scholarly journals Distributed Learning for Dynamic Channel Access in Underwater Sensor Networks

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 992 ◽  
Author(s):  
Huicheol Shin ◽  
Yongjae Kim ◽  
Seungjae Baek ◽  
Yujae Song
Keyword(s):  
Sensor Networks ◽  
Network Throughput ◽  
Underwater Sensor Networks ◽  
Channel Access ◽  
Q Learning ◽  
Acoustic Sensor Networks ◽  
Access Problem ◽  
Markov Decision ◽  
Dynamic Channel ◽  
Physical Features

In this study, the problem of dynamic channel access in distributed underwater acoustic sensor networks (UASNs) is considered. First, we formulate the dynamic channel access problem in UASNs as a multi-agent Markov decision process, wherein each underwater sensor is considered an agent whose objective is to maximize the total network throughput without coordinating with or exchanging messages among different underwater sensors. We then propose a distributed deep Q-learning-based algorithm that enables each underwater sensor to learn not only the behaviors (i.e., actions) of other sensors, but also the physical features (e.g., channel error probability) of its available acoustic channels, in order to maximize the network throughput. We conduct extensive numerical evaluations and verify that the performance of the proposed algorithm is similar to or even better than the performance of baseline algorithms, even when implemented in a distributed manner.

scholarly journals Packet Flow Based Reinforcement Learning MAC Protocol for Underwater Acoustic Sensor Networks

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2284
Author(s):  
Ibrahim B. Alhassan ◽  
Paul D. Mitchell
Keyword(s):  
Sensor Networks ◽  
Mac Protocol ◽  
Propagation Delay ◽  
Basic Function ◽  
Acoustic Sensor ◽  
Underwater Acoustic Sensor Networks ◽  
Medium Access ◽  
Underwater Acoustic ◽  
Q Learning ◽  
Acoustic Sensor Networks

Medium access control (MAC) is one of the key requirements in underwater acoustic sensor networks (UASNs). For a MAC protocol to provide its basic function of efficient sharing of channel access, the highly dynamic underwater environment demands MAC protocols to be adaptive as well. Q-learning is one of the promising techniques employed in intelligent MAC protocol solutions, however, due to the long propagation delay, the performance of this approach is severely limited by reliance on an explicit reward signal to function. In this paper, we propose a restructured and a modified two stage Q-learning process to extract an implicit reward signal for a novel MAC protocol: Packet flow ALOHA with Q-learning (ALOHA-QUPAF). Based on a simulated pipeline monitoring chain network, results show that the protocol outperforms both ALOHA-Q and framed ALOHA by at least 13% and 148% in all simulated scenarios, respectively.

scholarly journals A TDoA Localization Scheme for Underwater Sensor Networks with Use of Multilinear Chirp Signals

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
En Cheng ◽  
Xizhou Lin ◽  
Shengli Chen ◽  
Fei Yuan
Keyword(s):  
Sensor Networks ◽  
Fractional Fourier Transform ◽  
Detection Efficiency ◽  
Multiple Access Interference ◽  
Underwater Sensor Networks ◽  
Theoretical Derivation ◽  
Acoustic Sensor Networks ◽  
Localization Scheme ◽  
Efficient Detection ◽  
Node Location

Due to the multipath, Doppler, and other effects, the node location signals have high probability of access collision in the underwater acoustic sensor networks (UW-ASNs), and therefore, it causes the signal lost and the access block; therefore, it constrains the networks performance. In this paper, we take the multilinear chirp (MLC) signals as the location signal to improve the anticollision ability. In order to increase the detection efficiency of MLC, we propose a fast efficient detection method called mixing change rate-fractional Fourier transform (MCR-FrFT). This method transforms the combined rates of MLC into symmetry triangle rates and then separates the multiuser signals based on the transformed rates by using FrFT. Theoretical derivation and simulation results show that the proposed method can detect the locations signals, estimate the time difference of arrival (TDoA), reduce the multiple access interference, and improve the location performance.

scholarly journals A Cluster Based Localization Scheme with Partition Handling for Mobile Underwater Acoustic Sensor Networks

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1039 ◽  
Author(s):  
Tariq Islam ◽  
Yong Kyu Lee
Keyword(s):  
Energy Consumption ◽  
Sensor Networks ◽  
Sensor Nodes ◽  
Underwater Sensor Networks ◽  
Network Partitioning ◽  
Acoustic Sensor Networks ◽  
Localization Scheme ◽  
Control Scheme ◽  
Partitioned Networks ◽  
Retransmission Control

Many applications of underwater sensor networks (UWSNs), such as target tracking, reconnaissance and surveillance, and marine life monitoring require information about the geographic locations of the sensed data. This makes the localization of sensor nodes a crucial part of such underwater sensing missions. In the case of mobile UWSNs, the problem becomes challenging, not only due to a need for the periodic tracking of nodes, but also due to network partitioning as a result of the pseudo-random mobility of nodes. In this work, we propose an energy efficient solution for localizing nodes in partitioned networks. Energy consumption is minimized by clustering unlocalized partitioned nodes and allowing only clusterheads to carry out a major part of the localization procedure on behalf of the whole cluster. Moreover, we introduce a retransmission control scheme that reduces energy consumption by controlling unnecessary transmission. The major design goal of our work is to maximize localization coverage while keeping communication overheads at a minimum, thus achieving better energy efficiency. The major contributions of this paper include a clustering technique for localizing partitioned nodes and a retransmission control strategy that reduces unnecessary transmissions.

Sign in / Sign up

Export Citation Format

Share Document