Home // EMERGING 2010, The Second International Conference on Emerging Network Intelligence // View article

An Application of Pattern Matching for the Adjustment of Quality of Service Metrics

Authors:
Douglas Legge
Atta Badii

Keywords: Quality of Service (QoS); self organizing map (SOM); k Nearest Neighbour (kNN); agent

Abstract:
Quality of Service is an important component of Internet Protocol traffic as it allows a prioritisation of designated applications during periods of high utilisation or where there is restricted resource, such that the end-user experience can be optimised. Typically, Quality of Service is defined through manual policies with expert human input required. In this paper, we present initial support for the hypothesis that the definition and on-going change management of manual Quality of Service policies can be replaced through the use of pattern matching techniques, which classify traffic in real-time. This paper serves as an introduction to concepts, which may be new to many Internet Protocol-based network engineers, and as a motivation for those in the field of Artificial Intelligence, machine-learning, as to where advanced learning functions could be applied.

Pages: 1 to 5

Copyright: Copyright (c) IARIA, 2010

Publication date: October 25, 2010

Published in: conference

ISSN: 2326-9383

ISBN: 978-1-61208-103-8

Location: Florence, Italy

Dates: from October 25, 2010 to October 30, 2010