A Survey on Machine Learning Software-Defined Wireless Sensor Networks (ML-SDWSNs): Current Status and Major Challenges

Jurado-Lasso, F. Fernando; Marchegiani, Letizia; Jurado, J. F.; Abu‐Mahfouz, Adnan M.; Fafoutis, Xenofon

doi:10.1109/access.2022.3153521

Cited by 28 publications

(15 citation statements)

References 153 publications

(139 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We model the network as a Software-Defined Wireless Sensor Network (SDWSN). This architecture adopts concepts from Software-Defined Networking (SDN) which divides the control from the data functions, allowing the logically centralized controller to become reprogrammable and the WSN to be abstracted for applications and network services [19]. SDN separates the network into three network planes: application, control, and data plane.…”

Section: B Sdwsnsmentioning

confidence: 99%

“…Lastly, the data plane is the network infrastructure with little intelligence that follows orders from the control plane. Readers interested in a thorough background, challenges, and benefits of SDWSNs can refer to [19]- [21].…”

Section: B Sdwsnsmentioning

confidence: 99%

“…Overall the entire network infrastructure runs on a lightweight embedded operating system. Among the available embedded operating systems in the market [19], we have selected Contiki-NG [24] because (i) it is open-source, well documented, and it has a large community, (ii) it is widely used in the research community, (iii) it provides the implementation of TSCH and Orchestra, (iv) it can run on both Cooja network simulator [25] and real hardware. To align with SDWSN principles, we have re-engineered the protocol stack from layer three and above to support the following five functionalities.…”

Section: A Data Planementioning

confidence: 99%

“…This section takes the reader through the design and implementation of a reinforcement learning approach to optimize the slotframe size of TSCH in SDN-based IoT networks considering the user requirements. Readers interested in RL can refer to [27] and its applications to SDWSNs in [19].…”

Section: Reinforcement Learning Modulementioning

confidence: 99%

See 3 more Smart Citations

ELISE: A Reinforcement Learning Framework to Optimize the Sloftframe Size of the TSCH Protocol in IoT Networks

Lasso¹,

Barzegaran²,

Jurado³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>The Industrial Internet of Things (IIoT) is shaping the next generation of cyber-physical systems to improve the future industry for smart cities. It has created novel and essential applications that require specific network performance to enhance the quality of services. Since network performance requirements are application-oriented, it is of paramount importance to provide tailored solutions that seamlessly manage the network resources and orchestrate the network to satisfy user requirements. In this article, we propose ELISE, a Reinforcement Learning (RL) framework to optimize the slotframe size of the Time Slotted Channel Hopping (TSCH) protocol in IIoT networks while considering the user requirements. We primarily address the problem of designing a framework that self-adapts to the optimal slotframe length that best suits the user’s requirements. The framework takes care of all functionalities involved in the correct functioning of the network, while the RL agent instructs the framework with a set of actions to determine the optimal slotframe size each time the user requirements change. We evaluate the performance of ELISE through extensive analysis based on simulations and experimental evaluations on a testbed to demonstrate the efficiency of the proposed approach in adapting network resources at runtime to satisfy user requirements.</p>

show abstract

Section: B Sdwsnsmentioning

confidence: 99%

Section: B Sdwsnsmentioning

confidence: 99%

Section: A Data Planementioning

confidence: 99%

Section: Reinforcement Learning Modulementioning

confidence: 99%

See 2 more Smart Citations

ELISE: A Reinforcement Learning Framework to Optimize the Sloftframe Size of the TSCH Protocol in IoT Networks

Lasso¹,

Barzegaran²,

Jurado³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The sensing range of sensors is an issue as smaller ranges would cover smaller areas whereas larger ranges would result in delay and inaccuracy also increasing the cost and size of node. Various machine learning software defined wireless sensor networks have been surveyed in [6]. Their current status and challenges faced are also described.…”

Section: Literature Surveymentioning

confidence: 99%

Wireless sensor networks for forest fire monitoring: Issues and Challenges

Salaria

Singh

Sharma

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Forest fires have recently been the most critical issue faced by the world. The huge environmental, economic, and societal damages caused by wildfires are hindrances to social development. The increasing figures of such instances since the last few years make it the need of the hour to start considering it on priority and take appropriate actions. For this, intense knowledge is required about the nature of forest fires, their causes and appropriate technology to be used. Wireless sensor networks have always been a preferable technology in such kind of disaster management and environmental monitoring scenarios. However, there are yet some prominent issues that affect the overall performance of wireless sensor networks, especially in harsh terrains like forests. In this paper, information has been provided about the causes, damages and aftereffects of forest fires. Moreover, a study has been conducted on various articles highlighting the issues and challenges being faced in wireless sensor networks. The paper further provides a simple and easily understandable analysis highlighting the types and priority of challenges. This would benefit the researchers in identifying the current research gaps in the field of wireless sensor networks, especially in applications like forest fire monitoring or environmental monitoring and disaster management.

show abstract

Natural Image Reconstruction for Noise-Affected Satellite Images Using ICA

Rani¹,

Singh²,

Rawat³

et al. 2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

A Survey on Machine Learning Software-Defined Wireless Sensor Networks (ML-SDWSNs): Current Status and Major Challenges

Abstract: and Turkey. The document reflects only the authors' view, and the Commission is not responsible for any use that may be made of the information it contains. Danish participants are supported by Innovation Fund Denmark under grant agreemet No. 0228-00004A.

Cited by 28 publications

References 153 publications

ELISE: A Reinforcement Learning Framework to Optimize the Sloftframe Size of the TSCH Protocol in IoT Networks

ELISE: A Reinforcement Learning Framework to Optimize the Sloftframe Size of the TSCH Protocol in IoT Networks

Wireless sensor networks for forest fire monitoring: Issues and Challenges

Natural Image Reconstruction for Noise-Affected Satellite Images Using ICA

Contact Info

Product

Resources

About