PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 29, 2026IET Communications0 citationsOpen Access

Computationally Efficient Deep Learning Inference for High‐Rate Beamforming in Millimeter‐Wave Internet of Vehicles

View Full Paper
HZHaowen ZhengZLZihan LiJDJianxin Dai

Key Points

  • This research aims to develop a low-latency beamforming solution for millimeter-wave Internet-of-Vehicles using a deep learning framework.
  • Implemented an end-to-end deep learning framework mapping channel realizations to beamformers.
  • Explored backbones including MLP, DCGAN-style convolutional encoder, and U-Net encoder-decoder.
  • Developed rate-driven learning strategies to optimize achievable rates.
  • Achieved over 95% performance relative to optimization-based benchmarks on average.
  • U-Net backbone consistently yielded the highest accuracy in performance tests.
  • Trained networks demonstrated approximately 800-times inference speedup compared to iterative methods.

Abstract

ABSTRACT Millimeter‐wave (mmWave) Internet‐of‐Vehicles (IoV) communications rely on large antenna arrays to combat severe path loss and to provide high beamforming gains. However, practical vehicular deployments often adopt analog or hybrid beamforming with constant‐modulus constraints, leading to a highly non‐convex joint beamforming design problem whose iterative solvers incur prohibitive latency under fast channel variations. To enable low‐latency beamforming for dynamic IoV scenarios, we propose an end‐to‐end deep learning framework that directly maps instantaneous channel realizations to the transmit and receive beamformers. Three representative backbones are investigated, including a multilayer perceptron (MLP), a DCGAN‐style convolutional encoder, and a U‐Net encoder–decoder with multi‐scale feature extraction. Moreover, beyond conventional supervised imitation learning, we emphasize rate‐driven learning and develop training strategies that directly optimize the achievable‐rate objective. Extensive simulations demonstrate that the proposed rate‐driven learning substantially improves performance over the previous two‐stage scheme, with the U‐Net backbone consistently providing the best accuracy. Under the premise that the learned solutions achieve over 95% of the optimization‐based benchmark on average, the trained networks provide an approximately 800– inference‐time speedup compared with the iterative based method, highlighting their computational efficiency and practical potential for latency‐sensitive mmWave IoV systems.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Zheng et al. (2026) studied this question.

synapsesocial.com/papers/6a192da0fab5b468c4416716https://doi.org/10.1049/cmu2.70176
Ask AI
Helpful
Bookmark
Share
View Full Paper