Learning-Based User Association for MmWave Vehicular Networks With Kernelized Contextual Bandits
This work addresses timely base station association for vehicles in mmWave networks, offering an incremental improvement over existing methods by incorporating propagation characteristics into the kernel function.
The paper tackles the problem of costly channel estimation in mmWave vehicular networks by proposing a distributed kernelized contextual bandit algorithm that uses past contexts and transmission rates to estimate current rates, achieving improved learning speed with affordable communication costs.
Vehicles require timely channel conditions to determine the base station (BS) to communicate with, but it is costly to estimate the fast-fading mmWave channels frequently. Without additional channel estimations, the proposed Distributed Kernelized Upper Confidence Bound (DK-UCB) algorithm estimates the current instantaneous transmission rates utilizing past contexts, such as the vehicle's location and velocity, along with past instantaneous transmission rates. To capture the nonlinear mapping from a context to the instantaneous transmission rate, DK-UCB maps a context into the reproducing kernel Hilbert space (RKHS) where a linear mapping becomes observable. To improve estimation accuracy, we propose a novel kernel function in RKHS which incorporates the propagation characteristics of the mmWave signals. Moreover, DK-UCB encourages a vehicle to share necessary information when it has conducted significant explorations, which speeds up the learning process while maintaining affordable communication costs.