Thermal control of data center

Abstract

A method includes measuring a plurality of temperatures corresponding to a plurality of servers located in a data center, determining a subset of the plurality of servers as high-temperature servers based on the plurality of temperatures, and reassigning tasks from at least a portion of the subset of the plurality of servers to one or more other servers of the plurality of servers.

What is claimed is: 
     
         1 . A method for operating a heating, ventilation, or air conditioning (HVAC) system in a data center, comprising:
 removing heat from air in the data center utilizing the HVAC system, the HVAC system comprising at least one of a central plant, an airside system, a waterside system, rack cooling equipment, a computer-room air conditioner, a rooftop unit, a floor cooling system, or a liquid cooling system;   detecting a hot spot within the data center, the hot spot being caused by operations of one or more servers in the data center; and   directly providing cooling to the hot spot in response to detecting the hot spot.   
     
     
         2 . The method of  claim 1 , further comprising:
 using space temperature data, server temperature data, and a model of performance for the HVAC system and the data center to predict changes to the HVAC system and the data center, the changes predicted to conserve energy while complying with temperature constraints for the data center and meeting a processing demand on the data center; and   electronically controlling the HVAC system and the data center in accordance with the changes for both the HVAC system and the data center.   
     
     
         3 . The method of  claim 2 , wherein the model of performance of the HVAC system and the data center models an operational efficiency of servers of the data center as a function of at least one of the space temperature data or the server temperature data. 
     
     
         4 . The method of  claim 1 , wherein the hot spot is detected using one or more thermal cameras in the data center. 
     
     
         5 . The method of  claim 1 , wherein more than one hot spot is detected and the cooling is provided to the more than one hot spot and the method uses artificial intelligence. 
     
     
         6 . The method of  claim 1 , further comprising:
 shifting operations performed by the one or more servers in the hot spot to other servers outside of the hot spot.   
     
     
         7 . The method of  claim 6 , wherein the other servers are in a cooler location of the data center. 
     
     
         8 . The method of  claim 1 , further comprising:
 providing load information for the data center to a user interface.   
     
     
         9 . A system comprising:
 servers located at a data center;   equipment configured to cool the servers, the equipment comprising at least one of a central plant, an airside system, a waterside system, rack cooling equipment, a computer-room air conditioner, a rooftop unit, a floor cooling system, or a liquid cooling system;   a controller configured to control the equipment based on estimates of an amount of thermal energy output by each of the servers and energy cost.   
     
     
         10 . The system of  claim 9 , wherein the controller is configured to apply the estimates of the amount of thermal energy output by the servers in a feedforward control approach to generate setpoints for the equipment or is configured to use artificial intelligence. 
     
     
         11 . The system of  claim 10 , wherein the estimates of the amount of thermal energy output by the servers comprise predictions of the amount of thermal energy output by the servers for a plurality of time steps; and
 wherein the controller is configured to generate the setpoints for the equipment for the plurality of time steps based on the predictions.   
     
     
         12 . The system of  claim 11 , wherein the controller is configured to generate the setpoints by performing an optimization process that minimizes an overall resource usage of the servers and the equipment over a time horizon. 
     
     
         13 . The system of  claim 9 , wherein the controller is configured to reschedule operations of the servers based on a time-variant cost of operating the equipment. 
     
     
         14 . The system of  claim 9 , wherein the servers comprise fans and the controller is configured to control the fans. 
     
     
         15 . The system of  claim 14 , wherein the controller is configured to coordinate control of the waterside system, the airside system, the rack-cooling system, and the fans. 
     
     
         16 . A method comprising:
 controlling operations of servers at a data center;   controlling building equipment to cool the servers;   determining a high-cost period for operating the building equipment and a low-cost period for operating the building equipment;   identifying a time-insensitive task scheduled to occur during the high-cost period; and   causing the time-insensitive task to be executed during the low-cost period.   
     
     
         17 . The method of  claim 16 , comprising:
 predicting a high-activity period for the servers; and   operating the building equipment to reduce a temperature at the servers before the high-activity period.   
     
     
         18 . The method of  claim 16 , comprising shifting the time-insensitive task from a first server to a second server based on a temperature differential between the first server and the second server. 
     
     
         19 . The method of  claim 16 , wherein determining the high-cost period comprises predicting weather-based loads on the building equipment. 
     
     
         20 . The method of  claim 16 , wherein determining the high-cost period and the low-cost period comprises determining utility rates over a time horizon and wherein the building equipment comprises at least one of a central plant, an airside system, a waterside system, rack cooling equipment, a computer-room air conditioner, a rooftop unit, a floor cooling system, or a liquid cooling system.