-
公开(公告)号:US07925911B2
公开(公告)日:2011-04-12
申请号:US11862762
申请日:2007-09-27
CPC分类号: G06F1/3203
摘要: Methods, systems, and computer program products are provided for managing computer power among a plurality of computers so that the aggregate power consumption does not exceed a maximum subscription amount, the maximum subscription amount comprising the maximum amount of power that can be supplied to the plurality of computers. Embodiments include monitoring, by a central power management module, aggregate power consumption of the plurality of computers; the central power management module and the computers coupled for data communications through a power management network; determining, by the central power management module, whether the aggregate power consumption exceeds a predetermined maximum aggregate power threshold, the maximum aggregate power threshold less than the maximum subscription amount; if the aggregate power consumption exceeds the predetermined maximum aggregate power threshold, throttling-down the plurality of computers, reducing the aggregate power consumption to a level below the predetermined maximum aggregate power threshold. Typical embodiments also include determining, by a central power management module, whether the aggregate power consumption is below a predetermined minimum aggregate power threshold; and if the aggregate power consumption is below a predetermined minimum aggregate power threshold, throttling-up the plurality of computers increasing the aggregate power consumption to a level that exceeds the predetermined minimum threshold.
摘要翻译: 提供了用于管理多个计算机之间的计算机电力的方法,系统和计算机程序产品,使得总功率消耗不超过最大订阅量,最大订阅量包括可提供给多个计算机的最大功率量 的电脑。 实施例包括由中央电源管理模块监视多个计算机的总功耗; 中央电源管理模块和通过电力管理网络耦合用于数据通信的计算机; 由所述中央电源管理模块确定所述总功耗是否超过预定的最大总功率阈值,所述最大总功率阈值小于所述最大认购量; 如果总功率消耗超过预定的最大总功率阈值,则对多台计算机进行调节,将总功耗降低到低于预定最大总功率阈值的水平。 典型实施例还包括由中央电源管理模块确定总功耗是否低于预定的最小总功率阈值; 并且如果所述总功率消耗低于预定的最小总功率阈值,则将所述多个计算机调节到将所述总功耗增加到超过所述预定最小阈值的水平。
-
2.
公开(公告)号:US20090132842A1
公开(公告)日:2009-05-21
申请号:US11940896
申请日:2007-11-15
IPC分类号: G06F1/32
CPC分类号: G06F1/3203
摘要: Methods, systems, and computer program products are provided for managing power consumption of computing devices in a computer equipment rack. Embodiments include monitoring aggregate power consumption of a plurality of computing devices in the computer equipment rack; determining whether the aggregate power consumption exceeds a predetermined maximum threshold; if the aggregate power consumption exceeds the predetermined maximum threshold, selecting a number of computing devices for throttling in dependence upon priority; and throttling-down the selected computing devices computing devices, reducing the aggregate power consumption to a level below the predetermined maximum threshold. Some embodiments may also include determining whether the aggregate power consumption is below a predetermined minimum threshold; if the aggregate power consumption is below the predetermined minimum threshold, selecting a number of computing devices computing devices computing devices for throttling in dependence upon priority; and throttling-up the selected computing devices, increasing the aggregate power consumption to a level above the predetermined minimum threshold.
摘要翻译: 提供了用于管理计算机设备机架中计算设备的功耗的方法,系统和计算机程序产品。 实施例包括监视计算机设备机架中的多个计算设备的总体功耗; 确定所述总功耗是否超过预定的最大阈值; 如果总功率消耗超过预定的最大阈值,则根据优先级选择用于节流的计算设备的数量; 并且对所选择的计算设备计算设备进行调节,将总功耗降低到低于预定最大阈值的水平。 一些实施例还可以包括确定总功率消耗是否低于预定的最小阈值; 如果所述总功耗低于所述预定最小阈值,则根据优先级选择一些计算设备计算设备用于节流的计算设备; 并且调节所选择的计算设备,将总功率增加到高于预定最小阈值的水平。
-
公开(公告)号:US20090089595A1
公开(公告)日:2009-04-02
申请号:US11862762
申请日:2007-09-27
IPC分类号: G06F1/00
CPC分类号: G06F1/3203
摘要: Methods, systems, and computer program products are provided for managing computer power among a plurality of computers so that the aggregate power consumption does not exceed a maximum subscription amount, the maximum subscription amount comprising the maximum amount of power that can be supplied to the plurality of computers. Embodiments include monitoring, by a central power management module, aggregate power consumption of the plurality of computers; the central power management module and the computers coupled for data communications through a power management network; determining, by the central power management module, whether the aggregate power consumption exceeds a predetermined maximum aggregate power threshold, the maximum aggregate power threshold less than the maximum subscription amount; if the aggregate power consumption exceeds the predetermined maximum aggregate power threshold, throttling-down the plurality of computers, reducing the aggregate power consumption to a level below the predetermined maximum aggregate power threshold. Typical embodiments also include determining, by a central power management module, whether the aggregate power consumption is below a predetermined minimum aggregate power threshold; and if the aggregate power consumption is below a predetermined minimum aggregate power threshold, throttling-up the plurality of computers increasing the aggregate power consumption to a level that exceeds the predetermined minimum threshold.
摘要翻译: 提供了用于管理多个计算机之间的计算机电力的方法,系统和计算机程序产品,使得总功率消耗不超过最大订阅量,最大订阅量包括可提供给多个计算机的最大功率量 的电脑。 实施例包括由中央电源管理模块监视多个计算机的总功耗; 中央电源管理模块和通过电力管理网络耦合用于数据通信的计算机; 由所述中央电源管理模块确定所述总功耗是否超过预定的最大总功率阈值,所述最大总功率阈值小于所述最大认购量; 如果总功率消耗超过预定的最大总功率阈值,则对多台计算机进行调节,将总功耗降低到低于预定最大总功率阈值的水平。 典型实施例还包括由中央电源管理模块确定总功率消耗是否低于预定的最小总功率阈值; 并且如果所述总功率消耗低于预定的最小总功率阈值,则将所述多个计算机调节到将所述总功耗增加到超过所述预定最小阈值的水平。
-
公开(公告)号:US20090070611A1
公开(公告)日:2009-03-12
申请号:US11854398
申请日:2007-09-12
IPC分类号: G06F1/32
CPC分类号: G06F1/3203 , G06F1/329 , Y02D10/24
摘要: Methods, systems, and computer program products are provided for managing computer power consumption in a data center. Embodiments include monitoring aggregate power consumption of a plurality of computers in the data center, each of the computers being supplied power individually from a shared circuit in the data center; determining whether the aggregate power consumption exceeds a predetermined maximum threshold; if the aggregate power consumption exceeds the predetermined maximum threshold, selecting a number of computers for throttling in dependence upon priority; and throttling-down the selected computers, reducing the aggregate power consumption to a level below the predetermined maximum threshold. Some embodiments may also include determining whether the aggregate power consumption is below a predetermined minimum threshold; if the aggregate power consumption is below the predetermined minimum threshold, selecting a number of computers for throttling in dependence upon priority; and throttling-up the selected computers, increasing the aggregate power consumption to a level above the predetermined minimum threshold.
摘要翻译: 提供了方法,系统和计算机程序产品,用于管理数据中心中的计算机功耗。 实施例包括监视数据中心中的多个计算机的总体功耗,每个计算机分别从数据中心的共享电路供电; 确定所述总功耗是否超过预定的最大阈值; 如果总功率消耗超过预定最大阈值,则根据优先级选择用于节流的计算机数量; 并调节所选择的计算机,将总功耗降低到低于预定最大阈值的水平。 一些实施例还可以包括确定总功率消耗是否低于预定的最小阈值; 如果总功耗低于预定最小阈值,则根据优先级选择用于节流的计算机数量; 并调节所选择的计算机,将总功率增加到高于预定最小阈值的水平。
-
公开(公告)号:US07342797B2
公开(公告)日:2008-03-11
申请号:US11746322
申请日:2007-05-09
申请人: Vinod Kamath , Beth F. Loebach
发明人: Vinod Kamath , Beth F. Loebach
IPC分类号: H05K7/20
CPC分类号: H01L23/367 , G06F1/184 , G06F1/185 , G06F1/186 , G06F1/20 , H01L2924/0002 , H01L2924/00
摘要: A heat sink device for conventional memory modules, such as DIMMs, that is configured to be positioned between adjacent memory modules mounted in substantially parallel connectors on a printed circuit board. Each heat sink device includes thermally conductive first and second members configured to thermally couple with electronic components of a conventional memory module. The first and second members may be resiliently biased away from one another so that the resilient bias causes the members to abut respective electronic components when placed between adjacent memory modules. A separate wedge, or a lever-mounted wedge, may be provided for insertion between the members to urge them away from one another and into abutting relationship with electronic components on facing surfaces of the adjacent memory modules. When abutting opposing electronic components, a single heat sink device facilitates heat dissipation from both of the adjacent memory modules.
-
-
-
-