A Methodology to Comprehend the Features Importance in Hybrid RSA Using ML

Le résumé fourni par la source

The hybrid routing and spectrum assignment (HRSA) algorithm for the RSA problem in elastic optical networks (EONs) outperforms the classical RSA algorithms. However, the decision-making process remains largely unexplained. Here, we propose a methodology to study how topological features steer HRSA's adaptive choices between RSA ordering for source-destination node pairs in EONs. Using machine learning models, we aim to identify key topological metrics that govern HRSA's choices. The methodology provides a roadmap for deriving insights into the most relevant metrics to explain HRSA algorithm. Results show that it is possible to identify the minimum set of features that explain HRSA.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.