Skip to main content

How POST Luxembourg is leveraging Deep Learning to successfully troubleshoot the broadband network


“Nokia’s AI driven access analytics solution has given us the ability to proactively address issues, reducing customer calls by solving multiple issues in a single intervention and creating overall efficiencies in our troubleshooting process.”

- Patrick Rausch, Senior Project Manager, POST Luxembourg

High-resolution video, cloud services and the multiplication of connected devices require higher bandwidth as well as increased reliability. Today, for the copper medium to remain competitive relative to fiber, a similar quality of experience is expected from both an end-user and maintenance perspective. This is especially true given the uptake of Fiber in Europe, which stands at less than 50% for home subscribers.  See Figure 1.

FTTH/B Europe 2019

As a Tier-1 European service provider, POST Luxembourg was looking to improve the overall performance of its copper troubleshooting process to reduce OPEX and improve satisfaction among its customers. It was interested in utilizing artificial intelligence to diagnose impairments affecting the copper medium and in improving the efficiency of its field technicians in order to meet key performance metrics, including:

  • Reduced average handling time
  • Reduced field dispatch
  • Improved first call resolution

It adopted Nokia’s Home and Access Insights software to provide proactive analytics and actions to resolve network issues. The solution leverages Deep Learning along with domain expertise to deliver complete, highly accurate and reliable actionable troubleshooting insights.

POST Luxembourg ran a field validation campaign in their production network for several months, whereby different diagnosis insights and the troubleshooting recommendations were shared on each field technician’s tablet App. Field staff reported that they received correct and/or helpful diagnosis in 95% of the cases, together with the prediction of the capacity loss as well as the outstanding overall reliability. See Figure 2.

How POST Luxembourg is leveraging Deep Learning to successfully troubleshoot the broadband network Figure 2

Nokia’s home and access insights solution has enabled POST Luxembourg to meet their objectives in terms of OPEX savings and performance enhancements in many ways:

  • Field staff gain visibility on all DSL impacting problems before and during resolution and receive recommendations in terms of next best actions to efficiently restore the service.  This reduced both Time-to-Repair and truck rolls as agents were able to resolve issues on the first call.
  • With an accurate, pro-active and network wide diagnosis capabilities, POST Luxembourg has visibility on all issues that could be affecting subscriber lines, saving truck rolls and reducing averaging handling time  
  • The overall troubleshooting process has been transformed into an AI-driven automated process, simplifying the human effort at each step.

As service providers look to maintain the performance of their copper networks as fiber catches up, ensuring a positive subscriber experience remains paramount. Nokia’s work with POST Luxembourg is just one example of how service providers are gaining valuable AI driven network insights to support proactive issue resolution for their subscribers. To find out more, please visit our website at:


Share your thoughts on this topic by joining the Twitter discussion with @nokianetworks or @nokia using #CPS #AI

Patrick  Rausch

About Patrick Rausch

Patrick is a Senior Project Manager at POST Luxembourg, working as an interdisciplinary lead in infrastructure, residential troubleshooting and broadband technologies. Patrick is also in charge of staff training in the broadband domain, and is local loop and in-house expert and advisor and as such, also responsible for all related customer complaints.

Tweet POST Luxembourg at @PostTelecom

Nicolas  Dupuis

About Nicolas Dupuis

Winner of the two last Nokia global Conferences on AI, Nicolas Dupuis is a Technical Lead for AI Innovation & Machine Learning developments within Nokia Bell Labs. He is also a Distinguished Member of Technical Staff and the main author of 30+ patents. His strong technical background and experience in the broadband access network market led him to create pioneering product features that have been deployed by major service providers globally. He currently focuses on autonomous systems for network management, provisioning, optimization and troubleshooting.


Article tags