Title :
Keynote: Steps Toward Self-Aware Networks
Author_Institution :
Imperial Coll. London, London, UK
fDate :
June 29 2010-July 1 2010
Abstract :
The design of a packet network where paths are dynamically selected based on Quality-of-Service (QoS) metrics that can be specified by the users of the network or by the network´s access points will be presented. The approach uses on-line measurement associated with the traffic itself, and reinforcement learning throughout the nodes of the network, to try to satisfy the users´ QoS objectives. The talk will present numerous measurement studies of this approach on a large laboratory test-bed. The talk is based on the recent paper in the Communications of the ACM (July 2009), which integrates different aspects of the research including network design, performance evaluation models and methods, and probability models of neuronal networks.
Keywords :
learning (artificial intelligence); neural nets; probability; quality of service; telecommunication computing; telecommunication traffic; QoS metrics; network access point; network traffic; neuronal network; online measurement; packet network design; probability model; quality of service; reinforcement learning; self-aware network;
Conference_Titel :
Computer and Information Technology (CIT), 2010 IEEE 10th International Conference on
Conference_Location :
Bradford
Print_ISBN :
978-1-4244-7547-6
DOI :
10.1109/CIT.2010.508