Characterization of user mobility trajectories by implementing clustering techniques
Visualitza/Obre
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/105636
Tipus de documentProjecte Final de Màster Oficial
Data2017-05-08
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-SenseObraDerivada 3.0 Espanya
Abstract
Current and legacy technologies for wireless communications are facing an explosive demand of capacity and resources, triggered by an exponential growing of traffic, mainly due to the proliferation of smartphones and the introduction of demanding multimedia and video applications. There is the anticipation that future generation of wireless communications systems, 5G, will attend the growing demand on capacity and network resources, along with the necessity for blending novel technology concepts including Internet of Things, machine communications, the introduction of heterogeneous network architectures, massive arrays of antennas and dynamic spectrum allocation, among others. Moreover, self-organizing networks (SON) functions incorporated in present mobile communication standards provide limited levels of proactivity. Therefore, it is foreseen that future network are required of highly automation and real-time reaction to network problems, topology changes and dynamic parameterization. The flexibility to be introduced in 5G networks by incorporating virtualized hardware architecture and cloud computing, allow the inclusion of big data analytics capabilities for finding insights and taking advantage of the vast amounts of data generated in the network system. The full embodiment of big data analytics among the Radio Access Network optimization and planning processes, allow gathering an end to end knowledge and reaching the individual user level granularity. The purpose of this work is to provide a case of study for smartly processing collected data from mobility traces by using a hierarchical clustering function, an unsupervised method of data analytics, for characterizing the different user mobility trajectories to extract an individual user mobility profile. The methodology proposed references a knowledge discovery framework which uses Artificial Intelligence processes for finding insights in collected network data and the use of this knowledge for driving SON functions, other optimization and planning processes, and novel operator business cases.
TitulacióMÀSTER UNIVERSITARI EN ENGINYERIA DE TELECOMUNICACIÓ (Pla 2013)
Col·leccions
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
TFM Freddy Croquer MET.pdf | 1,957Mb | Visualitza/Obre |