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

Enhancing V2X Communication: Machine Learning Assisted Dynamic mmWave Beam Search

Best Paper Award

Ryo Iwaki, Jin Nakazato, Kazuki Maruta, Manabu Tsukada, Hideya Ochiai, Hiroshi Esaki

15th International Conference on Ubiquitous and Future Networks (ICUFN 2024), Budapest, Hungary, Jul 2, 2024

Summary in three lines

  • Fast-moving vehicles need responsive beam search to maintain millimeter-wave V2X links.
  • The method uses environmental data and vehicle dynamics to select beam directions.
  • Simulations based on a real road show improvements over conventional search in some conditions.

Figures from the paper

Figure 3: Machine learning model for dynamic beam search
Figure 3. Machine learning model for dynamic beam searchSource: Figure 3 from Iwaki et al., 15th International Conference on Ubiquitous and Future Networks (ICUFN 2024), 2024 (original artwork from the authors’ manuscript)The model uses information about the vehicle and road to select a beam-search method suited to the situation.

Abstract

Only the chairs can edit This paper addresses the challenges of dynamic beam search in millimeter wave (mmWave) communications for vehicle-to-everything (V2X) applications. With the rapid mobility of connected autonomous vehicles (CAVs) and dense urban environments, maintaining high-quality mmWave connections is critical for the reliability and efficiency of V2X communications. We propose a novel machine learning-assisted framework for dynamic mmWave beam search, which significantly enhances the adaptability and performance of V2X communication systems. Our approach leverages real-time environmental data and CAV dynamics to predict optimal beam directions, improving connection stability. Simulation results demonstrate the effectiveness of the proposed method in a real-world road scenario, offering a partial improvement over conventional beam search techniques.

How to cite

R. Iwaki, J. Nakazato, K. Maruta, M. Tsukada, H. Ochiai, and H. Esaki, “Enhancing V2X Communication: Machine Learning Assisted Dynamic mmWave Beam Search,” in 15th International Conference on Ubiquitous and Future Networks (ICUFN 2024), Budapest, Hungary, 2024, doi: 10.1109/ICUFN61752.2024.10625435.

BibTeX

@inproceedings{Iwaki2024b,
  title         = {Enhancing V2X Communication: Machine Learning Assisted Dynamic mmWave Beam Search},
  author        = {Ryo Iwaki and Jin Nakazato and Kazuki Maruta and Manabu Tsukada and Hideya Ochiai and Hiroshi Esaki},
  doi           = {10.1109/ICUFN61752.2024.10625435},
  year          = {2024},
  date          = {2024-07-02},
  urldate       = {2024-07-02},
  booktitle     = {15th International Conference on Ubiquitous and Future Networks (ICUFN 2024)},
  address       = {Budapest, Hungary},
  abstract      = {Only the chairs can edit This paper addresses the challenges of dynamic beam search in millimeter wave (mmWave) communications for vehicle-to-everything (V2X) applications. With the rapid mobility of connected autonomous vehicles (CAVs) and dense urban environments, maintaining high-quality mmWave connections is critical for the reliability and efficiency of V2X communications. We propose a novel machine learning-assisted framework for dynamic mmWave beam search, which significantly enhances the adaptability and performance of V2X communication systems. Our approach leverages real-time environmental data and CAV dynamics to predict optimal beam directions, improving connection stability. Simulation results demonstrate the effectiveness of the proposed method in a real-world road scenario, offering a partial improvement over conventional beam search techniques.},
  note          = {Best Paper Award},
  keywords      = {Award, ITS},
  pubstate      = {published},
  tppubtype     = {inproceedings}
}