CN113574510A - Data center management system and method for calculating density efficiency measurements - Google Patents
Data center management system and method for calculating density efficiency measurements Download PDFInfo
- Publication number
- CN113574510A CN113574510A CN201980093066.0A CN201980093066A CN113574510A CN 113574510 A CN113574510 A CN 113574510A CN 201980093066 A CN201980093066 A CN 201980093066A CN 113574510 A CN113574510 A CN 113574510A
- Authority
- CN
- China
- Prior art keywords
- data
- power
- facility
- computing
- data center
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000005259 measurement Methods 0.000 title description 2
- 238000001816 cooling Methods 0.000 claims abstract description 17
- 238000003860 storage Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 2
- 238000007726 management method Methods 0.000 description 37
- 238000004458 analytical method Methods 0.000 description 34
- 239000003570 air Substances 0.000 description 24
- 230000007613 environmental effect Effects 0.000 description 23
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 18
- 239000012080 ambient air Substances 0.000 description 14
- 238000012544 monitoring process Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 230000004075 alteration Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000002826 coolant Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
- H05K7/00—Constructional details common to different types of electric apparatus
- H05K7/20—Modifications to facilitate cooling, ventilating, or heating
- H05K7/20709—Modifications to facilitate cooling, ventilating, or heating for server racks or cabinets; for data centers, e.g. 19-inch computer racks
- H05K7/20836—Thermal management, e.g. server temperature control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/40—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using virtualisation of network functions or resources, e.g. SDN or NFV entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/20—Arrangements for monitoring or testing data switching networks the monitoring system or the monitored elements being virtualised, abstracted or software-defined entities, e.g. SDN or NFV
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Disclosed embodiments include Data Center Infrastructure Management (DCIM) systems and methods configured to collect computing system, power system, and facility system data, trigger one or more actions based on conditions diagnosed or predicted from the collected data, and thereby control the computing system, power system, and facility system of a data center through computing, power, and facility modules. According to an embodiment, control via the compute, power and facility modules includes calibrating the compute, power and facility systems based on the estimated compute demand and associated power, cooling and network data resource demands. The estimated computational demand includes estimating a computational density per real-time power wattage and a storage density per real-time power wattage.
Description
Technical Field
The present invention relates to infrastructure management systems, particularly with respect to, but not limited to, data centre facilities.
Background
Data centers and co-located providers struggle to supply the necessary power and cooling, among other things. As data center densities continue to increase, so too does the need for more energy efficient, cost effective data center and host hosting solutions.
A data center is a facility for housing computer systems and related components. To achieve this, data centers are designed to maintain environmental conditions suitable for the proper operation of the computer systems therein. Typically, to maintain the functionality of the systems therein, a data center will consume more than twice the power due to the inefficiency of the cooling system. The heat generated by the system is not proportional to the resources consumed in its operation. The amount of heat generated by the system is also difficult to track due to the unpredictability of real-time computing power consumption.
As data centers become more and more complex in structure and function, the utilization of energy by their systems, particularly for cooling and operation, has grown dramatically. Therefore, improving energy efficiency and reducing resource consumption of a data center becomes crucial for long-term maintenance of data center facilities.
Traditional data centers face challenges in technological innovation, operational efficiency, and modern design principles. With increasingly complex environments, such challenges in energy efficiency and resource utilization management become critical to the long-term maintenance of data center facilities. Current data center providers strive to monitor, collect and manage infrastructure systems to achieve optimal efficiency of the data center facility.
Traditional data centers are built using physical infrastructure that is static in nature. This constrained static infrastructure may expose serious infrastructure inefficiency problems when placed under dynamic workloads. These inefficiencies can only be addressed by continuously collecting and analyzing data center infrastructure and environmental data.
The DCIM system including predictive analysis may be employed to continuously collect and analyze infrastructure systems, components, and environmental data. DCIM systems that include predictive analysis can identify inefficiencies or previously unknown interdependencies. The continuous collection and analysis of infrastructure and environmental data enables automated management of infrastructure systems and components to maintain optimal infrastructure efficiency.
Prior art systems and methods have attempted to develop multi-index views that provide a broader understanding of data center cooling performance. These multi-index views attempt to take into account performance aspects by combining Power Usage Efficiency (PUE) ratios, IT thermal consistency, and IT thermal resiliency. However, a more detailed and multidimensional index is still needed to address the most critical aspects of data center cooling performance. The requirements to calculate cooling efficiency and future thermal state of the data center are also critical in order to build a more complete cooling view of the facility. There is still a need for a multi-dimensional index that is easy to scale and that can be adapted in the future to other new indices, as they are defined. The disclosed embodiments address this need.
Disclosure of Invention
A system of one or more computers may be configured to perform particular operations or actions by installing software, firmware, hardware, or a combination thereof on the system that in operation cause or result in the system performing the actions. The one or more computer programs may be configured to perform particular operations or actions by including instructions that, when executed by data processing apparatus, cause the apparatus to perform the actions. One general aspect includes a Data Center Infrastructure Management (DCIM) system configured to: collecting data centers including computing system, power system and facility system data over a network; diagnosing or predicting conditions to trigger operations based on collected data of the computing system, the power system, and the facility system; controlling a computing system, a power system, and a facility system of a data center through a computing, power, and facility module; wherein the controlling via the compute, power and facility modules includes calibrating the compute, power and facility systems based on the estimated compute demand and the associated power, cooling and network data resource demands; and wherein the estimated computational demand includes estimating a computational density per real-time power wattage and a storage density per real-time power wattage. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each configured to perform the actions of the methods.
One general aspect includes in a Data Center Infrastructure Management (DCIM) system including a processing unit coupled to a storage element and having instructions encoded thereon, a method comprising: collecting data centers including computing system, power system and facility system data over a network; triggering operations based on collected diagnostic or prognostic conditions of the computing, power, and facility systems; controlling a computing system, a power system, and a facility system of a data center through a computing, power, and facility module; wherein the controlling via the compute, power and facility modules includes calibrating the compute, power and facility systems based on the estimated compute demand and the associated power, cooling and network data resource demands; and wherein the estimated computational demand includes estimating a computational density per real-time power wattage and a storage density per real-time power wattage. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each configured to perform the actions of the methods.
A system for data center infrastructure management, comprising a processing unit coupled to a memory element and having instructions encoded thereon, wherein the encoded instructions cause the system to: collecting and storing data center infrastructure system condition data, environmental condition data, and component condition data; analyzing the collected infrastructure system, environment and component condition data; and automatically making zero or more adjustments to data center infrastructure system conditions, environmental conditions, and component conditions based on the collected and analyzed data.
In a system for data center infrastructure management, the system comprising a processing unit coupled to a storage element and having instructions encoded thereon, a method comprising: collecting and storing data center infrastructure system condition data, environmental condition data, and component condition data; analyzing the collected infrastructure system, environment and component condition data; and automatically making zero or more adjustments to data center infrastructure system conditions, environmental conditions, and component conditions based on the collected and analyzed data.
A system for data center infrastructure management, comprising a processing unit coupled to a memory element and having instructions encoded thereon, wherein the encoded instructions cause the system to: collecting and storing data center infrastructure system condition data, environmental condition data, and component condition data; analyzing the collected infrastructure system, environment and component condition data; and automatically adjusting the system condition, the environment condition and the component condition of the data center infrastructure for zero or more times according to the collected and analyzed data; wherein the zero or more adjustments are based on a predictive analytics function configured to continuously collect and analyze data, and wherein the predictive analytics function is further configured to implement a predictive analytics cloud computing network of single or multiple virtual machines, one or multiple instances, and to estimate demand for the virtual machines and cloud instances; and wherein the demand analysis comprises: estimating a baseline of virtual machine or cloud demand based on the collected real-time and historical demand data; estimating a baseline of virtual machine or cloud state from the collected real-time and historical demand data; predicting future states and demands based on a predictive model, the model further comprising collected real-time estimates; and dynamically implement one or more actions based on predictive modeling and analysis.
In a system for data center infrastructure management, the system comprising a processing unit coupled to a storage element and having instructions encoded thereon, a method comprising: collecting and storing data center infrastructure system condition data, environmental condition data, and component condition data; analyzing the collected infrastructure system, environment and component condition data; automatically adjusting the system condition, the environment condition and the component condition of the data center infrastructure for zero or more times according to the acquired and analyzed data; wherein the zero or more adjustments are based on a predictive analytics function configured to continuously collect and analyze data, and wherein the predictive analytics function is further configured to implement a predictive analytics cloud computing network of single or multiple virtual machines, one or multiple instances, and to estimate demand for the virtual machines and cloud instances; and wherein the demand analysis comprises: estimating a baseline of virtual machine or cloud demand based on the collected real-time and historical demand data; estimating a baseline of virtual machine or cloud state from the collected real-time and historical demand data; predicting future states and demands based on a predictive model, the model further comprising collected real-time estimates; and dynamically implement one or more actions based on predictive modeling and analysis.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
FIG. 1 illustrates an embodiment of a DCIM system.
FIG. 2 shows a block diagram depicting data collection and computational density efficiency calculations in a DCIM system.
Fig. 3 depicts a logical view of a DCIM system according to an embodiment.
FIG. 4 depicts a system and method for implementing a complete computation resource consumption estimate on each node of a connected data center network.
FIG. 5 illustrates another embodiment of a data center infrastructure-management (DCIM) element controller logical view.
FIG. 6 depicts a flow for managing infrastructure through an example flow diagram.
Fig. 7 depicts a logical view of a DCIM system according to an embodiment.
Detailed Description
The following is a detailed description of embodiments of the invention depicted in the accompanying drawings. The embodiments are described in such detail as to clearly communicate the invention. However, the embodiments presented herein are merely illustrative and are not intended to limit the anticipated variations of such embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the appended claims. The following detailed description is intended to make these embodiments obvious to one of ordinary skill in the art.
As noted above, traditional ways of monitoring data center infrastructure, collecting data from infrastructure systems, and managing systems to allow for maximizing operational efficiency are now struggling with new challenges presented by the increasing sophistication of data centers. The disclosed embodiments include systems and methods that effectively and efficiently address these challenges.
The disclosed embodiments include a Data Center Infrastructure Management (DCIM) system for continuously diagnosing and predicting the condition of computing, power, and facility systems to enable automatic estimation of computing demand and optimize the operation of the data center by managing the system using metrics that may allow the operator to further adapt to other performance considerations, if needed.
The disclosed embodiments are different from and superior to currently existing embodiments. The disclosed embodiments include methods and systems for data center infrastructure management and data center operations. According to one embodiment, a data center infrastructure management system includes an estimate of the computational requirements of a data center as described herein, and metrics that can further accommodate other performance metrics beyond the scope of existing systems.
The described Data Center Infrastructure Management (DCIM) system may be used to provide continuous monitoring and analysis of data to enable automated management of data center mechanical, electrical and cooling infrastructures to maintain optimal infrastructure efficiency.
The disclosed embodiments include new and improved methods and systems for infrastructure management and control, and more particularly for data center infrastructure management and control. According to one embodiment, a data center infrastructure management system (DCIM) system includes predictive analysis as described in this document, which is beyond the scope of existing systems. The ability to automate infrastructure management through collected data and predictive analytics provides significant advantages to currently existing embodiments.
Data center infrastructure is limited and static in nature. The inefficiencies of such constrained static designs quickly manifest when placed under dynamic loads. Management of data center infrastructure systems and components is a hit-and-go proposition if there is no continuous collection and analysis of infrastructure and environmental data. These limitations result in inefficient power consumption and prevent automated management of the data center infrastructure.
The described DCIM system including predictive analysis may be used to continuously collect and analyze infrastructure systems, components, and environmental data. DCIM systems that include predictive analysis can identify inefficiencies or previously unknown interdependencies. The continuous collection and analysis of infrastructure and environmental data enables automated management of infrastructure systems and components to maintain optimal infrastructure efficiency. Alternatively and additionally, embodiments of the invention may continuously monitor, collect, and analyze data to automate the management of virtual machine resources across a data center or multiple data centers, where monitoring, collection, analysis, and control may be performed on-site or in a centralized, remote manner.
FIG. 1 illustrates an embodiment of a Data Center Infrastructure Management (DCIM) system. The illustrated embodiment includes a processing unit 100 coupled to a memory element 104 and having instructions encoded thereon configured to: computing system data, power system data, and facility system data are collected from data centers 116A, 116B, and 116C over network 114. The disclosed embodiments are configured to trigger actions based on collected diagnostic or prognostic conditions of computing systems, power systems, and facility systems.
According to one embodiment, the configuration enables control of the computing systems, power systems, and facility systems in each of the illustrated data centers through the respective centralized computing module 108, power supply module 110, and facility module 112. Preferably, calibrating the computing, power and facility systems by the computing, power and facility modules includes calibrating the computing, power and facility systems based on the estimated computing demands and the associated power, cooling and network data resource demands. According to one embodiment, the estimated computational demand includes estimating a computational density per real-time power wattage and a storage density per real-time power wattage.
FIG. 2 shows a block diagram depicting data collection and computational density efficiency calculations in a DCIM system. The calculated data, power data and facility data are input to the DCIM system, which estimates the calculated density per real-time power wattage and the stored density per real-time power wattage, and outputs the results to the dashboard, network user interface and export. According to one embodiment, the export may be presented in virtual reality and displayed on a smart phone or other portable computing device.
According to one embodiment, the system is further configured to estimate future computing system conditions, future power system conditions, and future facility system conditions based on the collected data center computing system, power system, and facility system data as one of the derived types shown in FIG. 2.
Fig. 3 illustrates, by way of a flow chart, a method of adjusting different metrics to optimize system operation in view of performance metrics. Step 302 includes selecting a performance metric to consider. In step 304, relevant data is collected from the data center or predicted by the processor. In step 306, a decision is made based on the aggregated data in memory from the implemented machine learning to decide whether an adjustment or calibration is needed. Step 308 is performed in which adjustments are made to the system. In the metric-optimal step 306, the system continues to manually find or enter another performance metric and repeats step 304 until the data center operation is optimized.
FIG. 4 depicts a system and method for implementing a complete computation resource consumption estimate on each node of a connected data center network. The preferred embodiments implement a Total Resource Utilization Efficiency (TRUE) that optimizes not only the computational resource consumption, but also the overall efficiency of all components in the facility. According to this embodiment, the system is configured to: for each computing system resource 400, a cost per predetermined time unit for deploying and operating the computing system resource is determined, and a cost conversion factor is applied to each cost per predetermined time unit. In addition, for each computing resource, the system generates an average number of resource units by averaging the number of resource units 402 across multiple network infrastructure nodes. And for an application executing on at least one of the network infrastructure nodes 404, the system generates a plurality of resource units for use within a predetermined time period. Thus, the system may generate the total resource consumption 406 by adding the number of units consumed by the application for each computing resource over a predetermined period of time.
The disclosed embodiments further enable systems and methods that allow easy expansion and adaptation to additional new metrics in the future, as they are defined.
FIG. 5 illustrates an embodiment of a Data Center Infrastructure Management (DCIM) element controller logical view. The illustrated embodiment includes a DCIM element controller 500, a wireless temperature sensor 502, a wireless humidity sensor 504, an electrical system element 506, a mechanical system element, and a power element 512.
FIG. 6 depicts a flow for managing infrastructure through an example flow diagram. Step 602 includes measuring an air temperature. In step 604, a check is performed to assess whether the measured air temperature is within an acceptable range. If, in step 604, the air temperature is not within an acceptable range, then step 606 is performed in which the CRAC (computer room air conditioner), CDU (coolant distribution unit), or/and RDHX (rear door heat exchanger) are adjusted to raise or lower the air temperature as appropriate. If the air temperature is within the acceptable range, or after the air temperature is brought within the acceptable range, the next step 608 is performed in which the air flow is measured and in step 610 the measured air flow is evaluated to check if it is within the acceptable predefined range. Step 612 includes adjusting a VFD (variable frequency drive) fan to bring the airflow within an acceptable predetermined range. Note that the checks described above may be performed sequentially (as described above), or alternatively they may be performed simultaneously. Step 608 may include measuring the water flow and evaluating the measured water flow in step 610 to check if it is within a predetermined range.
Additionally, step 612 may include adjusting the VFD water pump or an automatic, adjustable flow control valve to bring the water flow within an acceptable predetermined range. It will be apparent to one of ordinary skill in the art that it is possible and in some cases desirable to check for changes in priority.
A system for data center infrastructure management, comprising a processing unit coupled to a memory element and having instructions encoded thereon, wherein the encoded instructions cause the system to collect and store data center infrastructure system condition data, environmental condition data, and component condition data; analyzing the collected infrastructure system, environment and component condition data; and automatically making zero or more adjustments to data center infrastructure system conditions, environmental conditions, and component conditions based on the collected and analyzed data. The analysis further includes predictive analysis configured to continuously collect and analyze data from the infrastructure system, the environment, and the one or more components. The collecting further includes collecting environmental data from the plurality of wireless sensors and collecting infrastructure system and component data from the infrastructure elements, wherein the infrastructure system and component data includes collecting air temperature data and air flow data. The analyzed data is further used by the system through a DCIM element controller, wherein the DCIM element controller includes means for configuring the operating state of the infrastructure system and components for optimal efficiency, and wherein configuring further includes determining whether the ambient air temperature is within a specified range based on the analysis. Configuration includes zero (if the ambient air temperature is within a defined range) or more (if the ambient air temperature is not within a defined range) adjustments to the CRAC, CDU, or/and RDHX to bring the ambient air temperature within a defined range. Additionally, the configuration includes measuring ambient air flow data and analyzing whether the measured air flow is within a defined range and adjusting the VFD fan or fans to bring the air flow within a defined range with zero (if the ambient air flow is within a defined range) or greater (if the ambient air flow is not within a defined range). Additionally, the configuration includes measuring the water flow data and analyzing whether the measured water flow is within an acceptable predetermined range, and making zero or more adjustments to the single or multiple VFD water pumps or automatically adjustable flow control valves to bring the water flow within a defined range. According to one embodiment, the system also allows the display of collected and analyzed data to a single or multiple users through presentation software modules. According to additional embodiments, the system is enabled to access the system over a secure network, and other systems may be accessed over the secure network.
According to one embodiment, the predictive analytics configured to continuously collect and analyze data is further configured to implement predictive analytics for a single or multiple virtual machines, one or more instances on a cloud computing network, and for the demand virtual machine and cloud instance, wherein the demand analytics comprise: estimating a baseline of virtual machine or cloud demand based on the collected real-time and historical demand data; estimating a baseline of virtual machine or cloud state from the collected real-time and historical demand data; predicting future states and demands based on a predictive model, the model further comprising collected real-time estimates; and dynamically implement one or more actions based on predictive modeling and analysis. Thus, in example embodiments, the disclosed predictive analytics are key features that enable not only monitoring of infrastructure (electrical/cooling/mechanical) but also enabling a monitoring system including virtual machines and entire cloud computing instances over a network. Predictive analysis of virtual machines and clouds allows the system to further exploit operational analysis. For example, based on real-time and historical data, a predictive analysis engine included in the system can predict when clouds will overflow due to demand and dynamically increase capacity.
Fig. 7 depicts a logical view of a DCIM system according to an embodiment. The illustrated embodiment includes a wireless sensor and infrastructure element 700, a DCIM element controller 702, data collection software 704, a predictive analytics engine or software 706, presentation software 708, a database 710, a presentation client 712, and a DCIM device or server 714.
A DCIM system including predictive analytics may include a plurality of DCIM devices or servers 714 that may be used to host presentation software 708, predictive analytics engine or software 706, data collection software 704, and DCIM element controller software 702. The data collection software 704 is configured to continuously collect environmental data from the plurality of wireless sensors 700 and infrastructure system and component data from the infrastructure elements 700. All collected data is stored in the database hardware 710. Predictive analysis engine or software 706 may be used to analyze the stored data. DCIM element controller 702 may be used to publish changes in operating state to infrastructure systems or components based on the collected and analyzed data.
In one example, the wireless sensor measures the Air temperature 602, analyzes the data to determine if the Air temperature is within a defined range 604, and if it is not within the defined range, the DCIM element controller may issue instructions to adjust CRAC (computer Room Air Conditioner), CDU, or/and RDHX to control the Air temperature within the defined range. The wireless sensor 700 may then measure the air flow/pressure 604, analyze the data to see if the air flow/pressure is within a defined range, and if not, the DCIM component controller 702 may issue commands to adjust the VFD (variable frequency drive) fan to bring the air flow/pressure within a defined range. The sensor may then measure the water flow rate using the analyzed data to determine if the water flow rate is within a predetermined range, and if not, the DCIM component controller may issue commands to adjust the VFD water pump or an automatic, adjustable flow control valve to achieve a water flow rate within a specified range. Note that the checks described above may be performed sequentially (as described above), or alternatively they may be performed simultaneously. It will be apparent to one of ordinary skill in the art that it is possible and in some cases desirable to check for changes in priority.
The described DCIM system including predictive analysis can continuously collect and analyze data from multiple infrastructure systems, components, and wireless sensors. Multiple wireless sensors may be employed to continuously collect environmental data.
The data collected by the DCIM system may be stored in a database. The stored data may then be analyzed by a predictive analysis engine. The DCIM element controller may use the analyzed data to manage the infrastructure system and component operating state to maintain optimal infrastructure efficiency.
In a preferred embodiment, predictive analytics configured for continuous collection and analysis of data and included in the DCIM are also configured for collection and analysis of data from a single or multiple virtual machines and one or more instances on the cloud computing network. Further, predictive analysis includes estimating demand for the virtual machines and cloud instances, wherein the estimating includes: estimating a baseline of virtual machine or cloud demand based on the collected real-time and historical demand data; estimating a baseline of virtual machine or cloud state from the collected real-time and historical demand data; predicting future states and demands based on a predictive model, the model further comprising collected real-time estimates; and dynamically implement one or more actions based on predictive modeling and analysis. DCIM element controller 702 may then be used to publish changes in operating state to the infrastructure system or component based on the collected and analyzed data.
The presentation software allows the end user to view all collected and analyzed data using the presentation client software. The DCIM system may be accessible and preferably configurable over a secure IP network (not shown). Additionally and alternatively, the DCIM system may remotely control infrastructure elements, systems, components, virtual machines, and cloud-based instances over a network.
In a system for data center infrastructure management, the system including a processing unit coupled to a storage element and having instructions encoded thereon, a method includes collecting and storing data center infrastructure system condition data, environmental condition data, and component condition data, analyzing the collected infrastructure system, environmental, and component condition data, and automatically making zero or more adjustments to data center infrastructure system conditions, environmental conditions, and component conditions based on the collected and analyzed data.
According to one embodiment, the analysis is included in a predictive analysis configured to continuously collect and analyze data from the infrastructure system, the environment, and the one or more components. Collecting further includes collecting environmental data from the plurality of wireless sensors and collecting infrastructure system and component data from the infrastructure elements, wherein the infrastructure system and component data includes collecting air temperature data and air flow data.
One embodiment includes employing the analyzed data via a DCIM element controller, wherein the DCIM element controller includes means for configuring the operating state of the infrastructure system and components for optimal efficiency.
Additionally, the configuring may include adjusting the CRAC, CDU, or/and RDHX to bring the ambient air temperature within a specified range based on analyzing whether the ambient air temperature is within a defined range and configuring to zero (if the ambient air temperature is within the defined range) or greater (if the ambient air temperature is not within the defined range). According to further embodiments, the configuring further comprises measuring ambient air flow data and analyzing whether the measured air flow is within a defined range and adjusting the VFD fan or fans to bring the air flow within a specified range with zero (if the ambient air flow is within the defined range) or greater (if the ambient air flow is not within the specified range). According to further embodiments, the configuration further includes measuring the water flow data and analyzing whether the measured water flow is within a defined range and making zero (if the water flow is within the defined range) or more (if the water flow is not within the defined range) adjustments to the single or multiple VFD water pumps or the automatic, adjustable flow control valve to make the water flow within the defined range.
In the method, the disclosed embodiments also include allowing, by the presentation software module, the display of collected and analyzed data to a single or multiple users, and allowing access and, preferably, configuration of the system over a secure network.
The disclosed embodiments include a DCIM system software suite, a DCIM device or server for installing and running the DCIM system software suite, system elements and wireless sensors for collecting data from electrical, mechanical and cooling infrastructure systems or/and components. The preferred embodiment also includes an intelligent predictive analytics engine to allow dynamic management of the infrastructure system or components.
Having described at least one embodiment of the present application, various alterations, modifications, and improvements will readily occur to those skilled in the art. Such alterations, modifications, and improvements are intended to be within the scope and spirit of the disclosure. Accordingly, the foregoing description is by way of example only and is not intended as limiting.
The preferred embodiment includes a DCIM system that includes all of the hardware, software, system elements, and wireless sensors described above. Ideally, the system is highly configurable, where the database and predictive analytics engine can be configured for a variety of scenarios that require analysis of the collected data. Further, the presentation client and presentation interface for presenting data to an end user may be configured according to various circumstances.
Embodiments of the described systems and methods may be employed by any field in which a system or component dynamically manages its operational state based on defined data ranges and defined control commands/instruction sets that may be executed to change.
Further variations of embodiments of the present invention enable continuous monitoring, collection and analysis of data to automate management of virtual machine resources across a data center or multiple data centers, either on-site or remotely, as will be apparent to those having ordinary skill.
Moreover, some or all embodiments of the disclosed invention may be used in alternative applications without departing from the scope and spirit of the present disclosure. For example, the DCIM system and predictive analytics may be used in an energy-efficient and cost-effective manner to manage electrical, mechanical, cooling, and other critical components in commercial or residential buildings, factories, supermarkets, stores, and other resource-consuming spaces (including, but not limited to, buildings or homes).
The disclosed embodiments provide for efficient on-site and remote monitoring of infrastructure systems, efficient and accurate collection of data from the infrastructure systems, and optionally automated management of these infrastructure systems to allow data center facilities and other such spaces to achieve optimal efficiencies.
The disclosed embodiments include dynamic, real-time management and control of infrastructure resources in data centers and other such facilities, thereby improving efficiency and reducing costs. The disclosed systems and methods provide continuous data collection, real-time data analysis, and accurate prediction for resource allocation through embodiments of predictive analysis engines, modules, and software.
Embodiments of the DCIM system including predictive analysis may be employed to continuously collect and analyze infrastructure system, component, and environmental data, identify inefficient or previously unknown interdependencies, and enable automated management of infrastructure systems and components to maintain optimal infrastructure efficiency.
Embodiments can increase the productivity of a data center and prevent standards from becoming obsolete for modern data center needs. Furthermore, the disclosed embodiments enable critical decisions to be made based on real-time evaluation rather than history-based guessing.
Since various possible embodiments may be made of the above invention, and since various changes may be made to the above embodiments, it is to be understood that all matters herein described or shown in the accompanying drawings are to be interpreted as illustrative and not in a limiting sense. Thus, those skilled in the art of infrastructure management, and in particular those related to data center automation infrastructure management, will understand that while preferred and alternative embodiments have been shown and described in accordance with the patent statutes, the invention is not limited thereto.
The figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. It should also be noted that, in some alternative implementations, the functions noted/illustrated may occur out of the order noted in the figures.
For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms a, an, and are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
In general, the routines executed to implement the embodiments of the invention, may be part of an operating system or a specific application, component, program, module, object, or sequence of instructions. The computer program of the present invention typically is comprised of a multitude of instructions that will be translated by the native computer into a machine-accessible format and hence executable instructions. Also, programs are comprised of variables and data structures that either reside locally to the program or are found in memory or on storage devices.
In addition, various programs described hereinafter may be identified based upon the application for which they are implemented in a specific embodiment of the invention. However, it should be appreciated that any particular program nomenclature that follows is used merely for convenience, and thus the invention should not be limited to use solely in any specific application identified and/or implied by such nomenclature.
The invention and some of its advantages have been described in detail for some embodiments. It should be understood that while the system and process are described with reference to automated power management and optimization of data centers, and automated infrastructure management of marine data centers, the system and process are highly reconfigurable and may be used in other contexts as well. It should also be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims. While an embodiment of the invention may achieve multiple objectives, not every embodiment falling within the scope of the attached claims will achieve every objective. Moreover, the scope of the present application is not intended to be limited to the particular embodiments of the process, machine, manufacture, composition of matter, means, methods and steps described in the specification. As one of ordinary skill in the art will readily appreciate from the disclosure of the present invention, processes, machines, manufacture, compositions of matter, means, methods, or steps, presently existing or later to be developed that are equivalent to and fall within the scope of the claimed invention. Accordingly, the appended claims are intended to include within their scope such processes, machines, manufacture, compositions of matter, means, methods, or steps.
Claims (11)
1. A Data Center Infrastructure Management (DCIM) system configured to:
collecting data centers including computing system, power system and facility system data over a network;
diagnosing or predicting conditions to trigger operations based on collected data of the computing system, the power system, and the facility system;
controlling a computing system, a power system, and a facility system of a data center through a computing, power, and facility module;
wherein the controlling via the compute, power and facility modules includes calibrating the compute, power and facility systems based on the estimated compute demand and the associated power, cooling and network data resource demands;
and wherein the estimated computational demand includes estimating a computational density per real-time power wattage and a storage density per real-time power wattage.
2. The system of claim 1, wherein the system is further configured to:
for each computing system resource, determining a cost per predetermined time unit to deploy and operate the computing system resource;
applying a cost conversion factor to each cost per predetermined time unit;
for each computing resource, generating an average number of resource units by averaging the number of resource units across a plurality of network infrastructure nodes;
generating a plurality of resource units for use within a predetermined time period for an application executing on at least one network infrastructure node;
the total resource consumption amount is generated by adding the number of units consumed by the application for each computing resource over a predetermined period of time.
3. The system of claim 1, wherein the system is further configured to:
analyzing and storing the collected operational data by a predictive analytics engine configured to communicate over a network;
and automatically adjusting the calculation conditions zero or more times based on the collected and analyzed operational data, and adjusting the calculation conditions, power supply conditions, and facility conditions.
4. The computer system of claim 1, wherein the system is further configured to:
estimating future computing system conditions, future power system conditions, and future facility system conditions based on the computing system, power system, and facility system data in the collected data center.
5. In a Data Center Infrastructure Management (DCIM) system comprising a processing unit coupled to a storage element and having instructions encoded thereon, a method comprising:
collecting data centers including computing system, power system and facility system data over a network;
triggering operations based on collected diagnostic or prognostic conditions of the computing, power, and facility systems;
controlling a computing system, a power system, and a facility system of a data center through a computing, power, and facility module;
wherein the controlling via the compute, power and facility modules includes calibrating the compute, power and facility systems based on the estimated compute demand and the associated power, cooling and network data resource demands;
and wherein the estimated computational demand includes estimating a computational density per real-time power wattage and a storage density per real-time power wattage.
6. The method of claim 5, further comprising:
for each computing system resource, determining a cost per predetermined time unit to deploy and operate the computing system resource;
applying a cost conversion factor to each cost per predetermined time unit;
for each computing resource, generating an average number of resource units by averaging the number of resource units across a plurality of network infrastructure nodes;
generating a plurality of resource units for use within a predetermined time period for an application executing on at least one network infrastructure node;
the total resource consumption amount is generated by adding the number of units consumed by the application for each computing resource over a predetermined period of time.
7. The method of claim 5, further comprising:
analyzing and storing the collected operational data by a predictive analytics engine configured to communicate over a network;
and automatically adjusting the calculation conditions zero or more times based on the collected and analyzed operational data, and based on adjustments to the calculation conditions, power conditions, and facility conditions.
8. The method of claim 5, further comprising:
based on the collected computing system, power system, and facility system data in the data center, future computing system conditions, future power system conditions, and future facility system conditions are estimated.
9. A Data Center Infrastructure Management (DCIM) system is configured to:
setting indexes which are vital to the operation of the data center infrastructure;
collecting accurate data from a data center over a network;
the trigger processor judges whether zero or multiple times of adjustment is needed according to the data stored in the memory;
and maximize the performance of the data center by tuning.
10. The processor of claim 9, wherein the metrics include different performance metrics including, but not limited to, a calculated density per real-time power wattage and a stored density per real-time power wattage; and allows the operator to adapt to new metrics that are scalable if necessary.
11. The data stored in the memory of claim 9, wherein the processor used as a criteria is collected through machine learning.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/US2019/019668 WO2020176080A1 (en) | 2019-02-26 | 2019-02-26 | Data center management systems and methods for compute density efficiency measurements |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113574510A true CN113574510A (en) | 2021-10-29 |
Family
ID=72239612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201980093066.0A Pending CN113574510A (en) | 2019-02-26 | 2019-02-26 | Data center management system and method for calculating density efficiency measurements |
Country Status (4)
| Country | Link |
|---|---|
| EP (1) | EP3942486A1 (en) |
| CN (1) | CN113574510A (en) |
| SG (1) | SG11202109334PA (en) |
| WO (1) | WO2020176080A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11262089B2 (en) | 2014-01-09 | 2022-03-01 | Nautilus True, Llc | Data center management systems and methods for compute density efficiency measurements |
| US12086001B2 (en) * | 2022-05-19 | 2024-09-10 | Honeywell International Inc. | System and method for proactively controlling an environmental condition in a server rack of a data center based at least in part on server load |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102460442A (en) * | 2009-05-18 | 2012-05-16 | 罗莫奈特有限公司 | Data centre simulator |
| CN102917031A (en) * | 2012-09-25 | 2013-02-06 | 浙江图讯科技有限公司 | Data computing system of safety production cloud service platform for industrial and mining enterprises |
| CN103329063A (en) * | 2010-10-04 | 2013-09-25 | 阿沃森特亨茨维尔公司 | System and method for monitoring and managing data center resources in real time |
| US20170219241A1 (en) * | 2014-01-09 | 2017-08-03 | Nautilus Data Technologies, Inc. | Data Center Infrastructure Management (DCIM) system comprising predictive analytics |
| CN108353034A (en) * | 2016-01-11 | 2018-07-31 | 环球互连及数据中心公司 | Framework for data center's infrastructure monitoring |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8346398B2 (en) * | 2008-08-08 | 2013-01-01 | Siemens Industry, Inc. | Data center thermal performance optimization using distributed cooling systems |
-
2019
- 2019-02-26 WO PCT/US2019/019668 patent/WO2020176080A1/en unknown
- 2019-02-26 EP EP19917364.2A patent/EP3942486A1/en not_active Withdrawn
- 2019-02-26 SG SG11202109334PA patent/SG11202109334PA/en unknown
- 2019-02-26 CN CN201980093066.0A patent/CN113574510A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102460442A (en) * | 2009-05-18 | 2012-05-16 | 罗莫奈特有限公司 | Data centre simulator |
| CN103329063A (en) * | 2010-10-04 | 2013-09-25 | 阿沃森特亨茨维尔公司 | System and method for monitoring and managing data center resources in real time |
| CN102917031A (en) * | 2012-09-25 | 2013-02-06 | 浙江图讯科技有限公司 | Data computing system of safety production cloud service platform for industrial and mining enterprises |
| US20170219241A1 (en) * | 2014-01-09 | 2017-08-03 | Nautilus Data Technologies, Inc. | Data Center Infrastructure Management (DCIM) system comprising predictive analytics |
| CN108353034A (en) * | 2016-01-11 | 2018-07-31 | 环球互连及数据中心公司 | Framework for data center's infrastructure monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| SG11202109334PA (en) | 2021-09-29 |
| EP3942486A1 (en) | 2022-01-26 |
| WO2020176080A1 (en) | 2020-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11906180B1 (en) | Data center management systems and methods for compute density efficiency measurements | |
| US20170219241A1 (en) | Data Center Infrastructure Management (DCIM) system comprising predictive analytics | |
| CN109800066B (en) | Energy-saving scheduling method and system for data center | |
| CN108595301B (en) | Server energy consumption prediction method and system based on machine learning | |
| US10852805B2 (en) | Data center total resource utilization efficiency (TRUE) system and method | |
| Li et al. | Thermocast: a cyber-physical forecasting model for datacenters | |
| CA2722946C (en) | Environmentally cognizant power management | |
| CN107923645B (en) | Air conditioning operation analysis device and non-transitory computer-readable recording medium having program recorded thereon | |
| US9310092B2 (en) | Analytics for optimizing usage of cooling subsystems | |
| US7716535B2 (en) | Kalman filtering for grid computing telemetry and workload management | |
| EP2604101A2 (en) | System and method for predicting transient cooling performance for data center | |
| CN107036238B (en) | Intelligent energy-saving control method for dynamically predicting external air and load | |
| WO2014101093A1 (en) | Power optimization for distributed computing system | |
| CN112070353B (en) | Method and system for accurately detecting energy efficiency of data center | |
| CN109088747A (en) | The management method and device of resource in cloud computing system | |
| US11847007B2 (en) | Data center total resource utilization efficiency (TRUE) system and method | |
| CN113574510A (en) | Data center management system and method for calculating density efficiency measurements | |
| CN110188932A (en) | Consumption of data center prediction technique based on evaluation optimization | |
| US20140088945A1 (en) | System and method for an energy management system | |
| KR20140119111A (en) | Computational fluid dynamics systems and methods of use thereof | |
| US10216606B1 (en) | Data center management systems and methods for compute density efficiency measurements | |
| KR20130065844A (en) | System and method for managing energy equipments efficiency in intelligent building | |
| CN117634217A (en) | Intelligent building management system and method based on digital twinning | |
| JP2017151617A (en) | Simulation device, simulation method, and program | |
| CN113225994A (en) | Intelligent air conditioner control method facing data center |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |