论文信息 - Bandwidth Allocation in ATNI Networks Using Genetic Algorithms and Neural Networkst

Bandwidth Allocation in ATNI Networks Using Genetic Algorithms and Neural Networkst

We propose a control scheme for the bandwidth allocation in ATM networks. The scheme is based on genetic algorithms and neural networks and thus is capable of selecting adaptively optimal step sizes of virtual paths. For the optimization problem is constrained, traditional genetic algorithms no longer are applicable. We, therefore, propose the Masked Genetic Algorithms with Seeds (MGAS) to solve the problem. To achieve better performance, the relationships among the QOS measures and the evaluation of seed scores are discussed.

Jean-Lien C. Wu | Li-Der Chou

[1] Dan Keun Sung,et al. A Trial Multilayer Perceptron Neural Network for ATM Connection Admission Control (Special Issue on Broadband ISDN : Application, Networking and Management) , 1993 .

[2] Atsushi Hiramatsu. Integration of ATM Call Admission Control and Link Capacity Control by Distributed Neural Networks , 1991, IEEE J. Sel. Areas Commun..

[3] Li-Der Chou,et al. Buffer management using genetic algorithms and neural networks , 1995, Proceedings of GLOBECOM '95.

[4] Xiaoqiang Chen,et al. Neural adaptive congestion control for broadband ATM networks , 1992 .

[5] Jean-Lien C. Wu,et al. Parameter Adjustment Using Neural-Network-Based Genetic Algorithms for Guaranteed QOS in ATM Networks , 1995 .

[6] Li-Der Chou,et al. Virtual paths with dynamic step sizes in ATM networks , 1995, Proceedings of GLOBECOM '95.

[7] J.-L.C. Wu,et al. Two-level dynamic step sizes of virtual paths on bandwidth allocation in ATM networks , 1995 .