Reinforcement Learning to Enhance Digital Twin-Based EDFA Fault Prediction in Optical Networks
Journal article, 2026
This study proposes a novel two-stage framework that integrates Digital Twin (DT) with Reinforcement Learning (RL) for failure prediction in optical communication networks. The framework focuses on optical amplifier failures, one of the most critical elements impacting network reliability. In the first stage, DTs are employed using the GNPy (Gaussian Noise model in Python) open-source optical network simulation framework to emulate amplifier behavior across diverse operational scenarios. This enables the generation of a comprehensive training dataset to train the Machine Learning (ML) model based on Long Short-Term Memory (LSTM). The LSTM model is able to achieve an accuracy of 98%. In the second stage, RL is applied to enhance the predictive accuracy to 99.5% and to improve the adaptability of the model. The LSTM model is rewarded for accurate predictions using external feedback, allowing it to iteratively refine its performance. This feedback-driven learning mechanism strengthens the robustness and decision-making capabilities of the model under dynamic network conditions. The proposed fine-tuning of the DT-based ML model using RL with external feedback enables proactive and adaptive fault management in optical networks.
proactive failure management
Optical waveguides
Circuits
Feedback
digital twin
network reliability
Communication systems
Deep learning
Radio broadcasting
fault detection
Quality of transmission
Optical fiber communication
Optical fiber networks
Frequency modulation
reinforcement learning
soft failures
optical amplifiers
Optical fibers
Author
Mashboob Cheruvakkadu Mohamed
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Renato Ambrosone
Polytechnic University of Turin
Muhammad Umar Masood
Polytechnic University of Turin
Gulmina Malik
Polytechnic University of Turin
Stefano Straullu
LINKS Foundation
Antonino Nespola
LINKS Foundation
Sai Kishore Bhyri
Optical Networks
Antonio Napoli
Optical Networks
Joao Pedro
Instituto Superior Tecnico
Optical Networks
Sasipim Srivallapanondh
Optical Networks
Gabriele Maria Galimberti
Optical Networks
Walid Wakim
Nokia
Vittorio Curri
Polytechnic University of Turin
IEEE Photonics Technology Letters
1041-1135 (ISSN) 19410174 (eISSN)
Vol. 38 17 1227-1230Subject Categories (SSIF 2025)
Communication Systems
Computer Sciences
Telecommunications
DOI
10.1109/LPT.2026.3681516