Dr. David Hock
Dr. David Hock is the Director of Research at Infosim®.With the solution StableNet®, Infosim® is a leading manufacturer of automated Service Fulfillment and Service Assurance solutions. StableNet® incorporates Fault, Performance, Configuration, and Services Management on a single platform.
At Infosim®, Dr. Hock is coordinating the research activities across all business areas, including among others Automated Network & Service Management, 5G/6G, Quantum Communication/QKD as well as many activities related to AI and Machine Learning. Since the very first day when starting as a spin off of the University of Würzburg, Infosim has always been very actively participating in different research activities and conducted numerous funded research projects together with other industry partners as well as Research institutes and academia. This is a very good driver for innovation and helps to bring together both the theoretical/methodological research work and the practical applications of it.
Prior to Infosim®, Dr. Hock was working as a Research Assistant and Post Doctoral Researcher at the Chair of Communication Networks at the Institute of Computer Science in Würzburg where he finished his Dr. rer. nat. degree in 2014.
Session
Communication networks are vital for society and network availability is therefore crucial. There is a huge potential in using network telemetry data and machine learning algorithms to proactively detect anomalies and remedy network problems before they affect the customers. In practice, however, there are many steps on the way to get there. In this presentation we would like to share the status of an ongoing research collaboration with the purpose of simplifying the operation and increase the availability of fiber access networks.
The research project is part of a CELTIC_NEXT flagship research program (AI-NET) that has the overall target of accelerating the digital transformation in Europe by intelligent network automation.
The project (“Palantir”) consists of two parts:
A field trial in a Swedish municipality network where telemetry data from more than 500 access switches, connecting more than 12000 households, are collected and analyzed for anomalies using machine learning. (The field trial is planned to be expanded to cover 1000 access switches during the project and synthetic errors are planned to be injected to emulate error situations.)
The second part is a demonstrator to be set up at Fraunhoffer HHI in Berlin (starting in October 2023). The demonstrator covers an end to end network and aims to demonstrate all aspects of the research program.
In the presentation we would like to describe our field trial and demonstrator, share our experiences in collecting and analyzing telemetry data in the field and describe our conclusions so far.
We would also like to open up for a discussion with the DENOG15 participants on what real life error situations that causes the most problems in fiber access networks and whether they would be suitable for AI detection (and potentially also for error emulation in our field trial).
Project Palantir is a collaboration between:
• Fraunhofer HHI (German Research Institute): Demonstrator
• Lunet (Swedish operator - open access municipality network): Field trial
• RISE (Independent Swedish research institute): Field trial
• Savantic (Swedish AI specialists): Field trial
• Waystream (FTTX vendor): Field trial and demonstrator