Cesar A. V. Melo

Envelope process and computation of the equivalent bandwidth of multifractal flows

Internet Protocol flows present high variability at small time scales as well as long range dependence, which can be captured by multifractal models. Estimating the bandwidth to support the Quality of Service required by these flows is the key to Traffic Engineering. This paper introduces a novel envelope process which is a minimalist yet accurate model for multifractal flows. The envelope process is an upper bound to the volume of arrivals from a multifractal Brownian motion. The envelope process accuracy was assessed using both real network traces and synthetically generated traces. Moreover, the solution of a queue fed by multifractal flows is presented and an expression for the time at which the queue length reaches its maximum is derived. This time instant is used for the derivation of an efficient method for the computation of the equivalent bandwidth of multifractal flows. Furthermore, a policing mechanisms to assure the conformance of a flow to the multifractal envelope process is presented. It is also shown that a monofractal approach for modeling multifractal flows leads to overestimation of the bandwidth needed.

An envelope process for multifractal traffic modeling

In this paper, a novel envelope process for multifractal traffic modeling is introduced. The envelope process is an upper bound for the amount of work arrived in a multifractal Brownian motion process. The time scale of interest of a queueing system fed by a multifractal stream is computed. Simulation experiments using both real and synthetic data show that the proposed model is accurate.

A content-oriented web cache poli

The increasing popularity of network-based multimedia applications poses many challenges for multimedia content providers to supply efficient and scalable multimedia services. Peer-to-Peer (P2P) networks have been shown to be a promising approach to provide large scale video services over Internet since these networks increase scalability and robustness. In this paper, we propose and analyze an object management policy approach for videos web cache in a P2P context, taking advantage of objects meta-data, e.g video popularity, and objects encoding techniques, e.g Scalable Video Coding (SVC). We carry out trace-driven simulation so as to evaluate the performance of our approach and compare it against traditional object management policy approaches. The experiment results show that our proposed approach can improve the performance of the cache substantially.

Statistical multiplexing of multifractal flows

This paper introduces the computation of an expression for the time at which the length of a queue fed by several multifractal flows reaches its maximum. Expressions for the equivalent bandwidth of an aggregate of multifractal flows are also presented. Moreover, it is shown that modelling based on monofractal process rather than based on multifractal processes leads to overprovisioning of resources.

A Traffic Model for UDP Flows

This paper introduces a traffic model for UDP streams. The model was derived after characterization of the marginal distributions existing in traces of UDP flows. The model has four states and it reproduces the multiscaling characteristics of UDP streams. The efficacy of the proposed model is verified comparing it to the ones of existing models.

On the Transformation of Multifractal Traffic at Ingress Optical Burst Switches

Ingress nodes of Optical Burst Switching (OBS) networks are responsible for assembling burst out of incoming packets and to forward these bursts into the OBS network. The most common criteria for burst assembly are based either on time or on traffic volume. The change of the statistical characteristics of a traffic stream at an ingress switch can affect the quality of service provisioning. Therefore, the statistical characteristics of the output flow of an ingress node need to be known for appropriate network dimensioning and service provisioning. This paper evaluates the impact of burst assembly mechanisms on the scaling properties of multifractal traffic flows. It is showed that the most relevant factor that determines the nature of the output traffic flow is the relationship between the cut-off time scale of the input traffic and the time scale of assembly threshold.

Promotion of content availability by playlist viewers in CDN-P2P systems

This paper assesses the effectiveness of playlists for improving the content availability in CDN-P2P networks that distributes YouTube-like videos. Real data collected from YouTube was used and the popularity patterns of playlists and first page videos were characterized. Moreover, the impact of playlist viewers on content availability was evaluated. Results show that the improvement in content availability is about 40% for highly connected playlist viewers. For systems with less connected playlist viewers, the improvement exceeds 20% for different scenarios.

A multiscaling traffic model for UDP streams

Abstract Although most of the traffic carried over the Internet uses the Transmission Control Protocol (TCP) as the transport layer protocol, it is of paramount importance to develop models for streams that use the User Datagram Protocol (UDP), since these streams are inelastic and, consequently, they can jeopardize the acquisition of bandwidth by TCP streams. This paper introduces a traffic model for UDP streams and its performance is compared to those of other traffic models. The proposed model can be used to generate streams of aggregated UDP sources in simulation experiments.

LatinCon01 - A Content-Oriented Web Cache Policy under P2P Video Distribution Systems

The increasing popularity of network-based multimedia applications poses many challenges for multimedia content providers to supply efficient and scalable multimedia services. Peer-to-Peer (P2P) networks have been shown to be a promising approach to provide large scale video services over Internet since they increase the scalability and robustness. In this paper, we propose and analyze an object management policy approach for video web cache in a P2P context, taking advantage of objects meta-data, e.g video popularity, and objects encoding techniques, e.g Scalable Video Coding (SVC). We exploit the peer-to-peer based approach to carry out the replication then eviction of videos in different web cache according to their popularity. Since videos are typically large and require high communication bandwidth for delivery, many peers may be unwilling to cache them in whole to serve others. Accordingly, we address this problem by proposing a new web caching approach for videos encoded in layers. Furthermore, in the proposed approach cooperation amongst the web caches may make it possible to replicate the video on several caches when this one is very popular. Afterward, we can gradually eliminate the replicas from the caches as the video popularity decrease. In addition, we structure our peer-to- peer network using interest-based communities. This network is made by ordinary nodes and super-nodes, and with peers clustered into communities. These communities are built around subjects (e.g., Science and Sports). The performance measurements we carried out allowed analyzing the traffic volume that flows from the community super-node to the first server into our content delivery network. The main goal is to measure how much our content-oriented management policy can help to decrease the demands put over the community output link. These measurements showed that the proposed approach (i) reduces the traffic volume, (ii) maximizes the overall bit rate of community demands, and (iii) optimizes the use of network resources.

Versioning-aware and QoE-oriented strategy for adaptative bitrate streaming

Several reports on Internet traffic have shown that HTTP adaptive streaming is fundamental for multimedia content transport and delivery. Despite the large body of work in this area, running streaming applications on overload channels demands effective delivery strategies. In this work, a video bitrate adaptation strategy, deployed in overloaded channel of an access network, is proposed and evaluated. This strategy takes decisions about bitrate switching based on QoE related parameters to minimize playback stalls. In the experiments conducted to evaluate the effectiveness of the proposed strategy, the average video bitrate, instability and fairness are measured over all of the played video sessions.