence.

Event-triggered sharing reduces communication overhead.

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.