Tsukada Lab. Computer Network Group
← Publications Int'l conference

Blockage-Aware Non-stationary Dynamic Bandit for User Association in mmWave V2X Networks

Weiqi Chi, Manabu Tsukada

IEEE Global Communications Conference (GLOBECOM 2026), Macau, China, Dec 7, 2026

Summary in three lines

  • BAND adapts base-station selection as vehicles encounter transient mmWave blockages.
  • Distributed bandits combine change detection with a blockage check and operate without channel state information.
  • In simulation, BAND reduced regret by 44% and raised network rate by 27.3% over the contextual-bandit baseline.

Figures from the paper

Figure 1: BAND workflow
Figure 1. BAND workflowSource: Figure 1 from Chi et al., IEEE Global Communications Conference (GLOBECOM 2026) (2026) (authors’ figure from the manuscript)The vehicle combines blockage assessment with selection and adaptation of available base-station options.

Abstract

In millimeter-wave (mmWave) vehicular networks, dense base station (BS) deployments and dynamic blockages introduce severe non-stationarity into the user association (UA), posing a critical mobility management challenge that hinders rapid and effective UA decisions. Traditional Multi-Armed Bandit (MAB) frameworks assume stationary reward distributions and fail to handle the rapid context-reward mapping shifts caused by vehicle mobility and transient blockages. To address this, we propose Blockage-Aware Non-stationary Dynamic Bandit (BAND), a fully distributed, Channel state information (CSI)-free mobility management framework for mmWave vehicular networks, formulating UA as a non-stationary contextual bandit problem and enables online adaptive optimization without requiring central coordination or offline training. BAND employs a cumulative sum-based change detection (CUSUM-CD) to dynamically narrow the active BS set, reducing exploration overhead while tracking reward distribution shifts. Proactive blockage detections suppress transient signal degradation in reward estimation. Simulations demonstrate over 44% regret reduction and up to 27.3% network communication rate improvement over hypercube-based contextual bandit baselines, with robustness validated across varying blockage rates and network configurations.

How to cite

W. Chi and M. Tsukada, “Blockage-Aware Non-stationary Dynamic Bandit for User Association in mmWave V2X Networks,” in IEEE Global Communications Conference (GLOBECOM 2026), Macau, China, 2026.

BibTeX

@inproceedings{Chi2026b,
  title         = {Blockage-Aware Non-stationary Dynamic Bandit for User Association in mmWave V2X Networks},
  author        = {Weiqi Chi and Manabu Tsukada},
  url           = {https://arxiv.org/abs/2606.08118},
  year          = {2026},
  date          = {2026-12-07},
  urldate       = {2026-12-07},
  booktitle     = {IEEE Global Communications Conference (GLOBECOM 2026)},
  address       = {Macau, China},
  abstract      = {In millimeter-wave (mmWave) vehicular networks, dense base station (BS) deployments and dynamic blockages introduce severe non-stationarity into the user association (UA), posing a critical mobility management challenge that hinders rapid and effective UA decisions. Traditional Multi-Armed Bandit (MAB) frameworks assume stationary reward distributions and fail to handle the rapid context-reward mapping shifts caused by vehicle mobility and transient blockages. To address this, we propose Blockage-Aware Non-stationary Dynamic Bandit (BAND), a fully distributed, Channel state information (CSI)-free mobility management framework for mmWave vehicular networks, formulating UA as a non-stationary contextual bandit problem and enables online adaptive optimization without requiring central coordination or offline training. BAND employs a cumulative sum-based change detection (CUSUM-CD) to dynamically narrow the active BS set, reducing exploration overhead while tracking reward distribution shifts. Proactive blockage detections suppress transient signal degradation in reward estimation. Simulations demonstrate over 44% regret reduction and up to 27.3% network communication rate improvement over hypercube-based contextual bandit baselines, with robustness validated across varying blockage rates and network configurations.},
  keywords      = {ITS},
  pubstate      = {published},
  tppubtype     = {inproceedings}
}