{"title":"Putting a CO2 figure on a piece of computation","authors":"Conor Kelly, E. Mangina, Antonio Ruzelli","doi":"10.1109/EPQU.2011.6128960","DOIUrl":null,"url":null,"abstract":"In recent years, energy efficiency has become a major focus of data centre designers and operators. This has predominantly been due to the rising cost of energy and the exponential increase in the absolute energy consumption of data centres. As carbon taxes, emissions trading and environmental imperatives become an increasing influence in the regions in which data centres are based, measuring and controlling the emissions resulting from the energy consumed in a data centre will become as important as controlling the energy consumption itself. In this paper, two bodies of research are investigated: granular energy monitoring in data centres and electricity generation emissions calculation. We propose a method to accurately calculate the emissions caused by a single piece of computation by correlating the two areas. It is shown that a saving of 45% of the resultant emissions of scheduling a piece of computation can be made by choosing one of two contrasting times with different marginal power plants on the Irish electricity grid. This saving increases to over 99% at times when wind generation is being curtailed.","PeriodicalId":369941,"journal":{"name":"11th International Conference on Electrical Power Quality and Utilisation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"11th International Conference on Electrical Power Quality and Utilisation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EPQU.2011.6128960","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
In recent years, energy efficiency has become a major focus of data centre designers and operators. This has predominantly been due to the rising cost of energy and the exponential increase in the absolute energy consumption of data centres. As carbon taxes, emissions trading and environmental imperatives become an increasing influence in the regions in which data centres are based, measuring and controlling the emissions resulting from the energy consumed in a data centre will become as important as controlling the energy consumption itself. In this paper, two bodies of research are investigated: granular energy monitoring in data centres and electricity generation emissions calculation. We propose a method to accurately calculate the emissions caused by a single piece of computation by correlating the two areas. It is shown that a saving of 45% of the resultant emissions of scheduling a piece of computation can be made by choosing one of two contrasting times with different marginal power plants on the Irish electricity grid. This saving increases to over 99% at times when wind generation is being curtailed.