Environment Sensing-aided Beam Prediction with Transfer Learning for Smart Factory

TL;DR

This paper introduces a transfer learning approach for environment sensing-aided beam prediction in smart factories, significantly reducing data and time costs while maintaining high accuracy.

Contribution

It presents a transfer learning strategy that fine-tunes a pre-trained beam prediction model with limited new environment data, reducing retraining costs.

Findings

94% Top-10 beam prediction accuracy with 30% labeled data

70% reduction in training data needed

75% decrease in training time

Abstract

In this paper, we propose an environment sensing-aided beam prediction model for smart factory that can be transferred from given environments to a new environment. In particular, we first design a pre-training model that predicts the optimal beam by sensing the present environmental information. When encountering a new environment, it generally requires collecting a large amount of new training data to retrain the model, whose cost severely impedes the application of the designed pre-training model. Therefore, we next design a transfer learning strategy that fine-tunes the pre-trained model by limited labeled data of the new environment. Simulation results show that when the pre-trained model is fine-tuned by 30\% of labeled data from the new environment, the Top-10 beam prediction accuracy reaches 94\%. Moreover, compared with the way to completely re-training the prediction model, the amount of training data and the time cost of the proposed transfer learning strategy reduce 70\% and 75\% respectively.