José Augusto Suruagy Monteiro

Statistical multiplexing in ATM networks

Abstract In this paper we evaluate the statistical multiplexing gain in ATM networks for bursty as well as variable bit rate (VBR) traffic using a fluid-flow approximate model. We obtain the required bandwidth per source in a finite buffer multiplexer in order to achieve a given Grade of Service (GOS), expressed by the cell loss probability. For both bursty and VBR traffic sources, we perform a sensitivity analysis of significant parameters in the homogeneous case (all traffic sources are of the same type). The required bandwidth for bursty sources is shown to depend on burst and buffer length through their ratio. Finally, the mixing of bursty traffic and variable bit rate is considered. We compare the results obtained through simulation with approximations proposed in the literature.

A minimum interference routing algorithm

Minimum interference routing is instrumental to MPLS traffic engineering under realistic assumptions of unknown traffic demand. This work presents a new algorithm for minimum interference routing, called light minimum interference routing (LMIR). This algorithm introduces a new approach for critical link identification that reduces the computational complexity. Results, derived via simulation, show that LMIR is precise and has indeed a low computational complexity.

Topological reconfiguration of ATM networks

The topological reconfiguration of an asynchronous transfer mode (ATM) network embedded into a backbone facility network that uses digital cross connect systems (DCSs) is addressed. The ATM topology consists of links (express pipes) obtained from the backbone facility via circuit switching through DCSs. The problem is formulated as a network optimization problem where performance is optimized, subject to capacity constraints posed by the underlying facility trunks. The variables in this problem are the selection of the express pipes, the routing of traffic on such pipes, and the allocation of bandwidth to pipes. Dynamic reconfiguration schemes where the embedded topology is periodically adjusted to track the fluctuations in traffic requirements are discussed. Such reconfigurations are shown to reduce congestion substantially.<<ETX>>

MonONTO: A Domain Ontology for Network Monitoring and Recommendation for Advanced Internet Applications Users

In order to make recommendations to users about the potential performance of advanced Internet applications - in the scope of network monitoring - it is not sufficient to just analyze the network performance metrics: it should be also considered information concerning the application type, the traffic generated, and the user profile. In the present paper, we propose a new approach for monitoring the performance of advanced Internet applications based on the use of an expert system. The expert system will infer from a domain ontology named MonONTO. This ontology amasses the main concepts and their relationships in the following sub-domains: quality of service of advanced applications, network performance measurements, and user profiles. The knowledge base, originated from MonONTO, demonstrated its use and importance in the domain described here through axioms creation and inferences performed using a specific experimental rule engine.

Bandwidth allocation in ATM networks

In an ATM network, bandwidth is allocated at different levels and in different stages. At the physical level, the ATM topology can be dynamically reconfigured by adding/removing truns between ATM switches. This allocation of bandwidth is made possible by the SONET Synchronous Transfer Mode (STM) infrastructure equipped with Digital Cross Connect Systems (DCSs). We will refer to this allocation asSTM allocation. At the ATM level, we can allocate bandwidth to individual Virtual Circuits (ATM-VC allocation) as well as to Virtual Paths (ATM-VP allocation). For example, in order to implement the Connectionless Network Access layer functions we find it convenient to organize the Virtual Paths in a Connectionless Overlay Network. This introduces another type of bandwidth allocation (CLS allocation). In this paper, we address and formulate the above bandwidth allocation problems, and propose efficient techniques for their solution. We illustrate these techniques with examples based on STM and CLS allocation, respectively.

A minimum interference routing algorithm with reduced computational complexity

Minimum interference routing algorithms are designed to reduce rejections of future requests for the establishment of Label Switched Paths (LSPs) but make no assumption about specific patterns of arrival request. This paper introduces a novel minimum interference routing algorithm, Light Minimum Interference Routing (LMIR), which is based on a new approach to the identification of critical links. This approach reduces the computational complexity involved in finding a path for the establishment of an LSP. The LMIR is shown to have the same precision as existing algorithms but with less computational complexity.

A knowledge and collaboration-based CBR process to improve network performance-related support activities

Abstract In a context characterized by a growing demand for networked services, users of advanced applications sometimes face network performance troubles that may actually prevent them from completing their tasks. Therefore, providing assistance for user communities that have difficulties using the network has been identified as one of the major issues of performance-related support activities. Despite the advances network management has made over the last years, there is a lack of guidance services to provide users with information that goes beyond merely presenting network properties. In this light, the research community has been highlighting the importance of User-Perceived Quality (UPQ) scores during the evaluation of network services for network applications, such as Quality of Experience (QoE) and Mean Opinion Score (MOS). However, despite their potential to assist end-users to deal with network performance troubles, only few types of network applications have well established UPQ scores. Besides that, they are defined through experiments essentially conducted in laboratory, rather than actual usage. This paper thus presents a knowledge and Collaboration-based Network Users’ Support (CNUS) Case-Based Reasoning (CBR) Process that predicts UPQ scores to assist users by focusing on the collaboration among them through the sharing of their experiences in using network applications. It builds (i) a knowledge base that includes not only information about network performance problems, but also applications’ characteristics, (ii) a case base that contains users’ opinions, and (iii) a user database that stores users’ profiles. By processing them, CNUS benefits users through the indication of the degree of satisfaction they may achieve based on the general opinion from members of their communities in similar contexts. In order to evaluate the suitability of CNUS, a CBR system was built and validated through an experimental study conducted in laboratory with a multi-agent system that simulated scenarios where users request for assistance. The simulation was supported by an ontology of network services and applications and reputation scheme implemented through the PageRank algorithm. The results of the study pointed to the effectiveness of CNUS, and its resilience to users’ collusive and incoherent behaviors. Besides that, they showed the influence of the knowledge about network characteristics, users’ profiles and application features on computer-based support activities.

Leaky bucket analysis for ATM networks

The authors investigate input rate control in ATM (asynchronous transfer mode) networks. More specifically, they focus on the policing mechanisms, whose function is to assure that the sources abide by their initial specification. They study one such mechanism, the leaky bucket, and use the uniform arrival and service model, as well as simulation to study its effectiveness in bursty traffic. They show that leaky bucket is not adequate for deletion of abusive traffic cells, and therefore, they propose a marking scheme to delete cells only in the case of congestion. They also introduce the notion of reaction time in input rate control and show that the use of multiple leaky buckets in parallel offers an effective tradeoff between average rate enforcement and reaction to sudden bursts.<<ETX>>

Defining bandwidth constraints with cooperative games

This paper proposes the use of cooperative game models to arbitrate bandwidth constraints in bandwidth constraint models. This work adopts cooperative games as a mathematical tool for arbitrating bandwidth constraints, considering differentiated service classes and network load information. Game solutions based on the Shapley Value are used to compose bandwidth constraints in two Bandwidth Constraint Models. Overload scenarios are explored in performance evaluation, and the new models are compared to the maximum allocation with reservation model. The results show that game-based allocations can not only achieve greater efficiency in bandwidth sharing but also provide bandwidth protection against QoS degradation and respect service differentiation for high, normal and low priority services.

Fair bandwidth sharing using Shapley value

In the Internet, applications with very distinct requirements share the same network resources. In order to avoid QoS degradation, the resource manager component from QoS mechanism should distribute the available bandwidth in efficient and fair way. Resource manager works as an arbitrator, when applications compete for scarce resources. This paper reviews and discusses some bandwidth mechanisms from the literature, and proposes a fair scheme for the bandwidth distribution under a class-based allocation. The proposed allocation method is based on Cooperative Games Justice Mode. The Shapley value is evaluated to find fair bandwidth allocations. When the demand exceeds the quantity to be allocated, Bankruptcy Games are applied to extend the Shapley value method. Numeric experiments with allocation of simultaneous flows from multi-class applications in a CBQ node showed the efficiency of the proposed method.