Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Wide-area traffic: the failure of Poisson modeling
SIGCOMM '94 Proceedings of the conference on Communications architectures, protocols and applications
On the use of fractional Brownian motion in the theory of connectionless networks
IEEE Journal on Selected Areas in Communications
| Hi-index | 0.00 |
Allocating resources to data traffic in telecommunication networks is a difficult problem because of the complex dynamics exhibited by this kind of traffic and because of the difficult trade-off between the delivered quality of service and the wasted bandwidth. We describe and compare the performances of two controllers of different designs (a Kalman filter and a neural network) to adaptatively control the bandwidth of a VP connecting two network nodes so as to keep the quality of service close to a given target. Simulations are carried out on a hardware emulator which allows a fast and faithful simulation of the switch functionalities. The Kalman filter obtains good performances and the original (and specific to this problem and its implementation constraints) neural network training strategy allows to obtain a faster and more accurate control.