{"title":"Analysis of a delay-dependent priority discipline in a multi-class traffic packet switching node","authors":"Y. Lim, J. Kobza","doi":"10.1109/INFCOM.1988.13004","DOIUrl":null,"url":null,"abstract":"A dynamic priority discipline called head-of-the-line with priority jumps is proposed as an efficient link schedule for a packet switch serving multiple classes of delay-sensitive traffic. Implementation of this discipline is considered to be relatively simple, and the processing overhead relatively small. It is shown that, by properly adjusting the control parameters, the discipline can: (i) satisfy any relative average delay requirements for the different classes, thus bringing fairness of service, and resulting in resource saving, and (ii) make the tail probability of the delay distributions for the different classes beyond their targeted maximum delays approximately the same, thus approximately minimizing the overall maximum tail probability in the system.<<ETX>>","PeriodicalId":436217,"journal":{"name":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1988-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"50","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE INFOCOM '88,Seventh Annual Joint Conference of the IEEE Computer and Communcations Societies. Networks: Evolution or Revolution?","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INFCOM.1988.13004","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 50
Abstract
A dynamic priority discipline called head-of-the-line with priority jumps is proposed as an efficient link schedule for a packet switch serving multiple classes of delay-sensitive traffic. Implementation of this discipline is considered to be relatively simple, and the processing overhead relatively small. It is shown that, by properly adjusting the control parameters, the discipline can: (i) satisfy any relative average delay requirements for the different classes, thus bringing fairness of service, and resulting in resource saving, and (ii) make the tail probability of the delay distributions for the different classes beyond their targeted maximum delays approximately the same, thus approximately minimizing the overall maximum tail probability in the system.<>