Intelligent linkage control method for data center air conditioner and related device

Abstract

The application provides an intelligent linkage control method and related device of a data center air conditioner, and the method comprises the following steps: obtaining the control quantity of each air conditioner in a data center air conditioner system at a current time and the target value of the running state parameter of a target air conditioner in a future prediction period; predicting the running state parameter of the target air conditioner in the future prediction period according to the control quantity of each air conditioner at the current time and the target value of the running state parameter of the target air conditioner in the future prediction period; optimizing the control quantity of the target air conditioner in the future prediction period according to the error between the predicted value of the running state parameter and the target value of the corresponding running state parameter, and obtaining the control quantity in the future prediction period; and controlling the target air conditioner by using the control quantity in the future prediction period. The application can optimize the control quantity in advance based on the predicted value of the running state parameter, so as to control the target air conditioner by using the optimized control quantity, thereby reducing the overshoot and improving the control stability of the target air conditioner system.

Description

Technical Field

[0001] This invention relates to the field of data center technology, and in particular to an intelligent linkage control method and related device for data center air conditioning. Background Technology

[0002] The rapid development of existing communication network technologies has led to a rapid increase in the scale and power density of data centers. The numerous servers and other electronic devices within data center air conditioning systems generate significant amounts of heat during operation. Therefore, to ensure the safety and high efficiency of these devices, the performance and energy consumption requirements for the target air conditioning systems are also increasing.

[0003] Traditional target air conditioners typically use PID control, which often suffers from overshoot and control lag, resulting in poor control stability and consequently poor energy-saving performance. Summary of the Invention

[0004] In view of this, the present invention provides an intelligent linkage control method and related device for data center air conditioners, which can solve the problem of poor control stability of the target air conditioner.

[0005] In a first aspect, embodiments of the present invention provide an intelligent linkage control method for data center air conditioning, comprising:

[0006] Obtain the control quantities of each air conditioner in the data center air conditioning system at the current moment and the target values ​​of the operating status parameters of the target air conditioner for the future predicted period; the target air conditioner is any air conditioner in the data center air conditioning system.

[0007] Based on the control quantities of each air conditioner at the current moment and the target values ​​of the operating status parameters of the target air conditioner in the future prediction period, the operating status parameters of the target air conditioner in the future prediction period are predicted to obtain the predicted values ​​of the operating status parameters in the future prediction period.

[0008] Based on the error between the predicted value of the operating status parameter of the target air conditioner and the corresponding target value of the operating status parameter in the future prediction period, the control quantity of the target air conditioner in the future prediction period is optimized to obtain the control quantity in the future prediction period.

[0009] The target air conditioner is controlled using control variables for a future predicted time period.

[0010] Secondly, embodiments of the present invention provide an intelligent linkage control device for data center air conditioning, comprising:

[0011] The data acquisition module is used to acquire the control quantities of each air conditioner in the data center air conditioning system at the current moment and the target values ​​of the operating status parameters of the target air conditioner for the future prediction period; the target air conditioner is any air conditioner in the data center air conditioning system.

[0012] The prediction module is used to predict the operating status parameters of the target air conditioner in the future prediction period based on the control quantity of each air conditioner at the current time and the target value of the operating status parameters of the target air conditioner in the future prediction period, so as to obtain the predicted value of the operating status parameters in the future prediction period.

[0013] The control quantity optimization module is used to optimize the control quantity of the target air conditioner in the future prediction period based on the error between the predicted value of the operating status parameter of the target air conditioner in the future prediction period and the corresponding target value of the operating status parameter, so as to obtain the control quantity in the future prediction period.

[0014] An air conditioning control module is used to control the target air conditioner using control quantities for a future predicted time period.

[0015] Thirdly, embodiments of the present invention provide a monitoring host, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described in any possible implementation of the first aspect above.

[0016] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in any possible implementation of the first aspect above.

[0017] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:

[0018] This invention, through obtaining the control quantities of each air conditioner in a data center air conditioning system at the current moment and the target values ​​of the operating status parameters of the target air conditioner for a predicted future period, can predict the operating status parameters for the next moment based on the control quantities of each air conditioner at the current moment and the target values ​​of the operating status parameters for the next moment, thus obtaining predicted values ​​of the operating status parameters. Based on the error between the predicted values ​​of the operating status parameters for the next moment and the target values ​​of the operating status parameters, the control quantities for the next moment are optimized, resulting in the control quantities for the next moment. Finally, the control quantities for the next moment are used to control the target air conditioner. This embodiment can predict the operating status parameters of the target air conditioner for a predicted future period based on the control quantities of all air conditioners in the data center air conditioning system, achieving intelligent linkage control of the data center air conditioning, improving the accuracy of the predicted operating status parameters, and optimizing the control quantities for the next moment in advance based on the predicted operating status parameter values. This allows for the gradual control of the target air conditioner using the optimized control quantities, avoiding lag control problems, reducing overshoot, improving the control stability of the target air conditioning system, and enhancing the energy-saving effect of the air conditioning. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the implementation of the intelligent linkage control method for data center air conditioning provided in this embodiment of the invention.

[0021] Figure 2 This is a flowchart illustrating the intelligent linkage control method for data center air conditioning provided in this embodiment of the invention.

[0022] Figure 3 This is a schematic diagram of the intelligent linkage control device for data center air conditioning provided in an embodiment of the present invention;

[0023] Figure 4 This is a schematic diagram of the monitoring host provided in an embodiment of the present invention. Detailed Implementation

[0024] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0025] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0026] See Figure 1 The document illustrates a flowchart of the implementation of the intelligent linkage control method for data center air conditioning provided in an embodiment of the present invention, which is described in detail below:

[0027] S101: Obtain the control quantity of each air conditioner in the data center air conditioning system at the current moment and the target value of the operating status parameter of the target air conditioner in the future prediction period; the target air conditioner is any air conditioner in the data center air conditioning system.

[0028] The execution subject of the method provided in this embodiment can be the monitoring host of the data center air conditioning system.

[0029] In this embodiment, the operating status parameters of the target air conditioner are parameters used to represent the output status of the target air conditioner, specifically including the actual return air temperature, actual outlet air temperature, actual return air humidity, cooling capacity, and fan speed. The control quantities are the adjustment quantities of the internal components of the air conditioner; specifically including compressor frequency, fan speed, electric heating on / off status, target return air temperature, and target outlet air temperature.

[0030] S102: Based on the control quantities of each air conditioner at the current moment and the target values ​​of the operating status parameters of the target air conditioner in the future prediction period, the operating status parameters of the target air conditioner in the future prediction period are predicted to obtain the predicted values ​​of the operating status parameters in the future prediction period.

[0031] In this embodiment, each air conditioner in the data center air conditioning system uploads its operating status data to the monitoring host through the COM port. The monitoring host periodically outputs control quantities for each air conditioner through control logic and then sends control commands back to each air conditioner to complete energy-saving linkage control.

[0032] Specifically, since all the air conditioners in the data center air conditioning system are located in the same space, the control quantities of other air conditioners besides the target air conditioner will also affect the operating status parameters of the target air conditioner at the next moment. Based on the above principle, this embodiment predicts the operating status parameters at the next moment in advance according to the control quantities of each air conditioner at the current moment and the target value of the operating status parameters of the target air conditioner at the next moment, which can improve the accuracy of the prediction of the operating status parameters.

[0033] S103: Based on the error between the predicted value of the operating status parameter of the target air conditioner in the future prediction period and the corresponding target value of the operating status parameter, optimize the control quantity of the target air conditioner in the future prediction period to obtain the control quantity in the future prediction period.

[0034] S104: The target air conditioner is controlled using control variables for a future predicted time period.

[0035] In this embodiment, the optimized control quantity enables the operating state parameters at the next moment to reach the target value of the operating state parameters in a gradual manner, thereby reducing overshoot, improving the control stability of the target air conditioning system, reducing air conditioning energy consumption, and improving energy-saving effect.

[0036] In one possible implementation, Figure 2 A detailed flowchart of the target air conditioner provided in this embodiment is shown. See also: Figure 2 The specific implementation process of S102 includes:

[0037] The control values ​​of each air conditioner at the current time and the target values ​​of the operating status parameters of the target air conditioner in the future prediction period are input into the operating parameter prediction model, and the predicted values ​​of the operating status parameters of the target air conditioner in the future prediction period are output.

[0038] In this embodiment, for each air conditioner model, a single-unit capability test is performed on the target air conditioner of that model, and the control quantities and operating status parameters of each air conditioner in the data center air conditioning system are recorded under various operating conditions and rack loads. Then, using the control quantities of each air conditioner in the data center air conditioning system at a certain moment and the target values ​​of the operating status parameters of the corresponding air conditioner of that model in a preset time period as input, and using the actual values ​​of the operating status parameters of the corresponding air conditioner of that model in the preset time period as output, a mathematical model is trained to obtain an operating parameter prediction model.

[0039] The future prediction period may include at least one point in time.

[0040] In this embodiment, the application may also use the amount of interference affecting the operating state parameters as another input to train the above model, thereby improving the prediction accuracy of the operating parameter prediction model.

[0041] For example, interference factors include data center rack load, ambient temperature, and ambient humidity.

[0042] In one possible implementation, see Figure 2 The specific implementation process of S103 includes:

[0043] Calculate the error between the predicted values ​​of the operating status parameters of the target air conditioner at each prediction time in the future prediction period and the target values ​​of the operating status parameters at the corresponding prediction time;

[0044] The error corresponding to each prediction period in the future prediction period is input into the optimal controller, and the cost function of the optimal controller is solved to obtain the control quantity of the target air conditioner in the future prediction period.

[0045] The optimal controller is constructed based on the optimal control algorithm.

[0046] Specifically, the optimal control algorithm is used to seek the optimal control strategy under certain constraints, so that the performance index reaches its maximum or minimum value. In this embodiment, the performance index is the difference between the predicted value and the target value of the operating state parameters. The control quantity corresponding to the minimum performance index is determined as the control quantity for the future prediction period.

[0047] In one possible implementation, when optimizing only the control quantity for the next time step, the cost function that can be used is:

[0048] minJ=qe 2 +ru 2 ;

[0049] Where q represents the first adjustment parameter, r represents the second adjustment parameter, e represents the error between the predicted value and the target value of the operating state parameter, and u represents the control quantity.

[0050] Specifically, when optimizing the control variables for future forecast periods, the cost function used is:

[0051]

[0052] Among them, E k Let k represent the error matrix at time k; U represents the transpose of the error matrix at time k. k This represents the control quantity matrix at time k; Let Q represent the transpose of the control matrix at time k; let Q represent the first adjustment parameter matrix; and let R represent the second adjustment parameter matrix.

[0053] Specifically, this embodiment employs a closed-loop optimization control strategy. When predicting the operating state parameters, it can predict the values ​​of the operating state parameters for the next N time moments. Then, the error between the predicted values ​​and the target values ​​of the operating state parameters for the next N time moments is substituted into the cost function. The optimization objective is to minimize the cumulative error over the next N time moments, thereby obtaining the control quantities for the next N time moments. This allows the actual values ​​of the operating state parameters for the next N time moments to gradually approach the target values. Then, the control quantity for the first time moment (the next time moment) is selected from the control quantities for the next time moment to control the target air conditioner. During the optimization process of the control quantity for the next time moment, the optimized control quantity for that time moment is used as the control quantity for the current time moment to optimize the control quantity for the next time moment. Through the above rolling optimization process, this embodiment can improve the robustness of intelligent linkage control of data center air conditioners, reduce system fluctuations, and thus improve the operational safety of data center servers and loads.

[0054] Specifically, the error matrix E k It includes the error between the predicted value and the target value of each operating state parameter at time k, and the control quantity matrix U. k The matrix includes all control variables corresponding to time k. The first adjustment parameter matrix includes the adjustment parameters corresponding to each error, and the second adjustment parameter matrix includes the adjustment parameters corresponding to each control variable.

[0055] For example, when there are two operating state parameters and two control variables, the above cost function can specifically be:

[0056]

[0057] in, Let q1 and q2 represent the errors between the predicted and target values ​​of the two operating state parameters at time k, respectively, and let q1 and q2 represent the adjustment parameters corresponding to different errors. Let r1 and r2 represent the two control variables at time k, respectively, and r1 and r2 represent the adjustment parameters corresponding to different control variables.

[0058] Specifically, the cost function can also be:

[0059]

[0060] The aforementioned cost function, based on minimizing the cumulative error over multiple steps as the optimization objective, focuses on minimizing the error in the final step as the optimization objective. This allows the actual values ​​of the target air conditioning operating state parameters to gradually approach the target values ​​of the operating state parameters, reducing overshoot and improving control robustness.

[0061] In one possible implementation, see Figure 2 Following S103, the method provided in this embodiment further includes:

[0062] Determine whether the control quantity of the target air conditioner at the next moment is within a first threshold range; the first threshold range includes a maximum critical value and a minimum critical value.

[0063] If the control quantity of the target air conditioner is not within the first threshold range at the next moment, then the first critical value is used as the control quantity at the next moment to control the target air conditioner.

[0064] The first threshold value is the threshold value closest to the control quantity of the target air conditioner at the next moment.

[0065] Specifically, if the control quantity of the target air conditioner at the next moment is greater than the maximum threshold value, then the maximum threshold value is used as the control quantity for the target air conditioner at the next moment; if the control quantity of the target air conditioner at the next moment is less than the minimum threshold value, then the minimum threshold value is used as the control quantity for the target air conditioner at the next moment. If the control quantity of the target air conditioner at the next moment is within the first threshold range, then the control quantity of the target air conditioner at the next moment is used to control the target air conditioner.

[0066] For example, when the control quantity is the outlet air temperature, the first threshold range can be 18–27°C. If the calculated control quantity for the target air conditioner at the next moment is 17°C, then 18°C ​​is used as the control quantity for the target air conditioner at the next moment. If the calculated control quantity for the target air conditioner at the next moment is 29°C, then 28°C is used as the control quantity for the target air conditioner at the next moment. This is to avoid the problem of poor temperature control effect caused by the control quantity being too low or too high.

[0067] In one possible implementation, the control quantity includes at least one; after S103, the method provided in this embodiment further includes:

[0068] After optimizing the control quantity of the target air conditioner for the future forecast period to obtain the control quantity for the future forecast period, the method further includes:

[0069] Determine whether the control quantity of the target air conditioner at the next moment is within the corresponding first preset range;

[0070] If the control quantity of the target air conditioner at the next moment is not within the corresponding first preset range, then the control quantity at the current moment is used to control the air conditioner, and the control quantity at the current moment is returned to the method of predicting the operating status parameters of the target air conditioner in the future prediction period based on the control quantity of each air conditioner at the current moment and the target value of the operating status parameters of the target air conditioner in the future prediction period, and then continuing to execute the predicted value of the operating status parameters in the future prediction period.

[0071] If the control quantity at the next moment satisfies the corresponding constraint condition, then the control quantity at the next moment is used to control the target air conditioner.

[0072] In this embodiment, each control quantity corresponds to a constraint condition. For example, the compressor frequency corresponds to the frequency adjustment range, and the fan speed corresponds to the speed adjustment range. If the control quantity output by the optimal controller at the next moment satisfies the corresponding constraint condition, then the control quantity is used to control the target air conditioner. If it does not satisfy the constraint condition, then the control quantity is used as the control quantity at the current moment, and the above algorithm is used again to optimize the control quantity at the next moment until the control quantity at the next moment satisfies the corresponding constraint condition.

[0073] In one possible implementation, the operating status parameters include the outlet air temperature, and correspondingly, the control variables include the target value of the outlet air temperature, the fan speed and the compressor operating frequency, and the disturbance variables include the cabinet load and the ambient temperature.

[0074] In one possible implementation, the operating status parameters include the outlet air humidity, and correspondingly, the control variables may include the compressor operating frequency and the electric heating on / off status, and the disturbance variables may include the ambient humidity and the cabinet load.

[0075] The above method can optimize the control quantity for the next moment by predicting the operating state parameters of the next moment, thereby using the optimized control quantity to control the target air conditioner, reducing system overshoot, reducing compressor operating energy consumption, solving the control lag problem, improving the stability of the target air conditioning system and improving energy saving effect.

[0076] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0077] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0078] Figure 3 A schematic diagram of the intelligent linkage control device for data center air conditioning provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0079] like Figure 3 As shown, the intelligent linkage control device 100 for data center air conditioning includes:

[0080] The data acquisition module 110 is used to acquire the control quantities of each air conditioner in the data center air conditioning system at the current moment and the target values ​​of the operating status parameters of the target air conditioner in the future prediction period; the target air conditioner is any air conditioner in the data center air conditioning system.

[0081] The prediction module 120 is used to predict the operating status parameters of the target air conditioner in the future prediction period based on the control quantity of each air conditioner at the current time and the target value of the operating status parameters of the target air conditioner in the future prediction period, so as to obtain the predicted value of the operating status parameters in the future prediction period.

[0082] The control quantity optimization module 130 is used to optimize the control quantity of the target air conditioner in the future prediction period based on the error between the predicted value of the operating status parameter of the target air conditioner in the future prediction period and the corresponding target value of the operating status parameter, so as to obtain the control quantity in the future prediction period.

[0083] The target air conditioning control module 140 is used to control the target air conditioning using control quantities for a future predicted time period.

[0084] In one possible implementation, the prediction module 120 includes:

[0085] The control values ​​of each air conditioner at the current time and the target values ​​of the operating status parameters of the target air conditioner in the future prediction period are input into the operating parameter prediction model, and the predicted values ​​of the operating status parameters of the target air conditioner in the future prediction period are output.

[0086] In one possible implementation, the prediction module 120 further includes:

[0087] The control quantities of each air conditioner at the current time, the target values ​​of the operating status parameters of the target air conditioner in the future prediction period, and the disturbance quantities that affect the control of the operating status parameters are input into the operating parameter prediction model, and the predicted values ​​of the operating status parameters of the target air conditioner in the future prediction period are output.

[0088] In one possible implementation, the control quantity tuning module 130 includes:

[0089] Calculate the error between the predicted values ​​of the operating status parameters of the target air conditioner at each prediction time in the future prediction period and the target values ​​of the operating status parameters at the corresponding prediction time;

[0090] The error corresponding to each prediction period in the future prediction period is input into the optimal controller, and the cost function of the optimal controller is solved to obtain the control quantity of the target air conditioner in the future prediction period.

[0091] The optimal controller is constructed based on the optimal control algorithm.

[0092] In one possible implementation, the cost function is:

[0093]

[0094] Among them, E k Let k represent the error matrix at time k; U represents the transpose of the error matrix at time k. k This represents the control quantity matrix at time k; Let Q represent the transpose of the control matrix at time k; let Q represent the first adjustment parameter matrix; and let R represent the second adjustment parameter matrix.

[0095] In one possible implementation, the intelligent linkage control device 100 for data center air conditioning further includes a model training module for:

[0096] Build machine learning models;

[0097] Obtain the control variables of each air conditioner in the data center air conditioning system, as well as the target values ​​and actual values ​​of the operating status parameters of each air conditioner over a period of time.

[0098] The control values ​​of each air conditioner in the data center air conditioning system at the first moment and the target values ​​of the operating status parameters of a single air conditioner in a preset period are used as inputs, and the actual values ​​of the operating status parameters of the single air conditioner in the preset period are used as outputs to generate training samples; the first moment is any moment in the operation of the air conditioner, and the preset period is the period after the first moment;

[0099] The machine learning model is trained using multiple training samples to obtain the running parameter prediction model.

[0100] In one possible implementation, the future prediction period includes the next moment; the intelligent linkage control device 100 for data center air conditioning further includes a control constraint module for:

[0101] Determine whether the control quantity of the target air conditioner at the next moment is within a first threshold range; the first threshold range includes a maximum critical value and a minimum critical value.

[0102] If the control quantity of the target air conditioner is not within the first threshold range at the next moment, then the first critical value is used as the control quantity at the next moment to control the target air conditioner.

[0103] The first threshold value is the threshold value closest to the control quantity of the target air conditioner at the next moment.

[0104] In one possible implementation, the operating status parameters include the actual value of the outlet air temperature, and correspondingly, the control variables include the target value of the outlet air temperature, the fan speed and the compressor operating frequency, and the disturbance variables include the cabinet load and the ambient temperature.

[0105] The aforementioned device can predict the operating status parameters of a target air conditioner in a future forecast period based on the control quantities of all air conditioners in the data center air conditioning system. This enables intelligent linkage control of the data center air conditioners, improves the accuracy of operating status parameter prediction, and optimizes the control quantities for the next moment in advance based on the predicted operating status parameter values. The optimized control quantities are then used to gradually control the target air conditioner, avoiding lag control problems, reducing overshoot, improving the control stability of the target air conditioning system, and enhancing the energy-saving effect of the air conditioning.

[0106] The intelligent linkage control device for data center air conditioning provided in this embodiment can be used to execute the above-described intelligent linkage control method embodiment for data center air conditioning. Its implementation principle and technical effect are similar, and will not be described again here.

[0107] Figure 4 This is a schematic diagram of a monitoring host provided in an embodiment of the present invention. Figure 4 As shown, the monitoring host 4 in this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, it implements the steps in the above-described embodiments of the intelligent linkage control method for various data center air conditioners, for example... Figure 1 Steps 101 to 104 are shown. Alternatively, when the processor 40 executes the computer program 42, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 3 The functions of modules 110 to 140 are shown.

[0108] For example, the computer program 42 can be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 42 in the monitoring host 4.

[0109] The monitoring host 4 can be a desktop computer, laptop, handheld computer, or cloud server, etc. The monitoring host 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that... Figure 4 This is merely an example of monitoring host 4 and does not constitute a limitation on monitoring host 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, the monitoring host may also include input / output devices, network access devices, buses, etc.

[0110] The processor 40 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0111] The memory 41 can be an internal storage unit of the monitoring host 4, such as a hard drive or memory of the monitoring host 4. The memory 41 can also be an external storage device of the monitoring host 4, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the monitoring host 4. Furthermore, the memory 41 can include both internal storage units and external storage devices of the monitoring host 4. The memory 41 is used to store the computer program and other programs and data required by the monitoring host. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0112] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0113] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0114] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0115] In the embodiments provided by this invention, it should be understood that the disclosed device / monitoring host and method can be implemented in other ways. For example, the device / monitoring host embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0116] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0117] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0118] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the above embodiments of the intelligent linkage control method for various data center air conditioners. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately added to or subtracted from the content as required by the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium may not include electrical carrier signals and telecommunication signals.

[0119] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for intelligent linkage control of data center air conditioning, characterized in that, include: Obtain the control quantities of each air conditioner in the data center air conditioning system at the current moment and the target values ​​of the operating status parameters of the target air conditioner for the future predicted period; the target air conditioner is any air conditioner in the data center air conditioning system. Based on the control quantities of each air conditioner at the current moment and the target values ​​of the operating status parameters of the target air conditioner in the future prediction period, the operating status parameters of the target air conditioner in the future prediction period are predicted to obtain the predicted values ​​of the operating status parameters in the future prediction period. Based on the error between the predicted value of the target air conditioner's operating status parameters and the corresponding target value of the operating status parameters in the future forecast period, the control quantity of the target air conditioner in the future forecast period is optimized to obtain the control quantity for the future forecast period. The target air conditioner is controlled using control variables for a future predicted time period; The step of optimizing the control quantity of the target air conditioner for the future forecast period based on the error between the predicted value of the operating status parameter of the target air conditioner and the corresponding target value of the operating status parameter for the future forecast period, to obtain the control quantity for the future forecast period, includes: Calculate the error between the predicted values ​​of the operating status parameters of the target air conditioner at each prediction time in the future prediction period and the target values ​​of the operating status parameters at the corresponding prediction time; The error corresponding to each prediction period in the future prediction period is input into the optimal controller, and the cost function of the optimal controller is solved to obtain the control quantity of the target air conditioner in the future prediction period. The optimal controller is constructed based on the optimal control algorithm; The step of predicting the operating status parameters of the target air conditioner for the future prediction period based on the control quantities of each air conditioner at the current moment and the target values ​​of the operating status parameters of the target air conditioner for the future prediction period, to obtain the predicted values ​​of the operating status parameters for the future prediction period, includes: The control values ​​of each air conditioner at the current time and the target values ​​of the operating status parameters of the target air conditioner in the future prediction period are input into the operating parameter prediction model, and the predicted values ​​of the operating status parameters of the target air conditioner in the future prediction period are output. The method further includes: Build machine learning models; Obtain the control variables of each air conditioner in the data center air conditioning system, as well as the target values ​​and actual values ​​of the operating status parameters of each air conditioner over a period of time. The control values ​​of each air conditioner in the data center air conditioning system at the first moment and the target values ​​of the operating status parameters of a single air conditioner in a preset period are used as inputs, and the actual values ​​of the operating status parameters of the single air conditioner in the preset period are used as outputs to generate training samples; the first moment is any moment in the operation of the air conditioner, and the preset period is the period after the first moment; The machine learning model is trained using multiple training samples to obtain the running parameter prediction model.

2. The intelligent linkage control method for data center air conditioning according to claim 1, characterized in that, The step of predicting the operating status parameters of the target air conditioner for the future prediction period based on the control quantities of each air conditioner at the current moment and the target values ​​of the operating status parameters of the target air conditioner for the future prediction period, to obtain the predicted values ​​of the operating status parameters for the future prediction period, includes: The control quantities of each air conditioner at the current time, the target values ​​of the operating status parameters of the target air conditioner in the future prediction period, and the disturbance quantities that affect the control of the operating status parameters are input into the operating parameter prediction model, and the predicted values ​​of the operating status parameters of the target air conditioner in the future prediction period are output.

3. The intelligent linkage control method for data center air conditioning according to claim 1, characterized in that, The future prediction period includes the next moment; after optimizing the control quantity of the target air conditioner in the future prediction period to obtain the control quantity for the future prediction period, the method further includes: Determine whether the control quantity of the target air conditioner at the next moment is within a first threshold range; the first threshold range includes a maximum critical value and a minimum critical value. If the control quantity of the target air conditioner is not within the first threshold range at the next moment, then the first critical value is used as the control quantity at the next moment to control the target air conditioner. The first threshold value is the threshold value closest to the control quantity of the target air conditioner at the next moment.

4. The intelligent linkage control method for data center air conditioning according to claim 2, characterized in that, Operating status parameters include the actual value of the outlet air temperature. Correspondingly, control variables include the target value of the outlet air temperature, the fan speed and the compressor operating frequency. Interference variables include the cabinet load and the ambient temperature.

5. An intelligent linkage control device for data center air conditioning, characterized in that, include: The data acquisition module is used to acquire the control quantities of each air conditioner in the data center air conditioning system at the current moment and the target values ​​of the operating status parameters of the target air conditioner for the future prediction period; the target air conditioner is any air conditioner in the data center air conditioning system. The prediction module is used to predict the operating status parameters of the target air conditioner in the future prediction period based on the control quantity of each air conditioner at the current time and the target value of the operating status parameters of the target air conditioner in the future prediction period, so as to obtain the predicted value of the operating status parameters in the future prediction period. The control quantity optimization module is used to optimize the control quantity of the target air conditioner in the future prediction period based on the error between the predicted value of the operating status parameter of the target air conditioner in the future prediction period and the corresponding target value of the operating status parameter, so as to obtain the control quantity in the future prediction period. An air conditioning control module is used to control the target air conditioner using control quantities for a future predicted time period; The control quantity optimization module includes: Calculate the error between the predicted values ​​of the operating status parameters of the target air conditioner at each prediction time in the future prediction period and the target values ​​of the operating status parameters at the corresponding prediction time; The error corresponding to each prediction period in the future prediction period is input into the optimal controller, and the cost function of the optimal controller is solved to obtain the control quantity of the target air conditioner in the future prediction period. The optimal controller is constructed based on the optimal control algorithm; The prediction module is used to: input the control quantities of each air conditioner at the current time and the target values ​​of the operating status parameters of the target air conditioner in the future prediction period into the operating parameter prediction model, and output the predicted values ​​of the operating status parameters of the target air conditioner in the future prediction period; The device further includes a model training module for: Build machine learning models; Obtain the control variables of each air conditioner in the data center air conditioning system, as well as the target values ​​and actual values ​​of the operating status parameters of each air conditioner over a period of time. The control values ​​of each air conditioner in the data center air conditioning system at the first moment and the target values ​​of the operating status parameters of a single air conditioner in a preset period are used as inputs, and the actual values ​​of the operating status parameters of the single air conditioner in the preset period are used as outputs to generate training samples; the first moment is any moment in the operation of the air conditioner, and the preset period is the period after the first moment; The machine learning model is trained using multiple training samples to obtain the running parameter prediction model.

6. A monitoring host, characterized in that, Used to establish communication connections with each air conditioner of the data center air conditioning system, and to perform the method as described in any one of claims 1 to 4.

7. A data center air conditioning system, characterized in that, It includes at least one air conditioner and the monitoring host as described in claim 6.

Images