{"title":"Energy-aware device drivers for embedded operating systems","authors":"Markus Buschhoff, Robert Falkenberg, O. Spinczyk","doi":"10.1145/3373400.3373401","DOIUrl":null,"url":null,"abstract":"Energy harvesting solutions with rechargeable batteries are a frequent choice to tackle the problems of supplying continuous power to deeply embedded devices like wireless sensor nodes. However, if the utilization of a node is not thoroughly planned, the battery may be drained too early and a continuous operation of such a device may become impossible. Here, an energy-management solution is required to control the flow of energy. As a foundation for energy management in software, we introduce a concept that allows to model energy consumption of hardware and to synthesize energy aware device drivers from these models. Our drivers are able to account the energy consumption of each driver function call at an accuracy of more than 90%. We provide a detailed overhead and accuracy evaluation of a driver implementation and hence prove the feasibility of our concept.","PeriodicalId":447904,"journal":{"name":"SIGBED Rev.","volume":"42 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"SIGBED Rev.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3373400.3373401","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
Energy harvesting solutions with rechargeable batteries are a frequent choice to tackle the problems of supplying continuous power to deeply embedded devices like wireless sensor nodes. However, if the utilization of a node is not thoroughly planned, the battery may be drained too early and a continuous operation of such a device may become impossible. Here, an energy-management solution is required to control the flow of energy. As a foundation for energy management in software, we introduce a concept that allows to model energy consumption of hardware and to synthesize energy aware device drivers from these models. Our drivers are able to account the energy consumption of each driver function call at an accuracy of more than 90%. We provide a detailed overhead and accuracy evaluation of a driver implementation and hence prove the feasibility of our concept.