Forecasting del tráfico de gigabytes

Ranz Casado, Jorge (2022). Forecasting del tráfico de gigabytes. Proyecto Fin de Carrera / Trabajo Fin de Grado, E.T.S.I. de Sistemas Informáticos (UPM), Madrid.

Description

Title: Forecasting del tráfico de gigabytes
Author/s:
  • Ranz Casado, Jorge
Contributor/s:
  • Lara Cabrera, Raúl
  • Yuen Duran, Abran Yiu-Sen
Item Type: Final Project
Degree: Grado en Ingeniería del Software
Date: July 2022
Subjects:
Freetext Keywords: Machine learning; Modelos predictivos; Redes neuronales; Deep learning; Telefonía; Tráfico
Faculty: E.T.S.I. de Sistemas Informáticos (UPM)
Department: Sistemas Informáticos
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img] PDF - Users in campus UPM only - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (3MB)
[img] Archive (ZIP) - Users in campus UPM only
Download (11MB)

Abstract

Este Trabajo de Fin de Grado, realizado en colaboración con la empresa MasMovil Ibercom S.A., consiste en el desarrollo de varios modelos predictivos mediante el uso de Machine Learning y/o redes neuronales con el fin de contemplar el consumo del tráfico de gigabytes en ciertas localizaciones con redes de telefonía determinadas. Gracias al proyecto, la distinción entre cada predicción del consumo de forma mensual será plenamente discernible. Este sistema tendrá presentes diferentes características seleccionadas de una base de datos, así como otras variables externas que puedan influir en los modelos. Además, tendrá en cuenta aspectos como anomalías en el consumo y/o las transiciones a otras redes. Como resultado final, obtendremos un modelo de predicción del tráfico de gigabytes consumidos a lo largo del tiempo, donde visualizaremos posibles errores o problemas temporales situacionales y otros potenciales cambios causantes de irregularidades. Abstract: This Final Degree Project, carried out in collaboration with the company MasMovil Ibercom S.A., consists of the development of several predictive models through the use of Machine Learning and/or neural networks in order to contemplate the consumption of gigabyte traffic in certain locations with specific telephone networks. Thanks to the project, the distinction between each consumption prediction on a monthly basis will be fully discernible. This system will take into account different characteristics selected from a database, as well as other external variables that may influence the models. In addition, it will take into account aspects such as anomalies in consumption and/or transitions to other networks. As a final result, we will obtain a predictive model of the traffic of gigabytes consumed over time, where we will visualize possible errors or temporal situational problems and other potential changes causing irregularities.

More information

Item ID: 71312
DC Identifier: https://oa.upm.es/71312/
OAI Identifier: oai:oa.upm.es:71312
Deposited by: Biblioteca Universitaria Campus Sur
Deposited on: 20 Jul 2022 19:34
Last Modified: 20 Jul 2022 19:34
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM