Performance study of Byzantine Agreement Protocol with artificial neural network

nce 1982, numerous Byzantine Agreement Protocols (BAPs) have been developed to solve arbitrary faults in the Byzantine Generals Problem (BGP). A novel BAP, using an artificial neural network (ANN), was proposed by Wang and Kao. It requires message exchange rounds similar to the traditional BAP and i...

Full description

Bibliographic Details
Main Authors: Lee, Kok-Wah, Ewe, Hong-Tat
Format: Article
Published: ELSEVIER SCIENCE INC 2007
Subjects:
Online Access:http://shdl.mmu.edu.my/2990/
_version_ 1848790203790000128
author Lee, Kok-Wah
Ewe, Hong-Tat
author_facet Lee, Kok-Wah
Ewe, Hong-Tat
author_sort Lee, Kok-Wah
building MMU Institutional Repository
collection Online Access
description nce 1982, numerous Byzantine Agreement Protocols (BAPs) have been developed to solve arbitrary faults in the Byzantine Generals Problem (BGP). A novel BAP, using an artificial neural network (ANN), was proposed by Wang and Kao. It requires message exchange rounds similar to the traditional BAP and its suitability, in the context of network size, has not been investigated. In the present study, we propose to adopt Nguyen-Widrow initialization in ANN training, which modifies message communication and limits the message exchange rounds to three rounds. This modified approach is referred to as BAP-ANN. The BAP-ANN performs better than the traditional BAP, when the network size n is greater than nine. We also evaluate the message exchange matrix (MEM) constructed during the message exchange stage. For a fixed number of faulty nodes and remainder cases of (n mod 3), the study shows that the mean epoch for ANN training decreases as the network size increases, which indicates better fault tolerance. (c) 2007 Elsevier Inc. All rights reserved.
first_indexed 2025-11-14T18:08:53Z
format Article
id mmu-2990
institution Multimedia University
institution_category Local University
last_indexed 2025-11-14T18:08:53Z
publishDate 2007
publisher ELSEVIER SCIENCE INC
recordtype eprints
repository_type Digital Repository
spelling mmu-29902011-09-26T03:10:40Z http://shdl.mmu.edu.my/2990/ Performance study of Byzantine Agreement Protocol with artificial neural network Lee, Kok-Wah Ewe, Hong-Tat T Technology (General) QA75.5-76.95 Electronic computers. Computer science nce 1982, numerous Byzantine Agreement Protocols (BAPs) have been developed to solve arbitrary faults in the Byzantine Generals Problem (BGP). A novel BAP, using an artificial neural network (ANN), was proposed by Wang and Kao. It requires message exchange rounds similar to the traditional BAP and its suitability, in the context of network size, has not been investigated. In the present study, we propose to adopt Nguyen-Widrow initialization in ANN training, which modifies message communication and limits the message exchange rounds to three rounds. This modified approach is referred to as BAP-ANN. The BAP-ANN performs better than the traditional BAP, when the network size n is greater than nine. We also evaluate the message exchange matrix (MEM) constructed during the message exchange stage. For a fixed number of faulty nodes and remainder cases of (n mod 3), the study shows that the mean epoch for ANN training decreases as the network size increases, which indicates better fault tolerance. (c) 2007 Elsevier Inc. All rights reserved. ELSEVIER SCIENCE INC 2007-11 Article NonPeerReviewed Lee, Kok-Wah and Ewe, Hong-Tat (2007) Performance study of Byzantine Agreement Protocol with artificial neural network. Information Sciences, 177 (21). pp. 4785-4798. http://dx.doi.org/10.1016/j.ins.2007.04.011 doi:10.1016/j.ins.2007.04.011 doi:10.1016/j.ins.2007.04.011
spellingShingle T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
Lee, Kok-Wah
Ewe, Hong-Tat
Performance study of Byzantine Agreement Protocol with artificial neural network
title Performance study of Byzantine Agreement Protocol with artificial neural network
title_full Performance study of Byzantine Agreement Protocol with artificial neural network
title_fullStr Performance study of Byzantine Agreement Protocol with artificial neural network
title_full_unstemmed Performance study of Byzantine Agreement Protocol with artificial neural network
title_short Performance study of Byzantine Agreement Protocol with artificial neural network
title_sort performance study of byzantine agreement protocol with artificial neural network
topic T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2990/
http://shdl.mmu.edu.my/2990/
http://shdl.mmu.edu.my/2990/