Efficient Routing Protocol for Wireless Sensor Network based on Reinforcement Learning

Bouzid, Salah Eddine; Serrestou, Youssef; Raoof, Kosai; Omri, Mohamed Nazih

doi:10.1109/atsip49331.2020.9231883

Cited by 24 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To compare the performance of DRSIR and RSIR, we also evaluate the consumption of CPU and storage memory of its DQN and Q-learning I briefly summarizes the work related to DRSIR by showing the type of control routing employed, the employed RL/DRL type of learning approach, the RL/DRL adopted action, and the metrics evaluated. The work in [13]- [17] explored RL techniques, such as Q-learning, in SDN either to employ actions for choosing the proper routing protocol within the environment state or at the next-hop node when building a routing path. In the following paragraphs, we compare DRSIR with the routing solutions proposed in [20]- [30], which employed DRL techniques for routing in SDN.…”

Section: ) Cpu and Memory Analysismentioning

confidence: 99%

See 1 more Smart Citation

DRSIR: A Deep Reinforcement Learning Approach for Routing in Software-Defined Networking

Casas-Velasco

Rendón

Fonseca

2022

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

Traditional routing protocols employ limited information to make routing decisions which leads to slow adaptation to traffic variability and restricted support to the quality of service requirements of the applications. To address these shortcomings, in previous work, we proposed RSIR, a routing solution based on Reinforcement Learning (RL) in Software-Defined Networking (SDN). However, RL-based solutions usually suffer an increase in the learning process when dealing with large action and state spaces. This paper introduces a different routing approach called Deep Reinforcement Learning and Software-Defined Networking Intelligent Routing (DRSIR). DRSIR defines a routing algorithm based on Deep RL (DRL) in SDN that overcomes the limitations of RL-based solutions. DRSIR considers path-state metrics to produce proactive, efficient, and intelligent routing that adapts to dynamic traffic changes. DRSIR was evaluated by emulation using real and synthetic traffic matrices. The results show that this solution outperforms the routing algorithms based on the Dijkstra's algorithm and RSIR, in relation to stretching (stretch), packet loss, and delay. Moreover, the results obtained demonstrate that DRSIR provides a practical and viable solution for routing in SDN.

show abstract

Section: ) Cpu and Memory Analysismentioning

confidence: 99%

“…The solutions in [13]- [17] have employed Reinforcement Learning (RL) to optimize the selection of routing algorithms. Compared with supervised ML techniques, RL learns by trial and error in the interaction with the environment, and, thus, does not depend on labeled datasets.…”

Section: Introductionmentioning

confidence: 99%

DRSIR: A Deep Reinforcement Learning Approach for Routing in Software-Defined Networking

Casas-Velasco

Rendón

Fonseca

2022

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…The experimental evaluation confirmed that the developed algorithm had an enhanced stability period, pro-longed network lifetime, and reduced energy consumption in WSN. Bouzid et al 14 presented a novel routing protocol based on distributed reinforcement learning for WSN. The presented routing protocol effectively optimized energy consumption and the lifetime of WSN.…”

Section: Related Workmentioning

confidence: 99%

Effective neighbor node discovery using improved Bayesian clock synchronization‐gossip routing protocol in mobile low duty cycle wireless sensor network

Bethi

Moparthi

2022

Concurrency and Computation

View full text Add to dashboard Cite

In wireless application, mobile low duty cycle wireless sensor network (MLDC‐WSN) gained more attention among the researchers, because it includes advantages like growing node life, saving node power, and network reliability. However, the sleeping features and mobility of MLDC‐WSN results in topology change that restricts the speed of neighbor node discovery. To highlight this concern, a novel routing protocol named as improved Bayesian clock synchronization‐gossip routing protocol is proposed for an effective neighbor node discovery in MLDC‐WSN. The proposed routing protocol reduces end‐to‐end delay, and clock drifts problems. Also, the proposed routing protocol improves the clock synchronization and captures the neighbor discovery nodes by identifying the next neighbor set in the next moment, due to the prediction of the distance and movement speed of neighbors. Simulation and analytical results showed that the proposed routing protocol superiorly decreases the end‐to‐end delay and energy consumption compared to the existing algorithms.

show abstract

“…Q-routing is not designed for wireless sensor networks (WSN). Bouzid et al [12] proposed to adapt Q-routing to WSN context. In order to improve Q-routing, they changed the reward formula.…”

Section: Reinforcement Learning For Lt Optimisationmentioning

confidence: 99%

“…2 -routing kept the delay, however other coefficients computed with QoS metrics were added. In [4] and [12], the modified Q-routing offers the best performance compared to the original Q-routing. Finally, the quality of the measured delay was not discussed in any of these propositions.…”

Section: E Conclusionmentioning

confidence: 99%

Latency filtering for Q-routing on wireless networks

Bitaillou

Parrein

Andrieux

et al. 2021

2021 International Wireless Communications and Mobile Computing (IWCMC)

View full text Add to dashboard Cite

Q-routing is inspired by Q-learning, a reinforcement learning algorithm. Originally, it uses latency as routing metric. But, latency can be difficult to estimate especially in a noisy wireless environment. In this paper, we propose to filter the latency measure with a moving average, in order to improve the quality of service metrics such as packet delivery ratio and average delay. We compare our modification to the original Q-routing and use OLSRv2 as reference routing protocol. We observe an improvement of the average delivery time on a wireless grid of 3 % compared to the original Q-routing. On our mobility scenario, the number of routes changes is at least twice lower (from 6 to 3 route changes between the two approaches in this scenario). The gain on QoS metrics depends mainly on the speed of the nodes. These improvements are obtained without making Q-routing more complex as a moving average is added. We provide all the materials to conduct reproducible research on our public git repository.

show abstract

Efficient Routing Protocol for Wireless Sensor Network based on Reinforcement Learning

Cited by 24 publications

References 19 publications

DRSIR: A Deep Reinforcement Learning Approach for Routing in Software-Defined Networking

DRSIR: A Deep Reinforcement Learning Approach for Routing in Software-Defined Networking

Effective neighbor node discovery using improved Bayesian clock synchronization‐gossip routing protocol in mobile low duty cycle wireless sensor network

Latency filtering for Q-routing on wireless networks

Contact Info

Product

Resources

About