{"title":"Cell level performance approach for link dimensioning of ATM networks","authors":"J. de Oliveira, I. S. Bonatti, P. Peres, A. Budri","doi":"10.1109/ITS.1998.713115","DOIUrl":null,"url":null,"abstract":"ATM network dimensioning depends on the determination of the link capacity to ensure traffic demand meets a specific grade of service (cell loss probability, cell transfer delay and maximum delay variation). This paper proposes a new approach regarding the determination of the ATM link capacity. Starting from traffic and quality of service parameters and descriptors proposed by the ITU-T and ATM Forum, the best match of the effective bandwidth definitions is selected for each service class, using probabilistic models for connection cell loss and worst-case models for connection cell delay.","PeriodicalId":205350,"journal":{"name":"ITS'98 Proceedings. SBT/IEEE International Telecommunications Symposium (Cat. No.98EX202)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1998-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ITS'98 Proceedings. SBT/IEEE International Telecommunications Symposium (Cat. No.98EX202)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ITS.1998.713115","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
ATM network dimensioning depends on the determination of the link capacity to ensure traffic demand meets a specific grade of service (cell loss probability, cell transfer delay and maximum delay variation). This paper proposes a new approach regarding the determination of the ATM link capacity. Starting from traffic and quality of service parameters and descriptors proposed by the ITU-T and ATM Forum, the best match of the effective bandwidth definitions is selected for each service class, using probabilistic models for connection cell loss and worst-case models for connection cell delay.