{"title":"改进大带宽延迟产品网络中的拥塞窗口增长","authors":"Joel Sing, B. Soh","doi":"10.1109/ICON.2007.4444117","DOIUrl":null,"url":null,"abstract":"TCP performance degrades significantly when used over networks with a large bandwidth delay product. This is primarily due to the exponential and linear congestion window growth algorithms employed by Jacobson based TCP variants. In this paper we present a logarithmic window growth algorithm that is based on bandwidth estimation, allowing it to perform well regardless of the network bandwidth delay product. Implementation details are presented for this algorithm, along with results achieved via simulation.","PeriodicalId":131548,"journal":{"name":"2007 15th IEEE International Conference on Networks","volume":"89 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Improving Congestion Window Growth in Large Bandwidth Delay Product Networks\",\"authors\":\"Joel Sing, B. Soh\",\"doi\":\"10.1109/ICON.2007.4444117\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"TCP performance degrades significantly when used over networks with a large bandwidth delay product. This is primarily due to the exponential and linear congestion window growth algorithms employed by Jacobson based TCP variants. In this paper we present a logarithmic window growth algorithm that is based on bandwidth estimation, allowing it to perform well regardless of the network bandwidth delay product. Implementation details are presented for this algorithm, along with results achieved via simulation.\",\"PeriodicalId\":131548,\"journal\":{\"name\":\"2007 15th IEEE International Conference on Networks\",\"volume\":\"89 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 15th IEEE International Conference on Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICON.2007.4444117\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 15th IEEE International Conference on Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICON.2007.4444117","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Improving Congestion Window Growth in Large Bandwidth Delay Product Networks
TCP performance degrades significantly when used over networks with a large bandwidth delay product. This is primarily due to the exponential and linear congestion window growth algorithms employed by Jacobson based TCP variants. In this paper we present a logarithmic window growth algorithm that is based on bandwidth estimation, allowing it to perform well regardless of the network bandwidth delay product. Implementation details are presented for this algorithm, along with results achieved via simulation.