{"title":"实时多媒体传播的鲁棒覆盖网络","authors":"Qiang Zeng, Hua Miao, Zhaoliang Zhu","doi":"10.1109/SITIS.2007.41","DOIUrl":null,"url":null,"abstract":"Robustness of overlay networks is an importantproperty as well as short delay for real-time media transmission. Unlike previous schemes, which achieve robustness by restoring spanning trees afternodes or links fail, we focus on reducing possible data loss when failure occurs. According to analysis of the relation between tree depth and data loss, we first present a spanning tree which minimizes dataloss but results in large delay. By introducing a factor, we propose a spanning tree which exhibits fine flexibility and tradeoff between data loss and delay. Simulation results show that it achieves relatively low data loss and delay simultaneously, as is optimum for a large range of applications.","PeriodicalId":234433,"journal":{"name":"2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System","volume":"99 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Robust Overlay Network for Real-Time Multimedia Dissemination\",\"authors\":\"Qiang Zeng, Hua Miao, Zhaoliang Zhu\",\"doi\":\"10.1109/SITIS.2007.41\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Robustness of overlay networks is an importantproperty as well as short delay for real-time media transmission. Unlike previous schemes, which achieve robustness by restoring spanning trees afternodes or links fail, we focus on reducing possible data loss when failure occurs. According to analysis of the relation between tree depth and data loss, we first present a spanning tree which minimizes dataloss but results in large delay. By introducing a factor, we propose a spanning tree which exhibits fine flexibility and tradeoff between data loss and delay. Simulation results show that it achieves relatively low data loss and delay simultaneously, as is optimum for a large range of applications.\",\"PeriodicalId\":234433,\"journal\":{\"name\":\"2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System\",\"volume\":\"99 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-12-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SITIS.2007.41\",\"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 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SITIS.2007.41","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Robust Overlay Network for Real-Time Multimedia Dissemination
Robustness of overlay networks is an importantproperty as well as short delay for real-time media transmission. Unlike previous schemes, which achieve robustness by restoring spanning trees afternodes or links fail, we focus on reducing possible data loss when failure occurs. According to analysis of the relation between tree depth and data loss, we first present a spanning tree which minimizes dataloss but results in large delay. By introducing a factor, we propose a spanning tree which exhibits fine flexibility and tradeoff between data loss and delay. Simulation results show that it achieves relatively low data loss and delay simultaneously, as is optimum for a large range of applications.