TY - GEN
T1 - Sensory Data Assisted Downlink Channel Prediction for Massive MIMO
AU - Yang, Yuwen
AU - Gao, Feifei
AU - Xing, Chengwen
AU - An, Jianping
AU - Alkhateeb, Ahmed
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant {61831013, 61771274}, and by Beijing Municipal Natural Science Foundation under Grant {L182042}.
Publisher Copyright:
© 2021 IEEE.
PY - 2021/6
Y1 - 2021/6
N2 - Existing deep learning (DL) based downlink channel prediction algorithms for frequency division duplex (FDD) massive multiple-input multiple-output (MIMO) systems mainly utilize single-source sensing information, e.g., the uplink channels, to predict the downlink channels. With the aid of multi-source sensing information (MSI) in communication systems, this paper explores deep multimodal learning (DML) technologies to improve the accuracy of downlink channel prediction. By leveraging various modality combinations and fusion levels, we design several DML based architectures for downlink channel prediction, which can also be easily extended to other communication problems like beam prediction. Simulation results demonstrate that the proposed DML based architectures can effectively exploit the constructive and complementary information of multimodal sensory data, thus achieving better performance than existing works.
AB - Existing deep learning (DL) based downlink channel prediction algorithms for frequency division duplex (FDD) massive multiple-input multiple-output (MIMO) systems mainly utilize single-source sensing information, e.g., the uplink channels, to predict the downlink channels. With the aid of multi-source sensing information (MSI) in communication systems, this paper explores deep multimodal learning (DML) technologies to improve the accuracy of downlink channel prediction. By leveraging various modality combinations and fusion levels, we design several DML based architectures for downlink channel prediction, which can also be easily extended to other communication problems like beam prediction. Simulation results demonstrate that the proposed DML based architectures can effectively exploit the constructive and complementary information of multimodal sensory data, thus achieving better performance than existing works.
UR - http://www.scopus.com/inward/record.url?scp=85115720630&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85115720630&partnerID=8YFLogxK
U2 - 10.1109/ICC42927.2021.9500427
DO - 10.1109/ICC42927.2021.9500427
M3 - Conference contribution
AN - SCOPUS:85115720630
T3 - IEEE International Conference on Communications
BT - ICC 2021 - IEEE International Conference on Communications, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Communications, ICC 2021
Y2 - 14 June 2021 through 23 June 2021
ER -