Temperature control method, device and system for data center machine room, medium and product

Abstract

The invention discloses a temperature control method, device and system for a data center machine room, a medium and a product. The method comprises the following steps: constructing a temperature model and an active-disturbance-rejection controller of the data center machine room; based on a particle swarm algorithm and the temperature model, setting parameters of the active-disturbance-rejection controller to obtain a set active-disturbance-rejection controller; and controlling the temperature of the data center machine room based on the set active-disturbance-rejection controller. According to the application, the active-disturbance-rejection controller is adopted to control the operation of the temperature control system of the data center machine room so as to improve the response speed and robustness of the temperature control of the data center machine room, and since the active-disturbance-rejection control is insensitive to the precision of the temperature model of the data center machine room, the modeling demand and difficulty of the temperature model are reduced; parameters of the active-disturbance-rejection controller are set based on the global search capability of the particle swarm algorithm, the set active-disturbance-rejection controller can achieve a better temperature control effect under different load scenes of the data center machine room, and the temperature control precision is improved.

Description

Technical Field

[0001] The present application relates to temperature control technology, and in particular to a temperature control method, device, system, medium and product for a data center computer room. Background Art

[0002] The data center room is the core of modern information technology infrastructure, used to host servers, storage devices, network devices, etc. Since the equipment in the data center room generates a lot of heat during operation, in order to avoid the high performance and stable operation of the equipment due to the high or low temperature inside the room, it is crucial to maintain the temperature inside the data center room within an appropriate temperature range for the operation of the data center room.

[0003] In the related art, the temperature control system of the data center room usually uses a proportional-integral-derivative (PID) controller to detect and adjust the temperature of the data center room. Among them, the proportional term of the PID control is used to output the deviation between the current temperature and the target temperature, the integral term is used to control the steady-state error, and the differential term reflects the temperature change rate. Based on the synergistic effect of the three components of proportional, integral and differential, the temperature of the data center room is stabilized near the target temperature. However, in actual applications, it is found that the use of the PID control method to adjust the temperature of the data center room still has the following problems: the control effect of the PID control is strongly dependent on the parameter configuration, the PID control lacks self-learning and adaptive capabilities, and because there are many interference items affecting the internal temperature, in order to avoid oscillation or overcharging during the control process, the parameter setting process of the PID controller is too complicated; due to the uncertainty of the dynamic load of the data center room and the changes in external environmental factors, the PID controller has limited capabilities for the fluctuating heat dissipation requirements, and it is difficult to timely and effectively control the response speed and overshoot. Summary of the invention

[0004] In view of this, embodiments of the present application provide a temperature control method, device, system, medium and product for a data center computer room, aiming to improve the temperature stability of the data center computer room.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides a temperature control method for a data center computer room, the method comprising:

[0007] Build a temperature model and active disturbance rejection controller for the data center room;

[0008] Based on the particle swarm algorithm and the temperature model, the parameters of the active disturbance rejection controller are adjusted to obtain a adjusted active disturbance rejection controller;

[0009] Based on the tuned active disturbance rejection controller, the temperature of the data center computer room is controlled.

[0010] In the above solution, the step of constructing a temperature model of a data center computer room includes:

[0011] Obtaining environmental parameters of a data center computer room and operating parameters of each device inside the data center computer room;

[0012] A temperature model of the data center computer room is constructed based on the environmental parameters and the operating parameters.

[0013] In the above solution, constructing the temperature model of the data center computer room based on the environmental parameters and the operating parameters includes:

[0014] Based on the environmental parameters, construct a structural model of the data center computer room;

[0015] Based on a computational fluid dynamics (CFD) simulation tool and the structural model, the temperature field inside the data center computer room is calculated to obtain an initial temperature model of the central computer room;

[0016] Based on the environmental parameters and the operating parameters, the parameters of the initial temperature model are configured to obtain the temperature model.

[0017] In the above scheme, an active disturbance rejection controller is constructed, including:

[0018] In the framework of active disturbance rejection control, a tracking differentiator, a nonlinear feedback model and an extended state observer are constructed.

[0019] Based on the temperature range of the data center room, initial parameters are configured for the tracking differentiator, the nonlinear feedback model and the extended state observer to obtain an active disturbance rejection controller;

[0020] Among them, the input of the tracking differentiator is the target temperature, and the tracking differentiator is used to transform the target temperature; the expanded state observer is used to observe the actual temperature of the data center room and the control quantity output by the active disturbance rejection controller, and estimate the compensation gain, and the compensation gain is used to correct the output of the nonlinear feedback model to obtain the control quantity output by the active disturbance rejection controller; the input of the nonlinear feedback model is the output error of the tracking differentiator, and the nonlinear feedback model is used to transform the output error of the tracking differentiator based on a nonlinear function; the control quantity output by the active disturbance rejection controller is used to control the operation of the temperature control system of the data center room.

[0021] In the above solution, the step of adjusting the parameters of the active disturbance rejection controller based on the particle swarm algorithm and the temperature model includes:

[0022] Based on the temperature model and the active disturbance rejection controller, a temperature control model of the data center computer room is constructed;

[0023] Based on particles of the particle swarm, multiple values ​​are assigned to parameters of the active disturbance rejection controller;

[0024] Running the temperature control model;

[0025] Based on the output of the temperature control model, an optimal parameter combination is determined, and the parameters of the active disturbance rejection controller are adjusted.

[0026] In the above solution, determining the optimal parameter combination based on the output of the temperature control model includes:

[0027] Calculating the fitness of the corresponding particle based on the output of the temperature control model;

[0028] Based on the fitness of the corresponding particle, updating the optimal position of the corresponding particle and the global optimal position of the particle swarm, and updating the speed and position of the particles in the particle swarm;

[0029] If it is determined that the preset convergence condition is met, the optimal parameter combination is determined based on the current optimal position of the particle and the global optimal position of the particle group.

[0030] In the above solution, the particle swarm-based particles assign multiple values ​​to the parameters of the active disturbance rejection controller, including:

[0031] Construct an initial particle swarm;

[0032] Assigning values ​​to the parameters of the active disturbance rejection controller based on the particles in the initial particle swarm; and

[0033] If it is determined that the preset convergence condition is not met, the parameters of the active disturbance rejection controller are assigned based on the particles in the updated particle swarm.

[0034] In a second aspect, an embodiment of the present application provides a temperature control device for a data center computer room, the control device comprising:

[0035] Building blocks for building temperature models and ADRCs for data center rooms;

[0036] A tuning module, used for tuning the parameters of the active disturbance rejection controller based on a particle swarm algorithm and the temperature model to obtain a tuned active disturbance rejection controller;

[0037] A control module is used to control the temperature of the data center computer room based on the adjusted active disturbance rejection controller.

[0038] In a third aspect, an embodiment of the present application provides a temperature control system for a data center computer room, the temperature control system comprising: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor, when running the computer program, executes the steps of the method described in the first aspect.

[0039] In a fourth aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method of the first aspect are implemented.

[0040] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method in the first aspect.

[0041] The temperature control method of the data center room provided by the embodiment of the present application includes: constructing a temperature model and an auto-disturbance rejection controller of the data center room; adjusting the parameters of the auto-disturbance rejection controller based on the particle swarm algorithm and the temperature model to obtain the adjusted auto-disturbance rejection controller; and controlling the temperature of the data center room based on the adjusted auto-disturbance rejection controller. In this way, in view of the uncertainty of the dynamic load and external environmental factors of the data center room, the embodiment of the present application adopts an auto-disturbance rejection controller to control the operation of the temperature control system of the data center room, and controls each uncertainty factor as a unified "unknown disturbance", which can improve the response speed and robustness of the temperature control of the data center room. Since the auto-disturbance rejection control is insensitive to the accuracy of the temperature model of the data center room, the modeling requirements and difficulty of the temperature model are reduced at the same time; in addition, the embodiment of the present application adjusts the parameters of the auto-disturbance rejection controller based on the global search capability of the particle swarm algorithm, which solves the problem that the parameters of the auto-disturbance rejection controller are too many and difficult to accurately optimize in the temperature control scenario of the data center room. The adjusted auto-disturbance rejection controller can achieve a better temperature control effect in the scenarios of different loads of the data center room, and improves the accuracy of temperature control. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a flow chart of a temperature control method for a data center computer room according to an embodiment of the present application;

[0043] Figure 2 A schematic diagram of a structural model of a data center computer room according to an embodiment of the present application;

[0044] Figure 3 This is a schematic diagram of the structure of the active disturbance rejection controller according to an embodiment of the present application;

[0045] Figure 4This is a schematic diagram of the structure of the temperature control model of the data center computer room in the embodiment of the present application;

[0046] Figure 5 A schematic diagram of the structure of a temperature control device for a data center computer room according to an embodiment of the present application;

[0047] Figure 6 This is a schematic diagram of the structure of the temperature control system of the data center computer room according to the embodiment of the present application. DETAILED DESCRIPTION

[0048] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0050] The present application embodiment provides a temperature control method for a data center computer room, such as Figure 1 As shown, the method includes:

[0051] Step 101, constructing a temperature model and an active disturbance rejection controller of a data center computer room.

[0052] Step 102: Based on the particle swarm algorithm and the temperature model, the parameters of the active disturbance rejection controller are adjusted to obtain a adjusted active disturbance rejection controller.

[0053] Step 103: Control the temperature of the data center computer room based on the tuned active disturbance rejection controller.

[0054] Here, the data center room is the core of modern information technology infrastructure, used to host servers, storage devices, network devices, etc. Since the equipment in the data center room generates a lot of heat when running, in order to avoid the high performance and stable operation of the equipment due to the high or low temperature inside the room, the temperature control system of the data center room is controlled based on the set target temperature to maintain the temperature inside the data center room within an appropriate temperature range.

[0055] Here, the temperature control system of the data center room may be an air conditioning system, which adjusts the temperature inside the data center room by controlling the operation of loads such as ventilators and compressors of the air conditioning system.

[0056] In the related art, the temperature control system of the data center computer room usually uses a PID controller to detect and adjust the temperature inside the data center computer room. Among them, the PID controller, as the core unit of the temperature control system, controls the output based on the actual temperature inside the computer room detected by the temperature sensor to maintain the temperature inside the data center computer room within an appropriate temperature range. Specifically, PID control is based on the coordinated control output of proportional terms, differential terms and integral terms. The proportional term increases or decreases the output based on the deviation between the current actual temperature and the target temperature; if the actual temperature remains above or below the target temperature for a long time, the integral term increases or decreases the output based on the temperature deviation in time to control the steady-state error; the differential term is used to control the speed of change of the actual temperature. If the actual temperature rises or decreases rapidly during the control process, the differential term reduces the output to reduce overshoot. It should be noted that the various devices in the data center computer room cannot be regarded as pure resistive loads during actual operation. The heat generated is closely related to the use of computing resources, storage resources, network resources and other resources of the equipment, and the temperature inside the computer room is directly affected by external environmental factors such as seasons and weather. Therefore, the temperature fluctuation inside the data center computer room is complex and there are many interference items.

[0057] It should be noted that although PID control is a control algorithm with strong adaptability and flexible adjustment, it is widely used in control systems in various fields. However, in actual applications, it is found that when using PID control to adjust the temperature inside the temperature center room, there are the following problems: the control effect of PID control is highly dependent on its own parameter configuration and the model accuracy of the controlled object, and PID control lacks self-learning and adaptive capabilities. Since there are many interference items affecting the internal temperature of the data center room, in order to avoid oscillation or overshoot during the control process, the parameter setting process of the PID controller is too complicated; due to the uncertainty of the dynamic load of the data center room and the changes in external environmental factors, the PID controller has limited capacity for the constantly fluctuating heat dissipation needs, and it is difficult to control the response speed and overshoot in a timely and effective manner.

[0058] It should be noted that the core idea of ​​Active Disturbance Rejection Control (ADRC) is to attribute all uncertainties acting on the controlled object to "unknown disturbances", and estimate and compensate for the disturbances through the input and output of the object; compared with PID control, ADRC has strong anti-interference ability and stronger robustness because it uniformly compensates for all uncertainties and interference terms as "unknown disturbances"; the control effect of ADRC is not sensitive to the model accuracy of the controlled object, and when adjusting parameters, it mainly adjusts the parameters involved in the estimation and compensation of disturbances, and the parameter adjustment is relatively simple.

[0059] It can be understood that in view of the uncertainties of the dynamic loads and external environmental factors of the data center room, the embodiment of the present application adopts an anti-disturbance control controller to control the operation of the temperature control system of the data center room, and controls various uncertain factors as a unified "unknown disturbance". This can improve the response speed and robustness of the temperature control of the data center room. Since the anti-disturbance control is insensitive to the accuracy of the temperature model of the data center room, it also reduces the modeling requirements and difficulty of the temperature model.

[0060] It should be noted that although the parameter tuning process of the ADRC is relatively simple compared to that of the PID control, there are more parameters that need to be tuned. It is difficult to ensure a parameter combination with good control effect by tuning the parameters through conventional manual testing. The embodiment of the present application uses a particle swarm optimization (PSO) algorithm to tune the parameters of the ADRC to improve the accuracy of temperature control inside the computer room of the data center.

[0061] Here, the particle swarm algorithm is an intelligent optimization algorithm that simulates the behavior of bird flocks. The core concept is to treat each particle in the particle swarm as an independent individual. During the iteration process of the particle swarm, the particles are not only restricted by their own evolution, but also can achieve global search capabilities through interactive learning with other particles and adapting to environmental changes.

[0062] It can be understood that the embodiment of the present application adjusts the parameters of the auto-disturbance rejection controller based on the global search capability of the particle swarm algorithm, which solves the problem that the parameters of the auto-disturbance rejection controller are too many and difficult to accurately optimize in the temperature control scenario of the data center computer room. The adjusted auto-disturbance rejection controller can achieve better temperature control effects under different load scenarios in the data center computer room, thereby improving the accuracy of temperature control.

[0063] The following further describes the temperature control method for a data center computer room based on the technical concept of the active disturbance rejection control + particle swarm algorithm parameter tuning of the present application.

[0064] Exemplarily, constructing a temperature model of a data center room includes: acquiring environmental parameters of the data center room and operating parameters of each device inside the data center room; and constructing a temperature model of the data center room based on the environmental parameters and the operating parameters.

[0065] Here, the environmental parameters of the data center room include but are not limited to: the structural shape of the data center room, the internal equipment layout, and the layout of the temperature control system.

[0066] Here, the operating parameters of each device include but are not limited to: the heat generation rate of each device under different load conditions.

[0067] It should be noted that in the related art, when constructing the temperature model of the computer room of a data center, a dummy load test is usually used to obtain the temperature dynamic characteristics inside the computer room, that is, based on the equipment layout inside the computer room, a pure resistive load is used to replace real equipment such as servers, storage devices and network equipment, and the heat dissipation of the equipment is simulated by energizing the pure resistive load. However, although the heat dissipation of the model equipment under different loads is modeled based on the size of the current passing through the pure resistive load, there are actually many types of equipment and many load influencing factors for each device. The test results obtained by the dummy load test have a large deviation from the actual temperature dynamic characteristics inside the computer room, and the process of arranging pure resistive loads in the computer room is cumbersome; in the embodiment of the present application, the temperature model of the computer room of a data center is modeled using a computational fluid dynamics simulation tool, which can not only improve the modeling efficiency, but also more accurately measure the temperature dynamic characteristics inside the computer room.

[0068] Exemplarily, based on environmental parameters and operating parameters, a temperature model of a data center computer room is constructed, including: based on environmental parameters, a structural model of the data center computer room is constructed; based on computational fluid dynamics simulation tools and structural models, the temperature field inside the data center computer room is calculated to obtain an initial temperature model of the center computer room; based on environmental parameters and operating parameters, parameters of the initial temperature model are configured to obtain a temperature model.

[0069] Here, based on the structural shape of the data center room, the internal equipment layout, the layout of the temperature control system, the layout of the air outlet and the air inlet, and other environmental parameters, a structural model of the data center room is constructed, and the structural model is divided into unit areas of a set order of magnitude to form a computing grid. In some embodiments, the structural model of the data center room is as follows: Figure 2 Here, the structural model can be a finite element model.

[0070] It can be understood that the finer the division granularity of the unit area of ​​the structural model, the higher the accuracy of the obtained temperature model of the data center computer room.

[0071] It should be noted that after the structural model of the data center room is constructed, the structural model is numerically solved through the CFD simulation tool. Specifically, the transient and / or steady-state temperature field inside the data center room is calculated through the numerical form of the mass conservation equation, momentum conservation equation, and energy conservation equation. Among them, the mass conservation equation, momentum conservation equation, and energy conservation equation are respectively as follows:

[0072]

[0073]

[0074] Where ρ is the air density; u, v, w are the components of the velocity vector in the x, y, and z directions respectively; U is the resultant velocity; τij is stress tension; c p is the specific heat capacity; λ is the thermal conductivity of air, F x 、F y 、F z are the volume forces in the x, y, and z directions respectively, T is the temperature, S T is the heat generation rate.

[0075] It can be understood that the initial temperature model of the data center room obtained based on the CFD simulation tool can reflect the dynamic characteristics of the room's internal temperature change rate, response time, and relationship with external environmental factors.

[0076] It should be noted that the embodiment of the present application does not specifically limit the CFD simulation tool used to calculate the temperature location inside the data center computer room. For example, the structural model can be numerically solved based on the Ansys Fluent simulation tool.

[0077] Here, after obtaining the initial temperature model of the data center room, the parameters of the initial temperature model are configured based on the heat generation rate of each device; in addition, the fluid properties and boundary conditions in the initial temperature model need to be defined, where the fluid properties include but are not limited to: air density, viscosity and thermal conductivity; boundary conditions include but are not limited to: room outlet temperature and the layout of the air outlet and air inlet. After completing the parameter configuration of the initial temperature model, the temperature model of the data center room is obtained, and the temperature model can simulate the temperature distribution and air flow inside the data center room under different load conditions.

[0078] Exemplarily, after the temperature model of the data center room as the controlled object is constructed, a matching auto-disturbance rejection controller can be constructed. The construction of the auto-disturbance rejection controller includes: constructing a tracking differentiator, a nonlinear feedback model and an extended state observer under the framework of the auto-disturbance rejection control; configuring initial parameters for the tracking differentiator, the nonlinear feedback model and the extended state observer based on the temperature range of the data center room to obtain the auto-disturbance rejection controller. The input of the tracking differentiator is the target temperature, and the tracking differentiator is used to convert the target temperature; the extended state observer is used to observe the actual temperature of the data center room and the control quantity output by the auto-disturbance rejection controller, and estimate the compensation gain, which is used to correct the output of the nonlinear feedback model to obtain the control quantity output by the auto-disturbance rejection controller; the input of the nonlinear feedback model is the output error of the tracking differentiator, and the nonlinear feedback model is used to convert the output error of the tracking differentiator based on a nonlinear function; the control quantity output by the auto-disturbance rejection controller is used to control the operation of the temperature control system of the data center room.

[0079] Here, if Figure 3As shown in the figure, the active disturbance rejection controller consists of three parts: tracking differentiator, nonlinear feedback model and extended state observer.

[0080] Specifically, the input of the tracking differentiator is the target temperature v0. The tracking differentiator is used to transform the target temperature v0 to prevent the target temperature v0 from causing a step change during the control process and causing an impact on the temperature control system. The tracking setting transition process is used to filter the noise interference of the target temperature v0. The form of the tracking differentiator is as follows:

[0081]

[0082] Among them, the fst function can prevent the high-frequency vibration of the temperature control system after entering the steady state, as shown below:

[0083]

[0084] Here, through the conversion of the tracking differentiator, the target temperature v0 is converted into a tracking signal v1 and a differential signal v2; the tracking error e1 is obtained by subtracting the tracking signal v1 from the tracking observation z1, and the differential error e2 is obtained by subtracting the differential signal v2 from the differential observation z2; the tracking error e1 and the differential error e2 are used as input quantities of the nonlinear feedback model, wherein the tracking observation z1 and the differential observation z2 are obtained through the extended state observer.

[0085] Specifically, the tracking error e1 and the differential error e2 are nonlinearly combined to reduce the steady-state error and obtain the initial control amount u0, as shown below:

[0086] u0=K p fal(e1,α1,δ)+K d fal(e2,α2,δ)

[0087]

[0088] Among them, the fal function may not be smooth in a specific interval. During the control process, the non-smooth interval may cause high-frequency vibration in the temperature control system at the linear and nonlinear switching point, and because there are too many parameters that need to be adjusted, the basic fal function cannot meet the control requirements. Considering the above problems, the embodiment of the present application uses a hyperbolic tangent function tanh(x,ξ) similar to the hyperbolic tangent function to improve the fal function to improve the control effect. Among them, the nonlinear function tanh(x,ξ) is specifically as follows:

[0089]

[0090] Among them, the nonlinear feedback model based on the nonlinear function tanh(x,ξ) is specifically as follows:

[0091] u0=K p tanh(e0,ξ2)+K d tanh(e2,ξ2)

[0092] Specifically, the extended state observer regards the changes f caused by other parameters except the control variable as disturbances, and estimates them by observing the differential and total disturbance of the input and output of the controlled object. The extended state observer is specifically shown as follows:

[0093]

[0094] Among them, the tracking observation z1 and the differential observation z2 are used to generate the tracking error e1 and the differential error e2; the compensation gain z3 is used to correct the initial control quantity u0 output by the nonlinear feedback model to obtain the control quantity u output by the anti-disturbance controller, and the control quantity u is used to control the operation of the temperature control system of the data center computer room.

[0095] It is understandable that the parameters of the active disturbance rejection controller are initially configured based on the temperature range of the data center room to avoid excessive parameter setting range and affecting parameter setting efficiency; here, the configured parameters can be part of the parameters of the active disturbance rejection control.

[0096] Here, after completing the initialization construction of the ADRC, the embodiment of the present application adjusts the parameters of the ADRC, wherein the adjusted parameters include but are not limited to: r, K P , K d , β 01 , β 02 and β 03 .

[0097] Exemplarily, based on the particle swarm algorithm and the temperature model, the parameters of the auto-disturbance rejection controller are adjusted, including: constructing a temperature control model of a data center computer room based on the temperature model and the auto-disturbance rejection controller; assigning multiple values ​​to the parameters of the auto-disturbance rejection controller based on particles of the particle swarm; running the temperature control model; determining the optimal parameter combination based on the output of the temperature control model, and adjusting the parameters of the auto-disturbance rejection controller.

[0098] Here, the temperature control model of the data center room is as follows Figure 4 As shown in the figure, after the target temperature is input into the ADRC, the output of the ADRC is used to control the operation of the temperature control system; the output of the temperature control model is the temperature inside the computer room in the temperature model. Based on the temperature inside the computer room and the target temperature, the control effect of the ADRC can be judged.

[0099] It should be noted that in the parameter setting process, the embodiment of the present application assigns the parameters of the self-disturbance rejection controller through the particle swarm algorithm, and determines the control effect corresponding to the current parameter combination based on the output of the temperature control model and updates the particle swarm iteratively. Exemplarily, the parameters of the self-disturbance rejection controller are assigned multiple times, including: constructing an initial particle swarm; assigning the parameters of the self-disturbance rejection controller based on the particles in the initial particle swarm.

[0100] Here, the embodiment of the present application randomly generates an initial particle swarm based on a set parameter range, and particles in the initial particle swarm are randomly assigned initial speeds and positions;

[0101] Exemplarily, based on the output of the temperature control model, determining the optimal parameter combination includes: calculating the fitness of the corresponding particle based on the output of the temperature control model; updating the optimal position of the corresponding particle and the global optimal position of the particle swarm based on the fitness of the corresponding particle, and updating the speed and position of the particles in the particle swarm; if it is determined that the preset convergence condition is met, determining the optimal parameter combination based on the current optimal position of the corresponding particle and the global optimal position of the particle swarm.

[0102] Here, after running the temperature control model, the fitness of the particles of the current particle swarm is calculated based on the temperature inside the computer room in the temperature model, the optimal position of the individual particle is updated based on the calculated fitness of the individual particle, and the global optimal position of the particle swarm is updated based on the calculated fitness of each particle in the particle swarm; after updating the optimal position of the individual particle and the global optimal position of the particle swarm, the speed and position of each particle in the particle swarm are updated, wherein the speed and position of the particle are specifically updated according to the following formula:

[0103]

[0104] Among them, v i is the velocity of particle i, x i is the position of particle i, w is the inertia weight, p i (k) is the individual extreme value, r1 and r2 are random numbers between [0,1], and c1 and c2 are learning factors.

[0105] Here, the parameter tuning process pre-sets the convergence condition, which may be, but is not limited to: the particle swarm is updated to a set number of times. After updating the speed and position of the particles in the particle swarm, if it is determined that the convergence condition is met, the current optimal particle is decoded into the optimal parameter combination and used as the parameter after the ADRC is tuned.

[0106] Exemplarily, assigning values ​​to the parameters of the active disturbance rejection controller multiple times also includes: if it is determined that a preset convergence condition is not met, assigning values ​​to the parameters of the active disturbance rejection controller based on particles in the updated particle swarm.

[0107] It is understandable that after updating the speed and position of the particles in the particle swarm, if it is determined that the convergence condition has not been met, the above steps are repeated to update the optimal parameter combination in the global search.

[0108] It can be understood that the temperature control system of the data center room is controlled based on the adjusted anti-disturbance controller, which improves the adaptability of the temperature control system to changes in dynamic loads and external environmental factors, so as to maintain the temperature inside the data center room near the target temperature.

[0109] In order to implement the method of the embodiment of the present application, the embodiment of the present application also provides a temperature control device for a data center computer room, which corresponds to the above-mentioned temperature control method, and each step in the above-mentioned temperature control method embodiment is also fully applicable to the embodiment of the present device.

[0110] The present application embodiment provides a temperature control device for a data center computer room, such as Figure 5 As shown, the control device includes: a construction module 501, a tuning module 502 and a control module 503. The construction module 501 is used to construct a temperature model and an auto-disturbance rejection controller of a data center computer room; the tuning module 502 is used to tune the parameters of the auto-disturbance rejection controller based on a particle swarm algorithm and a temperature model to obtain a tuned auto-disturbance rejection controller; the control module 503 is used to control the temperature of the data center computer room based on the tuned auto-disturbance rejection controller.

[0111] In some embodiments, the construction module 501 is specifically used to: obtain environmental parameters of the data center room and operating parameters of each device inside the data center room; and construct a temperature model of the data center room based on the environmental parameters and operating parameters.

[0112] In some embodiments, construction module 501 is specifically used to: construct a structural model of a data center room based on environmental parameters; calculate the temperature field inside the data center room based on computational fluid dynamics simulation tools and structural models to obtain an initial temperature model of the center room; configure parameters of the initial temperature model based on environmental parameters and operating parameters to obtain a temperature model.

[0113] In some embodiments, the construction module 501 is specifically used to: construct a tracking differentiator, a nonlinear feedback model and an extended state observer under the framework of active disturbance rejection control; based on the temperature range of the data center computer room, configure initial parameters for the tracking differentiator, the nonlinear feedback model and the extended state observer to obtain an active disturbance rejection controller; wherein the input of the tracking differentiator is the target temperature, and the tracking differentiator is used to convert the target temperature; the extended state observer is used to observe the actual temperature of the data center computer room and the control quantity output by the active disturbance rejection controller, and estimate the compensation gain, and the compensation gain is used to correct the output of the nonlinear feedback model; the input of the nonlinear feedback model is the output error of the tracking differentiator, and the nonlinear feedback model is used to convert the output error of the tracking differentiator based on a nonlinear function, and output the control quantity output by the active disturbance rejection controller after the compensation gain is corrected; the control quantity output by the active disturbance rejection controller is used to control the operation of the temperature control system of the data center computer room.

[0114] In some embodiments, the tuning module 502 is specifically used to: construct a temperature control model of a data center computer room based on a temperature model and an auto-disturbance rejection controller; assign multiple values ​​to the parameters of the auto-disturbance rejection controller based on particles of a particle swarm; run the temperature control model; determine the optimal parameter combination based on the output of the temperature control model, and tune the parameters of the auto-disturbance rejection controller.

[0115] In some embodiments, the tuning module 502 is specifically used to: calculate the fitness of the corresponding particle based on the output of the temperature control model; update the optimal position of the corresponding particle and the global optimal position of the particle swarm based on the fitness of the corresponding particle, and update the speed and position of the particles in the particle swarm; if it is determined that the preset convergence condition is met, determine the optimal parameter combination based on the current optimal position of the particle and the global optimal position of the particle swarm.

[0116] In some embodiments, the tuning module 502 is specifically used to: construct an initial particle swarm; assign parameters of the auto-disturbance rejection controller based on particles in the initial particle swarm; and, if it is determined that a preset convergence condition is not met, assign parameters of the auto-disturbance rejection controller based on particles in the updated particle swarm.

[0117] It should be noted that: the temperature control device provided in the above embodiment only uses the division of the above program modules as an example when performing temperature control. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the temperature control device provided in the above embodiment and the temperature control method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0118] In order to implement the method of the embodiment of the present application, the embodiment of the present application also provides a temperature control system for a data center computer room. Figure 6 Only an exemplary structure of the temperature control system is shown, not all structures, and can be implemented as needed. Figure 6 Partial or complete structure shown.

[0119] like Figure 6 As shown, the temperature control system 600 provided in the embodiment of the present application includes: at least one processor 601, a memory 602, a user interface 603 and at least one network interface 604. The various components in the temperature control system 600 are coupled together through a bus system 605. It can be understood that the bus system 605 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 605 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, in Figure 6 Various buses are labeled as bus system 605 .

[0120] The user interface 603 may include a display, a keyboard, a mouse, a trackball, a click wheel, keys, buttons, a touch pad or a touch screen.

[0121] The memory 602 in the embodiment of the present application is used to store various types of data to support the operation of the temperature control system 600. Examples of such data include: any computer program used to operate on the temperature control system 600.

[0122] The temperature control method of the front-end application framework disclosed in the embodiment of the present application can be applied to the processor 601, or implemented by the processor 601. The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the temperature control method of the front-end application framework can be completed by the hardware integrated logic circuit or software instructions in the processor 601. The above-mentioned processor 601 can be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 601 can implement or execute the methods, steps and logic block diagrams of the front-end application framework disclosed in the embodiment of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the memory 602, and the processor 601 reads the information in the memory 602, and completes the steps of the temperature control method of the front-end application framework provided in the embodiment of the present application in combination with its hardware.

[0123] In an exemplary embodiment, the temperature control system 600 can be implemented by one or more application-specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD), FPGA, general-purpose processor, controller, microcontroller (MCU), microprocessor, or other electronic components to execute the temperature control method of the aforementioned front-end application framework.

[0124] It can be understood that the memory 602 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).The memories described in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0125] In an exemplary embodiment, the present application embodiment further provides a storage medium, namely a computer storage medium, which may be a computer-readable storage medium, for example, a memory 602 storing a computer program, and the computer program may be executed by a processor 601 of a temperature control system 600 to complete the steps described in the temperature control method of the front-end application framework of the present application embodiment. The computer-readable storage medium may be a memory such as a ROM, a PROM, an EPROM, an EEPROM, a Flash Memory, a magnetic surface memory, an optical disk, or a CD-ROM.

[0126] In an exemplary embodiment, the present application also provides a computer program product, including a computer program, which can be executed by the processor 601 of the temperature control system 600 to complete the steps of the temperature control method of the front-end application framework of the present application embodiment. It should be noted that: "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0127] In addition, the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0128] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A temperature control method for a data center computer room, characterized in that: The method comprises: Build a temperature model and active disturbance rejection controller for the data center room; Based on the particle swarm algorithm and the temperature model, the parameters of the active disturbance rejection controller are adjusted to obtain a adjusted active disturbance rejection controller; Based on the tuned active disturbance rejection controller, the temperature of the data center computer room is controlled.

2. The method according to claim 1, characterized in that The step of constructing a temperature model of a data center computer room includes: Obtaining environmental parameters of a data center computer room and operating parameters of each device inside the data center computer room; A temperature model of the data center computer room is constructed based on the environmental parameters and the operating parameters.

3. The method according to claim 2, characterized in that The step of constructing a temperature model of the data center computer room based on the environmental parameters and the operating parameters includes: Based on the environmental parameters, construct a structural model of the data center computer room; Based on the computational fluid dynamics (CFD) simulation tool and the structural model, the temperature field inside the data center computer room is calculated to obtain an initial temperature model of the central computer room; Based on the environmental parameters and the operating parameters, the parameters of the initial temperature model are configured to obtain the temperature model.

4. The method according to claim 1, characterized in that Build an active disturbance rejection controller, including: In the framework of active disturbance rejection control, a tracking differentiator, a nonlinear feedback model and an extended state observer are constructed. Based on the temperature range of the data center room, initial parameters are configured for the tracking differentiator, the nonlinear feedback model and the extended state observer to obtain an active disturbance rejection controller; Among them, the input of the tracking differentiator is the target temperature, and the tracking differentiator is used to transform the target temperature; the expanded state observer is used to observe the actual temperature of the data center computer room and the control quantity output by the active disturbance rejection controller, and estimate the compensation gain, and the compensation gain is used to correct the output of the nonlinear feedback model; the input of the nonlinear feedback model is the output error of the tracking differentiator, and the nonlinear feedback model is used to transform the output error of the tracking differentiator based on a nonlinear function, and output the control quantity output by the active disturbance rejection controller after correction by the compensation gain; the control quantity output by the active disturbance rejection controller is used to control the operation of the temperature control system of the data center computer room.

5. The method according to claim 4, characterized in that The step of adjusting the parameters of the active disturbance rejection controller based on the particle swarm algorithm and the temperature model includes: Based on the temperature model and the active disturbance rejection controller, a temperature control model of the data center computer room is constructed; Based on particles of the particle swarm, multiple values ​​are assigned to parameters of the active disturbance rejection controller; Running the temperature control model; Based on the output of the temperature control model, an optimal parameter combination is determined, and the parameters of the active disturbance rejection controller are adjusted.

6. The method according to claim 5, characterized in that The determining of the optimal parameter combination based on the output of the temperature control model comprises: Calculating the fitness of the corresponding particle based on the output of the temperature control model; Based on the fitness of the corresponding particle, updating the optimal position of the corresponding particle and the global optimal position of the particle swarm, and updating the speed and position of the particles in the particle swarm; If it is determined that the preset convergence condition is met, the optimal parameter combination is determined based on the current optimal position of the particle and the global optimal position of the particle group.

7. The method according to claim 6, characterized in that The particles based on the particle swarm assign values ​​to the parameters of the active disturbance rejection controller multiple times, including: Construct an initial particle swarm; Assigning values ​​to the parameters of the active disturbance rejection controller based on the particles in the initial particle swarm; and If it is determined that the preset convergence condition is not met, the parameters of the active disturbance rejection controller are assigned based on the particles in the updated particle swarm.

8. A temperature control device for a data center computer room, characterized in that: The control device comprises: Building blocks for building temperature models and ADRCs for data center rooms; A tuning module, used for tuning the parameters of the active disturbance rejection controller based on a particle swarm algorithm and the temperature model to obtain a tuned active disturbance rejection controller; A control module is used to control the temperature of the data center computer room based on the adjusted active disturbance rejection controller.

9. A temperature control system for a data center computer room, characterized in that: The temperature control system comprises: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor is used to execute the steps of the method according to any one of claims 1 to 7 when running the computer program.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images