{"title":"Shared buffering in nonblocking copy networks","authors":"M. Hegde","doi":"10.1109/ISIT.1994.395024","DOIUrl":null,"url":null,"abstract":"This paper investigates the performance of nonblocking copy networks employing the shared buffering scheme. We use the technique of tagged Markov chains to derive the stationary distributions for the occupancy of the buffers. Based on these stationary distributions, the delay, throughput, and packet loss probability are calculated as critical performance measures of the copy network. We also carry out analyses for variations in the copying policy such as fanout splitting wherein a copy request from a single packet may be completed over two time slots, and feed channel priority wherein there exists a certain priority among input channels.<<ETX>>","PeriodicalId":331390,"journal":{"name":"Proceedings of 1994 IEEE International Symposium on Information Theory","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1994-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of 1994 IEEE International Symposium on Information Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISIT.1994.395024","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This paper investigates the performance of nonblocking copy networks employing the shared buffering scheme. We use the technique of tagged Markov chains to derive the stationary distributions for the occupancy of the buffers. Based on these stationary distributions, the delay, throughput, and packet loss probability are calculated as critical performance measures of the copy network. We also carry out analyses for variations in the copying policy such as fanout splitting wherein a copy request from a single packet may be completed over two time slots, and feed channel priority wherein there exists a certain priority among input channels.<>