FSS: Fuzzy Supervised Learning for Optimal Path Selection in RPL

IPV6 routing protocol for low power lossy network (RPL) is a standardized routing protocol developed by the IETF ROLL working group. RPL has attained a lot of attraction to the research community as it demands modification adding to its improvement. RPL constructs a Destination Oriented Directed Acy...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of physics. Conference series Ročník 1911; číslo 1; s. 12016 - 12024
Hlavní autoři: Gopika, D., Rukmani, P.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Bristol IOP Publishing 01.05.2021
Témata:
Algorithms
Artificial neural networks
Decision trees
Learning theory
Machine learning
Physics
Routing (telecommunications)
Supervised learning
ISSN:1742-6588, 1742-6596
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:IPV6 routing protocol for low power lossy network (RPL) is a standardized routing protocol developed by the IETF ROLL working group. RPL has attained a lot of attraction to the research community as it demands modification adding to its improvement. RPL constructs a Destination Oriented Directed Acyclic Graph (DODAG) considering the metrics and constraints through explicit Objective Functions (OFs). The OFs chooses the best parent for reliable data communication. The existing objective function due to a single metric lacks in satisfying the requirement of real-time IoT applications. Still, the mobility aspect of the node is not considered in the objective function for optimal path selection. In the proposed methodology a Fuzzy Supervised Learning algorithm for quality node prediction using the composite metric based OF from the candidate parent set. The testing phase shows 93% accuracy of prediction with Artificial Neural Network (ANN) classifier which outperforms Naïve Bayes and Decision Tree (DT).
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1911/1/012016