No description available.

No description available.

The video streaming applications contribute to a major share of the Internet traffic. Consequently, monitoring and management of video streaming quality has gained a significant importance in the recent years. The disturbances in the video, such as, amount of buffering and bitrate adaptations affect user Quality of Experience (QoE). Network operators usually monitor such events from network traffic with the help of Deep Packet Inspection (DPI). However, it is becoming difficult to monitor such events due to the traffic encryption. To address this challenge, this thesis work makes two key contributions. First, it presents a test-bed, which performs automated video streaming tests under controlled time-varying network conditions and measures performance at network and application level. Second, it develops and evaluates machine learning models for the detection of video buffering and bitrate adaptation events, which rely on the information extracted from packets headers. The findings of this work suggest that buffering and bitrate adaptation events within 60 second intervals can be detected using Random Forest model with an accuracy of about 70%. Moreover, the results show that the features based on time-varying patterns of downlink throughput and packet inter-arrival times play a distinctive role in the detection of such events.

[pt] A Rede Digital de serviços Integrados - Faixa Larga (RDSI- FL) caracteriza-se pela flexibilidade de integração de diversas fontes de tráfego tais como voz, dados e vídeo. Neste trabalho estudamos o controle de congestionamento nesta rede. Através de simulação das fontes de tráfego e de seu comportamento na rede, foi possível a exploração do ganho da multiplexação estatística alcançado principalmente pela utilização do Modo de Transferência Assíncrono (MTA). Apresentamos as fases que compreendem o controle de congestionamento e obtivemos resultados de Alocação de largura de banda para alguns tipos de fontes assim como resultados comparativos de critérios de Admissão com resultado de simulação. A largura de banda a ser alocada é utilizada na fase de controle de admissão para a decisão da aceitação de uma nova chamada. Apresentamos ainda, um simulador da fonte variável (vídeo) necessário em todas as análises. / [en] Broadbend Integrated Services Digital Networks (B-ISDN) are characterized by their flexibility of integrating a variety of traffic sources such as, voice, data and video. Congestion control of these networks is studied in this work. Through simulation of traffic sources, it have been possible to explore statistical multiplexing gain reached by the Asynchronous Tranfer Mode (ATM) utilization. We present the congetion control phases and results concerning the Bandwidth Allocation and Admission Control phases. The Bandwidth Allocation is used by the Admission control to decide a new call acceptance. We also present, the simulation results concerning the Bandwidth Allocation for each traffic source and a comparison between some admission criteria proposed in the literature and simulation results.

[pt] Neste trabalho é analisado o desempenho do mecanismo ATAP (Anticipated Traffic Allocation Protocol) para fontes de vídeo em redes do tipo ATM (Asynchronous Transfer Mode). O ATAP é uma proposta de alocação antecipada de banda passante para fontes de taxas variáveis (Variable Bit-Rate- VBR), periódicas, que tem como característica, o atendimento às aplicações com qualidade equivalente aos serviços da classe CBR (Costant Bit Rate) e com a vantagem de ainda apresentar ganho na multiplexação estatística. Para isso, o ATAP se baseia no controle de admissão do tráfego entrante no nó local e na predição de banda das fontes, efetuando dinamicamente a reserva de recursos na rede através dos protocolos de reserva rápida. No modelo de avaliação utilizamos seqüências com codificadores de vídeo distintos (H.261 e TV/HDTV) e os protocolos de reserva rápida FRP/DT (Fast Reservation Protocol with Delayed Transmission) e FBM (Fast Buffer Management). Os resultados obtidos através de simulação são apresentados e analisados. / [en] In this work the Anticipated Traffic Allocation Protocol (ATAP) for Video sources in ATM (Asynchronous Transfer Mode) networks is analyzed. The ATAP is an anticipated bandwidth allocation proposal for periodic variable bit rate (VBR) sources, which has the ability to handle application with QoS requirements equivalent to CBR (Costant Bit Rate) class services with the advantage of higher statistical gain. In order to achieve this, ATAP is based on traffic admission control at its input local node and on bandwidth source requirement prediction which done dinamically though resource reservation provided by the fast reservation protocols. In the evaluation models we used sequences from different video encoders (H.261 and TV/HDTV) combined with fast reservation protocols. FRP/DT - Fast Reservation Protocol with Delayed Transmission and FBM - Fast Buffer Management). Simulation results are presented and analyzed.

Internet traffic classification is an important field which several stakeholders are dependent on for a number of different reasons. Internet Service Providers (ISPs) and network operators benefit from knowing what type of traffic that propagates over their network in order to correctly treat different applications. Today Deep Packet Inspection (DPI) and port based classification are two of the more commonly used methods in order to classify Internet traffic. However, both of these techniques fail when the traffic is encrypted. This study explores a third method, classifying Internet traffic by machine learning in which the classification is realized by looking at Internet traffic flow characteristics instead of actual payloads. Machine learning can solve the inherent limitations that DPI and port based classification suffers from. In this study the Internet traffic is divided into two classes of interest: Video and Other. There exist several machine learning methods for classification, and this study focuses on Support Vector Machine (SVM) to classify traffic. Several traffic characteristics are extracted, such as individual payload sizes and the longest consecutive run of payload packets in the downward direction. Several experiments using different approaches are conducted and the achieved results show that overall accuracies above 90% are achievable. / HITS, 4707

Due to it being increasingly common that users' data is encrypted, the Internet service providers today find it difficult to adapt their service for the users' needs. Previously popular methods of classifying users data does not work as well today and new alternatives is therefore desired to give the users an optimal experience.This study focuses specifically on classifying data flows into video and non-video flows with the use of machine learning algorithms and with a focus on runtime performance. In this study the tested algorithms are created in Python and then exported into a C code implementation, more specifically the random forest and the gradient boosting trees algorithm.The goal is to find the algorithm with the fastest classification time relative to its accuracy, making the classification as fast as possible and the classification model to require as little space as possible.The results show that random forest was significantly faster at classification than gradient boosting trees, with initial tests showing it to be roughly 7 times faster after compiler optimization. After optimizing the C code random forest could classify more than 250,000 data flows each second with decent accuracy. Neither of the two algorithms required a lot of space (<3 megabyte). / HITS, 4707

Operational deployment of machine learning based classifiers in real-world networks has become an important area of research to support automated real-time quality of service decisions by Internet service providers (ISPs) and more generally, network administrators. As the Internet has evolved, multimedia applications, such as voice over Internet protocol (VoIP), gaming, and video streaming, have become commonplace. These traffic types are sensitive to network perturbations, e.g. jitter and delay. Automated quality of service (QoS) capabilities offer a degree of relief by prioritizing network traffic without human intervention; however, they rely on the integration of real-time traffic classification to identify applications. Accordingly, researchers have begun to explore various techniques to incorporate into real-world networks. One method that shows promise is the use of machine learning techniques trained on sub-flows – a small number of consecutive packets selected from different phases of the full application flow. Generally, research on machine learning classifiers was based on statistics derived from full traffic flows, which can limit their effectiveness (recall and precision) if partial data captures are encountered by the classifier. In real-world networks, partial data captures can be caused by unscheduled restarts/reboots of the classifier or data capture capabilities, network interruptions, or application errors. Research on the use of machine learning algorithms trained on sub-flows to classify VoIP and gaming traffic has shown promise, even when partial data captures are encountered. This research extends that work by applying machine learning algorithms trained on multiple sub-flows to classification of video streaming traffic. Results from this research indicate that sub-flow classifiers have much higher and more consistent recall and precision than full flow classifiers when applied to video traffic. Moreover, the application of ensemble methods, specifically Bagging and adaptive boosting (AdaBoost) further improves recall and precision for sub-flow classifiers. Findings indicate sub-flow classifiers based on AdaBoost in combination with the C4.5 algorithm exhibited the best performance with the most consistent results for classification of video streaming traffic.

Traffic classification is important for Internet providers and other organizations to solve some critical network management problems.The most common methods for traffic classification is Deep Packet Inspection (DPI) and port based classification. These methods are starting to become obsolete as more and more traffic are being encrypted and applications are starting to use dynamic ports and ports of other popular applications. An alternative method for traffic classification uses Machine Learning (ML).This ML method uses statistical features of network traffic flows, which solves the fundamental problems of DPI and port based classification for encrypted flows.The data used in this study is divided into video and non-video traffic flows and the goal of the study is to create a model which can classify video flows accurately in real-time.Previous studies found tree-based algorithms to work well in classifying network traffic. In this study random forest and gradient boosted trees are examined and compared as they are two of the best performing tree-based classification models.Random forest was found to work the best as the classification speed was significantly faster than gradient boosted trees. Over 93% correctly classified flows were achieved while keeping the random forest model small enough to keep fast classification speeds. / HITS, 4707

A garantia de qualidade de serviço (QoS) tem-se demonstrado muito importante em aplicações em tempo real. Este trabalho apresenta um estudo sobre Mecanismos de Policiamento na tecnologia A TM, mais especificamente, sobre o funcionamento do Mecanismo Dual Leaky Bucket, utilizado pela classe de serviço VBR em rede ATM. Para este estudo foi implementado um simulador por software do mecanismo Dual Leaky Bucket. Foram analisados dois tipos de tráfegos de vídeo com compressão MPEG-2, com pouca e muita movimentação. A partir da simulação pôde-se analisar como o erro na definição de parâmetros do contrato de QoS definidos pelo usuário no estabelecimento da conexão pode levar ao aumento na taxa de perda de informações e, conseqüentemente, a degradação da qualidade necessária pela aplicação / The guarantee of quality of service (QoS) has been demonstrating very important in real time applications. This work presents a study on Policing Mechanisms in the ATM technology, more specifically, on the operation of the Dual Leaky Bucket Mechanism, used by the class of service VBR in ATM networks. For this study a Dual Leaky Bucket mechanism simulator by software was implemented. Two kinds of MPEG-2 video traffics were analyzed with a little and a lot of movement. The simulation shows how a mistake in the definition of parameters in the QoS contract, defined by user, during of the connection establishment can leads to increase of information loss rate and, consequently, the degradation of the necessary quality for the application