SC483 - Hands-on: Machine Learning in Optical Networks
Monday, 09 March
08:30 - 12:30
Short Course Level:
Massimo Tornatore, Politecnico di Milano, Italy, Darko Zibar, DTU FOTONIK, Denmark
Short Course Description:
Machine learning (ML) has recently attracted a surge of interest in optical networking research due to its pattern recognition and predictive capabilities for various key networking applications. Large-scale monitoring data are generated every day in optical networks, which makes ML a promising solution for decision making. In this short course, we introduce the fundamental concepts and principles of ML, both from theoretical and industrial viewpoints, and the key emerging technologies in this process. We survey existing work on various applications in optical networking domain, ranging from predictive maintenance to quality of transmission estimation. Moreover, we discuss integration of advanced ML models into the network control and management architecture, and discuss potential challenges therein. Finally, we carry out a hands-on tutorial for participants who are interested in real-world application of ML in optical networks. We aim to provide a general overview of the key problems, common formulations, existing methodologies and future directions. This course will inspire the audience and facilitate ML research and development in optical networking.
The outline is given below,
- Industrial Perspective
- Fundamental concept of ML
- ML Model Learning and Evaluation
- Applications in Networks
- Quality of Transmission
- Failure detection and identification
- Overview of other applications
- Control and Management Architecture
- Hand-on lab activity
Short Course Benefits:
This course should enable participants to,
- Identify industrial drivers for ML in optical networking industry
- Explain the machine learning classes and categories necessary to build relevant algorithms
- Determine most relevant ML algorithms used in practice
- Understand the current status of the technology and its applications
- Compare properties and requirements for various ML evaluation techniques
- Determine integration of ML in state-of-the-art network architecture.
- Design a hands-on tutorial based on a real industry use case
Short Course Audience:
The course is intended for interested people from academia and industry without any previous knowledge in machine learning. A basic understanding of optical fiber transmission can be helpful but is not a hard requirement. Attendance is also beneficial for machine learning experts with limited optical networking background who want to learn about the potential applications in the area of optical communication and networking.
Massimo Tornatore is currently an Associate Professor at Politecnico di Milano, Italy. He also holds an appointment as Adjunct Professor at University of California, Davis, USA and as visiting professor at University of Waterloo, Canada. His research interests include performance evaluation and design of communication networks (with an emphasis on optical networking technologies), and machine learning application for network management. In these areas, he co-authored more than 300 peer-reviewed conference and journal papers (with 13 best paper awards) and of the recently published Springer “Handbook of Optical Networks”. He is an active member of the Editorial Board of, among others, IEEE Communication Surveys and Tutorials, IEEE Communication Letters.
Darko Zibar received the M.Sc. degree in telecommunication and the Ph.D. degree in optical communications from the Technical University of Denmark, in 2004 and 2007, respectively. He was a Visiting Researcher with the Optoelectronic Research Group (Prof. John E. Bowers), University of California, Santa Barbara, CA, USA, in 2006 and 2008, where he worked on coherent receivers for analog optical links. In 2009, he was a Visiting Researcher with Nokia-Siemens Networks, where he worked on clock recovery techniques for polarization multiplexed systems. He is currently Associate Professor at DTU Fotonik, Technical University of Denmark. His research efforts are currently focused on the application of machine learning methods to optical communication, ultra-sensitive amplitude and phase detection and optical fibre sensing systems. He is a recipient of Young Researcher Award by University of Erlangen-Nurnberg, in 2016, for his contributions to applications of machine learning techniques to optical technologies. He was a part of the team that won the HORIZON 2020 prize for breaking the optical transmission barriers. In 2017, he was granted European Research Council (ERC) Consolidator Grant where the focus is on the demonstration of nonlinear-distortion free optical communication systems by employing modulation of eigenvalues.