Federated Meta-Learning Enhanced Acoustic Radio Cooperative Framework for Ocean of Things

Zhao，Hao1; Ji，Fei2; Li，Qiang3; Guan，Quansheng4; Wang，Shuai5; Wen，Miaowen6

2022

10.1109/JSTSP.2022.3144020

IEEE Journal of Selected Topics in Signal Processing   影响因子和分区

1932-4553

1941-0484

Ocean of Things, consisting of multiple buoys distributed on the sea, is an acoustic radio cooperative wireless network that aims to acquire underwater information. In this paper, a deep neural network (DNN)-based receiver with data augmentation, termed chirp (C)-DNN, is developed for chirp modulation-based underwater acoustic communications at a single buoy. To further solve the problem that the training data at a single buoy may not be sufficient, a federated meta-learning (FML) scheme is proposed to train the DNN-based receiver by exploiting the model parameters from multiple buoys. We analyze the convergence performance of FML and derive a closed-form expression for the convergence rate, accounting for the impacts of scheduling ratios, local epochs, and data volumes on a single node. Simulation results show that the proposed C-DNN receiver that is trained with sufficient data achieves better bit error rate performance and lower complexity than classical matched filter (MF)-based detectors. The proposed FML also outperforms the MF-based method after several communication rounds and has better generalization than federated learning based systems.

Chirp chirp communications Chirp modulation convergence Convergence Data models distributed systems Federated meta-learning Radio frequency Receivers Training underwater acoustic communications

EI

英语

其他

2-s2.0-85123382168

Scopus

1.School of Electronic and Information Engineering, South China University of Technology, Guangzhou, Guangdong, China, (e-mail: ctzhaohao@mail.scut.edu.cn)
2.School of Electronic and Information Engineering, South China University of Tehcnology, Guang Zhou, Guang Dong, China, 510640 (e-mail: eefeiji@scut.edu.cn)
3.College of Information Science and Technology, Jinan University, 47885 Guangzhou, China, 510632 (e-mail: qiangli@jnu.edu.cn)
4.Guangzhou, Guangdong, China, 510640 (e-mail: eeqshguan@scut.edu.cn)
5.EEE and CSE, Southern University of Science and Technology, 255310 Shenzhen, China, 518055 (e-mail: s.wang@siat.ac.cn)
6.School of Electronic and Information Engineering, South China University of Technology, Guangzhou, Guangdong, China, 510641 (e-mail: eemwwen@scut.edu.cn)

Zhao，Hao,Ji，Fei,Li，Qiang,et al. Federated Meta-Learning Enhanced Acoustic Radio Cooperative Framework for Ocean of Things[J]. IEEE Journal of Selected Topics in Signal Processing,2022.

Zhao，Hao,Ji，Fei,Li，Qiang,Guan，Quansheng,Wang，Shuai,&Wen，Miaowen.(2022).Federated Meta-Learning Enhanced Acoustic Radio Cooperative Framework for Ocean of Things.IEEE Journal of Selected Topics in Signal Processing.

Zhao，Hao,et al."Federated Meta-Learning Enhanced Acoustic Radio Cooperative Framework for Ocean of Things".IEEE Journal of Selected Topics in Signal Processing (2022).