A Time-Slotted Data Gathering Medium Access Control Protocol Using Q-Learning for Underwater Acoustic Sensor Networks

Ahmed, Faisal; Cho, Ho-Shin

doi:10.1109/access.2021.3068407

Cited by 25 publications

(12 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When multiple interferes exists, the following condition must be met according to (6) for decoding the received signal:…”

Section: System Modelmentioning

confidence: 99%

“…MAC protocols are mainly classified as contention-free and contention-based protocols [6]. For underwater MAC protocols, contention-based protocols are preferred as they can fully utilize the underwater channel bandwidth [7].…”

Section: Introductionmentioning

confidence: 99%

“…It is widely applied in wireless sensor networks because it does not require prior knowledge of the environment or training data to determine the optimal solution. Moreover, it can operate distributively and has low complexity and computational requirements [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Reinforcement Learning-Based Power Control for MACA-Based Underwater MAC Protocol

Ahmed

Cho²,

Shitiri

et al. 2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

A major amount of the energy of battery-powered sensors is spent during packet transmissions. This issue has led to the development of power-control-based multiple-access collision avoidance (MACA) protocols that can reduce the packet transmission power and conserve energy. However, the reduction in transmission power renders the packets susceptible to collisions. To reduce these collisions while maintaining high energy efficiency, we propose a power control protocol that utilizes reinforcement learning to choose the optimal transmission power. The total reward is determined by the occurrence of a collision, amount of transmission power used, frequency of DATA packet retransmissions, and update of the interference range. A key feature of the proposed protocol is that it enables sensors to prevent collisions without any prior knowledge of interferences, thus eliminating the need for additional signaling. Further, simulation results reveal that compared with benchmark protocols such as collision avoidance power control media access control (MAC), two-level power control MAC, and MACA-based power control MAC protocols, the proposed protocol improves network throughput while minimizing the network energy consumption and collisions per packet. The efficacy of the proposed protocol is demonstrated through results obtained using varying average traffic loads.INDEX TERMS collisions, interference, medium access control, power control, Q-learning, underwater acoustic sensor networks.

show abstract

“…When multiple interferes exists, the following condition must be met according to (6) for decoding the received signal:…”

Section: System Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning-Based Power Control for MACA-Based Underwater MAC Protocol

Ahmed

Cho²,

Shitiri

et al. 2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…To this end, the MAC strategies in TRNs like CSMA, CDMA, etc. are not sufficient to avoid transmission collisions in UANs [8][9][10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Impact and Analysis of Spatial Correlation on Slotted Based MAC in UANs

Wang

Guan

2021

2021 IEEE International Conference on Communications Workshops (ICC Workshops)

View full text Add to dashboard Cite

The propagation delay is non-negligible in underwater acoustic networks (UANs) since the propagation speed is five orders of magnitude smaller than the speed of light. In this case, space and time factors are strongly coupled to determine the collisions of packet transmissions. To this end, this paper analyzes the impact of spatial-time coupling on slotted medium access control (MAC). We find that both inter-slot and intraslot collisions may exist, and the inter-slot collision may span multiple slots. The sending slot dependent interference regions could be an annulus inside the whole transmission range. It is pointed out that there exist collision-free regions when a guard interval larger than a packet duration is used in the slot setting. In this sense, the long slot brings spatial reuse in a transmission range. However, we further find that the successful transmission probabilities and throughput are the same for the slot lengths of one packet duration and two packet durations. Simulation results show that the maximum successful transmission probability and throughput can be achieved by a guard interval less than a packet duration, which is much shorter than the existing slot setting in typical Slotted-ALOHA. Simulations also show that the spatial impact is greater for vertical transmission than for horizontal transmissions due to the longer vertical transmission range in three-dimensional UANs.

show abstract

“…To minimize the average delay of transmitting nodes, an efficient energy sharing method is presented using the Q-learning algorithm. In [18], Q-learning-based Medium Access Control (MAC) protocol for underwater sensor networks is studied. Without extra message exchange, a node learns to optimize back-off slots to reduce collision through trial-and-error.…”

mentioning

confidence: 99%

Learning nodes: machine learning-based energy and data management strategy

Kim

Lee

2021

J Wireless Com Network

View full text Add to dashboard Cite

The efficient use of resources in wireless communications has always been a major issue. In the Internet of Things (IoT), the energy resource becomes more critical. The transmission policy with the aid of a coordinator is not a viable solution in an IoT network, since a node should report its state to the coordinator for scheduling and it causes serious signaling overhead. Machine learning algorithms can provide the optimal distributed transmission mechanism with little overhead. A node can learn by itself by utilizing the machine learning algorithm and make the optimal transmission decision on its own. In this paper, we propose a novel learning Medium Access Control (MAC) protocol with learning nodes. Nodes learn the optimal transmission policy, i.e., minimizing the data and energy queue levels, using the Q-learning algorithm. The performance evaluation shows that the proposed scheme enhances the queue states and throughput.

show abstract

A Time-Slotted Data Gathering Medium Access Control Protocol Using Q-Learning for Underwater Acoustic Sensor Networks

Abstract: This study was supported in part by the BK21 FOUR project funded by the Ministry of Education, Korea (4199990113966) and the project "Development of Distributed Underwater Monitoring and Control Networks" funded by the Ministry of Oceans and Fisheries, South Korea.

Cited by 25 publications

References 39 publications

Reinforcement Learning-Based Power Control for MACA-Based Underwater MAC Protocol

Reinforcement Learning-Based Power Control for MACA-Based Underwater MAC Protocol

Impact and Analysis of Spatial Correlation on Slotted Based MAC in UANs

Learning nodes: machine learning-based energy and data management strategy

Contact Info

Product

Resources

About