CARMA: Channel-Aware Reinforcement Learning-Based Multi-Path Adaptive Routing for Underwater Wireless Sensor Networks

Valerio, Valerio Di; Presti, Francesco Lo; Petrioli, Chiara; Picari, Luigi; Spaccini, Daniele; Basagni, Stefano

doi:10.1109/jsac.2019.2933968

Cited by 79 publications

(18 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the routing direction information of each node is updated through periodically broadcasting. Channel-Aware Reinforcement learning-based Multi-path Adaptive routing (CARMA) is a learning-based protocol that uses reinforcement learning framework to select an optimal candidate set [ 26 ]. The performance of this protocol is closely correlated to the effectiveness and reliability of the estimation of the network information.…”

Section: Relate Workmentioning

confidence: 99%

Cross-Layer-Aided Opportunistic Routing for Sparse Underwater Wireless Sensor Networks

Zhao

Lun

Xue

et al. 2021

Sensors

View full text Add to dashboard Cite

Underwater wireless sensor networks (UWSNs) have emerged as a promising technology to monitor and explore the oceans instead of traditional undersea wireline instruments. Traditional routing protocols are inefficient for UWSNs due to the specific nature of the underwater environment. In contrast, Opportunistic Routing (OR) protocols establish an online route for each transmission, which can well adapt with time-varying underwater channel. Cross-layer design is an effective approach to combine the metrics from different layers to optimize an OR routing in UWSNs. However, typical cross-layer OR routing protocols that are designed for UWSNs suffer from congestion problem at high traffic loads. In this paper, a Cross-Layer-Aided Opportunistic Routing Protocol (CLOR) is proposed to reduce the congestion in multi-hop sparse UWSNs. The CLOR consists of a negotiation phase and transmission phase. In the negotiation phase, the cross-layer information in fuzzy logic is utilized to attain an optimal forwarder node. In the transmission phase, to improve the transmission performance, a burst transmission strategy with network coding is exploited. Finally, we perform simulations of the proposed CLOR protocol in a specific sea region. Simulation results show that CLOR significantly improves the network performances at various traffic rates compared to existing protocols.

show abstract

Section: Relate Workmentioning

confidence: 99%

Cross-Layer-Aided Opportunistic Routing for Sparse Underwater Wireless Sensor Networks

Zhao

Lun

Xue

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Q-learning is used, where the node has packets to forward based on the state of the buffer, remaining energy, and proximity of adjacent nodes to select the next sender node. In [15], a channel-aware RL-oriented adaptive path selection technique is introduced for multi-hop UWSN. The protocol switches between single-path and multi-path routing accomplish joint optimization in energy consumption and packet delivery ratio.…”

Section: Related Workmentioning

confidence: 99%

NetAI-Gym: Customized Environment for Network to Evaluate Agent Algorithm using Reinforcement Learning in Open-AI Gym Platform

Vidyadhar¹,

Nagaraj²,

Ashoka³

2021

IJACSA

View full text Add to dashboard Cite

The growing size of the network imposes computational overhead during network route establishment using conventional approaches of the routing protocol. The alternate approach in contrast to the route table updating mechanism is the rule-based method, but this also provides a limited scope in the dynamic networks. Therefore, reinforcement learning promises a better way of finding the route, but it requires an evaluation platform to build a model synchronization between route and agent. Unfortunately, the de-facto platform for agent evaluation, namely Open-AI Gym, does not provide a suitable networking environment. Therefore, this paper aims to propose a networking environment as a novel contribution by designing a suitable customized environment for a network synchronically with Open-AI Gym. The successful deployment of the proposed network environment: NetAI-Gym provides a functional and practical result that can be used further to develop routing mechanisms based on Q-learning. The validation of the proposed NetAI-Gym is carried out with different nodes in the network regarding Episodes Vs. Reward. The experimental outcome justifies the validity of the proposed NetAI-Gym that it is suitable for solving network-related problems.

show abstract

“…The limitation of this proposed model is that this algorithm is fully based on the non-linear correlation between the parameters, so it is not suitable for real-world targets. Valerio Di Valerio, et al, have proposed a new data forwarding scheme based on the various relay selection routing algorithms for WSN in Underwater scenarios [10] - [13] . This routing algorithm is always swiftly adapting to the overwhelming dynamic change of the underwater environments.…”

Section: Related Workmentioning

confidence: 99%

Energy-eﬀicient virtual infrastructure based geo-nested routing protocol for wireless sensor networks

Varadharajan¹,

Gopalakrishnan²,

Varadharajan³

et al. 2021

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

CARMA: Channel-Aware Reinforcement Learning-Based Multi-Path Adaptive Routing for Underwater Wireless Sensor Networks

Cited by 79 publications

References 22 publications

Cross-Layer-Aided Opportunistic Routing for Sparse Underwater Wireless Sensor Networks

Cross-Layer-Aided Opportunistic Routing for Sparse Underwater Wireless Sensor Networks

NetAI-Gym: Customized Environment for Network to Evaluate Agent Algorithm using Reinforcement Learning in Open-AI Gym Platform

Energy-eﬀicient virtual infrastructure based geo-nested routing protocol for wireless sensor networks

Contact Info

Product

Resources

About