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

作     者：Chang Liu Xuemeng Liu Shuangyang Li Weijie Yuan Derrick Wing Kwan Ng 

作者机构：School of Electrical Engineering and Telecommunicationsthe University of New South WalesSydneyNSW 2052Australia School of Electrical and Information Engineeringthe University of SydneySydneyNSW 2006Australia Department of ElectricalElectronic and Computer Engineeringthe University of Western AustraliaPerth WA 6009Australia Department of Electrical and Electronic EngineeringSouthern University of Science and TechnologyShenzhen 518055China 

出 版 物：《Journal of Communications and Information Networks》 (通信与信息网络学报（英文）)

年 卷 期：2022年第7卷第3期

页      面：269-277页

核心收录：

学科分类：0810[工学-信息与通信工程] 082304[工学-载运工具运用工程] 08[工学] 080204[工学-车辆工程] 081001[工学-通信与信息系统] 0802[工学-机械工程] 0823[工学-交通运输工程] 

基　　金：supported by the National Natural Science Foundation of China under Grant 61801082 supported in part by the National Natural Science Foundation of China under Grant 62101232 in part by the Guangdong Provincial Natural Science Foundation under Grant 2022A1515011257 

主　　题：integrated sensing and communication predictive beamforming deep learning convolutional longshort term neural network vehicular networks 

摘      要：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 ***,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 *** further improve the prediction accuracy,in this paper,we focus on the ISAC in vehicle networks and propose a convolutional long-short term memory(CLSTM)recurrent neural network(CLRNet)to predict the angle of vehicles for the design of predictive *** 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 ***,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.