Bandwidth allocation in ATM networks using genetic algorithms and neural networks

Li Der Chou; Jean Lien C. Wu

Bandwidth allocation in ATM networks using genetic algorithms and neural networks

Li Der Chou, Jean Lien C. Wu

Department of Computer Science and Information Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

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.

Original language	English
Pages	962-966
Number of pages	5
State	Published - 1997
Event	Proceedings of the 1997 IEEE Global Telecommunications Conference. Part 2 (of 3) - Phoenix, AZ, USA Duration: 3 Nov 1997 → 8 Nov 1997

Conference

Conference	Proceedings of the 1997 IEEE Global Telecommunications Conference. Part 2 (of 3)
City	Phoenix, AZ, USA
Period	3/11/97 → 8/11/97

Cite this

@conference{965b2b9f32ec494e8e0c213248b6f870,

title = "Bandwidth allocation in ATM networks using genetic algorithms and neural networks",

abstract = "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.",

author = "Chou, {Li Der} and Wu, {Jean Lien C.}",

year = "1997",

language = "???core.languages.en_GB???",

pages = "962--966",

note = "Proceedings of the 1997 IEEE Global Telecommunications Conference. Part 2 (of 3) ; Conference date: 03-11-1997 Through 08-11-1997",

}

TY - CONF

T1 - Bandwidth allocation in ATM networks using genetic algorithms and neural networks

AU - Chou, Li Der

AU - Wu, Jean Lien C.

PY - 1997

Y1 - 1997

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0031337470&partnerID=8YFLogxK

M3 - 會議論文

AN - SCOPUS:0031337470

SP - 962

EP - 966

T2 - Proceedings of the 1997 IEEE Global Telecommunications Conference. Part 2 (of 3)

Y2 - 3 November 1997 through 8 November 1997

ER -

Bandwidth allocation in ATM networks using genetic algorithms and neural networks

Abstract

Conference

Fingerprint

Cite this