DocumentCode :
3117828
Title :
Evaluation of computer network Quality of Service using neural networks
Author :
Dogman, Aboagela ; Saatchi, Reza ; Al-Khayatt, S.
Author_Institution :
Fac. of Art, Comput., Eng. & Sci., Sheffield Hallam Univ., Sheffield, UK
fYear :
2012
fDate :
23-26 Sept. 2012
Firstpage :
217
Lastpage :
222
Abstract :
Evaluation of Quality of Service (QoS) is an important task in managing computer networks. In this study, an innovative QoS evaluation system was proposed. The system combines discrimination features of supervised and unsupervised neural networks to analyse and assess QoS for transmission of Voice over Internet Protocol (VoIP) in a simulated computer network. The transmitted application´ QoS parameters were initially analysed by the unsupervised learning Kohonen neural network. The analysed QoS parameters were then used as inputs to a supervised learning Multi-Layer Perceptron (MLP) neural network in order to quantify the overall QoS. The QoS assessment results from the proposed method correlated closely with the previously developed QoS assessment methods that were based on fuzzy logic, regression model, and Euclidean distance measure. However, the neural network´s learning ability resulted in the system´s parameters to be adaptively determined, reducing the complexity of the system design and facilitating ease of further improvements in the system´s capability.
Keywords :
Internet telephony; computational complexity; computational geometry; computer network management; fuzzy logic; multilayer perceptrons; quality of service; regression analysis; self-organising feature maps; unsupervised learning; Euclidean distance measure; MLP neural network; QoS assessment methods; QoS evaluation system; VoIP; computer network management; computer network quality-of-service evaluation; discrimination features; fuzzy logic; regression model; supervised learning multilayer perceptron neural network; system design complexity reduction; unsupervised learning Kohonen neural network; voice-over-Internet protocol; Delay; Jitter; Neurons; Packet loss; Quality of service; Training; multimedia computer networks; neural network; quality of service assessment;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Business, Engineering and Industrial Applications (ISBEIA), 2012 IEEE Symposium on
Conference_Location :
Bandung
Print_ISBN :
978-1-4577-1632-4
Type :
conf
DOI :
10.1109/ISBEIA.2012.6422873
Filename :
6422873
Link To Document :
بازگشت