CN118093301A - Method and device for regulating temperature of server cluster - Google Patents
Method and device for regulating temperature of server cluster Download PDFInfo
- Publication number
- CN118093301A CN118093301A CN202211501797.4A CN202211501797A CN118093301A CN 118093301 A CN118093301 A CN 118093301A CN 202211501797 A CN202211501797 A CN 202211501797A CN 118093301 A CN118093301 A CN 118093301A
- Authority
- CN
- China
- Prior art keywords
- temperature
- server cluster
- server
- parameter
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000001105 regulatory effect Effects 0.000 title claims abstract description 7
- 238000004378 air conditioning Methods 0.000 claims abstract description 71
- 230000003247 decreasing effect Effects 0.000 claims abstract description 47
- 230000033228 biological regulation Effects 0.000 claims abstract description 45
- 230000008859 change Effects 0.000 claims abstract description 34
- 230000007613 environmental effect Effects 0.000 claims abstract description 33
- 230000007423 decrease Effects 0.000 claims abstract description 31
- 238000012544 monitoring process Methods 0.000 claims abstract description 23
- 230000001276 controlling effect Effects 0.000 claims abstract description 18
- 230000009471 action Effects 0.000 claims abstract description 17
- 230000000630 rising effect Effects 0.000 claims abstract description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 15
- 230000005012 migration Effects 0.000 claims description 12
- 238000013508 migration Methods 0.000 claims description 12
- 238000001816 cooling Methods 0.000 description 24
- 230000009467 reduction Effects 0.000 description 16
- 238000004364 calculation method Methods 0.000 description 15
- 230000017525 heat dissipation Effects 0.000 description 15
- 238000005265 energy consumption Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 11
- 238000004134 energy conservation Methods 0.000 description 10
- 230000008901 benefit Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000011217 control strategy Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000005057 refrigeration Methods 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000009423 ventilation Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000020169 heat generation Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013398 bayesian method Methods 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
The application discloses a method and a device for regulating the temperature of a server cluster, which are used for solving the problem that the temperature of the server cluster is difficult to control timely and effectively. The scheme provided by the application comprises the following steps: monitoring load parameters of the server cluster in a history period and environment temperature parameters of the server cluster; predicting the server increase and decrease number of the server cluster in the future period based on the load parameter; determining a temperature regulation strategy in a future period according to the increasing and decreasing number of the servers and the environmental temperature parameter, wherein the temperature regulation strategy comprises a temperature rising and decreasing parameter, and the change trend of the increasing and decreasing number of the servers and the change trend of the temperature rising and decreasing parameter are inversely related; and controlling the air conditioning system to execute a temperature regulation strategy matching action in a future period so as to execute regulation on the environment temperature of the server cluster.
Description
Technical Field
The present application relates to the field of energy saving control, and in particular, to a method and an apparatus for adjusting a server cluster temperature.
Background
Along with the construction plan of the digital infrastructure and the centralized/intensive management of the server equipment of the data center, a scientific and effective calculation model is urgently needed for the implementation of accurate energy conservation and consumption reduction. The existing server cluster is often configured with an air conditioning system so as to realize heat dissipation of equipment of the server cluster, and the stability of the server equipment is guaranteed.
The current air conditioning system of the data center usually controls the frequency conversion operation of the air conditioning system according to the monitored peripheral temperature in a temperature monitoring mode, and regulates and controls the refrigerating capacity to realize temperature control. Temperature control in this way often has hysteresis, i.e. the cooling is performed after the temperature of the server device increases, and no timely and effective temperature control is possible.
How to improve the temperature control effectiveness of the server cluster is a technical problem to be solved by the application.
Disclosure of Invention
The embodiment of the application aims to provide a method and a device for regulating the temperature of a server cluster, which are used for solving the problem that the temperature of the server cluster is difficult to control timely and effectively.
In a first aspect, a method for adjusting a server cluster temperature is provided, including:
monitoring load parameters of a server cluster in a history period and environment temperature parameters of the server cluster;
predicting an increase or decrease in the number of servers of the server cluster within a future period based on the load parameter;
Determining a temperature regulation strategy in the future period according to the server increasing and decreasing number and the environmental temperature parameter, wherein the temperature regulation strategy comprises a temperature rising and decreasing parameter, and the change trend of the server increasing and decreasing number is inversely related to the change trend of the temperature rising and decreasing parameter;
and controlling an air conditioning system to execute the action matched with the temperature regulation strategy in the future period so as to execute regulation on the environment temperature of the server cluster.
In a second aspect, a server cluster temperature adjustment device is provided, including:
The monitoring module is used for monitoring load parameters of the server cluster in a history period and environment temperature parameters of the server cluster;
A prediction module for predicting the server increase/decrease number of the server cluster in a future period based on the load parameter;
the determining module is used for determining a temperature regulation strategy in the future period according to the server increasing and decreasing number and the environmental temperature parameter, wherein the temperature regulation strategy comprises a temperature increasing and decreasing parameter, and the change trend of the server increasing and decreasing number is inversely related to the change trend of the temperature increasing and decreasing parameter;
and the control module is used for controlling the air conditioning system to execute the action matched with the temperature regulation strategy in the future period so as to execute regulation on the environment temperature of the server cluster.
In a third aspect, there is provided an electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program implementing the steps of the method as in the first aspect when executed by the processor.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method as in the first aspect.
In the embodiment of the application, firstly, the load parameter of the server cluster in a historical period and the environmental temperature parameter of the server cluster are monitored, then, the server increasing and decreasing number of the server cluster in a future period is predicted based on the load parameter, and then, a temperature regulation strategy in the future period is determined according to the server increasing and decreasing number and the environmental temperature parameter, wherein the temperature regulation strategy comprises a temperature lifting parameter, the change trend of the server increasing and decreasing number and the change trend of the temperature lifting parameter are inversely related, and then, an air conditioning system is controlled to execute a temperature regulation strategy matching action in the future period so as to execute regulation on the environmental temperature of the server cluster. According to the method and the system, the load change is predicted by monitoring the load parameters of the server cluster, so that the temperature regulation strategy to be executed is predetermined before the actual temperature change of the server cluster, and the temperature regulation action of the air conditioning system can be correspondingly regulated along with the load change of the server cluster in a future period, so that effective temperature control is realized, the method and the system have the advantages of being effective in time, and energy conservation and consumption reduction are facilitated.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
Fig. 1 is a schematic flow chart of a server cluster temperature adjustment method according to an embodiment of the present application.
FIG. 2 is a second flow chart of a method for adjusting temperature of a server cluster according to an embodiment of the application.
FIG. 3a is a third flow chart illustrating a method for server cluster temperature adjustment according to an embodiment of the present application.
Fig. 3b is a schematic diagram of a control flow based on the air circulation strategy of fig. 3a performing an air external circulation.
FIG. 3c is a schematic diagram of a control flow based on the air circulation strategy of FIG. 3a for performing an in-air circulation.
FIG. 4 is a flow chart illustrating a method for server cluster temperature adjustment according to an embodiment of the present application.
Fig. 5a is a flowchart of a server cluster temperature adjustment method according to an embodiment of the present application.
Fig. 5b is a schematic flow chart of increasing the number of servers in a server cluster temperature adjustment method according to an embodiment of the present application.
Fig. 5c is a flow chart illustrating a method for adjusting server cluster temperature according to an embodiment of the present application.
Fig. 6 is a schematic structural diagram of a server cluster temperature adjustment device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. The reference numerals in the present application are only used for distinguishing the steps in the scheme, and are not used for limiting the execution sequence of the steps, and the specific execution sequence controls the description in the specification.
In the field of temperature regulation of server clusters, cooling is often performed through an air conditioning system after the temperature of the server is increased, and the scheme has hysteresis, can not control the temperature timely and effectively, and may cause resource waste.
For example, in one case, the server cluster load increases due to the increase in traffic, and the overall server cluster temperature continues to increase. And triggering the air conditioning system to execute cooling after the temperature rises to the warning value. At this time, the server cluster is already at a higher temperature for a period of time, and the normal temperature can be recovered after the air conditioning system is cooled for a period of time. It follows that this solution has hysteresis and is not effective in controlling the temperature in time.
In another case, in order to avoid that the server cluster is at a high temperature for a long time, and thus the warning value is reduced, the air conditioning system is triggered to execute cooling under the condition that the temperature of the server cluster is not too high. Although, in a scenario where the overall temperature of the server cluster continues to rise, such a lower alert value can control the temperature relatively timely. However, the traffic of the server cluster is continuously changed, if the load of the server cluster is increased first, the temperature reaches the warning value, the air conditioning system is triggered to perform cooling, and then the load is reduced again, the overall temperature increase speed of the server cluster is not envisaged to be as fast, so that the air conditioning system excessively reduces the temperature, and resource waste is caused.
Therefore, in the scene of server cluster temperature control, the execution and effective temperature control of the continuously changing server clusters are difficult, and resources are wasted.
In order to solve the problems in the prior art, an embodiment of the present application provides a method for adjusting a server cluster temperature, as shown in fig. 1, including:
s11: and monitoring load parameters of the server cluster in a history period and environment temperature parameters of the server cluster.
In practical application, load parameters of the server cluster can be obtained by monitoring the server cluster, and environmental temperature parameters of the server cluster can be obtained by the temperature collector.
For example, the server traffic load monitoring module may obtain the load parameters of the server cluster, and may continuously obtain the load parameters in a real-time monitoring manner. In practical applications, the monitored parameters may be obtained and counted by means of remote control, for example, counting, cleaning and persistence of the data by means of hypertext transfer security Protocol (Hypertext Transfer Protocol Secure, HTTPS) or security file transfer Protocol (SECRET FILE TRANSFER Protocol, SFTP).
The load parameter may refer to a parameter related to a device temperature of the server cluster, and may include, for example, a central processing unit (central processing unit, CPU) usage rate, a memory usage rate, a port flow rate, an application program interface (Application Programming Interface, API) service access number, and the like.
The above-mentioned environmental temperature parameters may be collected by the air conditioning management component, and may include, for example, outdoor temperature/humidity, cold air duct temperature/humidity, heat-dissipating air duct, server rack unit temperature, and the like. The environmental temperature parameters can represent the temperature, cooling efficiency, cooling intensity and the like of the server cluster, and the dynamic and flexible adjustment of the control strategy is facilitated based on the environmental temperature parameters so as to cope with the continuously changing actual temperature in the server cluster, and the temperature of the server cluster is facilitated to be kept in a safe range.
In general, after the load of the server cluster increases, the temperature of the server cluster also changes correspondingly, that is, the load parameter is closely related to the temperature of the server cluster. In the step, load parameters and environment temperature parameters in a history period are obtained, and the load change and the temperature change of the server cluster can be monitored, so that a data basis is provided for predicting and determining a control strategy in the subsequent step.
S12: predicting a server increase or decrease in the server cluster over a future period based on the load parameter.
The load parameter obtained in the above step can represent load change of the server cluster in a history period, generally speaking, the load of the server cluster has a certain continuity, and the load parameter in the history period can represent load change trend of the server cluster. If the load parameter indicates an increase in the overall load of the server cluster, the server cluster needs to increase server reserves to provide
For example, a server traffic load monitoring component or server traffic index collection module may be employed to perform the steps. Specifically, the required characteristic data can be collected through an agent in the server operating system, the collected data is cleaned and persisted, and then data analysis is performed, so that an analysis result of whether the server cluster can perform service migration/power-down/input power adjustment is obtained. The server cluster may then adjust the number of servers in the cluster by powering up or powering down the servers to account for the changing traffic load.
S13: and determining a temperature regulation strategy in the future period according to the server increasing and decreasing quantity and the environmental temperature parameter, wherein the temperature regulation strategy comprises a temperature rising and decreasing parameter, and the change trend of the server increasing and decreasing quantity is inversely related to the change trend of the temperature rising and decreasing parameter.
The temperature regulation strategy is determined based on the number of server increase and decrease and the environmental temperature parameter in the cluster determined in the steps. The temperature regulation strategy considers the overall temperature change of the server cluster caused by the change of the number of the servers on one hand, and considers the heat dissipation influence of the temperature of the environment where the server cluster is located on the server cluster on the other hand.
The temperature regulation strategy includes a temperature rise and fall parameter, if a server is added in the server cluster, the overall load of the server cluster is increased, and the heat generation is increased, and the temperature rise and fall parameter in the generated temperature regulation strategy is used for controlling the air conditioning system to increase the cooling efficiency of the server cluster, for example, increasing the ventilation quantity of the cold air or reducing the temperature of the cold air, so as to cope with the load to be increased.
Conversely, if the servers in the server cluster are reduced, the overall load of the server cluster is reduced, the heat generation is reduced, and the temperature rise and fall parameters in the generated temperature regulation strategy are used for controlling the air conditioning system to reduce the cooling efficiency of the server cluster, for example, the ventilation quantity of the cold air is reduced, or the temperature of the cold air is increased, so that energy conservation and emission reduction are realized when the load of the server cluster is lower.
S14: and controlling an air conditioning system to execute the action matched with the temperature regulation strategy in the future period so as to execute regulation on the environment temperature of the server cluster.
The temperature adjustment strategy generated in the above step may control the air conditioning system to perform a control operation to adjust the ambient temperature in which the server cluster is located in a future period of time. For example, a service scheduling component or a power computing scheduling module may be applied to dynamically schedule power computing service, and perform service migration and scheduling for servers added or reduced in a server cluster, and may further control a self module to shut down or enter an energy saving mode after completing scheduling, so as to achieve energy saving and emission reduction. After the power-off or the energy-saving mode is entered, if the scheduling and the migration of the service are needed to be executed again, the power-on and power-off management system of the server can be interacted, the power-on is executed based on the control instruction, the scheduling and the migration needed by the execution are executed, and the service capacity of the server cluster can be increased horizontally.
In practical application, the temperature regulation strategy and the server scheduling and migration of the server can be cooperatively performed, and in the aspect of service scheduling of the server, the traffic or service request of the entrance of the server cluster is guided to the background computing cluster in advance through load sharing software, so that the number of the servers needing to be operated is predicted according to the service request quantity, and the evaluation of the service quantity is realized. If the number of servers needs to be reduced, traffic aggregation may be performed during the future period, and shutdown or power down may be performed for redundant running servers. When the service request quantity rises, after the service scheduling module performs artificial intelligent calculation and judgment, if the number of servers needs to be increased, the redundant servers in a power-down state which can be scheduled can be pulled up in the future period.
The air conditioning system performs a matched action in accordance with a temperature regulation strategy during a future period of time to achieve temperature control. For example, the air conditioner management component can be used as an executive party of an accurate heat dissipation and energy saving control strategy, and control and production are carried out on the total refrigerating capacity according to the temperature regulation strategy, and accurate refrigerating capacity transmission is carried out through the electric control air duct, so that timely and effective temperature control is carried out on the server cluster.
In practical application, temperature control can be performed through an air conditioner air duct device capable of being controlled electrically, the air conditioner air duct device can specifically comprise a rack air cooling device, the rack air cooling device is used for accurately conducting independent air inlet and air outlet management on each server, and hot air at an air outlet of the rack can be collected into an air outlet air duct of an air conditioner system so as to be processed uniformly. In addition, the air conditioner air duct device can further comprise a fan pressurizing device, and the fan pressurizing device is used for flexibly adjusting the air pressure and controlling the amount of cold air introduced into the equipment of the server cluster based on the temperature adjusting strategy.
For example, in the case where it is determined that the server cluster may reduce the number of servers running, the service on the servers is migrated or concentrated to the servers that can be serviced, the redundant servers are powered down (or the power input is turned down), the cooling capacity of the air conditioning system is estimated in advance, the cooling capacity is reduced, and the redundant air conditioning equipment is shut down or taken out of service.
Under the condition that the running number of the servers needs to be increased in the server cluster, the servers in the power-down state are powered on (or adjusted to normal power input), so that the servers are automatically brought into the service cluster, the refrigerating capacity of an air conditioning system is estimated in advance, standby air conditioning equipment can be awakened, the production refrigerating capacity is increased, and accurate heat dissipation management is completed.
The scheme provided by the embodiment of the application is used for effectively controlling the temperature of the server cluster, wherein the load change is predicted by monitoring the load parameter of the server cluster, and the temperature is effectively controlled in a future period. Avoiding the temperature control hysteresis problem which exists when the temperature control is started after the temperature is raised.
According to the scheme, the sample data of the server business load data in different time periods are obtained through collecting parameters such as the working condition of the peripheral equipment, monitoring the server business load and the total running power. The collected load parameters can comprise parameters such as port flow of the switching equipment, access quantity of corresponding interface addresses on the firewall equipment and the like, so that service indexes of the server cluster can be modeled, the data collected after modeling are subjected to iterative training to obtain a prediction model, the increase and decrease quantity of the servers of the server cluster is judged by comprehensively considering various factors, and then a temperature regulation strategy is determined according to the increase and decrease quantity of the servers and the ambient temperature, so that effective and accurate temperature control of the server cluster is realized.
The scheme provided by the embodiment of the application can realize the whole energy consumption management and automatic control of the data center and can realize accurate and intelligent energy consumption management. When the service volume of the server cluster changes, the scheme can correspondingly control the air conditioning system to execute temperature control along with the change of the service volume, so that the energy consumption of the whole data center is accurately managed, the energy saving and consumption reduction targets are realized, and the maximization of economic benefit is facilitated.
Based on the solution provided in the foregoing embodiment, optionally, the load parameters of the server cluster include at least one of the following:
service traffic load parameters, network device traffic parameters, number of network device port requests, number of network link sessions.
According to the scheme provided by the embodiment of the application, the increase and decrease quantity of the servers in the server cluster can be comprehensively determined according to various parameters related to the service load, so that the service change of the server cluster can be predicted more accurately, and the accuracy of temperature control is improved.
Based on the solution provided in the foregoing embodiment, optionally, the load parameter of the server cluster includes a plurality of items;
As shown in fig. 2, the step S12 includes:
S21: inputting a plurality of load parameters into a parameter prediction model based on a naive Bayesian algorithm to obtain the predicted lifting probability of the plurality of load parameters in the future period.
The naive bayes algorithm (Naive Bayesian algorithm) is a classification method based on the independent assumption of bayes theorem and characteristic conditions. The naive Bayes classifier (Naive Bayes Classifier, NBC) model can be applied, parameters required to be estimated are fewer, the method is insensitive to missing data, the algorithm is simpler, and the parameter prediction can be conveniently and efficiently realized.
The naive Bayesian method applied in the scheme provided by the embodiment of the application is correspondingly simplified on the basis of Bayesian algorithm, namely, the mutual conditions among the attributes are independent when the given target value is assumed. There is no algorithm that has a greater specific gravity for the decision result, or which attribute variable has a smaller specific gravity for the decision result.
The naive bayes approach of the present scheme is described below.
The method is characterized in that a sample data set D= { D-1-, & gtd-2-, & gtd-n- }, a characteristic attribute set corresponding to the sample set is X= { X-1-, & gtx-2-, & gtx-D- }, a class variable is Y= { Y-1-, & gty-2-, & gty-m- }, namely D can be divided into Y-m-classes, wherein X-1-, & gtx-2-, & gtx-D-, & gtis mutually and randomly independent.
The prior probabilities P to priority to P (Y), and the posterior probabilities P to post to P (y|x) of Y.
The posterior probability can be calculated by the prior probability P-prior to=p (Y), the evidence P (X), and the class conditional probability P (x|y):
P(X|Y)＝P(Y)P(X∣Y)/P(X)P(X|Y)＝P(X)P(Y)P(X∣Y)
Based on the features being independent of each other, given a category y, the above formula can be further expressed as:
the posterior probability can be calculated from the above two formulas as:
In the scheme provided by the embodiment of the application, predictive computation is performed on a plurality of load parameters by applying the naive Bayesian model, so that the probability that the server set increases and decreases the servers is obtained.
For example, the solution provided by the embodiment of the present application may apply each load parameter shown in the "condition category" column in the following table 1, and execute the prediction calculation through the naive bayes model to obtain the probability that the server cluster corresponding to each load parameter increases the computing power or decreases the computing power (as shown in the "calculate probability" column in table 1). Wherein increasing the computing power indicates increasing the number of servers and decreasing the computing power indicates decreasing the number of servers.
TABLE 1
S22: and determining the server increase and decrease quantity of the server cluster in the future period according to the predicted lifting probability of the plurality of load parameters.
After the predicted lifting probabilities corresponding to the load parameters are obtained in the above steps, the lifting probabilities corresponding to the load parameters are summarized, specifically, P (lifting force) =a×c×e×g×i, P (reducing force) =b×d×h×j, where a to j are parameters of the "calculated probability" column in table 1.
And then, judging whether the server increases or decreases, and if the calculation force P is increased and the calculation force P is decreased, triggering the calculation server to horizontally expand and power up. And if P reduces the calculation power > P increases the calculation power, triggering the calculation server to serve the capacitor to power down.
And determining the horizontal expansion of the power of the server (power-on of the server) or calculating the scheduling decision of the capacity reduction of the power of the server (power-off of the server) according to the calculated decision result. Further, after determining to raise the computing power or lower the computing power, the number of server increases or decreases may be further determined based on the trend of variation of the plurality of load parameters. In practical applications, the server increase and decrease may be performed stepwise by presetting a level to avoid frequent variation of the number of servers.
For example, the server increase or decrease is performed in a unit number, and if it is determined that the server cluster increases the computing power, it is determined to increase the number of servers by one unit. Conversely, if it is determined that the server cluster reduces the computational effort, it is determined to reduce the number of servers by one unit.
It should be appreciated that the increase or decrease in the number of servers is related to the size of the server cluster and the actual load parameters, and may be flexibly adjusted according to the actual application.
Based on the solution provided in the foregoing embodiment, optionally, the environmental temperature parameter of the server cluster includes at least one of the following:
the system comprises a rack temperature of a server cluster, a refrigerating capacity parameter of an air conditioning system, an air duct pressure parameter of the air conditioning system, an outdoor temperature parameter of the server cluster, a temperature difference between a hot air duct of the air conditioning system and an outdoor fresh air inlet and an outdoor humidity parameter of the server cluster.
Wherein the rack temperature includes a rack temperature for each unit, may be used to calculate an average rack temperature for the server cluster. The air duct pressure comprises air inlet duct pressure and air outlet duct pressure, and the air duct pressure can be divided into indoor air duct pressure and outdoor air duct pressure.
By the scheme provided by the embodiment of the application, the temperature parameters can be acquired from a plurality of points in the environment where the server cluster is located, so that the temperature where the server cluster is located and the cooling efficiency where the server cluster is located can be acquired more accurately. Under the condition that the air conditioning system comprises outdoor ventilation pipelines and indoor ventilation pipelines, outdoor environment temperature can be obtained, comprehensive determination of a temperature control strategy is facilitated, indoor and outdoor temperature difference is flexibly called to perform temperature control, and energy conservation and emission reduction are facilitated.
Based on the solution provided in the foregoing embodiment, optionally, the environmental temperature parameter in which the server cluster is located includes a plurality of items, and the temperature adjustment policy includes an air circulation policy.
The air circulation strategy can comprise an indoor circulation strategy and an indoor and outdoor circulation strategy, and under the condition that outdoor air accords with temperature control conditions, the outdoor air can be called to directly perform temperature control on the server cluster, so that energy consumed by an air conditioning system for performing temperature control is reduced.
As shown in fig. 3a, the step S13 includes:
s31: and inputting the multiple environmental temperature parameters into a parameter prediction model based on a naive Bayes algorithm to obtain prediction circulation strategies respectively corresponding to the multiple environmental temperature parameters in the future period.
The parametric prediction model of the naive bayes algorithm applied in the step of the present application may be identical to the model described in the step S21 of the above embodiment. In the step, a plurality of environmental temperature parameters are respectively input into the parameter prediction model to obtain prediction circulation strategies respectively corresponding to the environmental temperature parameters.
For example, as shown in the following table 2, each environmental temperature parameter shown in the following "condition category" column is applied, and the prediction calculation is performed by the naive bayes model, so as to obtain the probability that the server cluster corresponding to each environmental temperature parameter switches the outer loop or the inner loop (as shown in the "calculated probability" column in table 2). The switching outer circulation indicates that outdoor air is introduced into the server cluster to realize indoor and outdoor air circulation, the switching inner circulation indicates that indoor air is introduced into the server cluster, and outdoor air is not used for air circulation.
TABLE 2
S32: and determining an air circulation strategy of the server cluster in a future period according to the prediction circulation strategies respectively corresponding to the environmental temperature parameters, wherein the air circulation strategy is used for indicating the air conditioning system to execute air internal circulation or air external circulation.
After the prediction loop strategies corresponding to the environmental temperature parameters are obtained in the above steps, the prediction loop strategies are summarized, specifically, P (switching outer loop) =a×c×g×i×k, P (switching inner loop) =b×d×f×h×j×l, where the parameters a to l are all parameters in the "calculated probability" column in table 2.
And then executing the judgment of the air circulation strategy, if the P switch outer circulation is greater than the P switch inner circulation, triggering the air conditioner switch outer circulation, and if the P switch inner circulation is greater than the P switch outer circulation, triggering the air conditioner switch inner circulation and outer circulation. The determined air circulation strategy is used for controlling the air conditioning system to execute the internal and external circulation actions in the fresh air mode.
According to the scheme provided by the embodiment of the application, decision judgment is carried out by combining the current server cluster running state data according to the temperature condition of the outdoor air, and the scheme can be used for controlling a fresh air suction/hot air discharge system of a data center to dynamically judge whether to use internal air circulation or switch to external fresh air suction. The scheme combines an intelligent calculation result with an automatic switching means, and can control the air conditioning system to operate with a more economical and flexible energy-saving strategy, so that energy conservation and emission reduction are realized on the basis of realizing effective control of the temperature of the server cluster.
The air circulation strategy determined in the scheme can be particularly used for controlling fresh air suction/hot air discharge equipment in an air conditioning system and is used for meeting the requirements of intelligent fresh air management. According to the scheme, outdoor temperature change is flexibly applied, and along with seasonal change and day-and-night temperature difference change, the scheme can flexibly call outdoor air to perform temperature control, so that energy full utilization is realized.
Fig. 3b shows a schematic control flow diagram of an air circulation strategy for executing air external circulation based on fig. 3a, when the temperature of the external air inlet meets the algorithm requirement, the hot air internal circulation system after the heat dissipation of the rack can be closed, the hot air is discharged to the outdoor environment, and the outdoor low-temperature air is sucked for refrigeration circulation.
Specifically, after the external circulation mode is judged to be switched, hot air after heat dissipation of the air conditioning system is discharged to the outdoor environment, low-temperature air sucked into the outdoor air conditioner air inlet is matched with decision calculation judgment of the refrigerating output of the air conditioner clusters, when the refrigerating output is confirmed to be reduced, the number of working equipment for refrigerating the air conditioner clusters is automatically adjusted, or the total power of refrigerating equipment is reduced, the total refrigerating output of the air conditioner clusters is reduced, energy is saved and consumption is reduced in a more economical heat dissipation mode, and the economic benefit is improved.
Fig. 3c shows a schematic control flow diagram of an air circulation strategy for executing air internal circulation based on fig. 3a, when the temperature of an external air inlet is high, external fresh air is cut off, and the internal cooling circulation is performed by using the hot air after the heat dissipation of the rack, so that the economical and environment-friendly temperature control is realized.
Specifically, after judging to switch to the internal circulation mode, external fresh air can be cut off, air after heat dissipation of the rack is recycled, the air enters the internal circulation pipeline, decision calculation and judgment of the refrigerating output of the air conditioner cluster are matched, when the refrigerating output is confirmed to be improved, a redundant standby air conditioner host is awakened or the power of a refrigerating system is improved, the refrigerating output is improved, and heat dissipation of equipment is more accurately and timely carried out.
Based on the solution provided in the foregoing embodiment, optionally, as shown in fig. 4, the method further includes:
S41: and monitoring the operation parameters of the air conditioning system.
According to the scheme provided by the embodiment of the application, the operation efficiency of the air conditioning system is monitored, so that the temperature control effectiveness can be improved, the stable operation of the air conditioning system is ensured, and the energy conservation and emission reduction are realized.
Wherein, the step S13 includes:
S42: and predicting the total power of the power-on servers of the server cluster according to the increase and decrease quantity of the servers.
In the step, the total power of the servers in the power-on state after the number of the servers in the server cluster is changed is calculated according to the number of the increased servers. The total power of the server can reflect the whole energy consumption of the server cluster, and further represents the whole heating trend of the server cluster.
S43: and respectively inputting the rack temperature of the server cluster, the air duct pressure parameter of the air conditioning system, the operation parameter of the air conditioning system and the total power of the power-on server into a parameter prediction model based on a naive Bayesian algorithm to obtain a plurality of air conditioning system refrigerating capacity parameters in the future period.
The parametric prediction model of the naive bayes algorithm applied in the step of the present application may be identical to the model described in the step S21 of the above embodiment. In this step, the four parameters of the rack temperature of the server cluster, the air duct pressure parameter of the air conditioning system, the operation parameter of the air conditioning system, and the total power of the power-on server are respectively input into the parameter prediction model, so as to obtain the air conditioning system refrigerating capacity parameters corresponding to the parameters.
For example, as shown in the following table 3, each parameter shown in the following "condition category" column is applied, and a predictive calculation is performed by the naive bayes model to obtain probabilities of increasing the refrigerating capacity and decreasing the refrigerating capacity corresponding to each parameter (as shown in the "calculated probability" column in table 3). The method comprises the steps of lifting refrigerating capacity to further reduce the temperature of air for entering a server cluster, and lifting the temperature of air for entering the server cluster.
TABLE 3 Table 3
S44: and determining the refrigerating capacity of the air conditioning system of the server cluster in a future period according to the refrigerating capacity parameters of the plurality of air conditioning systems.
After the prediction cycle strategies corresponding to the environmental temperature parameters are obtained in the above steps, the prediction cycle strategies are summarized, specifically, P (increasing refrigeration capacity) =a×c×e×g, P (decreasing refrigeration capacity) =b×d×f×h, where the parameters a to h are all parameters in the "calculated probability" column in table 3.
And then, judging the variation trend of the refrigerating capacity of the air conditioning system of the server cluster, if the P-lifting refrigerating capacity > P-lowering refrigerating capacity > triggers the air conditioner to switch the lifting refrigerating capacity, and if the P-lowering refrigerating capacity > P-lifting refrigerating capacity > triggers the air conditioner to switch the internal lifting refrigerating capacity. And executing an operation decision of whether the refrigerating capacity of the air conditioning unit is increased or reduced according to the calculated decision result.
. Further, after the determination of the increase or decrease in the cooling capacity, a specific value of the cooling capacity variation may be further determined based on the variation trend of the plurality of parameters applied in this example. In practical applications, the cooling capacity can be increased or decreased stepwise by presetting a level to avoid frequent variation of the cooling operation of the air conditioning system.
For example, the cooling capacity increase/decrease is performed in unit parameters, and if it is determined to increase the cooling capacity, it is determined to increase the cooling capacity by one unit parameter. Conversely, if it is determined to decrease the cooling capacity, it is determined to decrease the cooling capacity by one unit parameter.
It should be understood that the increase or decrease of the refrigeration capacity parameter is related to the scale of the server cluster and the actual environmental temperature, and can be flexibly adjusted according to the actual application.
Based on the solution provided in the foregoing embodiment, optionally, as shown in fig. 5a, after step S12, the method further includes:
s51: and if the server increasing and decreasing number indicates that the first number of servers is increased, generating a server increasing and scheduling strategy according to the first number, wherein the server increasing and scheduling strategy is used for executing power-on to the first number of unpowered servers in the server cluster in the future period, and executing service migration to the first number of servers after power-on.
Fig. 5b is a schematic flow chart of increasing the number of servers in a server cluster temperature adjustment method according to an embodiment of the present application. Under the conditions that the overall service volume of the server cluster is increased and the load is increased, according to the parameters of the acquired external service request quantity, the service volume sensed by the server service load monitoring module, the flow of the switching equipment, the port request of the switching equipment, the session of network connection, the comparison of the service volumes in the same time of history and the like, model calculation execution judgment is carried out through a pre-built algorithm module, and then the horizontal capacity expansion of the service is executed according to the judgment result.
When the number of servers is increased, the servers controlling the redundant standby state are powered on to be started so as to join the server cluster. And after the server is powered on, triggering total power data of the current monitored operation, and further controlling the air conditioning system to cooperatively execute the action of matching the temperature regulation strategy. Specifically, the method can comprise the steps of performing actions such as refrigerating capacity adjustment, air duct opening and closing angle adjustment of the rack, increasing or pressurizing cold air input quantity of the rack and the like by the air conditioning system so as to meet the heat dissipation requirement of the newly electrified and expanded computing cluster, realize accurate and effective control of temperature and simultaneously realize energy conservation and consumption reduction.
S52: and if the server increasing and decreasing number indicates that the second number of servers is decreased, generating a server decreasing scheduling policy according to the second number, wherein the server decreasing scheduling policy is used for executing service migration on the second number of servers in the server cluster in the future period, and executing power-down on the second number of servers after executing service migration.
Fig. 5c is a flow chart illustrating a method for adjusting server cluster temperature according to an embodiment of the present application. When the number of servers is reduced, model calculation and execution judgment are carried out through a pre-constructed algorithm module according to the parameters such as the number of acquired external service requests, the service load monitoring module of the servers senses the service volume, the flow of the switching equipment, the port request of the switching equipment, the network connection session, the comparison of the service volumes with the same histories and time, one or more servers in the cluster are isolated from the service cluster according to the judgment result, the services in the isolated servers are migrated to the available servers, and then the isolated servers are powered down through a server power-on and power-off management system. And after the server is powered down, triggering total power data of the current monitored operation, and further controlling the air conditioning system to cooperatively execute the action of matching the temperature regulation strategy. Specifically, the method can include the actions of an air conditioning system for adjusting the refrigerating capacity, adjusting the opening and closing angle of an air channel of a rack, reducing or reducing the cold air input quantity of the rack and the like, so that the energy conservation and consumption reduction are further realized on the basis of meeting the integral heat dissipation requirement of the server cluster after new power-down.
By the scheme provided by the embodiment of the application, the load parameters such as the port quantity of the switching equipment, the access quantity of the service interface monitored on the firewall equipment and the like can be combined with the traffic of the current server cluster to calculate, so that the future load change can be estimated. Therefore, whether the service migration of the service cluster, the operation of the capacity reduction and the horizontal capacity expansion under the corresponding computing cluster are required to be implemented is judged, so that the aims of saving energy and reducing consumption are realized more economically, and the economic benefit is improved.
The scheme provided by the embodiment of the application can dynamically adjust the refrigerating capacity by controlling the air conditioning system to execute the strategy matching action, dynamically manage the running or standby equipment of the air conditioning system cluster, realize accurate refrigerating capacity production, complete the energy saving and consumption reduction of the air conditioning system and realize the improvement of economic benefits.
In addition, the embodiment of the application executes parameter prediction based on a pre-constructed model, flexibly applies air resources formed by indoor and outdoor temperature difference, and controls a fresh air intake or hot air discharge system of a data center to calculate and judge whether an air conditioner is used or is switched into an external circulation. And further, more economic air conditioner operation mode management of internal and external circulation is realized, a more flexible heat dissipation strategy is used, the energy conservation and consumption reduction of a heat dissipation system are completed, and the economic benefit is improved.
In practical application, a set of accurate intelligent energy consumption management system can be built in a data center, monitoring hardware and software of index data to be collected are deployed, load parameters such as port flow of switching equipment, service interface access times monitored by firewall equipment and the like are monitored, and parameter prediction is performed through an artificial intelligent model and a naive Bayesian algorithm. And then according to the predicted parameters of the future period, the power-on lifting calculation force or the power-off capacity reduction operation is carried out on the server cluster, and meanwhile, the air conditioning system is controlled to correspondingly adjust the refrigerating capacity so as to meet the integral heat dissipation requirement of the server cluster, thereby being beneficial to realizing accurate energy consumption management.
In order to solve the problems in the prior art, an embodiment of the present application further provides a server cluster temperature adjusting device 60, as shown in fig. 6, including:
A monitoring module 61 for monitoring load parameters of the server cluster in a history period and environmental temperature parameters of the server cluster;
A prediction module 62 that predicts an increase or decrease in the number of servers of the server cluster over a future period based on the load parameter;
A determining module 63, configured to determine a temperature adjustment strategy in the future period according to the server increasing/decreasing number and the environmental temperature parameter, where the temperature adjustment strategy includes a temperature increasing/decreasing parameter, and a variation trend of the server increasing/decreasing number and a variation trend of the temperature increasing/decreasing parameter are inversely related;
The control module 64 controls the air conditioning system to perform the action of matching the temperature adjustment policy during the future period to perform adjustment to the ambient temperature in which the server cluster is located.
The device provided by the embodiment of the application can monitor the load parameters of the server cluster to predict the load change, so that the temperature regulation strategy to be executed is predetermined before the actual temperature change of the server cluster, and the temperature regulation action of the air conditioning system can be correspondingly regulated along with the load change of the server cluster in the future period, thereby realizing effective temperature control, having the advantage of being effective in time and being beneficial to energy conservation and consumption reduction.
The above modules in the apparatus provided by the embodiment of the present application may further implement the method steps provided by the foregoing method embodiment. Or the device provided by the embodiment of the application may further include other modules besides the above modules, so as to implement the method steps provided by the embodiment of the method. The device provided by the embodiment of the application can realize the technical effects achieved by the embodiment of the method.
Preferably, the embodiment of the present application further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, where the computer program when executed by the processor implements each process of the embodiment of the server cluster temperature adjustment method, and the same technical effects can be achieved, and for avoiding repetition, a description is omitted herein.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the processes of the above embodiment of the server cluster temperature adjustment method, and can achieve the same technical effects, so that repetition is avoided, and no further description is given here. The computer readable storage medium is, for example, a Read-Only Memory (ROM), a random access Memory (Random Access Memory RAM), a magnetic disk or an optical disk.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that 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 one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (10)
1. A method for regulating the temperature of a server cluster, comprising:
monitoring load parameters of a server cluster in a history period and environment temperature parameters of the server cluster;
predicting an increase or decrease in the number of servers of the server cluster within a future period based on the load parameter;
Determining a temperature regulation strategy in the future period according to the server increasing and decreasing number and the environmental temperature parameter, wherein the temperature regulation strategy comprises a temperature rising and decreasing parameter, and the change trend of the server increasing and decreasing number is inversely related to the change trend of the temperature rising and decreasing parameter;
and controlling an air conditioning system to execute the action matched with the temperature regulation strategy in the future period so as to execute regulation on the environment temperature of the server cluster.
2. The method of claim 1, wherein the load parameters of the server cluster include at least one of:
service traffic load parameters, network device traffic parameters, number of network device port requests, number of network link sessions.
3. The method of claim 2, wherein the load parameters of the server cluster include a plurality of terms;
Wherein predicting a server increase or decrease number of the server cluster within a future period based on the load parameter comprises:
Inputting a plurality of load parameters into a parameter prediction model based on a naive Bayesian algorithm to obtain the predicted lifting probability of the plurality of load parameters in the future period;
And determining the server increase and decrease quantity of the server cluster in the future period according to the predicted lifting probability of the plurality of load parameters.
4. The method of claim 2, wherein the environmental temperature parameter at which the server cluster is located comprises at least one of:
the system comprises a rack temperature of a server cluster, a refrigerating capacity parameter of an air conditioning system, an air duct pressure parameter of the air conditioning system, an outdoor temperature parameter of the server cluster, a temperature difference between a hot air duct of the air conditioning system and an outdoor fresh air inlet and an outdoor humidity parameter of the server cluster.
5. The method of claim 4, wherein the environmental temperature parameter at which the server cluster is located comprises a plurality of items, and wherein the temperature regulation strategy comprises an air circulation strategy;
Wherein determining a temperature adjustment strategy in the future period according to the server increase/decrease number and the temperature of the environment comprises:
Inputting a plurality of environmental temperature parameters into a parameter prediction model based on a naive Bayes algorithm to obtain prediction circulation strategies respectively corresponding to the plurality of environmental temperature parameters in the future period;
And determining an air circulation strategy of the server cluster in a future period according to the prediction circulation strategies respectively corresponding to the environmental temperature parameters, wherein the air circulation strategy is used for indicating the air conditioning system to execute air internal circulation or air external circulation.
6. The method as recited in claim 4, further comprising: monitoring an operating parameter of the air conditioning system;
Wherein determining a temperature adjustment strategy within the future period according to the server increase or decrease number and the ambient temperature parameter comprises:
Predicting the total power of the power-on servers of the server cluster according to the increase and decrease quantity of the servers;
Respectively inputting the rack temperature of the server cluster, the air duct pressure parameter of the air conditioning system, the operation parameter of the air conditioning system and the total power of the power-on server into a parameter prediction model based on a naive Bayesian algorithm to obtain a plurality of air conditioning system refrigerating capacity parameters in the future period;
And determining the refrigerating capacity of the air conditioning system of the server cluster in a future period according to the refrigerating capacity parameters of the plurality of air conditioning systems.
7. The method of any of claims 1-6, further comprising, after predicting a server increase or decrease in the server cluster over a future period based on the load parameter:
If the server increasing and decreasing number indicates that a first number of servers are increased, generating a server increasing and scheduling strategy according to the first number, wherein the server increasing and scheduling strategy is used for executing power-on a first number of unpowered servers in the server cluster in the future period, and executing service migration on the first number of servers after power-on;
And if the server increasing and decreasing number indicates that the second number of servers is decreased, generating a server decreasing scheduling policy according to the second number, wherein the server decreasing scheduling policy is used for executing service migration on the second number of servers in the server cluster in the future period, and executing power-down on the second number of servers after executing service migration.
8. A server cluster temperature adjustment apparatus, comprising:
The monitoring module is used for monitoring load parameters of the server cluster in a history period and environment temperature parameters of the server cluster;
A prediction module for predicting the server increase/decrease number of the server cluster in a future period based on the load parameter;
the determining module is used for determining a temperature regulation strategy in the future period according to the server increasing and decreasing number and the environmental temperature parameter, wherein the temperature regulation strategy comprises a temperature increasing and decreasing parameter, and the change trend of the server increasing and decreasing number is inversely related to the change trend of the temperature increasing and decreasing parameter;
and the control module is used for controlling the air conditioning system to execute the action matched with the temperature regulation strategy in the future period so as to execute regulation on the environment temperature of the server cluster.
9. An electronic device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, which when executed by the processor, performs the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211501797.4A CN118093301A (en) | 2022-11-28 | 2022-11-28 | Method and device for regulating temperature of server cluster |
| PCT/CN2023/109059 WO2024113906A1 (en) | 2022-11-28 | 2023-07-25 | Server cluster temperature adjustment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211501797.4A CN118093301A (en) | 2022-11-28 | 2022-11-28 | Method and device for regulating temperature of server cluster |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118093301A true CN118093301A (en) | 2024-05-28 |
Family
ID=91155977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211501797.4A Pending CN118093301A (en) | 2022-11-28 | 2022-11-28 | Method and device for regulating temperature of server cluster |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN118093301A (en) |
| WO (1) | WO2024113906A1 (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4152348B2 (en) * | 2004-06-03 | 2008-09-17 | 株式会社ソニー・コンピュータエンタテインメント | Electronic device cooling apparatus, electronic device system, and electronic device cooling method |
| US8225119B2 (en) * | 2009-02-23 | 2012-07-17 | Microsoft Corporation | Energy-aware server management |
| US8676397B2 (en) * | 2010-12-20 | 2014-03-18 | International Business Machines Corporation | Regulating the temperature of a datacenter |
| US9667498B2 (en) * | 2013-12-20 | 2017-05-30 | Facebook, Inc. | Self-adaptive control system for dynamic capacity management of latency-sensitive application servers |
| CN112539529A (en) * | 2020-11-27 | 2021-03-23 | 珠海格力电器股份有限公司 | Control method and control device of air conditioning system and machine room air conditioning system |
| CN112788101A (en) * | 2020-12-22 | 2021-05-11 | 宇龙计算机通信科技(深圳)有限公司 | Control method, device, terminal and storage medium of server cluster |
-
2022
- 2022-11-28 CN CN202211501797.4A patent/CN118093301A/en active Pending
-
2023
- 2023-07-25 WO PCT/CN2023/109059 patent/WO2024113906A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024113906A1 (en) | 2024-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021063033A1 (en) | Energy consumption model training method for air conditioner and air conditioning system control method | |
| US20210034022A1 (en) | Hvac system with predictive airside control | |
| CN109800066B (en) | Energy-saving scheduling method and system for data center | |
| CN104698843B (en) | A kind of data center's energy-saving control method based on Model Predictive Control | |
| CN102326134B (en) | Energy-aware server admin | |
| WO2021042339A1 (en) | Heat dissipation control and model training method, device and system, and storage medium | |
| CN109375994A (en) | Data center's task temperature prediction and dispatching method based on RBF neural | |
| CN107036238B (en) | Intelligent energy-saving control method for dynamically predicting external air and load | |
| CN110222398B (en) | Artificial intelligence control method and device for water chilling unit, storage medium and terminal equipment | |
| CN115164361B (en) | Data center control method and device, electronic equipment and storage medium | |
| JP2023532492A (en) | Air conditioning control method and device, electrical equipment, medium | |
| Ran et al. | Optimizing energy efficiency for data center via parameterized deep reinforcement learning | |
| CN114909945A (en) | Energy-saving intelligent control method and device for cooling tower, electronic device and medium | |
| CN110762739B (en) | Data center air conditioner control method, device, equipment and storage medium | |
| JP6403185B2 (en) | System control method and system | |
| WO2019227273A1 (en) | Hierarchical concept based neural network model for data center power usage effectiveness prediction | |
| CN111083201B (en) | Energy-saving resource allocation method for data-driven manufacturing service in industrial Internet of things | |
| CN108364114A (en) | A kind of voltage contracting cold-storage apparatus control method, device and voltage contracting cold accumulation system | |
| CN118093301A (en) | Method and device for regulating temperature of server cluster | |
| CN116261300A (en) | Combined optimization method and device for refrigerating equipment and airflow organization of data center | |
| Carnerero et al. | Particle based optimization for predictive energy efficient data center management | |
| KR102566824B1 (en) | A method for training long short term memory network and a method for minimizing energy costs using trained long short term memory network | |
| CN116880163B (en) | Intelligent data center cold source regulation and control method and system | |
| Oyefeso et al. | Control of aggregate air-conditioning load using packetized energy concepts | |
| KR102498340B1 (en) | Apparatus and method for determining an operation schedule of heat pumps based on building energy management system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |