Jorge Castro e Silva

It is increasingly common to use systems capable of transmitting multimedia content such as audio and video, in real-time infrainstructured networks, but it is not the same with Mobile Ad Hoc networks (MANET). A MANET is characterized by the free movement of its vehicles making packet routing with time delivery restrictions a complex problem. To solve this problem some works they propose the use of routing protocols with support for multiple paths. In this paper, we describe an extension to the Protocol OLSR, which has the goal to make it possible to support multimedia data transmission by multipath and use the data transmission quality present in RTCP reports to determine how many paths and which of them should be used to perform a real-time transmission in the most appropriate way.

The continual growth of high speed networks is a challenge for real-time network analysis systems. The real time traffic classification is an issue for corporations and ISPs (Internet Service Providers). This work presents the design and implementation of a real time flow-based network traffic classification system. The classifier monitor acts as a pipeline consisting of three modules: packet capture and pre-processing, flow reassembly, and classification with Machine Learning (ML). The modules are built as concurrent processes with well defined data interfaces between them so that any module can be improved and updated independently. In this pipeline, the flow reassembly function becomes the bottleneck of the performance. In this implementation, was used a efficient method of reassembly which results in a average delivery delay of 0.49 seconds, approximately. For the classification module, the performances of the K-Nearest Neighbor (KNN), C4.5 Decision Tree, Naive Bayes (NB), Flexi...

These are the results, PPS plots, and sensitivity analysis from Super-Cobb-Douglas-CCR-I used for optimisation of totally scaled experiments on virtual network settings throughout of fractal variables to predict the most effective set of virtual settings. The multicriteria decision-making herein proposed serves to deliver stable TCP services with superior performance in a long timescale. The results may change the manner as the parties making a deal on SLA should change as regards the issue of tax, audit, evaluate, and present the performance of virtual infrastructure based in this fractal analysis.

Some ways of comparison from results of Windows Multiplicative DEA model versus traditional Windows DEA model (raw/standard). Now, it is also including the LINDO´s formulations of the multiplicative windows DEA model bringing a sum of the slacks with a small infinitesimal number (ε=10^(-7)) in the objective function; however, the results are equals than the original windows multiplicative DEA formulation which has no slacks in the objective function, only in inputs and outputs formulations respectively.

It is essential for the network operator to anticipate events leading to network node and link capacity breakdown in order to guarantee the Quality of Service (QoS) contract. Traffic prediction can be undertaken based on link traffic (aggregate), or on origin-destination (OD) traffic that presents better results. This work investigates a methodology for traffic engineering based on multidimensional OD traffic,

Universidade Federal de Pernambuco posgraduacao@cin.ufpe.br www.cin.ufpe.br/~posgraduacao ... ProCon - Prognóstico de Congestionamento de Redes de Computadores usando Wavelets ... Tese de Doutorado – Universidade Federal de Pernambuco. Programa de Pós- ...

The active networks approach has been presented as an alternative technology for solving several problems in conventional networks, mainly in the network management area. New concepts were developed by many researches for improving their efficiency and providing a better flexibility and distribution. This work describes a data retrieval mechanism test bed, including design and implementation, which can be used for managing SNMP enabled networks, based on the ANTS (Active Node Transfer System) toolkit framework developed at the Massachusetts Institute of Technology (MIT). The results issued from the experiments have shown that the chosen approach is a good alternative for data retrieving operations, regarding the network management application with respect to performance on bandwidth needs, traffic load and manager overloading.

This work presents NetBook, a free tool, developed in Cin/UFPE with the goal of supporting performance analysis of communication systems, in particular, in this version, computer networks. NetBook has four modules: (i) Statistics, (ii) Generation, (iii) Transformation and (iv) Graphics. Except by the module of auto-similar traffic generation, implemented in C++, all the others NetBook modules were implemented in Java.

The continual growth of high speed networks is a challenge for real-time network analysis systems. The real time traffic classification is an issue for corporations and ISPs (Internet Service Providers). This work presents the design and implementation of a real time flow-based network traffic classification system. The classifier monitor acts as a pipeline consisting of three modules: packet capture and pre-processing, flow reassembly, and classification with Machine Learning (ML). The modules are built as concurrent processes with well defined data interfaces between them so that any module can be improved and updated independently. In this pipeline, the flow reassembly function becomes the bottleneck of the performance. In this implementation, was used a efficient method of reassembly which results in a average delivery delay of 0.49 seconds, approximately. For the classification module, the performances of the K-Nearest Neighbor (KNN), C4.5 Decision Tree, Naive Bayes (NB), Flexible Naive Bayes (FNB) and AdaBoost Ensemble Learning Algorithm are compared in order to validate our approach.