Paulo Henrique Portela de Carvalho

Learn More
This paper presents a machine learning approach for link adaptation in orthogonal frequency-division multiplexing systems through adaptive modulation and coding. Although machine learning techniques have attracted attention for link adaptation, most of the the schemes proposed so far are based on off-line training algorithms, which make them not well suited(More)
This work presents a traffic characterization procedure for traffic engineering (TE) in converged networks. An analytical model, focused in a self-similar aggregated traffic characterization is proposed, which considers QoS restrictions for delay metrics. The model, together with evolutionary techniques, is used for the optimization of the link capacity(More)
In this paper we present the development and validation of an experimental platform based in open source software and the development of a package for monitoring purposes. The software package with its components is described and validated through a group of tests and examples. These results are the initial support for future research which includes new(More)
This work presents a planning methodology for multimedia networks based on a hybrid traffic model and an evolutionary optimization procedure. The methodology intends to optimize the sizing of network elements to comply with two QoS simultaneous network parameters as well as to promote network stability and cost efficiency. The hybrid traffic model deals(More)
This work proposes a hybrid traffic model for multimedia networks as a fundamental element in a network planning optimization procedure. The proposed model uses a combination of the fBm (fractional Brownian motion) and Markovian traffic characterization procedures combined with link parameters in order to produce more accurate values of QoS metrics. The(More)
. This work presents a methodology for network traffic engineering based on a hybrid traffic model and an adaptive routing algorithm. The hybrid traffic model pursuits the calculation of more accurate Qos metrics and effective bandwidth for multimedia traffic in order to optimize the sizing of network elements at a minimal cost. During network operation,(More)
Evolutionary Algorithms can be inefficient in optimizing problems in which fitness evaluation of candidate solutions is computationally expensive. In this paper, single and multi-objective evolutionary methods assisted by meta-models are proposed and analyzed. Meta-models are used to identify promising regions of search space in order to save evaluations of(More)