CN118132244A - Energy-saving regulation and control method, system, equipment and medium thereof for intelligent data center - Google Patents
Energy-saving regulation and control method, system, equipment and medium thereof for intelligent data center Download PDFInfo
- Publication number
- CN118132244A CN118132244A CN202410560860.4A CN202410560860A CN118132244A CN 118132244 A CN118132244 A CN 118132244A CN 202410560860 A CN202410560860 A CN 202410560860A CN 118132244 A CN118132244 A CN 118132244A
- Authority
- CN
- China
- Prior art keywords
- energy
- energy consumption
- monitoring
- historical
- 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
- 230000033228 biological regulation Effects 0.000 title claims abstract description 195
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000005265 energy consumption Methods 0.000 claims abstract description 235
- 238000012806 monitoring device Methods 0.000 claims abstract description 182
- 238000012544 monitoring process Methods 0.000 claims abstract description 120
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000011217 control strategy Methods 0.000 claims abstract description 27
- 238000005057 refrigeration Methods 0.000 claims description 33
- 238000012546 transfer Methods 0.000 claims description 27
- 230000008569 process Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 14
- 238000013508 migration Methods 0.000 claims description 14
- 230000005012 migration Effects 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 11
- 238000007405 data analysis Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004134 energy conservation Methods 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 3
- 238000010438 heat treatment Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 11
- 230000008859 change Effects 0.000 description 8
- 230000001105 regulatory effect Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 239000002699 waste material Substances 0.000 description 5
- 238000002790 cross-validation Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000001816 cooling Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000009529 body temperature measurement Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application discloses an intelligent data center energy-saving regulation and control method, a system, equipment and a medium thereof, wherein the method comprises the steps of identifying and acquiring historical energy consumption interval data of a plurality of monitoring equipment of a data center to obtain working operation mode information of working operation phase intervals comprising a plurality of different power supply use efficiencies; training and optimizing the power supply use efficiency in a preset initial energy-saving regulation model to obtain an optimized energy-saving regulation model; according to a historical monitoring data set of the data center, determining the associated energy consumption factors among all monitoring devices to obtain energy consumption factor association coefficients; in the optimized energy-saving regulation model, determining the minimum value of the power supply use efficiency of each monitoring device in each working operation stage interval, and generating an optimal energy-saving regulation strategy; performing energy-saving regulation and control according to an optimal energy-saving regulation and control strategy; the intelligent energy-saving control method has the advantages that the intelligent energy-saving control effect of the data center is improved, and a reasonable energy-saving strategy is formulated to adapt to the load characteristics of different data centers.
Description
Technical Field
The application relates to the technical field of energy conservation of data centers, in particular to an energy conservation regulation and control method, system, equipment and medium thereof for an intelligent data center.
Background
With the rapid development of information technology and the wide application of cloud computing, data centers have become an indispensable infrastructure of modern society; however, the problem of high energy consumption of the data center is increasingly highlighted, so that the development of energy-saving optimization regulation technology of the data center is also attracting attention.
In the related art, the traditional energy-saving method is mainly focused on optimization and energy efficiency improvement of hardware equipment, such as a more efficient heat dissipation system, a low-power-consumption server, a storage device and the like, and the energy-saving method reduces the energy consumption of a data center to a certain extent, but has various limitations, such as high transformation cost and quick equipment elimination caused by quick technology update; based on this, there are currently energy-saving control methods that employ judgment and control based on monitoring sensor data of a data center, such as: when the temperature sensor of the data center detects that the temperature exceeds or falls below a set threshold, the energy-saving control system can trigger a corresponding control command, such as turning on or off the air conditioning equipment.
However, the energy-saving method for controlling based on the monitoring data of the data center still faces some challenges in practical applications, for example: how to formulate a reasonable energy-saving strategy to adapt to the load characteristics of different data centers, so that the defect of poor intelligent energy-saving regulation and control effects of the data centers exists, and there is room for improvement.
Disclosure of Invention
In order to improve the intelligent energy-saving regulation and control effect of the data center, a reasonable energy-saving strategy is formulated to adapt to the load characteristics of different data centers, and the application provides an intelligent data center energy-saving regulation and control method, system, equipment and medium thereof.
In a first aspect, the object of the application is achieved by the following technical scheme:
an intelligent data center energy-saving regulation and control method comprises the following steps:
According to a historical monitoring data set of the data center, identifying and acquiring historical energy consumption interval data of a plurality of monitoring devices of the data center in the operation process, and correspondingly obtaining working operation mode information of the plurality of monitoring devices; the working operation mode information comprises a plurality of working operation stage intervals corresponding to different power supply use efficiencies; the monitoring equipment associates equipment identification;
Acquiring a historical regulation and control data set of each monitoring device based on the device identifier, and performing training optimization based on the power supply use efficiency in a preset initial energy-saving regulation and control model to obtain an optimized energy-saving regulation and control model;
according to a historical monitoring data set of the data center, calculating and determining the associated energy consumption factors among all monitoring devices to obtain the energy consumption factor association coefficients of all the monitoring devices;
In the optimized energy-saving regulation model, determining the minimum value of the power supply use efficiency of each monitoring device in each working operation stage interval according to the energy consumption factor association coefficients of all the monitoring devices and the energy-saving parameter regulation strategies corresponding to the historical regulation data set, and generating an optimal energy-saving regulation strategy;
And carrying out energy-saving regulation and control on the energy consumption of each monitoring device of the data center according to the optimal energy-saving regulation and control strategy.
By adopting the technical scheme, the monitoring equipment is facility equipment of the data center; the monitoring data of the monitoring equipment comprise load data, temperature data and equipment energy consumption data; in the running process of the monitoring equipment, the energy consumption data is changed due to the difference of the temperature, the monitoring equipment and the running program quantity of the current load, so that the energy-saving regulation strategy of each monitoring equipment is optimally generated based on the data of the historical energy consumption interval data of different time intervals as an optimization reference of energy-saving regulation; the historical energy consumption interval data is total energy consumption data of each monitoring device in the historical operation process; different working operation phases are based on different electric energy utilization rates (namely power supply use efficiency) of the monitoring equipment, and can be divided into a high-energy consumption working operation phase, a medium-energy consumption working operation phase and a low-energy consumption working operation phase of the monitoring equipment, so that the power supply use efficiency of each monitoring equipment of the data center in different operation energy consumption states is further finely regulated and controlled, and each monitoring equipment is regulated to a corresponding high-power consumption mode or low-power consumption mode under different electric energy requirements, so that fine regulation and control of each monitoring equipment are facilitated.
Specifically, using a historical regulation data set recorded by a data center, training the power supply use efficiency (also called as PUE value) of an initial energy-saving regulation model used in a historical manner to obtain an optimized energy-saving regulation model; meanwhile, the historical monitoring dataset of the historical operation of the data center is used for obtaining the association relation of energy consumption factors among a plurality of monitoring devices in the data center, so that the combined energy-saving regulation and control of all the monitoring devices, such as loads, of the data center is facilitated, the overall energy consumption of the data center is reduced, a more reasonable energy-saving regulation and control strategy is conveniently formulated according to different load characteristics of different data centers, and the applicability of the intelligent energy-saving regulation and control strategy is higher; in the optimized energy-saving regulation model, the minimum value of the power supply use efficiency of each monitoring device in each working operation stage interval is required to be determined so as to generate an optimal energy-saving regulation strategy; then carrying out fine energy-saving control on each monitoring device of the data center according to the optimal energy-saving control strategy so as to realize providing optimal parameter control of each working operation stage interval of each monitoring device, namely formulating a reasonable energy-saving strategy to adapt to the load characteristics of different data centers; the whole energy consumption of the data center is effectively reduced, and the intelligent energy-saving regulation and control effect and the regulation and control quality of the data center are improved.
The present application is in a preferred example: the method specifically comprises the steps of identifying and acquiring historical energy consumption interval data of a plurality of monitoring devices of a data center in the operation process according to a historical monitoring data set of the data center, and correspondingly obtaining working operation mode information of the plurality of monitoring devices, wherein the working operation mode information comprises the following specific steps:
Acquiring historical task execution information and corresponding historical energy consumption data monitored by each monitoring device in a historical monitoring time period according to a historical monitoring data set of a data center;
creating a plurality of historical monitoring time intervals according to historical task execution information of each monitoring device and corresponding power consumption data;
Dividing the historical task execution information of each monitoring device and corresponding historical energy consumption data based on the device identification according to a plurality of historical monitoring time intervals, and correspondingly obtaining a plurality of historical energy consumption interval data of each monitoring device in the operation process;
And correspondingly determining and obtaining different working operation mode information of the plurality of monitoring devices according to the historical energy consumption data in the plurality of historical energy consumption interval data and preset operation mode judging conditions.
By adopting the technical scheme, in the preset historical monitoring time period, the historical task execution information (such as the task execution number and the load rate of the server) and the corresponding historical energy consumption data of each monitoring device are divided to obtain a plurality of historical energy consumption interval data, the energy consumption data of two adjacent historical energy consumption intervals are located in the energy consumption intervals with different degrees, so that the change condition of the operation mode of the monitoring device in the historical energy consumption interval data is conveniently distinguished, the change condition of the energy consumption data of the plurality of monitoring devices in the corresponding historical monitoring market is judged based on the operation mode judging condition and the value of the historical energy consumption data, and the operation mode of the monitoring device is judged to be in a high-energy consumption operation stage, a medium-energy consumption operation stage or a low-energy consumption operation stage according to the historical energy consumption interval data of the monitoring device.
The present application is in a preferred example: the associated energy consumption factors comprise IT equipment energy consumption factors, power supply and distribution loss factors, refrigeration system energy consumption factors and other energy consumption factors; according to the historical monitoring data set of the data center, calculating and determining the associated energy consumption factors among all monitoring devices to obtain the energy consumption factor associated coefficients of all the monitoring devices, wherein the method comprises the following steps:
According to the historical monitoring data set of the data center, historical power supply use efficiency limit values and corresponding electric energy loss data of all monitoring equipment are obtained;
Calculating and determining the performance coefficient value of the associated energy consumption factor of each detection device according to the connection between each detection device and the corresponding electric energy consumption data;
and determining and obtaining the energy consumption factor association coefficients of all monitoring devices based on the historical power supply use efficiency limit value of each monitoring device and the corresponding performance coefficient value of the associated energy consumption factors.
By adopting the technical scheme, in order to analyze the actual energy consumption composition of different data centers and the actual load characteristics of the data centers, the application carries out the verification calculation of the actual energy consumption value based on the corresponding relevant energy consumption factors in the historical monitoring data set of the data centers, and because the energy consumption of the monitoring equipment of the data centers can be influenced by the installation structure and the different load characteristics of the different monitoring equipment of the data centers, the power consumption of the power supply system of the data centers can also exist in the long-time operation process, the application determines the historical power supply use efficiency limit value (namely the PUE limit value and the numerical value size of the PUE limit value are limited in each working operation stage interval through the optimal energy-saving regulation strategy being executed by the monitoring equipment based on the historical monitoring data set monitored by the data centers in actual operation.
Since different historical power usage efficiency limits affect the coefficient of performance (i.e., COP) of the cooling system of the data center, then determining the coefficient of performance value of each monitoring device based on the connection relationship between each monitoring device, corresponding power consumption data, wherein the power consumption data includes power device consumption data and cable consumption data; and then, according to the historical power supply use efficiency limit value of each monitoring device and the performance coefficient value of the corresponding associated energy consumption factor, calculating and determining the corresponding energy consumption factor associated coefficient, so that the purpose of analyzing the actual energy consumption information of each detection device of the data center from the energy consumption associated relation among a plurality of devices and the associated energy consumption factors of a plurality of energy consumption influence factors is realized, a parameter value with higher detail and accuracy is provided for the follow-up execution of the energy saving regulation strategy, and the data support function is provided for the staff when the regulation operation of the energy saving regulation strategy is carried out.
The present application is in a preferred example: the monitoring equipment comprises a refrigeration system and IT equipment; the method further comprises the steps of:
Constraint calculation is carried out on the associated energy consumption factors of the monitoring equipment based on the formula (1):
wherein/> Historical power usage efficiency value for monitoring device identified as i for device,/>Is the total power consumption of the data center,/>Power consumption for all IT devices; /(I)Is the power supply and distribution loss factor, which is the ratio of the power supply and distribution loss to the energy consumption of IT equipment, and is/The heating value of the monitoring equipment with the equipment mark i accounts for the specific gravity of the load of the refrigeration system; /(I)The energy consumption ratio of the refrigeration system to the energy consumption of IT equipment; /(I)The energy consumption of the monitoring device identified as i for the device accounts for the ratio of the whole refrigeration system; /(I)For the refrigeration performance coefficient of the whole refrigeration system,/>The refrigeration energy consumption of the monitoring equipment with the equipment identifier i accounts for the ratio of the refrigeration energy consumption of the whole refrigeration system; /(I)The ratio of other energy consumption to IT equipment energy consumption; a is a constant coefficient, and the value range is 2% to 5%.
By adopting the technical scheme, the power supply using efficiency based on each monitoring deviceThe energy consumption coefficient of the IT equipment, the energy consumption coefficient of the refrigerating system and other energy consumption coefficient are calculated, and the energy consumption association relation of each energy consumption factor association coefficient of the data center is analyzed and evaluated according to the power supply and distribution loss factor (PLF) of the power distribution system in different data centers, the load Characteristic (CLF) of the IT equipment, the performance coefficient (COP value) of monitoring equipment in the refrigerating system and other energy consumption coefficients.
The present application is in a preferred example: the method further comprises the steps of: the optimal energy-saving regulation strategy comprises a server task migration strategy of IT equipment; the monitoring device comprises a server; the working operation mode information comprises a high-load operation mode, a low-load operation mode and an idle server mode; the high-load operation mode meets the condition that a server load value of the IT equipment is larger than a preset high-load threshold value, and the low-load operation mode meets the condition that the server load value of the IT equipment is smaller than the preset low-load threshold value;
The server task migration strategy satisfies that a server of a corresponding monitoring device in which all working operation modes of a plurality of continuous working operation phase intervals are in an idle server mode is dormant; the total duration of the continuous multiple working operation phase intervals exceeds the preset first timeout time;
The server task migration strategy is used for respectively calculating the task transfer priority and the task transfer priority of each corresponding server according to the server load value of each IT device in the high-load operation mode and the low-load operation mode in the off-peak period, and determining a transfer-out server for executing the transfer-out of the task and a transfer-in server for executing the transfer-in of the task.
By adopting the technical scheme, the server of the monitoring equipment is divided into a high-load operation mode, a low-load operation mode and an idle server mode due to actual task execution conditions and load conditions; in order to improve the electric energy utilization rate of the data center, the intelligent energy-saving regulation and control effect of the data center is further improved on the basis of meeting the electric energy supply requirement and the energy supply requirement of a server of the data center; according to the method, the servers of the corresponding monitoring devices in which the working operation modes of the continuous multiple working operation stage intervals are in the idle server mode are dormant, the task transfer priority and the task transfer priority of each IT device in the high-load operation mode and the low-load operation mode are calculated, and task transfer operation is carried out on the servers of the IT devices after the task transfer priority coefficient and/or the task transfer priority coefficient of each IT device are calculated, so that the situation that the low delay of task delay execution occurs on the servers in the high-load operation mode or the waste of energy is caused by too little task operation quantity of the servers in the low-load operation mode in the same working operation stage interval is effectively avoided, the energy utilization efficiency of the servers of the IT devices is improved, the task execution of the servers can be reasonably arranged, and the energy efficient utilization of the energy of the data center and the servers can be ensured.
The present application is in a preferred example: the said server task migration policy satisfies that in the off-peak period, according to the server load value of each IT device in the high load operation mode and the low load operation mode, the task transfer priority and the task transfer priority are calculated for each corresponding server, and the transfer server executing the task transfer are determined, including:
task transfer priority coefficients of servers of the IT devices are calculated correspondingly according to the formula (2) and the formula (3) And task switch priority coefficient/>：
Wherein/>A measured temperature value for an IT device identified as i for the device; /(I)Is a preset low load threshold,/>The load factor of the server of the IT equipment with the equipment identification of i is given, and N is the CPU core number of the server of each IT equipment; /(I)Is a preset high load threshold; /(I)Is a preset medium load threshold.
By adopting the technical scheme, the historical monitoring data set of the data center also comprises temperature measurement data of IT equipment; when the data center actually operates, real-time measurement temperature values of all monitoring devices of the measurement data center are also acquired; executing a server task migration strategy on each monitoring device of the data center based on the monitoring device (i.e., the IT device) measuring temperature and load conditions in real time and CPU core numbers of servers of each IT device; specifically, in the off-peak period of the data center, tasks in the server with lower load coefficient, low CPU core number and higher temperature of the server are preferentially transferred out, and the refrigeration energy consumption of the refrigeration system is reduced at intervals; and meanwhile, the task is preferentially shifted to a server with lower temperature, or when the temperatures of a plurality of shifting-in devices are the same, the task is preferentially shifted to a high CPU core number, so that the heat productivity of the server of the IT device can be effectively controlled, the high performance and the high reliability of the IT device are maintained, the overall power consumption of the IT device is reduced, and the electric energy is saved.
In a second aspect, the object of the present application is achieved by the following technical solutions:
An intelligent data center energy-saving regulation and control system for executing the intelligent data center energy-saving regulation and control method as described above, the system comprising:
the historical monitoring data analysis module is used for acquiring a historical regulation and control data set of each monitoring device based on the device identification, and training and optimizing based on the power supply use efficiency in a preset initial energy-saving regulation and control model to obtain an optimized energy-saving regulation and control model;
the power supply use efficiency training module is used for acquiring a historical regulation and control data set of each monitoring device based on the device identification, and training and optimizing based on the power supply use efficiency in a preset initial energy-saving regulation and control model to obtain an optimized energy-saving regulation and control model;
the associated energy consumption factor determining module is used for calculating and determining associated energy consumption factors among all monitoring devices according to a historical monitoring data set of the data center to obtain energy consumption factor association coefficients of all the monitoring devices;
The optimal regulation strategy generation module is used for determining the minimum power supply use efficiency value of each monitoring device in each working operation stage interval according to the energy consumption factor association coefficients of all the monitoring devices and the energy saving parameter adjustment strategies corresponding to the historical regulation data sets in the optimal energy saving regulation model, and generating an optimal energy saving regulation strategy;
And the optimal regulation and control strategy execution module is used for carrying out energy-saving regulation and control on the energy consumption of each monitoring device of the data center according to the optimal energy-saving regulation and control strategy.
By adopting the technical scheme, the power supply use efficiency of each monitoring device of the data center under different operation energy consumption states is further finely regulated, so that each monitoring device is regulated to a corresponding high-power consumption mode or low-power consumption mode under different electric energy requirements, and fine regulation and control of each monitoring device are facilitated.
Training the power supply use efficiency (also called PUE value) of the initial energy-saving regulation model for historical use by utilizing a historical regulation data set recorded by a data center to obtain an optimized energy-saving regulation model; meanwhile, the historical monitoring dataset of the historical operation of the data center is used for obtaining the association relation of energy consumption factors among a plurality of monitoring devices in the data center, so that the combined energy-saving regulation and control of all the monitoring devices, such as loads, of the data center is facilitated, the overall energy consumption of the data center is reduced, a more reasonable energy-saving regulation and control strategy is conveniently formulated according to different load characteristics of different data centers, and the applicability of the intelligent energy-saving regulation and control strategy is higher; in the optimized energy-saving regulation model, the minimum value of the power supply use efficiency of each monitoring device in each working operation stage interval is required to be determined so as to generate an optimal energy-saving regulation strategy; then carrying out fine energy-saving control on each monitoring device of the data center according to the optimal energy-saving control strategy so as to realize providing optimal parameter control of each working operation stage interval of each monitoring device, namely formulating a reasonable energy-saving strategy to adapt to the load characteristics of different data centers; the whole energy consumption of the data center is effectively reduced, and the intelligent energy-saving regulation and control effect and the regulation and control quality of the data center are improved.
In a third aspect, the object of the present application is achieved by the following technical solutions:
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of an intelligent data center energy saving regulation method as described above when executing the computer program.
In a fourth aspect, the object of the present application is achieved by the following technical solutions:
A computer readable storage medium storing a computer program which when executed by a processor implements the steps of an intelligent data center energy saving regulation method described above.
In summary, the present application includes at least one of the following beneficial technical effects:
1. In order to further finely regulate the power supply use efficiency of each monitoring device of the data center in different operation energy consumption states, each monitoring device is regulated to a corresponding high-power consumption mode or low-power consumption mode under different electric energy requirements, so that each monitoring device is finely regulated; specifically, using a historical regulation data set recorded by a data center, training the power supply use efficiency (also called as PUE value) of an initial energy-saving regulation model used in a historical manner to obtain an optimized energy-saving regulation model; meanwhile, the historical monitoring dataset of the historical operation of the data center is used for obtaining the association relation of energy consumption factors among a plurality of monitoring devices in the data center, so that the combined energy-saving regulation and control of all the monitoring devices, such as loads, of the data center is facilitated, the overall energy consumption of the data center is reduced, a more reasonable energy-saving regulation and control strategy is conveniently formulated according to different load characteristics of different data centers, and the applicability of the intelligent energy-saving regulation and control strategy is higher; in the optimized energy-saving regulation model, the minimum value of the power supply use efficiency of each monitoring device in each working operation stage interval is required to be determined so as to generate an optimal energy-saving regulation strategy; then carrying out fine energy-saving control on each monitoring device of the data center according to the optimal energy-saving control strategy so as to realize providing optimal parameter control of each working operation stage interval of each monitoring device, namely formulating a reasonable energy-saving strategy to adapt to the load characteristics of different data centers; the whole energy consumption of the data center is effectively reduced, and the intelligent energy-saving regulation and control effect and the regulation and control quality of the data center are improved;
2. In a preset historical monitoring duration, historical task execution information (such as task execution quantity and load rate of a server) and corresponding historical energy consumption data of each monitoring device are divided to obtain a plurality of historical energy consumption interval data, the data energy consumption of two adjacent historical energy consumption intervals are located in different degrees of energy consumption intervals, so that the change condition of a working operation mode of the monitoring device in the historical energy consumption interval data is conveniently distinguished, the change condition of the energy consumption data of the plurality of monitoring devices in the corresponding historical monitoring market is judged based on an operation mode judging condition and a value of the historical energy consumption data, if the working operation mode of the monitoring device is judged to be in a high-energy consumption working operation stage, a medium-energy consumption working operation stage or a low-energy consumption working operation stage according to the historical energy consumption interval data of the monitoring device, the change analysis of the historical monitoring data of each monitoring device is effectively completed, the resource waste of regulation and control analysis operation caused by a server of a data analysis working center is effectively avoided, the data analysis of an energy saving regulation and control system is ensured to be kept at higher efficiency, and the accurate analysis of the working mode of each monitoring device is facilitated;
3. The server of the monitoring equipment is divided into a high-load operation mode, a low-load operation mode and an idle server mode according to actual task execution conditions and load conditions; in order to improve the electric energy utilization rate of the data center, the intelligent energy-saving regulation and control effect of the data center is further improved on the basis of meeting the electric energy supply requirement and the energy supply requirement of a server of the data center; according to the method, the servers of the corresponding monitoring devices in which the working operation modes of the continuous multiple working operation stage intervals are in the idle server mode are dormant, the task transfer priority and the task transfer priority of each IT device in the high-load operation mode and the low-load operation mode are calculated, and task transfer operation is carried out on the servers of the IT devices after the task transfer priority coefficient and/or the task transfer priority coefficient of each IT device are calculated, so that the situation that the low delay of task delay execution occurs on the servers in the high-load operation mode or the waste of energy is caused by too little task operation quantity of the servers in the low-load operation mode in the same working operation stage interval is effectively avoided, the energy utilization efficiency of the servers of the IT devices is improved, the task execution of the servers can be reasonably arranged, and the energy efficient utilization of the energy of the data center and the servers can be ensured.
Drawings
FIG. 1 is a flow chart of a method for intelligent data center energy conservation control in an embodiment of the application;
FIG. 2 is a flowchart of step S1 in an intelligent data center energy saving control method according to an embodiment of the application;
FIG. 3 is a flowchart of step S3 in an intelligent data center energy saving control method according to an embodiment of the present application;
fig. 4 is a schematic diagram of an apparatus in an embodiment of the application.
Detailed Description
The present application will be described in further detail with reference to the accompanying drawings.
In one embodiment, as shown in fig. 1, the application discloses an intelligent data center energy-saving regulation method, which specifically comprises the following steps:
s1: according to a historical monitoring data set of the data center, identifying and acquiring historical energy consumption interval data of a plurality of monitoring devices of the data center in the operation process, and correspondingly obtaining working operation mode information of the plurality of monitoring devices; the working operation mode information comprises a plurality of working operation stage intervals corresponding to different power supply use efficiencies; the monitoring device associates a device identification.
In this embodiment, the monitoring device is a facility device of a data center; the data center comprises power equipment, a refrigerating system, IT equipment and other equipment, wherein the electronic equipment comprises a generator, a transformer, a storage battery and the like; the refrigerating system comprises a water chilling unit, a cooling tower, a water pump and the like; the IT equipment comprises a server, a switch, a monitoring computer host and the like; other equipment comprises lighting fixtures, fire-fighting equipment, monitoring systems and the like; the monitoring data of the monitoring equipment comprise load data, temperature data and equipment energy consumption data; the load data is the load data of the IT equipment; the equipment identifier is a unique information identification code of each equipment, and a plurality of monitoring equipment can be distinguished and distinguished through the equipment identifier; the historical energy consumption interval data are data corresponding to the same energy consumption data interval; the range operation mode information includes a high power consumption operation stage, a medium power consumption operation stage, and a low power consumption operation stage.
Specifically, in the running process of the monitoring equipment, the energy consumption data is changed due to different temperatures, different running program numbers of the monitoring equipment and the current load, so that the energy-saving regulation strategy of each monitoring equipment is optimally generated based on the data of the historical energy consumption interval data in different time intervals as an optimization reference for energy-saving regulation; and obtaining the historical energy consumption interval data of each monitoring device by carrying out sectional division on the historical energy consumption data of each monitoring device in the time dimension in the historical operation process.
S2: and acquiring a historical regulation and control data set of each monitoring device based on the device identifier, and performing training optimization based on the power supply use efficiency in a preset initial energy-saving regulation and control model to obtain an optimized energy-saving regulation and control model.
In this embodiment, the power use efficiency is also called PUE value; the initial energy-saving regulation model is an automatic machine learning Auto ML model; the user inputs training data (i.e., preset training data) in advance in the initial energy-saving regulation model.
Specifically, acquiring an algorithm set of an initial energy-saving regulation model and regulation parameters of a historical regulation data set of a data center; dividing a history regulation data set into K sub-training sets by using K-fold cross-validation, and dividing training data preset by a user into K test data by using K-fold cross-validation; the initial energy-saving regulation model is shown in formula 01:
In the formula (01), A is an algorithm set of an initial energy-saving regulation model, Wherein each/>The elements are used for representing different classification algorithms; /(I)Regulating parameters in a historical regulation data set of the data center; /(I)K training data sets are obtained by K-fold cross-validation division based on the historical regulation data sets; /(I)K training data sets are obtained by K-fold cross-validation division based on preset training data; the device identity is denoted i,/>The Loss value of the monitoring device for device identification i.
Further, current input data of the data center are collected, training is carried out according to the initial energy-saving regulation and control model pair, a historical data Auto ML model (namely an initial energy-saving regulation and control model) obtained through training corresponding to the historical regulation and control data is obtained, and a current data training Auto ML model corresponding to the current input data is obtained; acquiring a first weight corresponding to the historical data Auto ML model and a second weight corresponding to the current data training Auto ML model; and then, according to the historical data Auto ML model, the current data training Auto ML model, the first weight and the second weight, the historical data Auto ML model and the current data training Auto ML model are subjected to fine tuning according to the following formula (02), the Auto ML model after fine tuning optimization is obtained, and the Auto ML model after fine tuning is used as an optimized energy-saving regulation model after training optimization is completed.
In particular, the method comprises the steps of,Wherein M is an optimized energy-saving regulation model,/>An Auto ML model (i.e., an initial energy-saving regulation model) for historical data; /(I)Training an Auto ML model for current data; /(I)For the first weight,/>Is a second weight.
In practical application, the first weight is an average value of the historical regulation data in a plurality of specified working operation stage intervals of the monitoring equipment, the second weight is an average value of the preset training data in the plurality of specified working operation stage intervals of the monitoring equipment, and the first weight corresponds to the working operation stage intervals of the second weight.
S3: and calculating and determining the associated energy consumption factors among all the monitoring devices according to the historical monitoring data set of the data center to obtain the energy consumption factor association coefficients of all the monitoring devices.
Specifically, using a historical regulation data set recorded by a data center, training the power supply use efficiency (also called as PUE value) of an initial energy-saving regulation model used in a historical manner to obtain an optimized energy-saving regulation model; and meanwhile, the historical monitoring dataset of the historical operation of the data center is used for obtaining the association relation of the energy consumption factors among a plurality of monitoring devices in the data center, so that the combined energy-saving regulation and control of all the monitoring devices, such as loads, of the data center is facilitated, the overall energy consumption of the data center is reduced, a more reasonable energy-saving regulation and control strategy is conveniently formulated according to different load characteristics of different data centers, and the intelligent energy-saving regulation and control strategy has higher applicability.
S4: in the optimized energy-saving regulation model, according to the energy consumption factor association coefficients of all monitoring devices and the energy-saving parameter regulation strategies corresponding to the historical regulation data sets, determining the minimum value of the power supply use efficiency of each monitoring device in each working operation stage interval, and generating the optimal energy-saving regulation strategy.
S5: and carrying out energy-saving regulation and control on the energy consumption of each monitoring device of the data center according to the optimal energy-saving regulation and control strategy.
In the embodiment, in the optimized energy-saving regulation model, the minimum value of the power supply use efficiency of each monitoring device in each working operation stage interval is required to be determined so as to generate an optimal energy-saving regulation strategy; then carrying out fine energy-saving control on each monitoring device of the data center according to the optimal energy-saving control strategy so as to realize providing optimal parameter control of each working operation stage interval of each monitoring device, namely formulating a reasonable energy-saving strategy to adapt to the load characteristics of different data centers; the whole energy consumption of the data center is effectively reduced, and the intelligent energy-saving regulation and control effect and the regulation and control quality of the data center are improved.
In one embodiment, as shown in fig. 2, in step S1, according to a historical monitoring dataset of a data center, historical energy consumption interval data of a plurality of monitoring devices of the data center in an operation process are identified and obtained, and working operation mode information of the plurality of monitoring devices is correspondingly obtained, and specifically includes:
s11: according to the historical monitoring data set of the data center, historical task execution information and corresponding historical energy consumption data monitored by each monitoring device in the historical monitoring time period are obtained.
In this embodiment, in a preset history monitoring duration, the history task execution information (such as the task execution number and the load rate of the server) of each monitoring device and the corresponding history energy consumption data are divided to obtain a plurality of history energy consumption interval data, and the data energy consumption of two adjacent history energy consumption intervals are located in energy consumption intervals with different degrees.
S12: and creating a plurality of historical monitoring time intervals according to the historical task execution information of each monitoring device and the corresponding power consumption data.
In this embodiment, in order to facilitate distinguishing the change situation of the working operation mode of the monitoring device in the historical energy consumption interval data, based on the operation mode judgment condition and the value of the historical energy consumption data, the change situation of the energy consumption data of the plurality of monitoring devices in the corresponding historical monitoring market is judged, for example, the working operation mode of the monitoring device is judged to be in a high-energy consumption working operation stage, a medium-energy consumption working operation stage or a low-energy consumption working operation stage according to the historical energy consumption interval data of the monitoring device.
S13: according to the plurality of historical monitoring time intervals, the historical task execution information of each monitoring device and the corresponding historical energy consumption data are divided based on the device identification, and the plurality of historical energy consumption interval data of each monitoring device in the operation process are correspondingly obtained.
S14: and correspondingly determining and obtaining different working operation mode information of the plurality of monitoring devices according to the historical energy consumption data in the plurality of historical energy consumption interval data and preset operation mode judging conditions.
Specifically, the time interval sectional analysis of the energy consumption interval is carried out on the monitoring equipment, so that the change analysis of the historical monitoring data of each monitoring equipment is effectively completed, the resource waste of the regulation and control analysis operation caused by frequent data analysis work on a server of a data center is effectively avoided, the data analysis of the energy-saving regulation and control system is ensured to be kept at higher efficiency, and meanwhile, the working operation mode of each monitoring equipment is accurately analyzed.
In one embodiment, as shown in FIG. 3, the associated energy consumption factors include IT device energy consumption factors, power supply and distribution loss factors, refrigeration system energy consumption factors, and other energy consumption factors; in step S3: according to a historical monitoring data set of a data center, calculating and determining the associated energy consumption factors among all monitoring devices to obtain the energy consumption factor associated coefficients of all the monitoring devices, wherein the method comprises the following steps:
S31: and obtaining historical power supply use efficiency limit values and corresponding electric energy loss data of each monitoring device according to the historical monitoring data set of the data center.
Specifically, in order to analyze the actual energy consumption composition of different data centers and the actual load characteristics of the data centers, the application performs verification calculation of actual energy consumption values based on the corresponding associated energy consumption factors in the historical monitoring data set of the data centers, and because the energy consumption of the monitoring equipment of the data centers can be influenced by the installation structure and different load characteristics of different monitoring equipment of the data centers, and the power consumption of the power supply system of the data centers can exist in the long-time operation process, the application determines the historical power supply use efficiency limit value (namely the PUE limit value and the value size of the PUE limit value are limited in each working operation stage interval through the optimal energy-saving regulation strategy being executed by the monitoring equipment) of each monitoring equipment based on the historical monitoring data set monitored by the data center in actual operation.
S32: and calculating and determining the performance coefficient value of the associated energy consumption factor of each detection device according to the connection between each detection device and the corresponding energy consumption data.
S33: and determining and obtaining the energy consumption factor association coefficients of all monitoring devices based on the historical power supply use efficiency limit value of each monitoring device and the corresponding performance coefficient value of the associated energy consumption factors.
In this embodiment, since different historical power usage efficiency limits affect the coefficient of performance (i.e., COP) of the cooling system of the data center, then determining the coefficient of performance value of each monitoring device based on the connection relationship between each monitoring device, the corresponding power consumption data including power device consumption data and cable consumption data; and then, according to the historical power supply use efficiency limit value of each monitoring device and the performance coefficient value of the corresponding associated energy consumption factor, calculating and determining the corresponding energy consumption factor associated coefficient, so that the purpose of analyzing the actual energy consumption information of each detection device of the data center from the energy consumption associated relation among a plurality of devices and the associated energy consumption factors of a plurality of energy consumption influence factors is realized, a parameter value with higher detail and accuracy is provided for the follow-up execution of the energy saving regulation strategy, and the data support function is provided for the staff when the regulation operation of the energy saving regulation strategy is carried out.
In one embodiment, in step S3, the intelligent data center energy saving control includes:
S301: constraint calculation is carried out on the associated energy consumption factors of the monitoring equipment based on the formula (1):
wherein/> Historical power usage efficiency value for monitoring device identified as i for device,/>Is the total power consumption of the data center,/>Power consumption for all IT devices; /(I)Is the power supply and distribution loss factor, which is the ratio of the power supply and distribution loss to the energy consumption of IT equipment, and is/The heating value of the monitoring equipment with the equipment mark i accounts for the specific gravity of the load of the refrigeration system; /(I)The energy consumption ratio of the refrigeration system to the energy consumption of IT equipment; /(I)The energy consumption of the monitoring device identified as i for the device accounts for the ratio of the whole refrigeration system; /(I)For the refrigeration performance coefficient of the whole refrigeration system,/>The refrigeration energy consumption of the monitoring equipment with the equipment identifier i accounts for the ratio of the refrigeration energy consumption of the whole refrigeration system; /(I)The ratio of other energy consumption to IT equipment energy consumption; a is a constant coefficient, and the value range is 2% to 5%.
In this embodiment, the monitoring device includes a refrigeration system and IT equipment; power supply use efficiency based on each monitoring deviceThe energy consumption coefficient of the IT equipment, the energy consumption coefficient of the refrigerating system and other energy consumption coefficient are calculated, and the energy consumption association relation of each energy consumption factor association coefficient of the data center is analyzed and evaluated according to the power supply and distribution loss factor (PLF) of the power distribution system in different data centers, the load Characteristic (CLF) of the IT equipment, the performance coefficient (COP value) of monitoring equipment in the refrigerating system and other energy consumption coefficients.
Specifically, power usage efficiency based on individual monitoring devicesThe energy consumption coefficient of the IT equipment, the energy consumption coefficient of the refrigerating system and other energy consumption coefficient are calculated, and the energy consumption association relation of each energy consumption factor association coefficient of the data center is analyzed and evaluated according to the power supply and distribution loss factor (PLF) of the power distribution system in different data centers, the load Characteristic (CLF) of the IT equipment, the performance coefficient (COP value) of monitoring equipment in the refrigerating system and other energy consumption coefficients.
In an embodiment, the intelligent data center energy-saving regulation method further includes:
S10: the server task migration strategy satisfies that a server of a corresponding monitoring device in which all working operation modes of a plurality of continuous working operation phase intervals are in an idle server mode is dormant; the total duration of the continuous multiple working operation phase intervals exceeds the preset first timeout time.
In this embodiment, the server of the monitoring device is divided into a high-load operation mode, a low-load operation mode and an idle server mode due to actual task execution conditions and load conditions; in order to improve the electric energy utilization rate of the data center, the intelligent energy-saving regulation and control effect of the data center is further improved on the basis of meeting the electric energy supply requirement and the energy supply requirement of a server of the data center; according to the method, the server of the corresponding monitoring device, of which the working operation modes are in the idle server mode, of the continuous multiple working operation stage intervals is dormant, and the calculation of the task transfer-out priority and the task transfer-in priority is performed on each IT device in the high-load operation mode and the low-load operation mode.
S20: the server task migration strategy is used for respectively calculating the task transfer-out priority and the task transfer-in priority of the corresponding servers according to the server load values of the IT devices in the high-load operation mode and the low-load operation mode in the off-peak period, and determining a transfer-out server for executing the task transfer-out and a transfer-in server for executing the task transfer-in.
In this embodiment, the off-peak period satisfies that the load values of the servers of all IT devices of the data center are lower than the preset load threshold, and are higher than the preset load threshold, and the load values of the servers of the IT devices of the data center are lower than the ratio of more than one tenth of the preset load threshold, and the off-peak period is determined.
Specifically, after the task transfer-out priority coefficient and/or the task transfer-in priority coefficient of each IT device are calculated, the task transfer-out priority list and the task transfer-in priority list are generated by corresponding sorting according to the coefficients vertically from large to small, and a transfer-out server which needs to transfer out the task and a transfer-in server which transfers in the task are determined according to the task transfer-out priority list and the task transfer-in priority list.
Specifically, the task migration operation is performed on the servers of the IT equipment, so that the situation that the servers in the high-load operation mode have low delay in task delay execution or the servers in the low-load operation mode have too few task operation numbers to cause energy waste in the same working operation stage interval is effectively avoided, the energy utilization efficiency of the servers of the IT equipment is improved, the task execution of the servers can be reasonably arranged, and the energy efficient utilization of the servers of the data center can be ensured.
In an embodiment, the intelligent data center energy-saving regulation method further includes: the server task migration policy satisfies that during off-peak hours, according to server load values of the IT devices in the high-load operation mode and the low-load operation mode, the task transfer priority and the task transfer priority are calculated for the corresponding servers, and the transfer server for executing the task transfer are determined, including:
task transfer priority coefficients of servers of the IT devices are calculated correspondingly according to the formula (2) and the formula (3) And task switch priority coefficient/>：
Wherein/>A measured temperature value for an IT device identified as i for the device; /(I)Is a preset low load threshold,/>The load factor of the server of the IT equipment with the equipment identification of i is given, and N is the CPU core number of the server of each IT equipment; /(I)Is a preset high load threshold; /(I)Is a preset medium load threshold.
In this embodiment, the historical monitoring dataset of the data center also includes temperature measurement data for the IT equipment; when the data center actually operates, real-time measurement temperature values of all monitoring devices of the measurement data center are also acquired; executing a server task migration strategy on each monitoring device of the data center based on the monitoring device (i.e., the IT device) measuring temperature and load conditions in real time and CPU core numbers of servers of each IT device; specifically, in the off-peak period of the data center, tasks in the server with lower load coefficient, low CPU core number and higher temperature of the server are preferentially transferred out, and the refrigeration energy consumption of the refrigeration system is reduced at intervals; and meanwhile, the task is preferentially shifted to a server with lower temperature, or when the temperatures of a plurality of shifting-in devices are the same, the task is preferentially shifted to a high CPU core number, so that the heat productivity of the server of the IT device can be effectively controlled, the high performance and the high reliability of the IT device are maintained, the overall power consumption of the IT device is reduced, and the electric energy is saved.
It should be understood that the sequence number of each step in the above embodiment does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not be construed as limiting the implementation process of the embodiment of the present application.
In an embodiment, an intelligent data center energy saving control system is provided, which corresponds to an intelligent data center energy saving control method in the above embodiment.
An intelligent data center energy-saving regulation and control system comprises a historical monitoring data analysis module, a power supply use efficiency training module, an associated energy consumption factor determining module and an optimal regulation and control strategy generating module. The detailed description of each functional module is as follows:
the historical monitoring data analysis module is used for acquiring a historical regulation and control data set of each monitoring device based on the device identification, and training and optimizing based on the power supply use efficiency in a preset initial energy-saving regulation and control model to obtain an optimized energy-saving regulation and control model;
the power supply use efficiency training module is used for acquiring a historical regulation and control data set of each monitoring device based on the device identification, and training and optimizing based on the power supply use efficiency in a preset initial energy-saving regulation and control model to obtain an optimized energy-saving regulation and control model;
the associated energy consumption factor determining module is used for calculating and determining associated energy consumption factors among all monitoring devices according to a historical monitoring data set of the data center to obtain energy consumption factor association coefficients of all the monitoring devices;
the optimal regulation and control strategy generation module is used for determining the minimum value of the power supply use efficiency of each monitoring device in each working operation stage interval according to the energy consumption factor association coefficients of all the monitoring devices and the energy saving parameter adjustment strategies corresponding to the historical regulation and control data sets in the optimal energy saving regulation and control model, and generating an optimal energy saving regulation and control strategy;
and the optimal regulation and control strategy execution module is used for carrying out energy-saving regulation and control on the energy consumption of each monitoring device of the data center according to the optimal energy-saving regulation and control strategy.
Optionally, the historical monitoring data analysis module includes:
The task execution and energy consumption information identification sub-module is used for acquiring historical task execution information and corresponding historical energy consumption data monitored by each monitoring device in the historical monitoring time according to the historical monitoring data set of the data center;
the monitoring time interval creation sub-module is used for creating a plurality of historical monitoring time intervals according to historical task execution information of each monitoring device and corresponding power consumption data;
The energy consumption interval data dividing sub-module is used for dividing the historical task execution information of each monitoring device and the corresponding historical energy consumption data based on the device identification according to a plurality of historical monitoring time intervals, and correspondingly obtaining a plurality of historical energy consumption interval data of each monitoring device in the running process;
the working operation mode determining sub-module is used for correspondingly determining and obtaining different working operation mode information of the plurality of monitoring devices according to the historical energy consumption data in the plurality of historical energy consumption interval data and preset operation mode judging conditions.
For specific limitation of an energy-saving control system of an intelligent data center, reference may be made to the limitation of an energy-saving control method of an intelligent data center hereinabove, and detailed description thereof will be omitted herein; all or part of each module in the intelligent data center energy-saving control system can be realized by software, hardware and a combination thereof; the above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing a historical monitoring data set, an energy-saving regulation model, an optimal energy-saving regulation strategy and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by the processor is used for realizing an intelligent data center energy-saving regulation method.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s1: according to a historical monitoring data set of the data center, identifying and acquiring historical energy consumption interval data of a plurality of monitoring devices of the data center in the operation process, and correspondingly obtaining working operation mode information of the plurality of monitoring devices; the working operation mode information comprises a plurality of working operation stage intervals corresponding to different power supply use efficiencies; monitoring equipment associated equipment identification;
S2: acquiring a historical regulation and control data set of each monitoring device based on the device identifier, and performing training optimization based on the power supply use efficiency in a preset initial energy-saving regulation and control model to obtain an optimized energy-saving regulation and control model;
S3: according to a historical monitoring data set of the data center, calculating and determining the associated energy consumption factors among all monitoring devices to obtain the energy consumption factor association coefficients of all the monitoring devices;
S4: in the optimized energy-saving regulation model, determining the minimum value of the power supply use efficiency of each monitoring device in each working operation stage interval according to the energy consumption factor association coefficients of all the monitoring devices and the energy-saving parameter regulation strategies corresponding to the historical regulation data sets, and generating an optimal energy-saving regulation strategy;
s5: and carrying out energy-saving regulation and control on the energy consumption of each monitoring device of the data center according to the optimal energy-saving regulation and control strategy.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
s1: according to a historical monitoring data set of the data center, identifying and acquiring historical energy consumption interval data of a plurality of monitoring devices of the data center in the operation process, and correspondingly obtaining working operation mode information of the plurality of monitoring devices; the working operation mode information comprises a plurality of working operation stage intervals corresponding to different power supply use efficiencies; monitoring equipment associated equipment identification;
S2: acquiring a historical regulation and control data set of each monitoring device based on the device identifier, and performing training optimization based on the power supply use efficiency in a preset initial energy-saving regulation and control model to obtain an optimized energy-saving regulation and control model;
S3: according to a historical monitoring data set of the data center, calculating and determining the associated energy consumption factors among all monitoring devices to obtain the energy consumption factor association coefficients of all the monitoring devices;
S4: in the optimized energy-saving regulation model, determining the minimum value of the power supply use efficiency of each monitoring device in each working operation stage interval according to the energy consumption factor association coefficients of all the monitoring devices and the energy-saving parameter regulation strategies corresponding to the historical regulation data sets, and generating an optimal energy-saving regulation strategy;
s5: and carrying out energy-saving regulation and control on the energy consumption of each monitoring device of the data center according to the optimal energy-saving regulation and control strategy.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme described in the foregoing embodiments can be modified or some of the features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (9)
1. An intelligent data center energy-saving regulation and control method is characterized by comprising the following steps:
According to a historical monitoring data set of the data center, identifying and acquiring historical energy consumption interval data of a plurality of monitoring devices of the data center in the operation process, and correspondingly obtaining working operation mode information of the plurality of monitoring devices; the working operation mode information comprises a plurality of working operation stage intervals corresponding to different power supply use efficiencies; the monitoring equipment associates equipment identification;
Acquiring a historical regulation and control data set of each monitoring device based on the device identifier, and performing training optimization based on the power supply use efficiency in a preset initial energy-saving regulation and control model to obtain an optimized energy-saving regulation and control model;
according to a historical monitoring data set of the data center, calculating and determining the associated energy consumption factors among all monitoring devices to obtain the energy consumption factor association coefficients of all the monitoring devices;
In the optimized energy-saving regulation model, determining the minimum value of the power supply use efficiency of each monitoring device in each working operation stage interval according to the energy consumption factor association coefficients of all the monitoring devices and the energy-saving parameter regulation strategies corresponding to the historical regulation data set, and generating an optimal energy-saving regulation strategy;
And carrying out energy-saving regulation and control on the energy consumption of each monitoring device of the data center according to the optimal energy-saving regulation and control strategy.
2. The method for energy-saving regulation and control of an intelligent data center according to claim 1, wherein the method is characterized by identifying and acquiring historical energy consumption interval data of a plurality of monitoring devices of the data center in the operation process according to a historical monitoring data set of the data center and correspondingly obtaining working operation mode information of the plurality of monitoring devices, and specifically comprises the following steps:
Acquiring historical task execution information and corresponding historical energy consumption data monitored by each monitoring device in a historical monitoring time period according to a historical monitoring data set of a data center;
creating a plurality of historical monitoring time intervals according to historical task execution information of each monitoring device and corresponding power consumption data;
Dividing the historical task execution information of each monitoring device and corresponding historical energy consumption data based on the device identification according to a plurality of historical monitoring time intervals, and correspondingly obtaining a plurality of historical energy consumption interval data of each monitoring device in the operation process;
And correspondingly determining and obtaining different working operation mode information of the plurality of monitoring devices according to the historical energy consumption data in the plurality of historical energy consumption interval data and preset operation mode judging conditions.
3. The intelligent data center energy conservation regulation method of claim 1, wherein the associated energy consumption factors comprise IT equipment energy consumption factors, power supply and distribution loss factors, refrigeration system energy consumption factors and other energy consumption factors; according to the historical monitoring data set of the data center, calculating and determining the associated energy consumption factors among all monitoring devices to obtain the energy consumption factor associated coefficients of all the monitoring devices, wherein the method comprises the following steps:
According to the historical monitoring data set of the data center, historical power supply use efficiency limit values and corresponding electric energy loss data of all monitoring equipment are obtained;
Calculating and determining the performance coefficient value of the associated energy consumption factor of each detection device according to the connection between each detection device and the corresponding electric energy consumption data;
and determining and obtaining the energy consumption factor association coefficients of all monitoring devices based on the historical power supply use efficiency limit value of each monitoring device and the corresponding performance coefficient value of the associated energy consumption factors.
4. The intelligent data center energy saving control method according to claim 3, wherein the monitoring equipment comprises a refrigerating system and IT equipment; the method further comprises the steps of:
Constraint calculation is carried out on the associated energy consumption factors of the monitoring equipment based on the formula (1):
wherein/> Historical power usage efficiency value for monitoring device identified as i for device,/>Is the total power consumption of the data center,/>Power consumption for all IT devices; /(I)Is the power supply and distribution loss factor, which is the ratio of the power supply and distribution loss to the energy consumption of IT equipment, and is/The heating value of the monitoring equipment with the equipment mark i accounts for the specific gravity of the load of the refrigeration system; /(I)The energy consumption ratio of the refrigeration system to the energy consumption of IT equipment; /(I)The energy consumption of the monitoring device identified as i for the device accounts for the ratio of the whole refrigeration system; /(I)For the refrigeration performance coefficient of the whole refrigeration system,/>The refrigeration energy consumption of the monitoring equipment with the equipment identifier i accounts for the ratio of the refrigeration energy consumption of the whole refrigeration system; /(I)The ratio of other energy consumption to IT equipment energy consumption; a is a constant coefficient, and the value range is 2% to 5%.
5. The intelligent data center energy saving control method according to claim 4, further comprising: the optimal energy-saving regulation strategy comprises a server task migration strategy of IT equipment; the monitoring device comprises a server; the working operation mode information comprises a high-load operation mode, a low-load operation mode and an idle server mode; the high-load operation mode meets the condition that a server load value of the IT equipment is larger than a preset high-load threshold value, and the low-load operation mode meets the condition that the server load value of the IT equipment is smaller than the preset low-load threshold value;
The server task migration strategy satisfies that a server of a corresponding monitoring device in which all working operation modes of a plurality of continuous working operation phase intervals are in an idle server mode is dormant; the total duration of the continuous multiple working operation phase intervals exceeds the preset first timeout time;
The server task migration strategy is used for respectively calculating the task transfer priority and the task transfer priority of each corresponding server according to the server load value of each IT device in the high-load operation mode and the low-load operation mode in the off-peak period, and determining a transfer-out server for executing the transfer-out of the task and a transfer-in server for executing the transfer-in of the task.
6. The method for energy saving and control in an intelligent data center according to claim 5, wherein the server task migration policy satisfies that, during off-peak hours, the calculation of the task transfer-out priority and the task transfer-in priority is performed on the respective servers according to the server load values of the IT devices in the high load operation mode and the low load operation mode, and the determination of the transfer-out server performing the task transfer-out and the transfer-in server performing the task transfer-in includes:
task transfer priority coefficients of servers of the IT devices are calculated correspondingly according to the formula (2) and the formula (3) And task switch priority coefficient/>：
Wherein/>A measured temperature value for an IT device identified as i for the device; /(I)Is a preset low load threshold,/>The load factor of the server of the IT equipment with the equipment identification of i is given, and N is the CPU core number of the server of each IT equipment; /(I)Is a preset high load threshold; /(I)Is a preset medium load threshold.
7. An intelligent data center energy saving control system, for executing an intelligent data center energy saving control method according to any one of claims 1 to 6, the system comprising:
the historical monitoring data analysis module is used for acquiring a historical regulation and control data set of each monitoring device based on the device identification, and training and optimizing based on the power supply use efficiency in a preset initial energy-saving regulation and control model to obtain an optimized energy-saving regulation and control model;
the power supply use efficiency training module is used for acquiring a historical regulation and control data set of each monitoring device based on the device identification, and training and optimizing based on the power supply use efficiency in a preset initial energy-saving regulation and control model to obtain an optimized energy-saving regulation and control model;
the associated energy consumption factor determining module is used for calculating and determining associated energy consumption factors among all monitoring devices according to a historical monitoring data set of the data center to obtain energy consumption factor association coefficients of all the monitoring devices;
The optimal regulation strategy generation module is used for determining the minimum power supply use efficiency value of each monitoring device in each working operation stage interval according to the energy consumption factor association coefficients of all the monitoring devices and the energy saving parameter adjustment strategies corresponding to the historical regulation data sets in the optimal energy saving regulation model, and generating an optimal energy saving regulation strategy;
And the optimal regulation and control strategy execution module is used for carrying out energy-saving regulation and control on the energy consumption of each monitoring device of the data center according to the optimal energy-saving regulation and control strategy.
8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of a method for intelligent data center energy saving regulation according to any one of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of an intelligent data center energy saving control method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410560860.4A CN118132244A (en) | 2024-05-08 | 2024-05-08 | Energy-saving regulation and control method, system, equipment and medium thereof for intelligent data center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410560860.4A CN118132244A (en) | 2024-05-08 | 2024-05-08 | Energy-saving regulation and control method, system, equipment and medium thereof for intelligent data center |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118132244A true CN118132244A (en) | 2024-06-04 |
Family
ID=91248136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410560860.4A Pending CN118132244A (en) | 2024-05-08 | 2024-05-08 | Energy-saving regulation and control method, system, equipment and medium thereof for intelligent data center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118132244A (en) |
-
2024
- 2024-05-08 CN CN202410560860.4A patent/CN118132244A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021063033A1 (en) | Energy consumption model training method for air conditioner and air conditioning system control method | |
| CN109800066B (en) | Energy-saving scheduling method and system for data center | |
| US10767886B2 (en) | Building management system with saturation detection and removal for system identification | |
| CN104698843B (en) | A kind of data center's energy-saving control method based on Model Predictive Control | |
| CN110442170B (en) | Equipment operation and monitoring method, device, equipment and medium | |
| CN115682357B (en) | Cooling water optimizing method taking approximation degree as center and independent control system | |
| CN112070353B (en) | Method and system for accurately detecting energy efficiency of data center | |
| CN105577796A (en) | Cluster power consumption control method and device | |
| CN115164361B (en) | Data center control method and device, electronic equipment and storage medium | |
| CN103777737A (en) | Cloud computer room energy saving method based on server resource load and position sensing | |
| US20140246909A1 (en) | System and method for balancing supply and demand of energy on an electrical grid | |
| CN111552360A (en) | Industrial personal computer cooling method and device, computer equipment and storage medium | |
| CN118132244A (en) | Energy-saving regulation and control method, system, equipment and medium thereof for intelligent data center | |
| CN110008515B (en) | Renewable energy data center management method and device | |
| CN111968008A (en) | Comprehensive energy monitoring system and method based on multi-energy cooperation | |
| CN106094523B (en) | Based on efficiency and flow index area and maximum parallel operation system optimization method | |
| CN111988961B (en) | Cabinet temperature control method and control system | |
| TW202248577A (en) | Energy-saving control method and device for temperature regulation equipment capable of reducing power consumption by a building cooling and heating type prediction module and an optimal temperature setting module | |
| CN106159934B (en) | Based on efficiency and flow the parallel operation system optimized control method of index golden section | |
| CN117970009B (en) | Electric power acquisition terminal and electric energy meter of valley filling circuit | |
| WO2024113906A1 (en) | Server cluster temperature adjustment method and device | |
| CN106026205B (en) | Based on efficiency and current sharing energy area and maximum parallel operation system optimized control method | |
| CN118301911A (en) | Air conditioner control method for data center, electronic equipment and storage medium | |
| CN106026203B (en) | Based on efficiency and stream deviation it is expected the parallel operation system optimized control method of weighted sum matrix | |
| CN116431436A (en) | Energy consumption monitoring system and method based on cloud server crypto machine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |