A warm water circulation energy-saving heat dissipation device and heat dissipation system for a high-performance server

Abstract

This application relates to the technical field of non-electric variable control, and specifically relates to a warm water circulation energy-saving heat dissipation device and a heat dissipation system for a high-performance server. The device includes: a heat dissipation data acquisition module for real-time collecting temperature data and power consumption data of the server, and various parameter data of the heat dissipation device; a heat dissipation data analysis module for comprehensively analyzing all data within a preset time period before the current adjustment moment to determine whether to adjust the PID control parameters at the current adjustment moment, including: obtaining the change index, power consumption mutation, temperature change factor, temperature change coefficient, and temperature adjustment index at the current adjustment moment; and then determining whether to adjust the PID control parameters at the current adjustment moment; a control parameter adjustment module for adjusting the PID control parameters at the current adjustment moment. This application aims to adjust the PID control parameters according to the actual situation to improve the adjustment accuracy.

Description

Technical Field

[0001] This application relates to the technical field of non-electric variable control, and particularly to a warm water circulation energy-saving heat dissipation device and a heat dissipation system for a high-performance server. Background Art

[0002] With the development of information technology, the performance and density of data center servers have been continuously improved, resulting in higher heat density. Liquid cooling technology has gradually received extensive attention due to its energy-saving, efficient, and quiet characteristics. During the process of using liquid cooling technology to dissipate heat from servers, a PID (Proportional Integral Derivative) controller is used to maintain the operating temperature of server components (such as CPUs and GPUs) within a preset safe range. According to the actual temperature feedback by sensors, the PID controller dynamically adjusts the pump speed, fan speed, and valve opening to ensure that the water flow rate and temperature are suitable for the current load conditions.

[0003] During the process of adjusting the temperature of the server by the warm water circulation energy-saving heat dissipation system, considering the highly dynamic nature of the server load, the traditional fixed PID control parameters are insufficient to handle all situations, resulting in poor temperature adjustment effects. Therefore, according to the actual situation during the temperature adjustment process, the PID control parameters are dynamically adjusted. Summary of the Invention

[0004] In view of the above, it is necessary to provide a warm water circulation energy-saving heat dissipation device and a heat dissipation system for a high-performance server. Compared with the traditional heat dissipation device for high-performance servers, while ensuring the heat dissipation effect, the parameters of the heat dissipation device are dynamically adjusted according to the actual heat dissipation requirements, avoiding unnecessary energy consumption waste:

[0005] In a first aspect, an embodiment of the present application provides a warm water circulation energy-saving heat dissipation device for a high-performance server, and the device includes:

[0006] A heat dissipation data acquisition module, configured to collect the temperature data and power consumption data of the server in real time, and collect various parameter data of the heat dissipation device in real time, including the inlet water temperature and outlet water temperature of the heat dissipation device, and the water flow rate in the water pipe of the heat dissipation device;

[0007] A heat dissipation data analysis module, configured to preset the adjustment period of the PID control parameters to obtain the current adjustment moment of the PID control parameters, analyze all data within a preset time period, and determine whether to adjust the PID control parameters at the current adjustment moment. The process is as follows:

[0008] Based on the similarity of the change situations between all parameter data except the inlet water temperature and outlet water temperature of the heat dissipation device and all power consumption data, obtain the change index at the current adjustment moment;

[0009] Based on the mutation situation of all power consumption data, obtain the power consumption mutability at the current adjustment moment;

[0010] Based on the difference between the water inlet temperature and the water outlet temperature at each acquisition moment, combined with the water flow velocity at each acquisition moment, obtain the temperature change factor at each acquisition moment; Based on the dispersion degree of all temperature data and the correlation between all power consumption data and all temperature change factors, obtain the temperature change coefficient at the current adjustment moment;

[0011] Based on the power consumption mutability, the change index and the temperature change coefficient, obtain the temperature adjustment index at the current adjustment moment, and determine whether to adjust the PID control parameters at the current adjustment moment;

[0012] The control parameter adjustment module is used to, if the PID control parameters are adjusted, based on the similarity of all data except temperature data between each historical adjustment moment and the current adjustment moment and the similarity of the PID control parameters, obtain each reference adjustment moment at the current adjustment moment, and based on the PID control parameters at the next moment of each reference adjustment moment, combined with the temperature adjustment index, adjust the PID control parameters at the current adjustment moment.

[0013] In one embodiment, the various parameter data of the heat dissipation device further include the pump speed of the water pump in the heat dissipation device, the opening degree of the valve for adjusting the water flow velocity, and the rotation speed of the heat dissipation fan.

[0014] In one embodiment, the expression of the change index is:

[0015] ; where Fr represents the change index at the current adjustment moment; S represents the number of all power consumption data within the preset time period; represents the difference in power consumption data between the qth acquisition moment and the q - 1th acquisition moment within the preset time period; represents the difference in power consumption data between the qth acquisition moment and the q + 1th acquisition moment within the preset time period; Combine the pump speed, rotation speed, opening degree and water flow velocity at each acquisition moment to form a heat dissipation parameter vector, represents the distance of the heat dissipation parameter vector between the qth acquisition moment and the q + 1th acquisition moment within the preset time period; ε represents a preset value greater than 0.

[0016] In one embodiment, the process of obtaining the power consumption mutability is:

[0017] The difference in power consumption data between each acquisition moment and its adjacent acquisition moment is denoted as the power consumption difference at each acquisition moment. The threshold segmentation method is used to obtain the segmentation threshold of the power consumption differences at all acquisition moments, and the power consumption differences greater than the segmentation threshold are denoted as high difference data;

[0018] The expression for the power consumption mutation at the current adjustment moment is:

[0019] ; where, Tn represents the power consumption mutation at the current adjustment moment; A represents the mean of all high difference data; M represents the number of high difference data; S represents the number of all power consumption data within the preset time period; represents the time interval between the moments where the i-th high difference data and the (i + 1)-th high difference data are located; represents the average value of the time intervals of all any two adjacent high difference data; among them, the high difference data are arranged in time sequence.

[0020] In one embodiment, the process of obtaining the temperature change factor is:

[0021] The difference between the water inlet temperature and the water outlet temperature at each acquisition moment is denoted as the temperature difference;

[0022] The temperature change factor is the product of the temperature difference at each acquisition moment and the water flow velocity.

[0023] In one embodiment, the process of obtaining the temperature change coefficient is:

[0024] Calculate the reciprocal of the sum of the dispersion degree and a preset value greater than 0;

[0025] Calculate the correlation coefficient between all power consumption data and all temperature change factors within the preset time period;

[0026] The temperature change coefficient is the product of the reciprocal and the correlation coefficient.

[0027] In one embodiment, the expression for the temperature adjustment index is:

[0028] ; where, Bc represents the temperature adjustment index at the current adjustment moment; Tn represents the power consumption mutation at the current adjustment moment; Fr represents the change index at the current adjustment moment; H represents the temperature change coefficient at the current adjustment moment; norm( ) represents the normalization operation; β represents a preset constant greater than 0.

[0029] In one embodiment, based on the temperature adjustment index, it is determined whether the PID control parameters need to be adjusted at the current adjustment moment. The specific method is as follows: when the temperature adjustment index is less than or equal to the preset adjustment threshold, the PID control parameters at the current adjustment moment are not adjusted; otherwise, the PID control parameters at the current adjustment moment are adjusted.

[0030] In one embodiment, the process of adjusting the PID control parameters at the current adjustment moment is as follows:

[0031] The PID control parameters, pump speed, rotation speed, opening degree, water flow speed, inlet temperature, outlet temperature, and power consumption data at each adjustment moment are combined to form a control vector. According to the distance between the control vectors, all adjustment moments are clustered.

[0032] The remaining adjustment moments in the same clustering cluster as the current adjustment moment are denoted as the respective reference adjustment moments of the current adjustment moment.

[0033] ; where represents the adjusted PID control parameters at the current adjustment moment; Bc represents the temperature adjustment index at the current adjustment moment; Pi represents the PID control parameters at the current adjustment moment; N represents the total number of reference adjustment moments at the current adjustment moment; represents the PID control parameters at the next moment of the u-th reference adjustment moment at the current adjustment moment.

[0034] In a second aspect, an embodiment of the present application further provides a warm water circulation energy-saving heat dissipation system for a high-performance server, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it is used to implement the above-mentioned warm water circulation energy-saving heat dissipation device for a high-performance server.

[0035] The present application has at least the following beneficial effects:

[0036] By analyzing whether various parameter data of the heat dissipation device have changed correspondingly when the power consumption data of the server changes, the present application obtains a change index to reflect the regulation lag of the PID control parameters;

[0037] Furthermore, obtaining the power consumption mutability at the current adjustment moment can promptly detect abnormal changes in power consumption; by calculating the difference between the inlet water temperature and the outlet water temperature and combining with the water flow rate, a temperature change factor can be obtained to analyze the heat dissipation capacity of the heat dissipation device, providing a basis for whether to adjust the PID control parameters; based on the dispersion degree of temperature data and combining with the correlation between power consumption data and the temperature change factor, a temperature change coefficient can be obtained to analyze the adjustment ability of the PID control parameters, helping to understand the effectiveness of the current PID control parameters in regulating the parameters of the heat dissipation device; then, by comprehensively considering the change index, power consumption mutability, and temperature change coefficient, it can be determined whether to adjust the current PID control parameters, making the adjustment more in line with actual requirements. If the parameters of the heat dissipation device are regulated according to the current PID control parameters and the heat dissipation effect is not good, the PID control parameters can be adjusted, and then parameters such as the fan speed and pump speed can be adjusted to avoid unnecessary energy consumption waste and achieve more efficient and energy-saving heat dissipation control. However, if the parameters of the heat dissipation device can adapt to the power consumption change of the server when the parameters of the heat dissipation device are regulated according to the current PID control parameters, the PID control parameters will not be adjusted, avoiding unnecessary adjustment operations and saving time and resources.

[0038] Furthermore, when adjusting the PID control parameters, not only the temperature adjustment index at the current adjustment moment is considered, but also the adjustment moments with similar PID control parameters and heat dissipation device parameters to the current adjustment moment are combined, which can adjust the PID control parameters more meticulously and improve the adjustment accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for describing the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is a block diagram of a warm water circulation energy-saving heat dissipation device for a high-performance server provided by an embodiment of the present application;

[0041] Figure 2 It is a schematic flow chart for obtaining the temperature adjustment index;

[0042] Figure 3 It is a schematic flow chart for determining whether to adjust the PID control parameters. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example", etc. are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary", "or", "for example", etc. is intended to present related concepts in a specific manner.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. It should be understood that unless otherwise specified in this application, " / " means "or".

[0045] In addition, it should be noted that the terms "first" and "second" in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0046] The following specifically describes the specific solution of a warm water circulation energy-saving heat dissipation device for a high-performance server provided by this application with reference to the accompanying drawings.

[0047] Please refer to Figure 1 , which shows a block diagram of a warm water circulation energy-saving heat dissipation device for a high-performance server provided by an embodiment of this application. The device includes: a heat dissipation data acquisition module 101, a heat dissipation data analysis module 102, and a control parameter adjustment module 103.

[0048] The heat dissipation data acquisition module 101 is used to collect the temperature data and power consumption data of the server in real time, and collect various parameter data of the heat dissipation device in real time, including the inlet water temperature and outlet water temperature of the heat dissipation device, and the water flow velocity in the water pipe of the heat dissipation device.

[0049] The heat dissipation device mainly includes a water pump, a heat dissipation fan, a radiator, a water pipe and a water tank. A rotational speed sensor is installed on the motor of the water pump to collect the pump speed in real time; a flow meter is installed in the water pipe to collect the water flow velocity in real time; a temperature sensor is installed at the inlet of the pipeline where water enters the heat dissipation device to collect the inlet water temperature in real time; a temperature sensor is installed at the outlet of the pipeline where water flows out of the heat dissipation device to collect the outlet water temperature in real time; for the valve used to adjust the water flow velocity in the heat dissipation device, the opening degree of the valve is collected in real time through a position sensor; the rotational speed of the heat dissipation fan is collected in real time using a photoelectric sensor. The temperature and power consumption of the server are obtained through the server management interface.

[0050] Real-time collect the temperature data of the server, the power consumption data of the server, the inlet temperature and outlet temperature of the heat dissipation device, as well as multiple parameter data of the heat dissipation device, including the water flow rate in the water pipe, the pump speed of the water pump, the opening degree of the valve for adjusting the water flow rate, and the rotation speed of the heat dissipation fan.

[0051] In this embodiment, the collection frequencies of the temperature data, power consumption data, inlet temperature, outlet temperature, water flow rate, pump speed, opening degree, and rotation speed are all once per second. The value of the collection frequency is preset manually, and the implementer can set it by himself / herself. This application does not have special restrictions.

[0052] In this embodiment, the adjustment period of the control parameters of the PID control algorithm is W1 minutes, and the adjustment periods of the pump speed, rotation speed, opening degree, and water flow rate of the heat dissipation device are all W2 minutes. Among them, the values of W1 and W2 are both preset manually, and the implementer can set them by himself / herself. In this embodiment, the values of W1 and W2 are 10 and 1 respectively.

[0053] The heat dissipation data analysis module 102 is used to preset the adjustment period of the PID control parameters to obtain the current adjustment moment of the PID control parameters, comprehensively analyze all the data within the preset time period before the current adjustment moment, and determine whether to adjust the PID control parameters at the current adjustment moment.

[0054] Since the control parameters of the PID control algorithm are mainly adjusted through the residuals, there is a certain lag in the adjustment process. During the process of the PID control parameters regulating the parameters of the heat dissipation device, if the difference between the server power consumption at the previous moment and the server power consumption at the current moment is large, and the difference between the server power consumption at the current moment and the server power consumption at the next moment is small, if the adjustment result of the PID control parameters is reliable, then the difference between the parameters of each heat dissipation device between the current moment and the next moment is small. Therefore, this application analyzes the PID regulation lag.

[0055] The moment when the control parameters of the PID control algorithm are adjusted is recorded as the adjustment moment. Comprehensively analyze all the data within the preset time period before the current adjustment moment, and determine whether to adjust the PID control parameters at the current adjustment moment. The specific process is as follows:

[0056] Based on the similarity of the change situations between all parameter data except the inlet temperature and outlet temperature of the heat dissipation device and all power consumption data, obtain the change index at the current adjustment moment. The expression is:

[0057] ; In the formula, Fr represents the change index at the current adjustment moment; S represents the number of all power consumption data within the preset time period; Represents the difference in power consumption data between the q-th acquisition moment and the (q - 1)-th acquisition moment within the preset time period; Represents the difference in power consumption data between the q-th acquisition moment and the (q + 1)-th acquisition moment within the preset time period; The pump speed, rotation speed, opening degree, and water flow speed at each acquisition moment are combined to form a heat dissipation parameter vector, Represents the distance between the heat dissipation parameter vectors at the q-th acquisition moment and the (q + 1)-th acquisition moment within the preset time period; ε represents a preset value greater than 0, used to avoid a denominator of 0. The value of ε is preset manually, and the implementer can set it by themselves. In this embodiment, the value of ε is 0.01.

[0058] In this embodiment, the preset time period is the time period between the current adjustment moment and the previous adjacent adjustment moment.

[0059] In this embodiment, the distance between heat dissipation parameter vectors is the Euclidean distance. As other implementation manners, on the basis of being able to measure the distance between heat dissipation parameter vectors, the implementer can use other existing technologies for measurement, such as Manhattan distance, cosine distance, etc. This application does not make special restrictions.

[0060] In this embodiment, during the process of calculating the change index, the differences involved are all absolute values of differences. As other implementation manners, on the basis of being able to measure the difference between two power consumption data, the implementer can use other calculation methods, such as ratio, square of the difference, etc. This application does not make special restrictions.

[0061] It should be noted that: if the difference between the power consumption data of each acquisition moment and its previous acquisition moment is larger, and the difference between the power consumption data of each acquisition moment and its subsequent acquisition moment is smaller, and at the same time the difference between the parameters of each heat dissipation device between each acquisition moment and its subsequent acquisition moment is smaller, then the change situations of the power consumption data and the parameters of each heat dissipation device are more similar, indicating that the regulation lag of the PID control parameters at the current adjustment moment is weaker.

[0062] When the regulation lag of the PID control parameters is stronger, it is more necessary to adjust the PID control parameters. Therefore, it is also necessary to analyze the PID control parameters to obtain their adjustment necessity. During the PID control process, when the stability of the server power consumption change is stronger, the influence brought by the regulation lag of the PID control parameters is smaller. Therefore, it is necessary to analyze in combination with the power change characteristics of the server to determine the influence caused by the regulation lag of the PID control parameters.

[0063] Based on the above analysis, the difference in power consumption data between each acquisition moment and its adjacent acquisition moment is recorded as the power consumption difference at each acquisition moment. The threshold segmentation method is used to obtain the segmentation threshold of the power consumption differences of all acquisition moments, and the power consumption differences greater than the segmentation threshold are recorded as high-difference data.

[0064] In this embodiment, the difference between the power consumption data at each acquisition moment and the power consumption data at the previous adjacent acquisition moment is denoted as the power consumption difference at each acquisition moment. The difference between the power consumption data is the absolute value of the difference. As other implementation manners, on the basis of being able to measure the difference between the power consumption data, the implementer can adopt other calculation methods, such as the square of the difference, etc., and the present application does not make special restrictions.

[0065] In this embodiment, the Otsu threshold segmentation algorithm is used to obtain the segmentation threshold of the power consumption difference at all acquisition moments. The Otsu threshold segmentation algorithm is a well-known technology and will not be elaborated in the present application. As other implementation manners, the implementer can adopt other existing algorithms to obtain the segmentation threshold of the power consumption difference at all acquisition moments, such as global threshold segmentation, iterative threshold segmentation, etc., and the present application does not make special restrictions.

[0066] Based on the mutation situation of all power consumption data, the power consumption mutability at the current adjustment moment is obtained, and the expression is:

[0067] ; in the formula, Tn represents the power consumption mutability at the current adjustment moment; A represents the mean value of all high difference data; M represents the number of high difference data; S represents the number of all power consumption data within the preset time period; represents the time interval between the time when the i-th high difference data and the (i + 1)-th high difference data are located; represents the average value of the time intervals of all any two adjacent high difference data; wherein, the high difference data are arranged in time sequence.

[0068] It should be noted that: when the power consumption difference of the server at adjacent acquisition moments is smaller, and the proportion of the large change in the power consumption of the server is smaller, the regularity of the power consumption change of the server is stronger, indicating that the mutability of the power consumption change of the server is weaker, and the influence of the regulation lag of the PID control parameter on the regulation lag of the parameters of the heat dissipation device is smaller, and it is less necessary to adjust the PID control parameter.

[0069] Arrange all the temperature data within the preset time period in time sequence to form a temperature sequence; arrange all the power consumption data within the preset time period in time sequence to form a power consumption sequence. Then, analyze the temperature change coefficient according to the temperature sequence and the power consumption sequence.

[0070] First, calculate the temperature stability of the server. The specific calculation method is: calculate the dispersion degree of all the data in the temperature sequence, and calculate the reciprocal of the sum of the dispersion degree and a preset value α greater than 0; when the reciprocal is larger, it indicates that the temperature stability of the server is stronger. The purpose of adding α is to avoid the denominator being 0, and the value of α is preset artificially, and the implementer can set it by himself. In this embodiment, the value of α is 0.01.

[0071] In this embodiment, the degree of dispersion of all data in the temperature sequence is the variance. As other implementation manners, on the basis of being able to measure the uneven degree of distribution of all data in the temperature sequence, the implementer can use other existing technologies for measurement, such as the standard deviation, coefficient of variation, etc. This application does not make special restrictions.

[0072] The difference between the water inlet temperature and the water outlet temperature at each collection moment is recorded as the temperature difference. The product of the temperature difference at each collection moment and the water flow velocity is used as the temperature change factor at each collection moment. When the difference between the water inlet temperature and the water outlet temperature is larger and the water flow velocity is larger, the heat dissipation capacity of the heat dissipation device is larger.

[0073] In this embodiment, the difference between the water inlet temperature and the water outlet temperature is the absolute value of the difference. On the basis of being able to measure the difference between the water inlet temperature and the water outlet temperature, the implementer can use other calculation methods, such as the square of the difference, ratio, etc. This application does not make special restrictions.

[0074] Arrange the temperature change factors at all collection moments within the preset time period in chronological order to form a temperature change sequence, and calculate the correlation coefficient between the power consumption sequence and the temperature change sequence. The larger the correlation coefficient, the better the regulation effect of the PID control parameters.

[0075] In this embodiment, the correlation coefficient between the power consumption sequence and the temperature change sequence is the Pearson correlation coefficient. As other implementation manners, on the basis of being able to measure the correlation between the power consumption sequence and the temperature change sequence, the implementer can use other existing technologies to measure the correlation between the power consumption sequence and the temperature change sequence, such as the Spearman correlation coefficient, Kendall rank correlation coefficient, etc. This application does not make special restrictions.

[0076] Further, the product of the reciprocal and the correlation coefficient is used as the temperature change coefficient at the current adjustment moment; when the temperature stability of the server is stronger and the correlation between the heat dissipation capacity and the server power consumption during the PID control process is stronger, the value of the temperature change coefficient is larger, indicating that the adjustment ability of the PID control parameters is stronger.

[0077] Further, based on the power consumption mutation at the current adjustment moment, the change index at the current adjustment moment, and the temperature change coefficient at the current adjustment moment, obtain the temperature adjustment index at the current adjustment moment, and the expression is:

[0078] ; where, Bc represents the temperature adjustment index at the current adjustment moment; Tn represents the power consumption mutability at the current adjustment moment; Fr represents the change index at the current adjustment moment; H represents the temperature change coefficient at the current adjustment moment; norm( ) represents the normalization operation; β represents a preset constant greater than 0, used to avoid the denominator being 0, and the value of β is preset manually, and the implementer can set it by himself. In this embodiment, the value of β is 0.01. In this embodiment, the hyperbolic tangent function is used for the normalization operation.

[0079] It should be noted that: when all the data within the preset time period are analyzed, if the adjustment ability of the PID control parameters is stronger, the power consumption mutability of the server is weaker, and the regulation hysteresis of the PID control parameters is smaller, it indicates that the necessity of adjusting the PID control parameters at the current adjustment moment is smaller. The schematic flow chart for obtaining the temperature adjustment index is as Figure 2 shown.

[0080] Furthermore, the time period between the current adjustment moment and the adjacent next adjustment moment is used as the adjustment interval for the next adjustment moment, and an adjustment threshold is set. If the temperature adjustment index at the current adjustment moment is less than or equal to the preset adjustment threshold, within the adjustment interval of the next adjustment moment after the current adjustment moment, the PID control parameters at the current adjustment moment are still used to regulate the parameters of the heat dissipation device; otherwise, the PID control parameters at the current adjustment moment need to be adjusted. The schematic flow chart for determining whether to adjust the PID control parameters is as Figure 3 shown.

[0081] In this embodiment, the value of the preset adjustment threshold is 0.5, and the value of the preset adjustment threshold is preset manually, and the implementer can set it by himself. This application does not make special restrictions.

[0082] The control parameter adjustment module 103 is used to, if the PID control parameters are adjusted, based on the similarity of all data except the temperature data between each historical adjustment moment and the current adjustment moment and the similarity of the PID control parameters, obtain each reference adjustment moment of the current adjustment moment, and based on the PID control parameters at the next moment of each reference adjustment moment, combine the temperature adjustment index to adjust the PID control parameters at the current adjustment moment.

[0083] The specific method for adjusting the PID control parameters at the current adjustment moment is as follows:

[0084] The PID control parameters, pump speed, rotation speed, opening degree, water flow speed, inlet water temperature, outlet water temperature and power consumption data at each adjustment moment are combined to form a control vector at each adjustment moment, and all adjustment moments are clustered according to the distance between the control vectors. The remaining adjustment moments that are in the same clustering cluster as the current adjustment moment are recorded as each reference adjustment moment of the current adjustment moment.

[0085] In this embodiment, the K-Means algorithm is used to cluster all adjustment moments according to the distance between control vectors, where the distance between control vectors is the Euclidean distance. The K-Means algorithm is a well-known technology and will not be elaborated in this application. Implementers can select other feasible clustering algorithms to cluster all adjustment moments by themselves, and this application does not make special restrictions.

[0086] Furthermore, based on the temperature adjustment index at the current adjustment moment and the PID control parameters at the next moment of each reference adjustment moment at the current adjustment moment, the PID control parameters at the current adjustment moment are adjusted. The expression is:

[0087] ; where represents the adjusted PID control parameter at the current adjustment moment; Bc represents the temperature adjustment index at the current adjustment moment; Pi represents the PID control parameter at the current adjustment moment; N represents the total number of reference adjustment moments at the current adjustment moment; represents the PID control parameter at the next moment of the u-th reference adjustment moment at the current adjustment moment. Among them, the initial value of the control parameter of the PID control algorithm is determined by the decay curve method. The decay curve method is a well-known technology and will not be elaborated in this application.

[0088] Within the adjustment range of the next adjustment moment after the current adjustment moment, the adjusted PID control parameter at the current adjustment moment is used to regulate the heat dissipation device parameters.

[0089] Based on the same inventive concept as the above method, an embodiment of this application also provides a warm water circulation energy-saving heat dissipation system for a high-performance server, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it is used to implement the above-mentioned warm water circulation energy-saving heat dissipation device for a high-performance server.

[0090] In summary, by analyzing whether various parameter data of the heat dissipation device have corresponding changes when the power consumption data of the server changes, this application obtains a change index to reflect the regulation lag of the PID control parameter;

[0091] Furthermore, obtaining the power consumption mutability at the current adjustment moment can promptly detect abnormal changes in power consumption; by means of the difference between the inlet water temperature and the outlet water temperature and in combination with the water flow rate, a temperature change factor is obtained to analyze the heat dissipation capacity of the heat dissipation device, providing a basis for whether to adjust the PID control parameters; based on the dispersion degree of the temperature data and in combination with the correlation between the power consumption data and the temperature change factor, a temperature change coefficient is obtained for analyzing the adjustment ability of the PID control parameters, which helps to understand the effectiveness of the current PID control parameters in regulating the parameters of the heat dissipation device; and then, by comprehensively considering the change index, power consumption mutability and temperature change coefficient, it is determined whether to adjust the current PID control parameters, enabling the adjustment to be more in line with the actual requirements. If regulating the parameters of the heat dissipation device according to the current PID control parameters results in poor heat dissipation effect, the PID control parameters are adjusted, and then parameters such as the fan speed and pump speed are adjusted to avoid unnecessary energy consumption waste and achieve more efficient and energy-saving heat dissipation control. However, if the parameters of the heat dissipation device can adapt to the power consumption change of the server when regulating the parameters of the heat dissipation device according to the current PID control parameters, the PID control parameters are not adjusted, avoiding unnecessary adjustment operations and saving time and resources.

[0092] Furthermore, when adjusting the PID control parameters, not only the temperature adjustment index at the current adjustment moment is considered, but also the adjustment moments with similar PID control parameters and heat dissipation device parameters to the current adjustment moment are combined, which can adjust the PID control parameters more meticulously and improve the adjustment accuracy.

[0093] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code includes one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the block may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, which may depend on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, which may depend on the functions involved. Each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0094] It will be apparent to those skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the basic characteristics of the present application. Therefore, from any point of view, the above-described embodiments of the present application should be regarded as exemplary and non-limiting.

Claims

1. A warm water circulation energy-saving heat dissipation device for a high-performance server, characterized in that, The device includes: A heat dissipation data acquisition module, which is used to acquire the temperature data and power consumption data of the server in real time, and acquire various parameter data of the heat dissipation device in real time, including the inlet temperature and outlet temperature of the heat dissipation device, the water flow velocity in the water pipe of the heat dissipation device, the pump speed of the water pump in the heat dissipation device, the opening degree of the valve for adjusting the water flow velocity, and the rotation speed of the heat dissipation fan; A heat dissipation data analysis module, which is used to preset the adjustment period of the PID control parameters to obtain the current adjustment moment of the PID control parameters, analyze all the data within a preset time period, and judge whether to adjust the PID control parameters at the current adjustment moment. The process is as follows: Obtain the change index at the current adjustment moment, and the expression is: ; where Fr represents the change index at the current adjustment moment; S represents the number of all power consumption data within the preset time period; represents the difference in power consumption data between the q-th acquisition moment and the (q - 1)-th acquisition moment within the preset time period; represents the difference in power consumption data between the q-th acquisition moment and the (q + 1)-th acquisition moment within the preset time period; The pump speed, rotation speed, opening degree, and water flow speed at each acquisition moment are combined to form a heat dissipation parameter vector, represents the distance of the heat dissipation parameter vector between the q-th acquisition moment and the (q + 1)-th acquisition moment within the preset time period; ε represents a preset value greater than 0; Record the difference in power consumption data between each acquisition moment and its adjacent acquisition moment as the power consumption difference at each acquisition moment. Use the threshold segmentation method to obtain the segmentation threshold of the power consumption difference at all acquisition moments, and record the power consumption difference greater than the segmentation threshold as the high difference data; the expression of the power consumption mutation at the current adjustment moment is: ; where, Tn represents the power consumption mutability at the current adjustment moment; A represents the mean value of all high difference data; M represents the number of high difference data; S represents the number of all power consumption data within the preset time period; represents the time interval between the time when the i-th high difference data is located and the time when the i+1-th high difference data is located; represents the average value of the time intervals of all any two adjacent high difference data; wherein, the high difference data is arranged in time sequence; based on the difference between the inlet water temperature and the outlet water temperature at each acquisition moment, combined with the water flow velocity at each acquisition moment, the temperature change factor at each acquisition moment is obtained; based on the dispersion degree of all temperature data and the correlation between all power consumption data and all temperature change factors, the temperature change coefficient at the current adjustment moment is obtained; Based on the power consumption mutation, the change index, and the temperature change coefficient, obtain the temperature adjustment index at the current adjustment moment, and judge whether to adjust the PID control parameters at the current adjustment moment; A control parameter adjustment module, which is used to, if the PID control parameters are adjusted, obtain the reference adjustment moments at the current adjustment moment based on the similarity of all data except the temperature data and the similarity of the PID control parameters between each historical adjustment moment and the current adjustment moment, and adjust the PID control parameters at the current adjustment moment based on the PID control parameters at the next moment of each reference adjustment moment and in combination with the temperature adjustment index.

2. The warm water circulation energy-saving heat dissipation device for a high-performance server according to claim 1, characterized in that, The process of obtaining the temperature change factor is as follows: Record the difference between the inlet temperature and the outlet temperature at each acquisition moment as the temperature difference; The temperature change factor is the product of the temperature difference at each acquisition moment and the water flow velocity.

3. The warm water circulation energy-saving heat dissipation device for a high-performance server according to claim 1, wherein, The process of obtaining the temperature change coefficient is as follows: Calculate the reciprocal of the sum of the dispersion degree and a preset value greater than 0; Calculate the correlation coefficient between all the power consumption data and all the temperature change factors within the preset time period; The temperature change coefficient is the product of the reciprocal and the correlation coefficient.

4. The warm water circulation energy-saving heat dissipation device for a high-performance server according to claim 1, characterized in that, The expression of the temperature adjustment index is: ; where, Bc represents the temperature adjustment index at the current adjustment moment; Tn represents the power consumption mutation at the current adjustment moment; Fr represents the change index at the current adjustment moment; H represents the temperature change coefficient at the current adjustment moment; norm( ) represents the normalization operation; β represents a preset constant greater than 0.

5. The warm water circulation energy-saving heat dissipation device for a high-performance server according to claim 1, characterized in that, The method for judging whether to adjust the PID control parameters at the current adjustment moment is as follows: when the temperature adjustment index is less than or equal to the preset adjustment threshold, do not adjust the PID control parameters at the current adjustment moment; otherwise, adjust the PID control parameters at the current adjustment moment.

6. The warm water circulation energy-saving heat dissipation device for a high-performance server according to claim 1, characterized in that, The process of adjusting the PID control parameters at the current adjustment moment is as follows: Form a control vector with the PID control parameters, pump speed, rotation speed, opening degree, water flow velocity, inlet temperature, outlet temperature, and power consumption data at each adjustment moment, and cluster all the adjustment moments according to the distance between the control vectors; Record the remaining adjustment moments in the same clustering cluster as the current adjustment moment as the reference adjustment moments at the current adjustment moment; ; where represents the adjusted PID control parameter at the current adjustment moment; Bc represents the temperature adjustment index at the current adjustment moment; Pi represents the PID control parameter at the current adjustment moment; N represents the total number of reference adjustment moments at the current adjustment moment; represents the PID control parameter at the next moment of the u-th reference adjustment moment at the current adjustment moment.

7. A warm water circulation energy-saving heat dissipation system for a high-performance server, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it is used to implement the warm water circulation energy-saving heat dissipation device of the high-performance server according to any one of claims 1-6.

Images