Publicação

Forecasting techniques for information and communication systems: application to mobile cellular networks

Ver documento

Detalhes bibliográficos
Resumo:The rapid proliferation of information and communication technologies around the world has increased the need for careful planning of infrastructures. This is true in the situation like mobile telecommunication networks, data centers, web servers, etc. By developing and implementing intelligent solutions to improve the measurement and planning, telecommunication service operators can anticipate problems and minimize cost. This dissertation focuses on forecasting mobile telecommunication capacity networks to maximize existing resources and avoid problems related to performance or capacity, such as bottlenecks and latencies. In the case of mobile telecommunication networks, the data forecast can be used to predict traffic growth, contributing to better network planning. Therefore, a poorly designed forecast may lead to mobile network operators not being prepared for possible network problems, such as reaching the limit of an RNC, which may become expensive in terms of OPEX. Thus, it is fundamental to study different quantitative methods to forecast the trend and the volume of traffic in the RNCs. This paper analyzes some basic forecast methods used in scenarios where the data do not present behavioral complexity and some models such as ARIMA and Holt Winters used in data with behavioral complexity (presence of trend and seasonality). It also evaluates the accuracy of the forecasts determined from the application of these models.
Autores principais:Mesquita , Michael Jordan Karagianis
Assunto:Forecasting capacity Mobile Network Forecasting Models ARIMA LTE UMTS
Ano:2017
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Universidade de Aveiro
Idioma:inglês
Origem:RIA - Repositório Institucional da Universidade de Aveiro

Registos relacionados

Registos relacionados