阅读说明：本技术 一种电力容量管理方法及装置 (Power capacity management method and device ) 是由 张宇 陈龙辉 刘谦 操奎 屈大伟 高文峰 于 2021-08-06 设计创作，主要内容包括：本发明提供一种电力容量管理方法及装置,包括获取预部署设备的设备信息；对设备信息进行处理,确定统计信息和用电画像信息；基于用电预测模型对统计信息、用电画像信息和设备基础信息进行处理,输出预部署设备的预测用电量,用电预测模型基于LSTM算法构建得到；在确定所述预测用电量不符合数据中心的设备用电标准时,输出电力风险预警。在本方案中,通过基于LSTM算法构建的用电预测模型,可以预测出待部署设备所需要的预测用电量,从而实现对待部署设备所需要电流进行预测,并在确定预测用电量不符合数据中心的设备用电标准时,输出电力风险预警。能够解决数据中心过度配置及性能风险的问题,从而可以显著提高数据中心的运营效率。(The invention provides a power capacity management method and a device, comprising the steps of obtaining equipment information of pre-deployment equipment; processing the equipment information, and determining statistical information and power utilization portrait information; processing the statistical information, the electricity utilization portrait information and the equipment basic information based on an electricity utilization prediction model, outputting the predicted electricity consumption of the pre-deployed equipment, and constructing the electricity utilization prediction model based on an LSTM algorithm; and outputting a power risk early warning when the predicted power consumption is determined not to meet the equipment power consumption standard of the data center. In the scheme, the electricity utilization prediction model constructed based on the LSTM algorithm can predict the predicted electricity consumption needed by the equipment to be deployed, so that the current needed by the equipment to be deployed is predicted, and the electricity risk early warning is output when the predicted electricity consumption is determined to be not in accordance with the equipment electricity utilization standard of the data center. The problems of excessive configuration and performance risk of the data center can be solved, and therefore the operation efficiency of the data center can be obviously improved.)

1. A power capacity management method, the method comprising:

acquiring equipment information of pre-deployment equipment;

processing the equipment information, and determining statistical information and power utilization portrait information;

the statistical information, the electricity utilization portrait information and the equipment basic information are used as input of an electricity utilization prediction model, the statistical information, the electricity utilization portrait information and the equipment basic information are processed based on the electricity utilization prediction model, predicted electricity consumption of the pre-deployed equipment is output, the electricity utilization prediction model is constructed based on an LSTM algorithm, and the equipment basic information is obtained based on a configuration management database CMDB;

determining whether the predicted power consumption meets the equipment power consumption standard of the data center or not based on the acquired power consumption data of the data center;

and outputting a power risk early warning when the predicted power consumption is determined not to meet the equipment power consumption standard of the data center.

2. The method of claim 1, wherein said processing said device information to determine statistical information and power usage profile information comprises:

counting the serial number of the equipment in the equipment information to obtain the statistical information;

classifying the pre-deployment equipment based on the equipment information to determine equipment information of each type;

determining the performance and power consumption corresponding to each type of equipment information;

and obtaining the power utilization portrait information based on the performance and power consumption corresponding to each type of equipment information.

3. The method of claim 1, wherein the process of constructing the electricity usage prediction model based on the LSTM algorithm comprises:

acquiring historical data, wherein the historical data comprises power utilization data of a data center;

extracting characteristic data in the historical data;

and determining an initial LSTM network model, training the LSTM network model based on the characteristic data, and determining that the LSTM network model obtained by current training is a power utilization prediction model.

4. The method of claim 3, further comprising:

after pre-deployment equipment is deployed for a preset time, acquiring current power utilization data of the pre-deployment equipment;

optimizing a power usage prediction model based on the current power usage data.

5. The method of claim 1, further comprising:

and when the predicted electricity consumption is determined to meet the equipment electricity utilization standard of the data center, generating an electricity utilization statistical report based on the electricity utilization data of the data center, and outputting the electricity utilization statistical report.

6. An apparatus for power capacity management, the apparatus comprising:

the acquisition module is used for acquiring the equipment information of the pre-deployment equipment;

the determining module is used for processing the equipment information and determining statistical information and power utilization portrait information;

the power utilization prediction model is used for taking the statistical information, the power utilization portrait information and the equipment basic information as input of the power utilization prediction model, processing the statistical information, the power utilization portrait information and the equipment basic information based on the power utilization prediction model, and outputting predicted power consumption of the pre-deployed equipment, wherein the power utilization prediction model is constructed based on an LSTM algorithm, and the equipment basic information is obtained based on a configuration management database CMDB;

the power utilization limiting and outputting module is used for determining whether the predicted power utilization amount meets the equipment power utilization standard of the data center based on the acquired power utilization data of the data center; and outputting a power risk early warning when the predicted power consumption is determined not to meet the equipment power consumption standard of the data center.

7. The apparatus of claim 6, wherein the determining module is specifically configured to: counting the serial number of the equipment in the equipment information to obtain the statistical information; classifying the pre-deployment equipment based on the equipment information to determine equipment information of each type; determining the performance and power consumption corresponding to each type of equipment information; and obtaining the power utilization portrait information based on the performance and power consumption corresponding to each type of equipment information.

8. The apparatus of claim 6, further comprising: building a module;

the building module is used for acquiring historical data, and the historical data comprises power utilization data of a data center; extracting characteristic data in the historical data; and determining an initial LSTM network model, training the LSTM network model based on the characteristic data, and determining that the LSTM network model obtained by current training is a power utilization prediction model.

9. The apparatus of claim 8, further comprising:

the system comprises a power data acquisition module, a data processing module and a data processing module, wherein the power data acquisition module is used for acquiring current power utilization data of pre-deployment equipment after the pre-deployment equipment is deployed to a machine room for preset time;

and the optimizing unit is used for optimizing the power utilization prediction model based on the current power utilization data.

10. The apparatus of claim 6, further comprising:

and the generating module is used for generating and outputting a power utilization statistical report based on the power utilization data of the data center when the predicted power utilization amount is determined to meet the equipment power utilization standard of the data center.

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a power capacity management method and apparatus.

Background

In order to ensure the power utilization performance problem of the data center caused by the unexpected power utilization requirement of the equipment to be deployed, enough spare capacity must be reserved before the equipment to be deployed is deployed.

At present, a headroom allocation method is often adopted to reduce the effective utilization rate of deployed infrastructure, so as to reserve sufficient spare capacity for the device to be deployed, so as to provide an unexpected power demand. Since the headroom allocation method actually reduces the effective utilization rate of the infrastructure and cannot completely reserve sufficient spare capacity for the device to be deployed, after the device to be deployed is deployed, the problems of excessive configuration of the data center and performance risk are caused.

Disclosure of Invention

In view of the above, embodiments of the present invention provide a power capacity management method and apparatus to solve the problems of data center over-configuration and performance risk occurring in the existing real-time system.

In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:

a first aspect of an embodiment of the present invention shows a power capacity management method, where the method includes:

acquiring equipment information of pre-deployment equipment;

processing the equipment information, and determining statistical information and power utilization portrait information;

the statistical information, the electricity utilization portrait information and the equipment basic information are used as input of an electricity utilization prediction model, the statistical information, the electricity utilization portrait information and the equipment basic information are processed based on the electricity utilization prediction model, predicted electricity consumption of the pre-deployed equipment is output, the electricity utilization prediction model is constructed based on an LSTM algorithm, and the equipment basic information is obtained based on a configuration management database CMDB;

determining whether the predicted power consumption meets the equipment power consumption standard of the data center or not based on the acquired power consumption data of the data center;

and outputting a power risk early warning when the predicted power consumption is determined not to meet the equipment power consumption standard of the data center.

Optionally, the processing the device information to determine statistical information and power consumption portrait information includes:

counting the serial number of the equipment in the equipment information to obtain the statistical information;

classifying the pre-deployment equipment based on the equipment information to determine equipment information of each type;

determining the performance and power consumption corresponding to each type of equipment information;

and obtaining the power utilization portrait information based on the performance and power consumption corresponding to each type of equipment information.

Optionally, the process of constructing the power consumption prediction model based on the LSTM algorithm includes:

acquiring historical data, wherein the historical data comprises power utilization data of a data center;

extracting characteristic data in the historical data;

and determining an initial LSTM network model, training the LSTM network model based on the characteristic data, and determining that the LSTM network model obtained by current training is a power utilization prediction model.

Optionally, the method further includes:

after pre-deployment equipment is deployed for a preset time, acquiring current power utilization data of the pre-deployment equipment;

optimizing a power usage prediction model based on the current power usage data.

Optionally, the method further includes:

and when the predicted electricity consumption is determined to meet the equipment electricity utilization standard of the data center, generating an electricity utilization statistical report based on the electricity utilization data of the data center, and outputting the electricity utilization statistical report.

A second aspect of an embodiment of the present invention shows a power capacity management apparatus, including:

the acquisition module is used for acquiring the equipment information of the pre-deployment equipment;

the determining module is used for processing the equipment information and determining statistical information and power utilization portrait information;

the power utilization prediction model is used for taking the statistical information, the power utilization portrait information and the equipment basic information as input of the power utilization prediction model, processing the statistical information, the power utilization portrait information and the equipment basic information based on the power utilization prediction model, and outputting predicted power consumption of the pre-deployed equipment, wherein the power utilization prediction model is constructed based on an LSTM algorithm, and the equipment basic information is obtained based on a configuration management database CMDB;

the power utilization limiting and outputting module is used for determining whether the predicted power utilization amount meets the equipment power utilization standard of the data center based on the acquired power utilization data of the data center; and outputting a power risk early warning when the predicted power consumption is determined not to meet the equipment power consumption standard of the data center.

Optionally, the determining module is specifically configured to: counting the serial number of the equipment in the equipment information to obtain the statistical information; classifying the pre-deployment equipment based on the equipment information to determine equipment information of each type; determining the performance and power consumption corresponding to each type of equipment information; and obtaining the power utilization portrait information based on the performance and power consumption corresponding to each type of equipment information.

Optionally, the method further includes: building a module;

the building module is used for acquiring historical data, and the historical data comprises power utilization data of a data center; extracting characteristic data in the historical data; and determining an initial LSTM network model, training the LSTM network model based on the characteristic data, and determining that the LSTM network model obtained by current training is a power utilization prediction model.

Optionally, the method further includes:

the system comprises a power data acquisition module, a data processing module and a data processing module, wherein the power data acquisition module is used for acquiring current power utilization data of pre-deployment equipment after the pre-deployment equipment is deployed to a machine room for preset time;

and the optimizing unit is used for optimizing the power utilization prediction model based on the current power utilization data.

Optionally, the method further includes:

and the generating module is used for generating and outputting a power utilization statistical report based on the power utilization data of the data center when the predicted power utilization amount is determined to meet the equipment power utilization standard of the data center.

Based on the above method and apparatus for managing power capacity provided by the embodiments of the present invention, the method includes: acquiring equipment information of pre-deployment equipment; processing the equipment information, and determining statistical information and power utilization portrait information; the statistical information, the electricity utilization portrait information and the equipment basic information are used as the input of an electricity utilization prediction model, the statistical information, the electricity utilization portrait information and the equipment basic information are processed based on the electricity utilization prediction model, the predicted electricity consumption of the pre-deployed equipment is output, and the electricity utilization prediction model is constructed based on an LSTM algorithm; determining whether the predicted power consumption meets the equipment power consumption standard of the data center or not based on the acquired power consumption data of the data center; and outputting a power risk early warning when the predicted power consumption is determined not to meet the equipment power consumption standard of the data center. In the embodiment of the invention, the predicted power consumption required by the equipment to be deployed can be predicted through the power consumption prediction model constructed based on the LSTM algorithm, so that the current required by the equipment to be deployed is predicted, and the power risk early warning is output when the predicted power consumption is determined to be not in accordance with the equipment power consumption standard of the data center. By means of the method, the problems of over-configuration and performance risks of the data center can be solved, and a strong basis can be provided for a manager to plan resources, so that the operation efficiency of the data center can be remarkably improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

FIG. 1 is a flow chart illustrating a power capacity management method according to an embodiment of the present invention;

FIG. 2 is a flow chart illustrating another power capacity management method according to an embodiment of the present invention;

FIG. 3 is a schematic structural diagram of an electric power capacity management apparatus according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of another power capacity management apparatus according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of another power capacity management apparatus according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of another power capacity management apparatus according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

In the embodiment of the invention, the data center usually adopts a cloud delivery mode and is planned according to the machine rooms, that is, after a large amount of equipment to be deployed arrives, delivery work can be carried out according to a pre-planned position, once the machine rooms are used, the equipment scale and power consumption reach higher levels instantly, and at the moment, each machine room basically has no large amount of free space, so that the adoption of a headroom distribution method is not enough to meet the deployment requirement of the equipment to be deployed. According to the method, the predicted power consumption required by the equipment to be deployed can be effectively predicted through the power consumption prediction model constructed based on the LSTM algorithm, so that the current required by the equipment to be deployed is predicted, and the power risk early warning is output when the predicted power consumption is determined to be not in accordance with the equipment power consumption standard of the data center. More timely and accurate data support can be provided for capacity management.

For convenience of understanding, terms appearing in the embodiments of the present invention are explained below:

the Configuration Management Database (CMDB) is used for storing and managing various Configuration information of devices in the enterprise IT architecture, is closely connected with all service support and service delivery processes, supports the operation of the processes, exerts the value of the Configuration information, and ensures the accuracy of data depending on the related processes.

Capacity management means that a T infrastructure-capacity management tool can generate reports related to infrastructure-capacity, can perform historical data analysis and capacity related analysis, and has the capability of IT and business scenario planning.

Grafana is a cross-platform open-source measurement analysis and visualization tool, and can query and then visually display collected data and notify the collected data in time.

And the substrate management controller BMC is used for recording event messages in the event logs of the machine room, the power distribution cabinet and the cabinet.

Referring to fig. 1, a flow chart of a power capacity management method according to an embodiment of the present invention is shown, where the method includes:

s101: and acquiring the equipment information of the pre-deployment equipment.

In the process of implementing step S101 specifically, the dynamic change of the pre-deployment device is detected by using the internet of things positioning system, so as to obtain the device information of the pre-deployment device.

The device information includes a device serial number, a device location, a device type, a change type, and the like.

Optionally, the method further includes: through the asset strips deployed on each device by the data center, the basic information of the device can be associated with the space, and the power utilization data of each device is updated to the Internet of things positioning system in real time.

S102: and processing the equipment information to determine statistical information and power utilization portrait information.

In the process of executing step S102 to process the device information and determine the statistical information and the electricity usage figure information, the method includes the following steps:

s11: and counting the equipment serial number in the equipment information to obtain the statistical information.

Specific contents of S11: and counting based on the equipment serial number in the equipment information to determine the number of the pre-deployed equipment and obtain the statistical information.

S12: and classifying the pre-deployment equipment based on the equipment information to determine the equipment information of each type.

In the process of implementing step S12 specifically, the pre-deployment devices are classified according to three levels of application scenarios, machine types, and configurations, and device information of each category is obtained.

It should be noted that the configuration refers to RAID level, hard disk type, and the number of hard disks of the pre-deployment device.

S13: and determining the performance and power consumption corresponding to each type of equipment information.

In the process of implementing step S13, the performance and power consumption of the pre-deployment devices under different categories are obtained from the visualization tool GRAFANA and the baseboard management controller BMC, respectively.

S14: and obtaining the power utilization portrait information based on the performance and power consumption corresponding to each type of equipment information.

In the process of implementing step S14, statistics are performed on the power consumption fluctuation condition, the load fluctuation condition, and the relationship between power consumption and load of each type of device information, so as to obtain the power consumption image information of the pre-deployed device, that is, the power consumption image at the device level.

S103: and taking the statistical information, the electricity utilization portrait information and the equipment basic information as the input of an electricity utilization prediction model, processing the statistical information, the electricity utilization portrait information and the equipment basic information based on the electricity utilization prediction model, and outputting the predicted electricity consumption of the pre-deployed equipment.

In S103, the power utilization prediction model is constructed based on the LSTM algorithm, and the device basic information is obtained based on the configuration management database CMDB.

It should be noted that the process of constructing the electricity consumption prediction model based on the LSTM algorithm includes the following steps:

s21: acquiring historical data, wherein the historical data comprises historical electricity utilization data of the machine room and the cabinet.

In the process of implementing step S21 specifically, index data of energy efficiency of the historical data center, that is, electricity consumption data of the historical machine room and the historical cabinet of the data center, is obtained.

S22: and extracting characteristic data in the historical data.

In the process of implementing step S22, different categories of feature data in the history data are extracted.

The different categories refer to types, scenes, configurations, and the like.

S23: and determining an initial LSTM network model, training the LSTM network model based on the characteristic data, and determining that the LSTM network model obtained by current training is a power utilization prediction model.

It should be noted that the Long Short-Term Memory network (LSTM) model is a time-cycle neural network.

In the process of implementing step S103 specifically, the device basic information of each category of existing running devices is obtained from the CMDB, that is, the device basic information such as application scenario, model, configuration, and the like of the device is obtained from the CMDB. And predicting the statistical information, the electricity utilization portrait information and the equipment basic information obtained in the step S102 by using the constructed electricity utilization prediction model to obtain the predicted electricity consumption of the pre-deployed equipment.

It should be noted that the device basic information includes device power consumption and performance data.

The amount of power may be indirectly manifested by power, i.e., power consumption.

Optionally, the method further includes: after the predicted power consumption of the pre-deployment equipment is determined, the predicted power consumption increment of the machine room, the power distribution cabinet and the cabinet can be further determined based on the predicted power consumption of the pre-deployment equipment.

S104: determining whether the predicted power consumption amount meets the equipment power consumption standard of the data center or not based on the acquired power consumption data of the data center, executing step S105 when determining that the predicted power consumption amount does not meet the equipment power consumption standard of the data center, and executing step S106 when determining that the predicted power consumption amount meets the equipment power consumption standard of the data center.

Specific contents of S104: the UPS output cabinet is used for acquiring power utilization data of the machine room, and then the power utilization data of the precise power distribution cabinet and the appointed cabinet are respectively acquired from the primary air starting point data and the secondary air starting point data of the precise power distribution cabinet. Calculating based on the electricity utilization data of the machine room, the electricity utilization data of the precise power distribution cabinet and the specified cabinet and the predicted electricity consumption, determining the electricity utilization conditions of different levels after the pre-deployment equipment is deployed, judging whether the electricity utilization conditions of all levels exceed the equipment electricity utilization standard of the data center, if so, indicating that the predicted electricity consumption does not conform to the equipment electricity utilization standard of the data center, namely, the pre-deployment equipment cannot be directly deployed, and executing step S105, otherwise, indicating that the predicted electricity consumption conforms to the equipment electricity utilization standard of the data center, namely, the electricity capacity can provide electricity for the pre-deployment equipment, and the pre-deployment equipment can be normally installed to the machine room, and executing step S106.

It should be noted that, the power utilization standard of the equipment in the data center is set according to the power utilization condition of the equipment, and the equipment can be implemented according to the actual condition, and the embodiment of the present invention is not limited.

Optionally, in the operation process of the data center, the power consumption condition of the data center can be monitored in real time, specifically: the method comprises the steps that power utilization data of a machine room are obtained through a UPS output cabinet, then the power utilization data of a precise power distribution cabinet and a designated machine cabinet are respectively obtained from primary empty test point data and secondary empty test point data of the precise power distribution cabinet, the power utilization data are divided into equipment data of each level, the equipment data of each level are respectively compared with corresponding threshold values, if the equipment data of each level are larger than the threshold values, power risk early warning is output, namely step S105 is executed, if the equipment data of each level are smaller than or equal to the threshold values, historical power monitoring data of each level are respectively subjected to statistical analysis, a historical power utilization statistical report is generated, namely step S106 is executed, and guidance is provided for resource planning configuration of a subsequent resource manager.

It should be noted that each level has a threshold, and the threshold corresponding to each level is calculated according to data of the level, such as rated power and power factor.

S105: and outputting electric power risk early warning.

In the process of implementing step S105 specifically, it is determined that the power capacity of the current data center is not enough to deploy the pre-deployment device, that is, it is determined that the pre-deployment device cannot be deployed directly, so as to generate a real-time early warning based on the power capacity risk, so that the operation and maintenance personnel can adjust the resource planning in time, that is, the resource administrator is alerted to adjust the resource deployment of the device hierarchy.

S106: and generating a power utilization statistical report based on the power utilization data of the data center, and outputting the power utilization statistical report.

In the process of implementing step S106, the power consumption data of the data center is divided into power consumption data of each level, and then the power consumption data of each level is subjected to statistical analysis to generate a historical power consumption statistical report, so that a resource administrator provides guidance for resource planning and configuration.

In the embodiment of the invention, the predicted power consumption required by the equipment to be deployed can be predicted through the power consumption prediction model constructed based on the LSTM algorithm, so that the current required by the equipment to be deployed is predicted, and the power risk early warning is output when the predicted power consumption is determined to be not in accordance with the equipment power consumption standard of the data center. By means of the method, the problems of over-configuration and performance risks of the data center can be solved, and a strong basis can be provided for a manager to plan resources, so that the operation efficiency of the data center can be remarkably improved.

Based on the power capacity management method shown in the above embodiment of the present invention, referring to fig. 2, another power capacity management method shown in the embodiment of the present invention is a method, including:

s201: and acquiring current power utilization data of the pre-deployment equipment after the pre-deployment equipment is deployed to a machine room for a preset time.

In the process of implementing step S201, in order to continuously improve the accuracy of the power utilization prediction model, the result of the power utilization prediction needs to be verified afterwards. After the pre-deployment equipment is deployed for the preset time, the monitoring system of the UPS output cabinet acquires the current power consumption of the machine room where the pre-deployment equipment is deployed, and the current power consumption of the precise power distribution cabinet and the current power consumption of the cabinet where the pre-deployment equipment is deployed can be respectively obtained from the data of the primary air switch point and the secondary air switch point of the precise power distribution cabinet.

The preset time is set by the technician according to actual conditions, and may be, for example, 1 week, one month, or half a year.

S202: optimizing a power usage prediction model based on the current power usage data.

In the process of specifically implementing the step S202, the power consumption prediction model is post-corrected according to the current power consumption of the machine room where the pre-deployment device is deployed and the current power consumption of the precise power distribution cabinet and the cabinet where the pre-deployment device is deployed, so that the estimation of the power consumption at the device level in the power consumption prediction model is more accurate and reliable.

Corresponding to the power capacity management method shown in the embodiment of the invention, the predicted power consumption can be corrected afterwards through power consumption real-time monitoring, and the equipment-level power consumption prediction using the power prediction model is more accurate, so that powerful support is provided for a resource manager to perform capacity planning.

Corresponding to the power capacity management method described in the above embodiment of the present invention, an embodiment of the present invention further correspondingly shows a power capacity management device, as shown in fig. 3, which is a schematic structural diagram of a power capacity management device shown in the embodiment of the present invention, and the device includes:

an obtaining module 301, configured to obtain device information of a pre-deployment device.

And the determining module 302 is configured to process the device information, and determine statistical information and power consumption portrait information.

Optionally, the determining module 302 is specifically configured to: counting the serial number of the equipment in the equipment information to obtain the statistical information; classifying the pre-deployment equipment based on the equipment information to determine equipment information of each type; determining the performance and power consumption corresponding to each type of equipment information; and obtaining the power utilization portrait information based on the performance and power consumption corresponding to each type of equipment information.

And the power utilization prediction model 303 is used for inputting the statistical information, the power utilization portrait information and the equipment basic information as a power utilization prediction model, processing the statistical information, the power utilization portrait information and the equipment basic information based on the power utilization prediction model, and outputting the predicted power consumption of the pre-deployed equipment, wherein the power utilization prediction model is constructed based on an LSTM algorithm, and the equipment basic information is obtained based on a configuration management database CMDB.

The power utilization limiting and outputting module 304 is configured to determine whether the predicted power utilization amount meets an equipment power utilization standard of the data center based on the acquired power utilization data of the data center; and outputting a power risk early warning when the predicted power consumption is determined not to meet the equipment power consumption standard of the data center.

It should be noted that, the specific principle and the implementation process of each unit in the power capacity management apparatus disclosed in the above embodiment of the present invention are the same as the power capacity management method shown in the above embodiment of the present invention, and reference may be made to corresponding parts in the power capacity management method disclosed in the above embodiment of the present invention, and details are not repeated here.

In the embodiment of the invention, the predicted power consumption required by the equipment to be deployed can be predicted through the power consumption prediction model constructed based on the LSTM algorithm, so that the current required by the equipment to be deployed is predicted, and the power risk early warning is output when the predicted power consumption is determined to be not in accordance with the equipment power consumption standard of the data center. By means of the method, the problems of over-configuration and performance risks of the data center can be solved, and a strong basis can be provided for a manager to plan resources, so that the operation efficiency of the data center can be remarkably improved.

Optionally, based on the power capacity management apparatus shown in the above embodiment of the present invention, referring to fig. 4 in combination with fig. 3, the power capacity management apparatus is further provided with a building module 305.

A construction module 305, configured to obtain historical data, where the historical data includes power consumption data of a data center; extracting characteristic data in the historical data; and determining an initial LSTM network model, training the LSTM network model based on the characteristic data, and determining that the LSTM network model obtained by current training is a power utilization prediction model.

In the embodiment of the invention, the electricity utilization prediction model constructed based on the LSTM algorithm and the historical data is used for predicting the predicted electricity consumption needed by the equipment to be deployed based on the constructed electricity utilization prediction model, so that the current needed by the equipment to be deployed is predicted, and the electric power risk early warning is output when the predicted electricity consumption is determined to be not in accordance with the equipment electricity utilization standard of the data center. By means of the method, the problems of over-configuration and performance risks of the data center can be solved, and a strong basis can be provided for a manager to plan resources, so that the operation efficiency of the data center can be remarkably improved.

Optionally, based on the power capacity management apparatus shown in the foregoing embodiment of the present invention, referring to fig. 5 in combination with fig. 4, the power capacity management apparatus further includes:

the power data acquisition module 306 is configured to acquire current power consumption data of the pre-deployment device after the pre-deployment device is deployed for a preset time.

And an optimizing unit 307 configured to optimize the power utilization prediction model based on the current power utilization data.

In the embodiment of the invention, the predicted power consumption can be corrected afterwards through real-time power consumption monitoring, and the equipment-level power consumption prediction using the power prediction model is more accurate, thereby providing powerful support for a resource manager to perform capacity planning.

Alternatively, the power capacity management apparatus shown based on the above-described embodiment of the present invention, with reference to fig. 5, refer to fig. 6.

And the generating module 308 is configured to generate and output a power consumption statistics report based on the power consumption data of the data center.

In the embodiment of the invention, the predicted power consumption required by the equipment to be deployed can be predicted through the power consumption prediction model constructed based on the LSTM algorithm, so that the current required by the equipment to be deployed is predicted, and the power risk early warning is output when the predicted power consumption is determined to be not in accordance with the equipment power consumption standard of the data center. And when the predicted electricity consumption is determined to meet the equipment electricity utilization standard of the data center, generating an electricity utilization statistical report based on the electricity utilization data of the data center, and outputting the electricity utilization statistical report. By means of the method, the problems of over-configuration and performance risks of the data center can be solved, and a strong basis can be provided for a manager to plan resources, so that the operation efficiency of the data center can be remarkably improved.

The embodiment of the invention also discloses an electronic device, which is used for operating the database storage process, wherein the power capacity management method disclosed in the figure 1 is executed when the database storage process is operated.

The embodiment of the invention also discloses a computer storage medium, which comprises a storage database storage process, wherein when the storage database storage process runs, the equipment where the storage medium is located is controlled to execute the power capacity management method disclosed in the figure 1.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.