Machine learning aided quality of transission estimation in optical networks
Reference persons ANDREA BIANCO
Research Groups Telecommunication Networks Group
Thesis type SIMULATION/ANALYSIS
Description Predicting the Quality of Transmission of a lightpath prior to its deployment is a step of capital importance for an optimized design of optical networks. Due to the continuous advances in optical transmission, the number of design parameters available to system engineers (e.g., modulation formats, baud rate, code rate, etc.) is growing dramatically, thus significantly increasing the alternative scenarios for lightpath deployment. Machine Learning algorithms capable of predicting whether the bit-error rate of lightpaths meet a given acceptability threshold prior to their establishment have recently been proposed to overcome the computational complexity issues related to the explosion of design parameters, while ensuring real-time prediction timings and high accuracy. The research actitivity of this thesis is aimed at exploring different learning mechanisms (e.g. online learning, cost-sensitive learning, transfer learning) to reduce the size of training datasets and improve the adaptability of such algorithms to eterogeneous network topologies and transmission technologies.
Required skills Programming skills
Deadline 08/01/2020 PROPONI LA TUA CANDIDATURA