Machine learning for digital twins of optical networking infrastructure

In core networks there is a huge quantity of metrology available ranging from SNR and BER measured by the transceivers through to the input and output powers of optical amplifiers and switches. The aim of this PhD project would be to use machine learning applied to metrology information, combined with the underpinning physics to create a digital twin of the physical optical network infrastructure. Not only would the digital twin be updated in real-time, but it would also incorporate the uncertainty into the model allowing for real-time margin allocation to improve the operation of the optical network. Ultimately it would allow the optical network to operate at the limits of performance, based on measurements of the actual infrastructure, so as to allow the throughput as a function of availability to be optimised, to give the best user experience of a given installed infrastructure.
Key challenges the student will need to consider include:
1. The choice of the models for the digital twins (including whether it is a statistical model rather than purely a deterministic physics-based model)
2. The optimal means of incorporating measurement uncertainty into the models to create the digital twin
3. How to use the digital twin to give information regarding throughput, availability etc. so as to optimise the overall performance of the optical network
4. Ultimately, how to change current practice regarding the design and operation of the high availability
optical networks based on a data driven, probabilistic based approach, rather than the established margin-based approach.
The research strategy would start with a single element, such as an optical amplifier, transmitter or receiver and create a mathematical model that is refined based on measurements taken. Research currently carried out in Cambridge has demonstrated that using Gaussian Processes with priors based on a physical model allows for a physically informed machine learning approach. While it is anticipated a Bayesian framework would be utilised, options of physical models and shades of grey, ranging from white box models to black box models would be explored. Having created the mathematical basis for a digital twin the statistical variation in the performance can be quantified and verified, with the complexity of the system increased until initially a digital twin is created for the 1200 km link in the Cambridge lab.
The application of the digital twin to optical infrastructure is a concept that is only just emerging.
Within the Cambridge University Engineering Department work is already underway on the National Digital Twin Programme https://www.cdbb.cam.ac.uk/what-we-do/national-digital-twin-programme, which we would hope to leverage as part of the same department as the PhD student and the PI.
While the project would create a methodology and software to enable a digital twin of the optical infrastructure to be formulated, ultimately the aim of the project would be to create a paradigm shift
in the design and operation of the high-availability optical networks.

The impact of the CDT in Connected Electronic and Photonic Systems is expected to be wide ranging and include both scientific research and industry outcomes. In terms of academia, it is envisaged that there will be a growing range of research activity in this converged field in coming years, and so the research students should not only have opportunities to continue their work as research fellows, but also to increasingly find posts as academics and indeed in policy advice and consulting.

The main area of impact, however, is expected to be industrial manufacturing and service industries. Relevant industries will include those involved in all areas of Information and Communication Technologies (ICT), together with printing, consumer electronics, construction, infrastructure, defence, energy, engineering, security, medicine and indeed systems companies providing information systems, for example for the financial, retail and medical sectors. Such industries will be at the heart of the digital economy, energy, healthcare, security and manufacturing fields. These industries have huge markets, for example the global consumer electronics market is expected to reach $2.97 trillion in 2020. The photonics sector itself represents a huge enterprise. The global photonics market was $510B in 2013 and is expected to grow to $766 billion in 2020. The UK has the fifth largest manufacturing base in electronics in the world, with annual turnover of £78 billion and employing 800,000 people (TechUK 2016). The UK photonics industry is also world leading with annual turnover of over £10.5 billion, employing 70,000 people and showing sustained growth of 6% to 8% per year over the last three decades (Hansard, 25 January 2017 Col. 122WH). As well as involving large companies, such as Airbus, Leonardo and ARM, there are over 10,000 UK SMEs in the electronics and photonics manufacturing sector, according to Innovate UK. Evidence of the entrepreneurial culture that exists and the potential for benefit to the UK economy from establishing the CDT includes the founding of companies such as Smart Holograms, PervasID, Light Blue Optics, Zinwave, Eight19 and Photon Design by staff and our former PhD students. Indeed, over 20 companies have been spun out in the last 10 years from the groups proposing this CDT.

The success of these industries has depended upon the availability of highly skilled researchers to drive innovation and competitive edge. 70% of survey respondents in the Hennik Annual Manufacturing Report 2017 reported difficulty in recruiting suitably skilled workers. Contributing to meeting this acute need will be the primary impact of the CEPS CDT.

Centre research activities will contribute very strongly to research impact in the ICT area (Internet of Things (IoT), data centre interconnects, next generation access technologies, 5G+ network backhaul, converged photonic/electronic integration, quantum information processing etc), underpinning the Information and Communications Technologies (ICT) and Digital Economy themes and contributing strongly to the themes of Energy (low energy lighting, low energy large area photonic/electronics for e-posters and window shading, photovoltaics, energy efficient displays), Manufacturing the Future (integrated photonic and electronic circuits, smart materials processing with photonics, embedded intelligence and interconnects for Industry 4.0), Quantum Technologies (device and systems integration for quantum communications and information processing) Healthcare Technologies (optical coherence tomography, discrete and real time biosensing, personalised healthcare), Global Uncertainties and Living with Environmental Change (resilient converged communications, advanced sensing systems incorporating electronics with photonics).