{"title":"混合式液空冷却服务器的热性能建模","authors":"R. Zeighami, W. Saunders, Henry Coles, S. Branton","doi":"10.1109/ITHERM.2014.6892333","DOIUrl":null,"url":null,"abstract":"This paper discusses data center scale performance characterization of hybrid liquid-air cooling solutions for a full 42U rack of servers. Using data collected in a production data center at Lawrence Berkeley Laboratories, we interpret the results with a simple three parameter model which allows characterization of the major factors affecting heat recovery efficiency of the system. The model is shown to agree with a broad set of data under a variety of temperature and workload conditions. To our knowledge, this is the first large scale characterization of a hybrid cooling solution's performance in terms relevant to data center operation. We discuss how this method can be extended to other systems for meaningful comparison of solution performance.","PeriodicalId":12453,"journal":{"name":"Fourteenth Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm)","volume":"155 1","pages":"583-587"},"PeriodicalIF":0.0000,"publicationDate":"2014-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Thermal performance modeling of hybrid liquid-air cooled servers\",\"authors\":\"R. Zeighami, W. Saunders, Henry Coles, S. Branton\",\"doi\":\"10.1109/ITHERM.2014.6892333\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper discusses data center scale performance characterization of hybrid liquid-air cooling solutions for a full 42U rack of servers. Using data collected in a production data center at Lawrence Berkeley Laboratories, we interpret the results with a simple three parameter model which allows characterization of the major factors affecting heat recovery efficiency of the system. The model is shown to agree with a broad set of data under a variety of temperature and workload conditions. To our knowledge, this is the first large scale characterization of a hybrid cooling solution's performance in terms relevant to data center operation. We discuss how this method can be extended to other systems for meaningful comparison of solution performance.\",\"PeriodicalId\":12453,\"journal\":{\"name\":\"Fourteenth Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm)\",\"volume\":\"155 1\",\"pages\":\"583-587\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-05-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Fourteenth Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ITHERM.2014.6892333\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fourteenth Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ITHERM.2014.6892333","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Thermal performance modeling of hybrid liquid-air cooled servers
This paper discusses data center scale performance characterization of hybrid liquid-air cooling solutions for a full 42U rack of servers. Using data collected in a production data center at Lawrence Berkeley Laboratories, we interpret the results with a simple three parameter model which allows characterization of the major factors affecting heat recovery efficiency of the system. The model is shown to agree with a broad set of data under a variety of temperature and workload conditions. To our knowledge, this is the first large scale characterization of a hybrid cooling solution's performance in terms relevant to data center operation. We discuss how this method can be extended to other systems for meaningful comparison of solution performance.