Research Round-up: January - February 2021

Take a look at the research the TRANSNET team have published during the first two months of 2021, featuring two papers on network optimisation and a third on neural networks for nonlinearity mitigation.

Journal Paper 
Self-organization scheme for balanced routing in large-scale multi-hop networks (doi.org/10.1088/1751-8121/abd34b)
Journal of Physics A: Mathematical and Theoretical

David Saad, TRANSNET Co-Investigator from Aston University, is a co-author on this paper which proposes an algorithmic strategy for balanced routing in large-scale networks (like the IoT). The nodes in the proposed scheme are programmed to coordinate and organise themselves to route information to its destination in a cost-efficient and load-balanced way, and this is tested numerically in the paper using a wireless sensor network made up of 200 sensors. The research is a collaboration with colleagues from the Department of Engineering Science at the University of Oxford.

Journal Paper
Advanced Convolutional Neural Networks for Nonlinearity Mitigation in Long-Haul WDM Transmission Systems (doi.org/10.1109/JLT.2021.3051609)
Journal of Lightwave Technology 

This paper presents a new design of a deep convolutional neural network for mitigating the nonlinear signal distortions in a long-haul ultra-high capacity fibre optic transmission system. Numerical simulations show that the new scheme is better than conventional digital back propagation methods, in terms of reduced complexity and improved performance, demonstrating its potential in extending the capacity of future communication systems. The research is a collaboration between Aston University and Novosibirsk State University.

Journal Paper
Futility of being selfish in optimized traffic (doi.org/10.1103/PhysRevE.103.022306)
APS Physical Review E

This paper theoretically analyses the impact of selfish route choices on the performance of transportation networks using a generalised cavity method, finding that selfish route choices can reduce the efficiency of coordinated transportation systems. The presented framework can be readily adapted to study other problems based on iterative alterations by network participants in response to the state of the system, like how to build an intelligent optical infrastructure, for example. The work is a collaboration between the University of Hong Kong and Aston University.


 For a full list of published TRANSNET research, including journal and conference papers, please take a look at our publications page.