Autonomic Computing, International Conference on (2004)
New York, New York
May 17, 2004 to May 18, 2004
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICAC.2004.21
Erol Gelenbe , Imperial College
Michael Gellman , University of Central Florida
Ricardo Lent , University of Central Florida
Peixiang Liu , University of Central Florida
Pu Su , University of Central Florida
We present an autonomous adaptive quality of service (QoS) driven network system called a "Cognitive Packet Network" (CPN), which adaptively selects paths so as to offer best effort QoS to the end users based on user defined QoS. CPN uses neural network based reinforcement learning to make routing decisions separately at each node. Measurements on an experimental test-bed are provided to show how the system responds to the choice of QoS goals. We also discuss and evaluate an extension of CPN that uses a genetic algorithm to generate and maintain paths from previously discovered information by matching their "fitness" with respect to the desired QoS.
P. Su, R. Lent, E. Gelenbe, M. Gellman and P. Liu, "Autonomous Smart Routing for Network QoS," Autonomic Computing, International Conference on(ICAC), New York, New York, 2004, pp. 232-239.