MENTOR will transform Europe’s global communication networks

European Industrial Doctorate (EID) MENTOR will provide a world class, advanced, interdisciplinary training programme for six early stage researchers (ESRs). The goal is to make them the next generation of engineering and research leaders in multi band optical communications. Our ESRs will spend 50% of their three years in academia and 50% in industry, a noteworthy feature of an EID.

colour wire single 1280x880
ai 1280x880
ml 1280x880

The aim of the project is to design the next generation of high-capacity optical networks, which are a key enabler of the global telecommunication infrastructure. Increasing demand (+ 20 % per year) requires a boost in capacity, and calls for operators to reduce the cost per transmitted bit. The search for a solution is leading researchers in the direction of ML techniques. In fact, ML is the technique of choice to tackle this kind of complex technical problem.

Overcoming new challenges

Optical fibre networks are major drivers in societal progress and a key enabler of the global telecommunication infrastructure. Optical networks underwent considerable changes over the past decade as consequence of a continuous growth (20%+ per year) of bandwidth demand. The current growth sets requirements in terms of capacity and costs for operators, who are seeking to decrease the cost per transmitted bit.


Several solutions have been proposed. Among them, wide-band networks are more favourable to network operators, compared to more (or novel) fibres. However, wide-band optical systems present new major challenges:

  • optical components must guarantee similar performance over a broad spectrum
  • network optimization is carried out on a non-flat spectrum
  • a much larger number of channels makes design, optimization and control a complex problem.

Therefore, the application of machine-learning (ML) techniques is of growing importance for high-capacity multi-band (MB) optical systems.

Machine-learning is becoming the choice technique to solve complex nonlinear technical problems

A great benefit of the training and research provided to the MENTOR Early Stage Researchers will be using realistic data, including historical monitored types – provided by the industrial partners – for designing, developing and testing algorithms crucial for real life application.

Thanks to the combination of partners (universities, a system vendor and telecommunication operators), MENTOR represents a unique consortium to facilitate the realistic implementation of ML&AI within the next generation of optical networks.