Increasing internet throughput with machine learning

16 January, 2017

UNLOC researchers have developed a low complexity machine learning scheme that could help increase the throughput of fibre broadband.

Dr Mariia Sorokina, an Aston University researcher on the UNLOC programme, has proposed the use of a new tool called the sparse identification method for optical systems, or SINO. This new approach determines the minimal, optimum number of variables in the transmission system required for adaptive mitigation of effects (nonlinearities in fibre optic cable) that limit the throughput of standard optical fibre.

Demand for data is high with today’s online culture and the introduction of 8K TV, the Internet of Things and the ever-increasing use of streaming services mean that this demand could outstrip network capacity. Novel techniques, such as SINO, could help to future-proof our broadband infrastructure.

The SINO method is significantly less complex than other similar compensation techniques. This bodes well for future commercial deployment.

Dr Sorokina and her team saw significant gains when they demonstrated the SINO scheme in standard fibre, the type of fibre most often used today. It is via this fibre that we all receive our home broadband – if not all the way to our front door. Unlocking the capacity of existing fibre infrastructure, rather than laying new types of cable, will help ensure the demands for data are met sooner rather than later.

SINO is particularly useful for flexible smart-grid networks, as it does not require a knowledge of system parameters and is scalable to difference power levels. Such networks are more sustainable and more reliable, considering the needs of modern society.

“Machine learning techniques are finding new applications in the field of optical communications as they enable fast processing and are low complexity. Our machine learning scheme can be straightforwardly adapted for different optical communication systems too.” says Dr Sorokina.

This research is published in a feature issue of Optics Express, Nonlinearity Mitigation for Coherent Transmission Systems: Mariia Sorokina, Stylianos Sygletos, and Sergei Turitsyn, "Sparse identification for nonlinear optical communication systems: SINO method," Opt. Express 24, 30433-30443 (2016)