{"title":"Microprocessor-based adaptive thermal control for an air-cooled computer CPU module","authors":"C. Lundquist, V. Carey","doi":"10.1109/STHERM.2001.915174","DOIUrl":null,"url":null,"abstract":"This paper summarizes an exploration of design strategies for a microprocessor-based adaptive thermal control system for heat-dissipating computer CPU modules. The thermal control system contains a cold plate with an air-cooled base mode and a thermo-electric heat pump element that can boost cooling performance when needed. The microprocessor programming includes models of the heat transfer in the cold plate and the thermal performance of the thermo-electric heat pump and the fan coolers. The microprocessor is programmed to compare the thermal control system model predictions to the existing operating conditions. The results of this comparison are used to facilitate control of the cooling system and to provide fault detection during its operation. This paper reports the progress of an ongoing study that will explore different ways that the computational capability of the processor can be used to minimize power consumption while maintaining adequate processor temperature control over broadly varying operating conditions. The investigation also explores the merits of different strategies for incorporating fault detection features into the microprocessor programming to enhance the reliability and robustness of the system.","PeriodicalId":307079,"journal":{"name":"Seventeenth Annual IEEE Semiconductor Thermal Measurement and Management Symposium (Cat. No.01CH37189)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2001-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"16","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Seventeenth Annual IEEE Semiconductor Thermal Measurement and Management Symposium (Cat. No.01CH37189)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/STHERM.2001.915174","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 16
Abstract
This paper summarizes an exploration of design strategies for a microprocessor-based adaptive thermal control system for heat-dissipating computer CPU modules. The thermal control system contains a cold plate with an air-cooled base mode and a thermo-electric heat pump element that can boost cooling performance when needed. The microprocessor programming includes models of the heat transfer in the cold plate and the thermal performance of the thermo-electric heat pump and the fan coolers. The microprocessor is programmed to compare the thermal control system model predictions to the existing operating conditions. The results of this comparison are used to facilitate control of the cooling system and to provide fault detection during its operation. This paper reports the progress of an ongoing study that will explore different ways that the computational capability of the processor can be used to minimize power consumption while maintaining adequate processor temperature control over broadly varying operating conditions. The investigation also explores the merits of different strategies for incorporating fault detection features into the microprocessor programming to enhance the reliability and robustness of the system.