Artificial intelligence and machine learning methods for intelligent optical networks

• Grant number: 23/01433-0
• Support Opportunities: Scholarships abroad - Research
• Start date: September 01, 2023
• End date: August 31, 2024
• Field of knowledge: Engineering - Electrical Engineering - Telecommunications
• Principal Investigator: Gustavo Sousa Pavani
• Grantee: Gustavo Sousa Pavani
• Host Investigator: Christine Tremblay
• Host Institution: Centro de Matemática, Computação e Cognição (CMCC). Universidade Federal do ABC (UFABC). Santo André , SP, Brazil
• Institution abroad: Université du Québec à Montréal (UQÀM), Canada
• Associated research grant: 15/24341-7 - New strategies to confront with the threat of capacity exhaustion, AP.TEM

Abstract

Artificial Intelligence (AI) and Machine Learning (ML) techniques may play a significant role in the intelligent control of optical networks by offering improved performance over traditional methods. This is of particular importance as optical networks constitute the foundations of many of today's communication systems. In this project, we propose the investigation of the Quality of Transmission (QoT) and Optical Performance Monitoring (OPM) by using Supervised Learning models. Those models can be used to estimate and forecast the QoT of the lightpaths, or to provide early detection of anomalies in the network that may affect the QoT of the lightpaths. We also investigate, for the first time, the routing in Filterless Optical Networks (FON) equipped with programmable optical switches by means of the Ant Colony Optimization (ACO) algorithm. In effect, the ACO algorithm has been successfully employed in many different optical networking architectures, such as Wavelength-Switched and Elastic Optical Networks. In this context, it can be considered a suitable candidate for controlling the FON. Finally, this project establishes a new international collaboration with the research group led by Prof. Christine Tremblay at ÉTS-Montreal. (AU)

Scientific publications

(The scientific publications listed on this page originate from the Web of Science or SciELO databases. Their authors have cited FAPESP grant or fellowship project numbers awarded to Principal Investigators or Fellowship Recipients, whether or not they are among the authors. This information is collected automatically and retrieved directly from those bibliometric databases.)

PAVANI, GUSTAVO SOUSA; SENGUPTA, DIPANKAR; FREIRE-HERMELO, MARIA; LAVIGNOTTE, ANTOINE; TREMBLAY, CHRISTINE; LEPERS, CATHERINE. Reinforcement learning-based wavelength-dependent power control for WDM systems. Optical Fiber Technology, v. 95, p. 8-pg., 2025-10-31. (15/24341-7, 23/01433-0)