Deep CLSTM for Predictive Beamforming in Integrated Sensing and Communication-enabled Vehicular Networks

TL;DR

This paper introduces a novel deep learning model combining CNN and LSTM to improve vehicle angle prediction for predictive beamforming in high-mobility vehicular networks, enhancing ISAC system performance.

Contribution

The paper proposes a convolutional LSTM network (CLRNet) that effectively exploits spatial and temporal features for accurate vehicle angle prediction, outperforming existing methods.

Findings

CLRNet significantly improves angle prediction accuracy.

The method is robust to estimation errors.

Achieves higher sum-rate performance in ISAC systems.

Abstract

Predictive beamforming design is an essential task in realizing high-mobility integrated sensing and communication (ISAC), which highly depends on the accuracy of the channel prediction (CP), i.e., predicting the angular parameters of users. However, the performance of CP highly depends on the estimated historical channel stated information (CSI) with estimation errors, resulting in the performance degradation for most traditional CP methods. To further improve the prediction accuracy, in this paper, we focus on the ISAC in vehicle networks and propose a convolutional long-short term (CLSTM) recurrent neural network (CLRNet) to predict the angle of vehicles for the design of predictive beamforming. In the developed CLRNet, both the convolutional neural network (CNN) module and the LSTM module are adopted to exploit the spatial features and the temporal dependency from the estimated historical angles of vehicles to facilitate the angle prediction. Finally, numerical results demonstrate that the developed CLRNet-based method is robust to the estimation error and can significantly outperform the state-of-the-art benchmarks, achieving an excellent sum-rate performance for ISAC systems.