Underwater Acoustic MAC Protocol for Multi-Objective Optimization Based on Multi-Agent Reinforcement Learning

In underwater acoustic networks (UANs), communication between nodes is susceptible to long propagation delays, limited energy, and channel conflicts, and traditional multi-access control (MAC) protocols cannot easily cope with these challenges. To enhance network throughput and balance channel alloc...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinfang Jiang, Yiling Dong, Guangjie Han, Gang Su
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Drones
Subjects:
Online Access:https://www.mdpi.com/2504-446X/9/2/123
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850081260669501440
author Jinfang Jiang
Yiling Dong
Guangjie Han
Gang Su
author_facet Jinfang Jiang
Yiling Dong
Guangjie Han
Gang Su
author_sort Jinfang Jiang
collection DOAJ
description In underwater acoustic networks (UANs), communication between nodes is susceptible to long propagation delays, limited energy, and channel conflicts, and traditional multi-access control (MAC) protocols cannot easily cope with these challenges. To enhance network throughput and balance channel allocation fairness and energy efficiency, this paper proposes a multi-objective optimization MAC protocol (MOMA-MAC) based on multi-agent reinforcement learning. MOMA-MAC utilizes a delay reward mechanism combined with the Multi-agent Proximal Policy Optimization Algorithm (MAPPO) to design a dual reward mechanism, which enables agents to adaptively collaborate and compete to optimize the use of network resources. According to experimental results, MOMA-MAC performs noticeably better than traditional MAC protocols and deep reinforcement learning-based methods in terms of throughput, energy efficiency, and fairness in multi-agent scenarios, showing great potential for improving communication efficiency and energy utilization.
format Article
id doaj-art-09c9f2aa445b49e6acd0f1fced3934cb
institution DOAJ
issn 2504-446X
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Drones
spelling doaj-art-09c9f2aa445b49e6acd0f1fced3934cb2025-08-20T02:44:46ZengMDPI AGDrones2504-446X2025-02-019212310.3390/drones9020123Underwater Acoustic MAC Protocol for Multi-Objective Optimization Based on Multi-Agent Reinforcement LearningJinfang Jiang0Yiling Dong1Guangjie Han2Gang Su3Key Laboratory of Maritime Intelligent Cyberspace Technology, Hohai University, Ministry of Education, Changzhou 213200, ChinaKey Laboratory of Maritime Intelligent Cyberspace Technology, Hohai University, Ministry of Education, Changzhou 213200, ChinaKey Laboratory of Maritime Intelligent Cyberspace Technology, Hohai University, Ministry of Education, Changzhou 213200, ChinaKey Laboratory of Maritime Intelligent Cyberspace Technology, Hohai University, Ministry of Education, Changzhou 213200, ChinaIn underwater acoustic networks (UANs), communication between nodes is susceptible to long propagation delays, limited energy, and channel conflicts, and traditional multi-access control (MAC) protocols cannot easily cope with these challenges. To enhance network throughput and balance channel allocation fairness and energy efficiency, this paper proposes a multi-objective optimization MAC protocol (MOMA-MAC) based on multi-agent reinforcement learning. MOMA-MAC utilizes a delay reward mechanism combined with the Multi-agent Proximal Policy Optimization Algorithm (MAPPO) to design a dual reward mechanism, which enables agents to adaptively collaborate and compete to optimize the use of network resources. According to experimental results, MOMA-MAC performs noticeably better than traditional MAC protocols and deep reinforcement learning-based methods in terms of throughput, energy efficiency, and fairness in multi-agent scenarios, showing great potential for improving communication efficiency and energy utilization.https://www.mdpi.com/2504-446X/9/2/123underwater acoustic networksmulti-access control protocolmulti-objective optimization
spellingShingle Jinfang Jiang
Yiling Dong
Guangjie Han
Gang Su
Underwater Acoustic MAC Protocol for Multi-Objective Optimization Based on Multi-Agent Reinforcement Learning
Drones
underwater acoustic networks
multi-access control protocol
multi-objective optimization
title Underwater Acoustic MAC Protocol for Multi-Objective Optimization Based on Multi-Agent Reinforcement Learning
title_full Underwater Acoustic MAC Protocol for Multi-Objective Optimization Based on Multi-Agent Reinforcement Learning
title_fullStr Underwater Acoustic MAC Protocol for Multi-Objective Optimization Based on Multi-Agent Reinforcement Learning
title_full_unstemmed Underwater Acoustic MAC Protocol for Multi-Objective Optimization Based on Multi-Agent Reinforcement Learning
title_short Underwater Acoustic MAC Protocol for Multi-Objective Optimization Based on Multi-Agent Reinforcement Learning
title_sort underwater acoustic mac protocol for multi objective optimization based on multi agent reinforcement learning
topic underwater acoustic networks
multi-access control protocol
multi-objective optimization
url https://www.mdpi.com/2504-446X/9/2/123
work_keys_str_mv AT jinfangjiang underwateracousticmacprotocolformultiobjectiveoptimizationbasedonmultiagentreinforcementlearning
AT yilingdong underwateracousticmacprotocolformultiobjectiveoptimizationbasedonmultiagentreinforcementlearning
AT guangjiehan underwateracousticmacprotocolformultiobjectiveoptimizationbasedonmultiagentreinforcementlearning
AT gangsu underwateracousticmacprotocolformultiobjectiveoptimizationbasedonmultiagentreinforcementlearning