Knowledge Distillation for mmWave Beam Prediction Using Sub-6 GHz Channels
This work addresses the computational overhead in mmWave beamforming for high-mobility environments, offering an incremental improvement over existing deep learning methods.
The paper tackles the problem of high computational and memory requirements in predicting optimal mmWave beams from sub-6 GHz channels by proposing a knowledge distillation framework with compact student models, achieving a 99% reduction in parameters and complexity while matching the teacher model's accuracy and spectral efficiency.
Beamforming in millimeter-wave (mmWave) high-mobility environments typically incurs substantial training overhead. While prior studies suggest that sub-6 GHz channels can be exploited to predict optimal mmWave beams, existing methods depend on large deep learning (DL) models with prohibitive computational and memory requirements. In this paper, we propose a computationally efficient framework for sub-6 GHz channel-mmWave beam mapping based on the knowledge distillation (KD) technique. We develop two compact student DL architectures based on individual and relational distillation strategies, which retain only a few hidden layers yet closely mimic the performance of large teacher DL models. Extensive simulations demonstrate that the proposed student models achieve the teacher's beam prediction accuracy and spectral efficiency while reducing trainable parameters and computational complexity by 99%.