Routing Protocol Design for Underwater Optical Wireless Sensor Networks: A Multiagent Reinforcement Learning Approach

Xinge Li; Xiaoya Hu; Rongqing Zhang; Liuqing Yang

doi:10.1109/JIOT.2020.2989924

Routing Protocol Design for Underwater Optical Wireless Sensor Networks: A Multiagent Reinforcement Learning Approach

Xinge Li, Xiaoya Hu, Rongqing Zhang, Liuqing Yang

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

28 Scopus citations

Abstract

Underwater optical wireless sensor networks (UOWSNs) have been attracting many interests for the advantages of high transmission rate, ultrawide bandwidth, and low latency. However, due to limited energy resources and highly dynamic topology caused by the water flow movement, it is challenging to provide a low-consumption and reliable routing in UOWSNs. To tackle this issue, in this article, we propose an efficient routing protocol based on multiagent reinforcement learning, termed as DMARL, for UOWSNs. The network is first modeled as a distributed multiagent system, and residual energy and link quality are considered into the routing protocol design to improve the adaptation to a dynamic environment and the support of prolonging network life. Additionally, two optimization strategies are proposed to accelerate the convergence of the reinforcement learning algorithm. On the basis, a reward mechanism is provided for the distributed system. The simulation results show that the DMARL-based routing protocol has low energy consumption and high packet delivery ratio (over 90%), and it is suitable for networks where the average number of neighbor nodes is less than 14.

Original language	English (US)
Article number	9076600
Pages (from-to)	9805-9818
Number of pages	14
Journal	IEEE Internet of Things Journal
Volume	7
Issue number	10
DOIs	https://doi.org/10.1109/JIOT.2020.2989924
State	Published - Oct 2020

Bibliographical note

Funding Information:
Manuscript received November 5, 2019; revised March 2, 2020; accepted April 12, 2020. Date of publication April 23, 2020; date of current version October 9, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61471177 and Grant 61901302, and in part by the Open Research Fund from Shenzhen Research Institute of Big Data under Grant 2019ORF01014. (Corresponding author: Xiaoya Hu.) Xinge Li is with the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China (e-mail: xingeli@hust.edu.cn).

Publisher Copyright:
© 2014 IEEE.

Keywords

Dynamic environment
energy consumption
multiagent reinforcement learning (MARL)
routing protocol
underwater optical wireless sensor network (UOWSN)

Publisher link

10.1109/JIOT.2020.2989924

Find It

Find It at U of M Libraries

Cite this

@article{0066d99f9c5d4932a2ab2660e12a55ad,

title = "Routing Protocol Design for Underwater Optical Wireless Sensor Networks: A Multiagent Reinforcement Learning Approach",

abstract = "Underwater optical wireless sensor networks (UOWSNs) have been attracting many interests for the advantages of high transmission rate, ultrawide bandwidth, and low latency. However, due to limited energy resources and highly dynamic topology caused by the water flow movement, it is challenging to provide a low-consumption and reliable routing in UOWSNs. To tackle this issue, in this article, we propose an efficient routing protocol based on multiagent reinforcement learning, termed as DMARL, for UOWSNs. The network is first modeled as a distributed multiagent system, and residual energy and link quality are considered into the routing protocol design to improve the adaptation to a dynamic environment and the support of prolonging network life. Additionally, two optimization strategies are proposed to accelerate the convergence of the reinforcement learning algorithm. On the basis, a reward mechanism is provided for the distributed system. The simulation results show that the DMARL-based routing protocol has low energy consumption and high packet delivery ratio (over 90%), and it is suitable for networks where the average number of neighbor nodes is less than 14.",

keywords = "Dynamic environment, energy consumption, multiagent reinforcement learning (MARL), routing protocol, underwater optical wireless sensor network (UOWSN)",

author = "Xinge Li and Xiaoya Hu and Rongqing Zhang and Liuqing Yang",

note = "Funding Information: Manuscript received November 5, 2019; revised March 2, 2020; accepted April 12, 2020. Date of publication April 23, 2020; date of current version October 9, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61471177 and Grant 61901302, and in part by the Open Research Fund from Shenzhen Research Institute of Big Data under Grant 2019ORF01014. (Corresponding author: Xiaoya Hu.) Xinge Li is with the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China (e-mail: xingeli@hust.edu.cn). Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2020",

month = oct,

doi = "10.1109/JIOT.2020.2989924",

language = "English (US)",

volume = "7",

pages = "9805--9818",

journal = "IEEE Internet of Things Journal",

issn = "2327-4662",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "10",

}

TY - JOUR

T1 - Routing Protocol Design for Underwater Optical Wireless Sensor Networks

T2 - A Multiagent Reinforcement Learning Approach

AU - Li, Xinge

AU - Hu, Xiaoya

AU - Zhang, Rongqing

AU - Yang, Liuqing

N1 - Funding Information: Manuscript received November 5, 2019; revised March 2, 2020; accepted April 12, 2020. Date of publication April 23, 2020; date of current version October 9, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61471177 and Grant 61901302, and in part by the Open Research Fund from Shenzhen Research Institute of Big Data under Grant 2019ORF01014. (Corresponding author: Xiaoya Hu.) Xinge Li is with the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China (e-mail: xingeli@hust.edu.cn). Publisher Copyright: © 2014 IEEE.

PY - 2020/10

Y1 - 2020/10

N2 - Underwater optical wireless sensor networks (UOWSNs) have been attracting many interests for the advantages of high transmission rate, ultrawide bandwidth, and low latency. However, due to limited energy resources and highly dynamic topology caused by the water flow movement, it is challenging to provide a low-consumption and reliable routing in UOWSNs. To tackle this issue, in this article, we propose an efficient routing protocol based on multiagent reinforcement learning, termed as DMARL, for UOWSNs. The network is first modeled as a distributed multiagent system, and residual energy and link quality are considered into the routing protocol design to improve the adaptation to a dynamic environment and the support of prolonging network life. Additionally, two optimization strategies are proposed to accelerate the convergence of the reinforcement learning algorithm. On the basis, a reward mechanism is provided for the distributed system. The simulation results show that the DMARL-based routing protocol has low energy consumption and high packet delivery ratio (over 90%), and it is suitable for networks where the average number of neighbor nodes is less than 14.

AB - Underwater optical wireless sensor networks (UOWSNs) have been attracting many interests for the advantages of high transmission rate, ultrawide bandwidth, and low latency. However, due to limited energy resources and highly dynamic topology caused by the water flow movement, it is challenging to provide a low-consumption and reliable routing in UOWSNs. To tackle this issue, in this article, we propose an efficient routing protocol based on multiagent reinforcement learning, termed as DMARL, for UOWSNs. The network is first modeled as a distributed multiagent system, and residual energy and link quality are considered into the routing protocol design to improve the adaptation to a dynamic environment and the support of prolonging network life. Additionally, two optimization strategies are proposed to accelerate the convergence of the reinforcement learning algorithm. On the basis, a reward mechanism is provided for the distributed system. The simulation results show that the DMARL-based routing protocol has low energy consumption and high packet delivery ratio (over 90%), and it is suitable for networks where the average number of neighbor nodes is less than 14.

KW - Dynamic environment

KW - energy consumption

KW - multiagent reinforcement learning (MARL)

KW - routing protocol

KW - underwater optical wireless sensor network (UOWSN)

UR - http://www.scopus.com/inward/record.url?scp=85092704386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85092704386&partnerID=8YFLogxK

U2 - 10.1109/JIOT.2020.2989924

DO - 10.1109/JIOT.2020.2989924

M3 - Article

AN - SCOPUS:85092704386

SN - 2327-4662

VL - 7

SP - 9805

EP - 9818

JO - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

IS - 10

M1 - 9076600

ER -

Routing Protocol Design for Underwater Optical Wireless Sensor Networks: A Multiagent Reinforcement Learning Approach

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this