Reinforcement Learning Based MAC Protocol (UW-ALOHA-QM) for Mobile Underwater Acoustic Sensor Networks

Park, Sung Hyun; Mitchell, Paul; Grace, David

doi:10.1109/access.2020.3048293

Cited by 25 publications

(20 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Diferent MAC and routing protocols use Artiicial Intelligence (AI) and Machine Learning (ML)-based techniques to solve dynamic underwater communication behaviour and challenges. RL-based approaches are developed over ALOHA protocol for reducing collisions [30,31]. Re-transmission of the data packet happens if the transmitter node does not receive the acknowledgement packet at the end of the guard time.…”

Section: Motivationmentioning

confidence: 99%

“…In an underwater environment, such a scheme delivers up to 30% improved throughput performance [29]. Moreover, [30], and [31] studied the terrestrial ALOHA-Q and implemented it in an underwater environment. ALOHA-Q protocols can utilize the channel eiciently with minimum collision and less overhead in time synchronization.…”

Section: Motivationmentioning

confidence: 99%

“…The existing acoustic communication protocols such as [12], [31] and [42] lack eiciency in multi-hop underwater communication. High network overhead occurs for acoustic communication to be reliable.…”

Section: Motivationmentioning

confidence: 99%

See 2 more Smart Citations

Reinforcement Learning-Based MAC Protocol for Underwater Multimedia Sensor Networks

Gazi

Ahmed

Misra

et al. 2022

ACM Trans. Sen. Netw.

View full text Add to dashboard Cite

High propagation delay, high error probability, floating node mobility, and low data-rate, are the key challenges for Underwater Wireless Multimedia Sensor Networks (UMWSNs). In this paper, we propose RL-MAC, a Reinforcement Learning (RL)-based Medium Access Control (MAC) protocol for multimedia sensing in an Underwater Acoustic Network (UAN) environment. The proposed scheme uses Transmission Opportunity (TXOP) for relay nodes in a multi-hop network for improved efficiency concerning the mobility of the relays and sensor nodes. The AP and relay nodes calculate traffic demands from the initial contention of the sensor nodes. Our solution uses Q-learning to enhance the contention mechanism at the initial phase of multimedia transmission. Based on the traffic demands, RL-MAC allocates TXOP duration for the uplink multimedia reception. Further, Structural Similarity Index Measure (SSIM) and compression techniques are used for calculating the image quality at the receiver side and reduce the image at the destination, respectively. We implement a prototype of the proposed scheme over an off-the-shelf, low-cost hardware setup. Moreover, extensive simulation over NS-3 shows a significant packet delivery ratio and throughput compared to the existing state-of-the-art.

show abstract

Section: Motivationmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning-Based MAC Protocol for Underwater Multimedia Sensor Networks

Gazi

Ahmed

Misra

et al. 2022

ACM Trans. Sen. Netw.

View full text Add to dashboard Cite

show abstract

“…The study wastes computing resources in that it merely selects one channel in a slot. Sung et al [28] proposed the UW-ALOHA-QM protocol, which use reinforcement learning to allow nodes to adapt to the time varying environment through trial-and-error interaction and thereby improve network resilience and adaptability. In the smart ocean scenario, it is necessary to adapt to changes in the network topology.…”

Section: Related Workmentioning

confidence: 99%

Backoff‐toleration‐based opportunistic MAC protocol for underwater acoustic sensor networks

Chen

2022

IET Communications

View full text Add to dashboard Cite

With the development of underwater internet, Underwater Acoustic Sensor Networks (UASNs) have become an important method for collecting marine parameters and data. The Medium Access Control (MAC) protocol is the underlying infrastructure of UASNs. It directly affects the utilization of the underwater acoustic channel and the overall performance of the network. The ALOHA protocol is the basis of the random accessing protocols. It freely accesses the channel, so the collision between data packets is very serious. To this end, this paper proposes a Backoff‐Toleration‐Based Opportunistic (BTBO) protocol. In this protocol, each sensor node opportunistically learns by backoffing tolerantly, and finds the optimal transmission time respectively to transmit the data packet. Simulation results show that the BTBO protocol has better throughput and average end‐to‐end delay. At the same time, the authors added adaptive design to the dynamic topology networks in the UASNs. The simulation results show that the protocol can effectively alleviate these problems and improve performance.

show abstract

“…In supporting underwater applications, some MAC protocols waste network resources and need further attention to meet the QoS requirements of target applications [ 7 , 8 ]. The oil/gas industry is considered critical infrastructure to several countries as it helps to improve their economic competitiveness and growth [ 6 , 9 ]. In the last decade, many incidents have occurred, such as the Deepwater Horizon oil spill in the Gulf of Mexico, which resulted in 11 people killed, 3.19 million barrels of oil entering and damaging the Gulf ecosystem, and a cost in damages estimated by British Petroleum (BP) of about $62 billion [ 10 , 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

DAMAC: A Delay-Aware MAC Protocol for Ad Hoc Underwater Acoustic Sensor Networks

Guqhaiman

Akanbi

Aljaedi

et al. 2021

Sensors

View full text Add to dashboard Cite

In a channel shared by several nodes, the scheduling algorithm is a key factor to avoiding collisions in the random access-based approach. Commonly, scheduling algorithms can be used to enhance network performance to meet certain requirements. Therefore, in this paper we propose a Delay-Aware Media Access Control (DAMAC) protocol for monitoring time-sensitive applications over multi-hop in Underwater Acoustic Sensor Networks (UASNs), which relies on the random access-based approach where each node uses Carrier Sense Multiple Access/Collision Avoidance (CSMA/CA) to determine channel status, switches nodes on and off to conserve energy, and allows concurrent transmissions to improve the underwater communication in the UASNs. In addition, DAMAC does not require any handshaking packets prior to data transmission, which helps to improve network performance in several metrics. The proposed protocol considers the long propagation delay to allow concurrent transmissions, meaning nodes are scheduled to transmit their data packets concurrently to exploit the long propagation delay between underwater nodes. The simulation results show that DAMAC protocol outperforms Aloha, BroadcastMAC, RMAC, Tu-MAC, and OPMAC protocols under varying network loads in terms of energy efficiency, communication overhead, and fairness of the network by up to 65%, 45%, and 726%, respectively.

show abstract

Reinforcement Learning Based MAC Protocol (UW-ALOHA-QM) for Mobile Underwater Acoustic Sensor Networks

Cited by 25 publications

References 41 publications

Reinforcement Learning-Based MAC Protocol for Underwater Multimedia Sensor Networks

Reinforcement Learning-Based MAC Protocol for Underwater Multimedia Sensor Networks

Backoff‐toleration‐based opportunistic MAC protocol for underwater acoustic sensor networks

DAMAC: A Delay-Aware MAC Protocol for Ad Hoc Underwater Acoustic Sensor Networks

Contact Info

Product

Resources

About