Alan Yuan
PhD Student
Dr Md Saifuddin Faruk
Research Fellow
Dr Sam Nallaperuma
Sam Nallaperuma joined the TRANSNET Programme in March 2020, having previously contributed to the algorithm analysis of artificial intelligence (AI) and applications of AI to transport networks working as a research fellow as part of an industry collaboration project. Sam works on Research Theme 1: Intelligent Network Architectures and Topologies, applying AI for network parameter optimisation and data-driven modelling of optical networks. She is also responsible for maintaining TRANSNET Virtual Lab (TVL) as the Cambridge TVL representative.
Prof Seb Savory
TRANSNET Co-Investigator
My research is focused on optical fibre communication, whereby digital data modulates light that is then transmitted over huge distances using optical fibres. According to the 2009 IEEE ROGUCCI report, over 99% of all long distance international data traffic is carried using optical fibres and as such they underpin the internet and today’s global communication infrastructure. It is rich area of research, which encompasses both the theory and practice of engineering, ranging from developing new science, mathematics and technology to understanding the environmental, economic and societal impact which these optical fibre communication systems have on today’s global community. It is an area I have found fascinating that I have been actively carrying out research in for almost twenty five years. I have been TRANSNET Co-Investigator since 2018.
My current research explores four areas:
1.Algorithms for digital coherent transceivers.
2.Ultra-dense passive optical networks.
3.Statistical optical communication system design.
4.Cognitive optical networks
Contact:
TRANSNET researchers propose a novel application for reinforcement learning
In a paper published today in the Journal of Optical Communications and Networking, TRANSNET researchers propose a novel application of reinforcement learning (RL) with invalid action masking and a novel training methodology for routing and wavelength assignment (RWA) in fixed-grid optical networks.
Due to the well-known NP hard problem associated with the routing and wavelength assignment (RWA) in optical networks, there has been a widespread interest in finding new methods that improve on the efficacy of existing heuristic approaches. Through the introduction of invalid action masking and a new training method, the paper demonstrates that the applicability of reinforcement learning (RL) to routing and wavelength assignment (RWA) in fixed-grid networks can be extended from considering connection requests between nodes to servicing demands of a given bit rate. Thus, lightpaths can be used to service multiple demands, as long it has sufficient remaining capacity.