| KEYWORD |
Autonomic network monitoring
Tesi all'estero
Parole chiave AUTONOMIC NETWORKS
Riferimenti PAOLO GIACCONE
Riferimenti esterni Prof.Antonio Liotta (Technische Universiteit Eindhoven, The Netherlands)
Gruppi di ricerca Telecommunication Networks Group
Tipo tesi EXPERIMENTAL, SIMULATIVE
Descrizione As networks become increasingly dynamic, the task of monitoring their activity for the purposes of management is extremely arduous. This project explores the use of machine learning for the development of a novel approach to network monitoring. The aim is to build an autonomic monitoring system whereby each node gradually develops estimates of the state of its surroundings. This 'predicted' state is matched against the 'real' state for self-learning purposes and is then shared with adjacent nodes. The hypothesis is that this 'probabilistic' approach can be more accurate, scalable and adaptive than the more conventional 'deterministic' monitoring systems.
In order to assess this hypothesis, the student will design the protocol internals, implement it within a network simulator, and carry out a comparative analysis.
Conoscenze richieste The student is expected to have a strong background in networking, excellent programming skills in C/C++, and a good knowledge of Unix/Linux.
Note This study will be executed at Technische Universiteit Eindhoven, The Netherlands. The student will be responsible for the travel and life expenses. Travel can be possibly funded through ERASMUS mobility grants for which the student has to apply in advance.
Deadline: December 2010
Scadenza validita proposta 25/10/2010
PROPONI LA TUA CANDIDATURA