Kota Srinivas Reddy, Arunabh Saxena, Sharayu Moharir, N. Karamchandani
{"title":"内容交付的在线服务策略","authors":"Kota Srinivas Reddy, Arunabh Saxena, Sharayu Moharir, N. Karamchandani","doi":"10.1109/SPCOM50965.2020.9179501","DOIUrl":null,"url":null,"abstract":"Content Delivery Networks (CDNs) are an essential component of Video on Demand (VoD) services. We consider a content delivery system comprising a central server connected to several co-located caches, each with limited storage and service capabilities. We evaluate the performance of our storage policy when coupled with online service policies as a function of cache size, file library size, and the number of caches. We show that for file libraries with Zipf popularity profiles, our storage policy, when coupled with any online service policy, which allocates each request to a cache if possible, is as effective as the best offline service policy existing in the literature. The advantage of online service policies is that they have smaller time complexity than offline service policies. We also support our theoretical results via simulations for finite-size systems.","PeriodicalId":208527,"journal":{"name":"2020 International Conference on Signal Processing and Communications (SPCOM)","volume":"16 8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Online Service Policies for Content Delivery\",\"authors\":\"Kota Srinivas Reddy, Arunabh Saxena, Sharayu Moharir, N. Karamchandani\",\"doi\":\"10.1109/SPCOM50965.2020.9179501\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Content Delivery Networks (CDNs) are an essential component of Video on Demand (VoD) services. We consider a content delivery system comprising a central server connected to several co-located caches, each with limited storage and service capabilities. We evaluate the performance of our storage policy when coupled with online service policies as a function of cache size, file library size, and the number of caches. We show that for file libraries with Zipf popularity profiles, our storage policy, when coupled with any online service policy, which allocates each request to a cache if possible, is as effective as the best offline service policy existing in the literature. The advantage of online service policies is that they have smaller time complexity than offline service policies. We also support our theoretical results via simulations for finite-size systems.\",\"PeriodicalId\":208527,\"journal\":{\"name\":\"2020 International Conference on Signal Processing and Communications (SPCOM)\",\"volume\":\"16 8 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 International Conference on Signal Processing and Communications (SPCOM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SPCOM50965.2020.9179501\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International Conference on Signal Processing and Communications (SPCOM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SPCOM50965.2020.9179501","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Content Delivery Networks (CDNs) are an essential component of Video on Demand (VoD) services. We consider a content delivery system comprising a central server connected to several co-located caches, each with limited storage and service capabilities. We evaluate the performance of our storage policy when coupled with online service policies as a function of cache size, file library size, and the number of caches. We show that for file libraries with Zipf popularity profiles, our storage policy, when coupled with any online service policy, which allocates each request to a cache if possible, is as effective as the best offline service policy existing in the literature. The advantage of online service policies is that they have smaller time complexity than offline service policies. We also support our theoretical results via simulations for finite-size systems.