Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Knowledge Distillation for Sensing-Assisted Long-Term Beam Tracking in mmWave Communications

Mengyuan Ma, Nhan Thanh Nguyen, Nir Shlezinger, Yonina C. Eldar, A. Lee Swindlehurst, Markku Juntti

TL;DR

This work presents an efficient sensing-assisted long-term beam tracking framework that selects optimal beams from a codebook for current and multiple future time slots that significantly enhances data efficiency, reduces latency, and reduces power consumption in sensing and processing.

Abstract

Infrastructure-mounted sensors can capture rich environmental information to enhance communications and facilitate beamforming in millimeter-wave systems. This work presents an efficient sensing-assisted long-term beam tracking framework that selects optimal beams from a codebook for current and multiple future time slots. We first design a large attention-enhanced neural network (NN) to fully exploit past visual observations for beam tracking. A convolutional NN extracts compact image features, while gated recurrent units with attention capture the temporal dependencies within sequences. The large NN then acts as the teacher to guide the training of a lightweight student NN via knowledge distillation. The student requires shorter input sequences yet preserves long-term beam prediction ability. Numerical results demonstrate that the teacher achieves Top-5 accuracies exceeding 93% for current and six future time slots, approaching state-of-the-art performance with a 90% reduction of model parameters. The student closely matches the teacher's performance while reducing the number of model parameters by over 1670% and cutting complexity by over 450%, despite operating with 60% shorter input sequences. This improvement significantly enhances data efficiency, reduces latency, and reduces power consumption in sensing and processing.

Knowledge Distillation for Sensing-Assisted Long-Term Beam Tracking in mmWave Communications

TL;DR

This work presents an efficient sensing-assisted long-term beam tracking framework that selects optimal beams from a codebook for current and multiple future time slots that significantly enhances data efficiency, reduces latency, and reduces power consumption in sensing and processing.

Abstract

Infrastructure-mounted sensors can capture rich environmental information to enhance communications and facilitate beamforming in millimeter-wave systems. This work presents an efficient sensing-assisted long-term beam tracking framework that selects optimal beams from a codebook for current and multiple future time slots. We first design a large attention-enhanced neural network (NN) to fully exploit past visual observations for beam tracking. A convolutional NN extracts compact image features, while gated recurrent units with attention capture the temporal dependencies within sequences. The large NN then acts as the teacher to guide the training of a lightweight student NN via knowledge distillation. The student requires shorter input sequences yet preserves long-term beam prediction ability. Numerical results demonstrate that the teacher achieves Top-5 accuracies exceeding 93% for current and six future time slots, approaching state-of-the-art performance with a 90% reduction of model parameters. The student closely matches the teacher's performance while reducing the number of model parameters by over 1670% and cutting complexity by over 450%, despite operating with 60% shorter input sequences. This improvement significantly enhances data efficiency, reduces latency, and reduces power consumption in sensing and processing.

Paper Structure

This paper contains 28 sections, 19 equations, 14 figures, 7 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Prior Work
  3. Contributions
  4. System Model and Problem formulation
  5. System Model
  6. Problem Formulation
  7. Vision-based Long-term Beam Tracking
  8. ML Task Definition
  9. Data Preprocessing
  10. ML Model Design
  11. Motivation
  12. Model Structures
  13. Teacher Model
  14. Student Model
  15. Knowledge Distillation Aided Learning
  16. ...and 13 more sections

Figures (14)

  • Figure 1: Illustration of the considered system model. The BS senses the environment and the moving UE with an RGB camera. The sensory data are collected and cached for beam tracking using the designed ML model.
  • Figure 2: Illustration of the ML model.
  • Figure 3: Illustration of the teacher and student model structures.
  • Figure 4: Scenario 9 of the DeepSense 6G dataset.
  • Figure 5: Statistics of the optimal beam index in the considered dataset.
  • ...and 9 more figures