Combining machine learning and optimization algorithms in 5G networks
Visualitza/Obre
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/368992
Tipus de documentProjecte Final de Màster Oficial
Data2022-06
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-CompartirIgual 3.0 Espanya
Abstract
Optical networks are a good option to absorb simultaneous services, offering high broadband capacity. Indeed, optical network automation based on artificial intelligence-based methods and models has been recently proposed to offer adaptability to traffic changes and variable needs. In particular, modelling in-phase and quadrature optical constellation samples is key to analyse optical connection characteristics. This necessity has previously been addressed by researchers with the proposition of gaussian mixture models as a tool for automated optical constellation characterization. After understanding its flaws, we propose a new methodology, named Gaussian Slicing with Association of Clusters (GSAC), which combines the strengths of gaussian behavior and the flexibility of unsupervised learning methods by the application of clustering algorithms.
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
memoria.pdf | 2,472Mb | Visualitza/Obre |