Predictive Beamforming for Integrated Sensing and Communication in Vehicular Networks: A Deep Learning Approach

Chang Liu1; Weijie Yuan2; Shuangyang Li3; Xuemeng Liu4; Derrick Wing Kwan Ng3; Yonghui Li4

10.1109/ICC45855.2022.9839000

2022

IEEE International Conference on Communications (ICC)

1550-3607

978-1-5386-8348-4

ICC 2022 - IEEE International Conference on Communications

2022-May

1948-1954

16-20 May 2022

Seoul, Korea, Republic of

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

The implementation of integrated sensing and communication (ISAC) highly depends on the effective beamforming design exploiting accurate instantaneous channel state information (ICSI). However, channel tracking in ISAC requires large amount of training overhead and prohibitively large computational complexity. To address this problem, in this paper, we focus on ISAC-assisted vehicular networks and exploit a deep learning approach to implicitly learn the features of historical channels and directly predict the beamforming matrix for the next time slot to maximize the average achievable sum-rate of system, thus bypassing the need of explicit channel tracking for reducing the system signaling overhead. To this end, a general sum-rate maximization problem with Cramer-Rao lower bounds-based sensing constraints is first formulated for the considered ISAC system. Then, a historical channels-based convolutional long short-term memory network is designed for predictive beamforming that can exploit the spatial and temporal dependencies of communication channels to further improve the learning performance. Finally, simulation results show that the proposed method can satisfy the requirement of sensing performance, while its achievable sum-rate can approach the upper bound obtained by a genie-aided scheme with perfect ICSI available.

Deep learning Training Upper bound Protocols Array signal processing Convolution Simulation

其他

英语

EI ; CPCI-S

National Natural Science Foundation of China[61801082]

Telecommunications

Telecommunications

WOS:000864709902042

20223712710859

Channel state information ; Deep learning

Ergonomics and Human Factors Engineering:461.4 ; Electromagnetic Waves in Relation to Various Structures:711.2

IEEE

1.State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China
2.Department of Electronic and Electrical Engineering, Southern University of Science and Technology, China
3.School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, Australia
4.School of Electrical and Information Engineering, University of Sydney, Sydney, Australia

Chang Liu,Weijie Yuan,Shuangyang Li,et al. Predictive Beamforming for Integrated Sensing and Communication in Vehicular Networks: A Deep Learning Approach[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2022:1948-1954.