A Type-2 Fuzzy Genetic Approach to Uncertain & Dynamic Resilient Routing within Telecommunications Networks

Data and voice connections are an important part of any modern society, thus it is important for telecoms companies to provide resilience for network routing. Network conditions can fluctuate, redefining an optimal path through a network, which can introduce high levels of uncertainty. In this paper...

Full description

Saved in:
Bibliographic Details
Published in2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) pp. 1 - 6
Main Authors Veryard, Lewis, Hagras, Hani, Conway, Anthony, Owusu, Gilbert
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2020
Subjects
genetic algorithms
resilience routing
telecommunications
Type-2 fuzzy logic
Online AccessGet full text

Cover

More Information
Summary:Data and voice connections are an important part of any modern society, thus it is important for telecoms companies to provide resilience for network routing. Network conditions can fluctuate, redefining an optimal path through a network, which can introduce high levels of uncertainty. In this paper, we will present a type-2 fuzzy genetic system that can provide multiple routes between two locations with some ability to resist network fluctuations and uncertainty. We have tested the proposed system against a real world telecommunications data set with high levels of uncertainty, and compared this to a type-1 fuzzy system counterpart and the crisp system employed in the industry. The results indicate an average reduction in the occurrence of unique routes by 13%. Moreover, on average it increases the occurrence of a route occurring more than once by 26% when compared to a crisp version of the system. With Dijkstra's algorithm and A* being unable to perform the resilient routing task effectively.
ISSN:1558-4739
DOI:10.1109/FUZZ48607.2020.9177786