A method, system and medium for optimizing energy consumption of a refrigeration system for a computing center

Abstract

This invention discloses a method, system, and medium for optimizing the energy consumption of a refrigeration system in a computing center. The method includes configuring the control environment and its control factors required for the refrigeration system; measuring the thermal state of the computing center's host system and environmental information about the control environment; and using a pre-trained refrigeration control decision model to determine control actions for the refrigeration system's control factors based on the host system's thermal state and the environmental information about the control environment. The invention aims to adaptively control and adjust the refrigeration system based on the physical thermal state of the host system in a large-scale computing center, achieving real-time, refined, and intelligent regulation of the refrigeration system's energy consumption, effectively meeting the needs of energy conservation and emission reduction.

Description

Technical Field

[0001] The present invention belongs to the technical field of refrigeration energy consumption optimization, and in particular relates to a method, system and medium for optimizing energy consumption of a refrigeration system for a computing center. Background Art

[0002] With the rapid development of digitalization across society, all industries are in urgent need of computing power. As the primary carrier of computing power, large-scale computing centers have become a vital infrastructure for the digital economy. The construction of large-scale computing centers, such as data centers and supercomputing centers, has entered a new phase of rapid development, further accelerating the industrialization and large-scale application of digital technologies.

[0003] While the mainframe systems in large-scale computing centers provide powerful computing power, they also continuously generate significant amounts of heat. To ensure that all computing components operate within a safe temperature range and achieve optimal performance, the cooling system must provide sufficient cooling capacity. Currently, large-scale computing centers often employ relatively extensive cooling control methods, resulting in significant cooling energy waste. Relevant research shows that the cooling system is the subsystem with the highest energy consumption in large-scale computing centers, aside from the mainframe systems. From a green and energy-saving perspective, optimizing the energy consumption of cooling systems in large-scale computing centers is urgent.

[0004] Currently, there has been a significant amount of research on optimizing the energy consumption of refrigeration systems, primarily focusing on modeling and analyzing refrigeration system energy consumption. Based on the quantitative analysis of the correlation between system energy consumption and key parameters of each device, recommendations are made for optimizing the operating parameters of the refrigeration system, thereby reducing the energy consumption of the refrigeration system. However, the overall structure of the refrigeration system in large-scale computing centers is complex, with a wide variety of functional equipment, a large number of multi-level and mutually constrained features. This leads to complex nonlinear relationships between the various operating parameters of the refrigeration system and the cooling capacity and cooling energy consumption. Furthermore, the operating conditions of the refrigeration equipment may change over time, making it difficult to formulate clear control strategies based on actual cooling needs with existing technologies. Summary of the Invention

[0005] The technical problem to be solved by the present invention is as follows: In response to the above-mentioned problems of the prior art, a method, system and medium for optimizing the energy consumption of a refrigeration system for a computing center are provided. The present invention aims to adaptively control and adjust the refrigeration system according to the physical thermal state of the host system in a large-scale computing center, thereby realizing real-time, refined and intelligent regulation of the energy consumption of the refrigeration system, and effectively meeting the needs of energy conservation and emission reduction.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0007] A method for optimizing energy consumption of a refrigeration system for a computing center comprises the following steps:

[0008] S101, configuring the control environment and control factors required to be enabled for the refrigeration system;

[0009] S102, measuring the thermal status of the host system of the computing center and environmental information of the control environment;

[0010] S103, using a pre-trained refrigeration control decision model to decide a control action for a control factor of the refrigeration system based on the host system thermal state and environmental information of the control environment;

[0011] Before step S103, the process also includes training the refrigeration control decision model:

[0012] S401, constructing a training data sample consisting of the thermal state of the host system of the computing center and environmental information of the control environment, the control action of the control factor, and the cooling efficiency, wherein the environmental information of the control environment includes part or all of the ambient temperature and ambient humidity of the control environment;

[0013] S402, based on the deep deterministic policy gradient algorithm DDPG, the cooling control decision model is trained, and the thermal state of the host system of the computing center and the environmental information of the control environment are used as the "state" of the cooling control decision model, and the control factor of the cooling system is used as the "action" of the cooling control decision model. The action control amplitude is the control range corresponding to the control factor, and the cooling benefit is used as the "reward" of the cooling control decision model. The cooling control decision model is trained through training data samples to establish a mapping relationship between the thermal state of the host system and the environmental information of the control environment, and the control action of the control factor of the cooling system.

[0014] Optionally, step S101 includes:

[0015] S201, configuring the control environment to be enabled according to the preset default control environment;

[0016] S202, respectively configuring subordinate control factors for the enabled control environment, and each configured control factor includes a control factor name and a physical device parameter identifier corresponding to the control factor; the control factors under the host system include part or all of the terminal air supply temperature, terminal air supply volume, terminal water supply temperature, and terminal water supply volume; the control factors under the refrigeration system include part or all of the refrigerator power, pump power, water supply volume, fan speed, and water pump flow rate; the control factors under the computer room environment include part or all of the computer room air conditioning temperature and the computer room air conditioning humidity; the control factors under the outdoor environment include part or all of the outdoor air ventilation volume and the outdoor ventilation duration;

[0017] S203, determine the configuration control range for each control factor, the control range is a triple < u, f, s >, where uIndicates the upper limit of regulation, f Indicates the lower limit of regulation, s Indicates the adjustable range each time.

[0018] Optionally, the default control environment preset in step S201 is represented by a four-tuple:<S, C, H, T> , where S represents the host system; C represents the cooling system; H represents the computer room environment; and T represents the outdoor environment. Configuring the control environment to be enabled includes configuring the control environment to be enabled for each control environment in the preset default control environment using a key-value pair consisting of the control environment and whether it is included in the control strategy. The value of whether it is included in the control strategy is "1" indicating that it is included in the control strategy, and the value of "0" indicates that it is not included in the control strategy.

[0019] Optionally, measuring the thermal state of the host system of the computing center in step S102 includes:

[0020] S301, using a motherboard management controller (BMC) installed and configured on a multi-source heterogeneous computing device of a host system to collect temperature data from various temperature sensors on the computing device, and performing out-of-band collection of the temperature data of the computing device based on the IPMI protocol;

[0021] S302, using a preset aggregation algorithm to determine whether the temperature of the computing device is abnormal using a temperature data set of the computing device;

[0022] S303 , summing the number of computing devices with abnormal temperatures in each preset area of ​​the host system to obtain the total number of computing devices with abnormal temperatures in the host system, which is used as the obtained thermal status of the host system of the computing center.

[0023] Optionally, in step S302, using a preset aggregation algorithm to determine whether the computing device has a temperature abnormality includes: using a preset statistical method to calculate the aggregated temperature value of the computing device for the temperature data set of the computing device, and then determining whether the computing device has a temperature abnormality based on whether the aggregated temperature value exceeds a preset threshold.

[0024] Optionally, the calculation function expression of the cooling benefit is:

[0025] ,

[0026] In the above formula, Represents the cooling efficiency, is a penalty factor with a negative value, is the thermal status of the host system in the computing center, The energy efficiency of the computing center is the ratio of all energy consumption of the computing center to the energy consumption of the host system.

[0027] In addition, the present invention also provides a refrigeration system energy consumption optimization system for a computing center, comprising a microprocessor and a memory connected to each other, wherein the microprocessor is programmed or configured to execute the refrigeration system energy consumption optimization method for a computing center.

[0028] In addition, the present invention also provides a computer-readable storage medium, which stores a computer program or instruction. The computer program or instruction is programmed or configured to execute the energy consumption optimization method for the refrigeration system of the computing center through a processor.

[0029] In addition, the present invention also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the method for optimizing energy consumption of a refrigeration system for a computing center through a processor.

[0030] Compared with the prior art, the present invention mainly has the following advantages: the method for optimizing the energy consumption of the refrigeration system of the computing center of the present invention includes configuring the control environment and its control factors required to be enabled for the refrigeration system; measuring the thermal state of the host system of the computing center and the environmental information of the control environment; using a pre-trained refrigeration control decision model to decide the control action of the control factor of the refrigeration system based on the thermal state of the host system and the environmental information of the control environment. The present invention decides the control action of the control factor of the refrigeration system based on the thermal state of the host system and the environmental information of the control environment, thereby realizing adaptive control and adjustment of the refrigeration system according to the physical thermal state of the host system in a large-scale computing center, and can minimize the energy consumption of the refrigeration system under the premise of ensuring the normal operation of the host system, realize real-time, refined and intelligent control of the energy consumption of the refrigeration system, and effectively meet the needs of energy conservation and emission reduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 Schematic diagram of the basic flow of a method according to embodiment 1 of the present invention.

[0032] Figure 2 Schematic diagram of the basic principle of the method of embodiment 1 of the present invention. DETAILED DESCRIPTION

[0033] Example 1:

[0034] like Figure 1 As shown, the energy consumption optimization method for the refrigeration system of the computing center in this embodiment includes the following steps:

[0035] S101, configuring the control environment and control factors required to be enabled for the refrigeration system;

[0036] S102, measuring the thermal status of the host system of the computing center and environmental information of the control environment;

[0037] S103: Using a pre-trained refrigeration control decision model to decide on a control action for a control factor of the refrigeration system based on the host system thermal state and environmental information of the control environment.

[0038] In this embodiment, the operation and maintenance manager of the large-scale computing center initializes the energy consumption optimization task in step S101 through template parameter configuration. Specifically, step S101 in this embodiment includes:

[0039] S201, configuring the control environment to be enabled according to the preset default control environment;

[0040] S202: Configure the subordinate control factors for the enabled control environment respectively. Each configured control factor includes the control factor name and the physical device parameter identifier corresponding to the control factor. For example, the configuration content of the terminal air conditioner temperature is:

[0041] Terminal air conditioning temperature: end_ac_temp;

[0042] like Figure 2As shown, for each environmental element included in the control strategy, the operation and maintenance management personnel can further configure a specific set of control factors. For example, the control factors under the host system include part or all of the terminal air supply temperature, terminal air supply volume, terminal water supply temperature, and terminal water supply volume; the control factors under the cooling system include part or all of the refrigerator power, pump power, water supply volume, fan speed, and water pump flow rate; the control factors under the computer room environment include part or all of the computer room air conditioning temperature and computer room air conditioning humidity; the control factors under the outdoor environment include part or all of the outdoor air ventilation volume and outdoor ventilation time; Among them, the control factors under the host system are related to the cooling mechanism of the host system. For example, as an optional implementation method, the cooling mechanism of the host system in this embodiment includes a host air cooling unit and a host water cooling unit. The host air cooling unit introduces low-temperature natural wind from the outdoor environment through a fan at the terminal pass position and sends it into each host system in the computer room through a pipe. The host water cooling unit uses a pump at the terminal pass position to send the cooling water cooled by the refrigeration mechanism through a pipe into each host system in the computer room. Therefore, the terminal supply air temperature, terminal supply air volume, terminal supply water temperature, and terminal supply water volume can be used as the control factors under the host system. The control factors under the refrigeration system are related to the refrigeration system of the computer room. The refrigeration system of the computer room generally adopts a dual-medium circulation loop. The dual-medium circulation loops exchange heat through a heat exchanger. The first medium circulation loop is the refrigerant, which is circulated by a pump and cooled by a refrigerator. The second medium circulation loop is water, which is circulated by a water pump and heat exchanged with the computer room by a fan. Therefore, the refrigerator power, pump power, water supply, fan speed, and water pump flow rate can be used as the control factors under the refrigeration system. The control factors under the computer room environment are related to the air-conditioning system of the computer room environment. Therefore, the computer room air-conditioning temperature and computer room air-conditioning humidity can be used as control factors; the control factors under the outdoor environment are related to the ventilation method of the computer room. Therefore, the outdoor air ventilation volume and outdoor ventilation time can be used as control factors;

[0043] S203, determine the configuration control range for each control factor, the control range is a triple < u, f, s >, where u Indicates the upper limit of regulation, f Indicates the lower limit of regulation, s Indicates the adjustable range each time.

[0044] The default control environment preset in step S201 of this embodiment is represented by a quadruple:<S, C, H, T> , where S represents the host system; C represents the cooling system; H represents the computer room environment; and T represents the outdoor environment. Configuring the control environment to be enabled includes configuring the control environment to be enabled for each control environment in the preset default control environment using a key-value pair consisting of the control environment and whether it is included in the control policy. The value of "1" for "whether it is included in the control policy" indicates that it is included in the control policy, and a value of "0" indicates that it is not included in the control policy. For example:

[0045] {

[0046] S:1

[0047] C:1

[0048] H:1

[0049] T:0

[0050] }

[0051] Indicates that the outdoor environment is not included in the control strategy, while the other three control environments are included in the control strategy.

[0052] In step S102 of this embodiment, measuring the thermal status of the host system of the computing center includes:

[0053] S301, using a baseboard management controller (BMC) installed and configured on a multi-source heterogeneous computing device of a host system to collect temperature data from various temperature sensors on the computing device, and performing out-of-band collection of the temperature data of the computing device based on the IPMI (Intelligent Platform Management Interface) protocol;

[0054] S302: A preset aggregation algorithm is used to determine whether a computing device has an abnormal temperature using a collection of temperature data from the computing device. Based on the host system's structure and topology, the system is divided into zones at a granular level, such as a chassis or cabinet, to determine the various zones pre-set on the host system. A data aggregation module is then set up within each zone. This module is responsible for aggregating the raw temperature data of all computing devices within the zone. The aggregate value is the number of computing devices within the zone with abnormal temperatures. The aggregation module reports this aggregate value to the previous control zone, improving data transmission efficiency.

[0055] S303 , summing the number of computing devices with abnormal temperatures in each preset area of ​​the host system to obtain the total number of computing devices with abnormal temperatures in the host system, which is used as the obtained thermal status of the host system of the computing center.

[0056] The aggregation algorithm preset in step S302 of this embodiment is designed in a plug-in manner, and operation and maintenance management personnel can easily configure the required aggregation algorithm. The purpose of the aggregation algorithm is to aggregate and map multiple temperature data of the computing device to determine whether the computing device has a temperature abnormality. The specific mapping method can be used as needed. For example, as an optional implementation, in step S302 of this embodiment, the temperature data set of the computing device is determined to be abnormal using the preset aggregation algorithm. The method includes: using a preset statistical method (such as taking the average value, median value, maximum value, minimum value, etc. in the set) to calculate the aggregate temperature value of the computing device for the temperature data set of the computing device, and then determining whether the computing device has a temperature abnormality based on whether the aggregate temperature value exceeds a preset threshold.

[0057] The cooling control decision model can adopt a desired machine learning model as needed, and establish a mapping relationship between the host system thermal state and the environmental information of the control environment and the control action of the control factor of the cooling system through training. In this embodiment, step S103 also includes training the cooling control decision model:

[0058] S401, constructing a training data sample consisting of the thermal state of the host system of the computing center and environmental information of the control environment, the control action of the control factor, and the cooling efficiency, wherein the environmental information of the control environment includes part or all of the ambient temperature and ambient humidity of the control environment;

[0059] In step S402, a cooling control decision model is trained using the Deep Deterministic Policy Gradient (DDPG) algorithm. The model uses the thermal state of the computing center's host system and the environmental information of the control environment as its "state," the cooling system's control factor as its "action," and the action's control range as the control factor's corresponding control range. The cooling benefit is its "reward." The model is trained using training data samples to establish a mapping relationship between the host system's thermal state and the environmental information of the control environment, and the control actions of the cooling system's control factors. Training the cooling control decision model using the DDPG algorithm requires three pieces of input: "state," "action," and "reward." The "state" is the environmental information of the control environment and the host system's thermal state configured in step S101; the "action" is the cooling system's control factor configured in step S101; the action's control range is the control range corresponding to the control factor; and the "reward" is the cooling benefit evaluation. The trained decision model can directly output the optimal action to be taken next based on the input state, achieving adaptive control of the cooling equipment. This embodiment models the refrigeration system energy consumption optimization problem as a Markov decision process to combine "reward" to train and complete the mapping of "state" and "action", thereby adjusting the operating parameters of the refrigeration system according to the current thermal state of the host system, and minimizing the energy consumption of the refrigeration system while ensuring the normal operation of the host system.

[0060] In this example, a customized cooling benefit evaluation is performed based on the host system's thermal state and system energy consumption, and the control strategy is adjusted using a reinforcement learning model. As an optional implementation, the goal of cooling system energy consumption optimization is to minimize cooling system energy consumption while ensuring the normal operation of the host system. The cooling benefit calculation function is expressed as:

[0061] ,

[0062] In the above formula, Represents the cooling efficiency, is a penalty factor with a negative value, is the thermal status of the host system in the computing center, Power Usage Effectiveness (PUE) is the energy efficiency of a computing center, defined as the ratio of its total energy consumption to the energy consumption of the host system. The above formula indicates that when a computing device in the host system experiences an abnormal temperature, the cooling efficiency is the product of the number of abnormal components and the penalty factor. When all computing devices in the host system are within the normal temperature range, the cooling efficiency is the inverse of the PUE (Power Usage Effectiveness), meaning that the lower the PUE, the higher the cooling efficiency.

[0063] In summary, the cooling system energy consumption optimization method for computing centers in this embodiment is based on a configured cooling energy consumption optimization task generation framework, which improves the applicability and flexibility of the method in this embodiment and can be widely applied in various large-scale computing centers. This embodiment's method, based on a host system thermal state measurement method that integrates software and hardware collaboration and regional data aggregation, improves the efficiency of large-scale heat source data collection and processing, enabling the control program to quickly respond to changes in the host system state. This embodiment's method, a multi-refrigeration device collaborative control method based on reinforcement learning, improves the adaptability and intelligence of the cooling energy consumption optimization process, and can continuously and in real time automatically generate the optimal cooling control strategy based on the host system thermal state and cooling device operating conditions. This embodiment uses the host system thermal state and environmental information of the control environment to determine the control action for the cooling system's control factors. This enables adaptive control and adjustment of the cooling system based on the physical thermal state of the host system in a large-scale computing center. This minimizes cooling system energy consumption while ensuring the normal operation of the host system, achieving real-time, refined, and intelligent control of cooling system energy consumption, effectively meeting the needs of energy conservation and emission reduction.

[0064] Example 2:

[0065] This embodiment is basically the same as the first embodiment, with the main difference being that the method for configuring the control environment to be enabled is different. In this embodiment, configuring the control environment to be enabled includes configuring the control environment to be enabled by using a fixed order of whether each control environment in the preset default control environment is included in the control policy. The value of "1" indicates that the control environment is included in the control policy, and the value of "0" indicates that the control environment is not included in the control policy. For example:

[0066] {1,1,1,0}

[0067] Indicates that the outdoor environment is not included in the control strategy, while the other three control environments are included in the control strategy.

[0068] Example 3:

[0069] This embodiment is substantially the same as the first embodiment, with the primary difference being that the aggregation algorithm preset in step S302 of this embodiment utilizes a machine learning model. This machine learning model is trained to establish a relationship between multiple temperature data sets of a computing device and whether the computing device has a temperature anomaly. During use, the multiple temperature data sets of the computing device are input into the machine learning model to obtain a prediction result regarding whether the computing device has a temperature anomaly. This approach also enables mapping the relationship between multiple temperature data sets of a computing device and whether the computing device has a temperature anomaly.

[0070] Example 4:

[0071] This embodiment is basically the same as the first embodiment, with the main difference being that the cooling control decision model in this embodiment is a machine learning model trained using conventional supervised training. The supervised training enables it to establish a mapping relationship between the thermal state of the host system and the environmental information of the control environment, and the control actions of the control factors of the refrigeration system. Similarly, the mapping between the thermal state of the host system and the environmental information of the control environment, and the control actions of the control factors of the refrigeration system can also be achieved.

[0072] In addition, this embodiment also provides a system for optimizing the energy consumption of a refrigeration system for a computing center, comprising an interconnected microprocessor and memory, wherein the microprocessor is programmed or configured to execute the method for optimizing the energy consumption of a refrigeration system for a computing center. In addition, this embodiment also provides a computer-readable storage medium storing a computer program or instructions, wherein the computer program or instructions are programmed or configured to execute the method for optimizing the energy consumption of a refrigeration system for a computing center via a processor. In addition, this embodiment also provides a computer program product, comprising a computer program or instructions, wherein the computer program or instructions are programmed or configured to execute the method for optimizing the energy consumption of a refrigeration system for a computing center via a processor.

[0073] Those skilled in the art should understand that the technical solution of the present invention can be provided as a method, system, or computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the functions described in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including the instruction device, which implements the function specified in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0074] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the concept of the present invention are within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A method for optimizing energy consumption of a refrigeration system in a computing center, characterized in that: The steps include: S101, configuring the control environment and control factors required to be enabled for the refrigeration system; S102, measuring the thermal status of the host system of the computing center and environmental information of the control environment; S103, using a pre-trained refrigeration control decision model to decide a control action for a control factor of the refrigeration system based on the host system thermal state and environmental information of the control environment; Before step S103, the process also includes training the refrigeration control decision model: S401, constructing training data samples consisting of the thermal status of the host system of the computing center and environmental information of the control environment, the control action of the control factor, and the cooling efficiency, wherein the environmental information of the control environment includes part or all of the ambient temperature and ambient humidity of the control environment; S402: A cooling control decision model is trained using the Deep Deterministic Policy Gradient (DDPG) algorithm. The thermal state of the computing center's host system and environmental information about the controlled environment are used as the "state" of the cooling control decision model. The control factors of the cooling system are used as the "actions" of the cooling control decision model. The action control range is the control range corresponding to the control factors. The cooling benefit is used as the "reward" of the cooling control decision model. The cooling control decision model is trained using training data samples to establish a mapping relationship between the thermal state of the host system, environmental information about the controlled environment, and the control actions of the control factors of the cooling system. Step S101 includes: S201, configuring the control environment to be enabled according to the preset default control environment; S202, respectively configuring subordinate control factors for the enabled control environment, and each configured control factor includes a control factor name and a physical device parameter identifier corresponding to the control factor; the control factors under the host system include part or all of the terminal air supply temperature, terminal air supply volume, terminal water supply temperature, and terminal water supply volume; the control factors under the refrigeration system include part or all of the refrigerator power, pump power, water supply volume, fan speed, and water pump flow rate; the control factors under the computer room environment include part or all of the computer room air conditioning temperature and the computer room air conditioning humidity; the control factors under the outdoor environment include part or all of the outdoor air ventilation volume and the outdoor ventilation duration; S203, determine the configuration control range for each control factor, the control range is a triple < u, f, s >, where u Indicates the upper limit of regulation, f Indicates the lower limit of regulation, s Indicates the adjustable range each time; The default control environment preset in step S201 is represented by a four-tuple:<S, C, H, T> , where S represents the host system; C represents the cooling system; H represents the computer room environment; and T represents the outdoor environment. Configuring the control environment to be enabled includes configuring the control environment to be enabled for each control environment in the preset default control environment using a key-value pair consisting of the control environment and whether it is included in the control strategy. The value of "1" for whether it is included in the control strategy indicates that it is included in the control strategy, and the value of "0" indicates that it is not included in the control strategy.

2. The method for optimizing energy consumption of a refrigeration system for a computing center according to claim 1, characterized in that: Measuring the thermal status of the host system of the computing center in step S102 includes: S301, using a motherboard management controller (BMC) installed and configured on a multi-source heterogeneous computing device of a host system to collect temperature data from various temperature sensors on the computing device, and performing out-of-band collection of the temperature data of the computing device based on the IPMI protocol; S302, using a preset aggregation algorithm to determine whether the temperature of the computing device is abnormal using a temperature data set of the computing device; S303 , summing the number of computing devices with abnormal temperatures in each preset area of ​​the host system to obtain the total number of computing devices with abnormal temperatures in the host system, which is used as the obtained thermal status of the host system of the computing center.

3. The method for optimizing energy consumption of a refrigeration system for a computing center according to claim 2, characterized in that: In step S302, the temperature data set of the computing device is subjected to a preset aggregation algorithm to determine whether the computing device has a temperature abnormality, including: using a preset statistical method to calculate the aggregated temperature value of the computing device for the temperature data set of the computing device, and then determining whether the computing device has a temperature abnormality based on whether the aggregated temperature value exceeds a preset threshold.

4. The method for optimizing energy consumption of a refrigeration system for a computing center according to claim 1, characterized in that: The calculation function expression of the cooling benefit is: ， In the above formula, Represents the cooling efficiency, is a penalty factor with a negative value, is the thermal status of the host system in the computing center, The energy efficiency of the computing center is the ratio of all energy consumption of the computing center to the energy consumption of the host system.

5. A cooling system energy consumption optimization system for a computing center, comprising a microprocessor and a memory connected to each other, characterized in that: The microprocessor is programmed or configured to execute the method for optimizing energy consumption of a refrigeration system for a computing center according to any one of claims 1 to 4.

6. A computer-readable storage medium having a computer program or instruction stored therein, characterized in that: The computer program or instruction is programmed or configured to execute the method for optimizing energy consumption of a refrigeration system for a computing center according to any one of claims 1 to 4 through a processor.

7. A computer program product comprising a computer program or instructions, characterized in that The computer program or instruction is programmed or configured to execute the method for optimizing energy consumption of a refrigeration system for a computing center according to any one of claims 1 to 4 through a processor.

Images