Multimedia traffic quality of service management using statistical and artificial intelligence techniques

Abstract

Managing quality of service (QoS) is an important network operation, especially in hybrid wired and wireless multimedia networks. In this study, a two-stage approach to intelligently manage QoS for multimedia traffic was developed. Voice over Internet protocol (VoIP) was included in the study as an example of a typical multimedia application. Initially an adaptive statistical sampling technique was employed. It determined the traffic's statistics and used them in a fuzzy inference system to determine the optimum interval between every two consecutive sections of the traffic sampled. In the second stage, a fuzzy c-means (FCM) clustering was used to pre-process QoS parameters (delay, jitter and packet loss ratio) obtained from the devised sampling scheme. A multilayer perceptron (MLP) neural network then used the information from FCM to assess the QoS provided for VoIP. It was shown that the developed adaptive statistical sampling represents the traffic more correctly than the systematic, stratified and random non-adaptive sampling methods. Also, the combination of statistical sampling followed by FCM and MLP accurately indicated the QoS for VoIP.

Quality of service evaluation and assessment methods in wireless networks

“…Linear regression model is shown in (10) which defines the relationship model between independent variables (X) and dependent variable (Y) [18] [19]. (10) B is the regression coefficients and E is associated with measurement error which was considered as zeros in this study.…”

“…Neural networks enabled assessment of QoS in wired and wireless networks. An innovative QoS evaluation method that used neural networks to analyse and assess QoS for VoIP transmitted traffic (VoIP) in NS-2 simulated networks was proposed [9] [10]. The traffic parameters were initially classified into different categories of QoS by an unsupervised learning Kohonen neural network.…”

A Critical Review on the Implementation of Static Data Sampling Techniques to Detect Network Attacks

“…In order to quantify the distortion introduced by the sampling procedures, we consider comparing different statistical metrics. The overall quantification of statistical changes between sampled and unsampled traffic is defined by the Overall Statistic (OS) calculated as follows [37], [38]:…”

Privacy Preserving Big Data publishing- A scalable K-anonymization approach using MapReduce

“…In this paper [5], authors given a reviewed and developed an approach based on two stages to intelligently manage QoS for multimedia traffic. As a typical multimedia application they have considered VoIP and applied an adaptive statistical sampling technique in initial stages.…”