Cargando…
Efficient Asynchronous Federated Learning for AUV Swarm
The development of automatic underwater vehicles (AUVs) has brought about unprecedented profits and opportunities. In order to discover the hidden valuable data detected by an AUV swarm, it is necessary to aggregate the data detected by AUV swarm to generate a powerful machine learning model. Tradit...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9692812/ https://www.ncbi.nlm.nih.gov/pubmed/36433323 http://dx.doi.org/10.3390/s22228727 |
_version_ | 1784837362831851520 |
---|---|
author | Meng, Zezhao Li, Zhi Hou, Xiangwang Du, Jun Chen, Jianrui Wei, Wei |
author_facet | Meng, Zezhao Li, Zhi Hou, Xiangwang Du, Jun Chen, Jianrui Wei, Wei |
author_sort | Meng, Zezhao |
collection | PubMed |
description | The development of automatic underwater vehicles (AUVs) has brought about unprecedented profits and opportunities. In order to discover the hidden valuable data detected by an AUV swarm, it is necessary to aggregate the data detected by AUV swarm to generate a powerful machine learning model. Traditional centralized machine learning generates a large number of data exchanges and faces problems of enormous training data, large-scale models, and communication. In underwater environments, radio waves are strongly absorbed, and acoustic communication is the only feasible technology. Unlike electromagnetic wave communication on land, the bandwidth of underwater acoustic communication is extremely limited, with the transmission rate being only [Formula: see text] of the electromagnetic wave. Therefore, traditional centralized machine learning cannot support underwater AUV swarm training. In recent years, federated learning could only interact with model parameters without interacting with data, which greatly reduced communication costs. Therefore, this paper introduces federated learning into the collaboration of an AUV swarm. In order to further reduce the constraints of underwater scarce communication resources on federated learning and alleviate the straggler effect, in this work, we designed an asynchronous federated learning method. Finally, we constructed the optimization problem of minimizing the weighted sum of delay and energy consumption, relying on jointly optimizing the AUV CPU frequency and signal transmission power. In order to solve this complex optimization problem of high-dimensional non-convex time series accumulation, we transformed the problem into a Markov decision process (MDP) and use the proximal policy optimization 2 (PPO2) algorithm to solve this problem. The simulation results demonstrate the effectiveness and superiority of our method. |
format | Online Article Text |
id | pubmed-9692812 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96928122022-11-26 Efficient Asynchronous Federated Learning for AUV Swarm Meng, Zezhao Li, Zhi Hou, Xiangwang Du, Jun Chen, Jianrui Wei, Wei Sensors (Basel) Article The development of automatic underwater vehicles (AUVs) has brought about unprecedented profits and opportunities. In order to discover the hidden valuable data detected by an AUV swarm, it is necessary to aggregate the data detected by AUV swarm to generate a powerful machine learning model. Traditional centralized machine learning generates a large number of data exchanges and faces problems of enormous training data, large-scale models, and communication. In underwater environments, radio waves are strongly absorbed, and acoustic communication is the only feasible technology. Unlike electromagnetic wave communication on land, the bandwidth of underwater acoustic communication is extremely limited, with the transmission rate being only [Formula: see text] of the electromagnetic wave. Therefore, traditional centralized machine learning cannot support underwater AUV swarm training. In recent years, federated learning could only interact with model parameters without interacting with data, which greatly reduced communication costs. Therefore, this paper introduces federated learning into the collaboration of an AUV swarm. In order to further reduce the constraints of underwater scarce communication resources on federated learning and alleviate the straggler effect, in this work, we designed an asynchronous federated learning method. Finally, we constructed the optimization problem of minimizing the weighted sum of delay and energy consumption, relying on jointly optimizing the AUV CPU frequency and signal transmission power. In order to solve this complex optimization problem of high-dimensional non-convex time series accumulation, we transformed the problem into a Markov decision process (MDP) and use the proximal policy optimization 2 (PPO2) algorithm to solve this problem. The simulation results demonstrate the effectiveness and superiority of our method. MDPI 2022-11-11 /pmc/articles/PMC9692812/ /pubmed/36433323 http://dx.doi.org/10.3390/s22228727 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Meng, Zezhao Li, Zhi Hou, Xiangwang Du, Jun Chen, Jianrui Wei, Wei Efficient Asynchronous Federated Learning for AUV Swarm |
title | Efficient Asynchronous Federated Learning for AUV Swarm |
title_full | Efficient Asynchronous Federated Learning for AUV Swarm |
title_fullStr | Efficient Asynchronous Federated Learning for AUV Swarm |
title_full_unstemmed | Efficient Asynchronous Federated Learning for AUV Swarm |
title_short | Efficient Asynchronous Federated Learning for AUV Swarm |
title_sort | efficient asynchronous federated learning for auv swarm |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9692812/ https://www.ncbi.nlm.nih.gov/pubmed/36433323 http://dx.doi.org/10.3390/s22228727 |
work_keys_str_mv | AT mengzezhao efficientasynchronousfederatedlearningforauvswarm AT lizhi efficientasynchronousfederatedlearningforauvswarm AT houxiangwang efficientasynchronousfederatedlearningforauvswarm AT dujun efficientasynchronousfederatedlearningforauvswarm AT chenjianrui efficientasynchronousfederatedlearningforauvswarm AT weiwei efficientasynchronousfederatedlearningforauvswarm |