Optimizing Deep Learning-based Failure Management in Optical Networks by Monitoring Relative Neural Activity
Pedro, J. M.
; Costa, N.
Optimizing Deep Learning-based Failure Management in Optical Networks by Monitoring Relative Neural Activity, Proc International Conference on Optical Network Design and Modeling ONDM, Madrid, Spain, Vol. , pp. - , May, 2024.
Digital Object Identifier:
Abstract
Despite demonstrating exceptional performance in optical networks, neural networks often receive criticism due to their significant computational complexity. To address this, we propose a novel relative-neural-activity-based algorithm to optimize neural networks for low computational complexity and memory footprint for failure management in optical networks, with failure identification as the considered use-case. The results suggest up to 96.31% and 87.12% reduction in computational and memory requirements, respectively.
