Server cabinet control method and device, energy consumption management system and server cabinet

Abstract

The invention relates to a server cabinet control method and device, an energy consumption management system and a server cabinet. The method comprises the following steps: acquiring energy consumption distribution information of a server cabinet to be controlled and cabinet working condition information of the server cabinet; obtaining a target energy consumption optimization model matched with the server cabinet from a plurality of pre-constructed energy consumption optimization models according to the cabinet working condition information; inputting the energy consumption distribution information into a target energy consumption optimization model to obtain an energy consumption optimization instruction for the server cabinet; the energy consumption optimization instruction is used for controlling refrigeration equipment arranged in the server cabinet to carry out refrigeration processing according to the energy consumption optimization instruction. By adopting the method, the energy consumption optimization model can be determined based on the cabinet working condition of the server cabinet, the energy consumption distribution of the server cabinet is analyzed by using the energy consumption optimization model, and the energy consumption optimization instruction for controlling the refrigeration equipment is generated, so that the refrigeration equipment is regulated and controlled by using the energy consumption optimization instruction, the resource configuration in the server cabinet is optimized, and the refrigeration efficiency is improved. And the control efficiency of the server cabinet is improved.

Description

Technical Field

[0001] The present application relates to the technical field of server cabinets, and in particular to a server cabinet control method, device, energy consumption management system, server cabinet, computer-readable storage medium and computer program product. Background Art

[0002] With the rapid development of information technology, the application of servers is becoming more and more extensive. Data centers (IDCs) are an important part of the new infrastructure. The various computing power and communication equipment in the computer room provide the hardware foundation for data center services. Such hardware equipment is placed in the server cabinet in the computer room.

[0003] In traditional technology, server cabinets only have simple data display functions. However, as the interior of server cabinets becomes increasingly complex, traditional technology cannot meet the management needs of server cabinets and is not conducive to improving the control efficiency of server cabinets. Summary of the invention

[0004] Based on this, it is necessary to provide a server cabinet control method, device, energy consumption management system, server cabinet, computer-readable storage medium and computer program product that can improve the control efficiency of the server cabinet in response to the above technical problems.

[0005] In a first aspect, the present application provides a server cabinet control method, comprising:

[0006] Obtaining energy consumption distribution information of a server cabinet to be controlled and cabinet operating condition information of the server cabinet;

[0007] According to the cabinet operating condition information, a target energy consumption optimization model matching the server cabinet is obtained from a plurality of pre-built energy consumption optimization models;

[0008] The energy consumption distribution information is input into the target energy consumption optimization model to obtain an energy consumption optimization instruction for the server cabinet; the energy consumption optimization instruction is used to control the refrigeration equipment provided in the server cabinet to perform refrigeration processing according to the energy consumption optimization instruction.

[0009] In one embodiment, there are multiple server cabinets; inputting the energy consumption distribution information into the target energy consumption optimization model to obtain energy consumption optimization instructions for the server cabinets includes:

[0010] Inputting the energy consumption distribution information of each of the server cabinets into the target energy consumption optimization model to obtain an initial energy consumption optimization instruction for each of the server cabinets;

[0011] Adjusting the initial energy consumption optimization instruction of each server cabinet according to the energy consumption distribution information of each server cabinet to obtain an adjusted energy consumption optimization instruction for each server cabinet;

[0012] The adjusted energy consumption optimization instruction is adjusted according to the coordination relationship between the server cabinets to obtain the energy consumption optimization instruction for each server cabinet.

[0013] In one embodiment, adjusting the initial energy consumption optimization instruction of each server cabinet according to the energy consumption distribution information of each server cabinet to obtain the adjusted energy consumption optimization instruction for each server cabinet includes:

[0014] Acquire preset energy consumption information corresponding to the cabinet operating condition information; the preset energy consumption information represents the preset energy consumption of each area in the server cabinet under the operating condition corresponding to the cabinet operating condition information;

[0015] According to the difference between the preset energy consumption information and the energy consumption distribution information, the initial energy consumption optimization instruction is adjusted to obtain an adjusted energy consumption optimization instruction for each of the server cabinets.

[0016] In one embodiment, adjusting the initial energy consumption optimization instruction according to the difference between the preset energy consumption information and the energy consumption distribution information includes:

[0017] Determining energy-saving adjustment reference information according to the difference between the preset energy consumption information and the energy consumption distribution information; the energy-saving adjustment reference information is used to control the working state of the refrigeration equipment provided in the server cabinet;

[0018] Controlling the refrigeration equipment in the server cabinet according to the energy-saving adjustment reference information, and determining the energy-saving index information of the server cabinet;

[0019] According to the difference between the energy-saving index information and the preset energy-saving index reference information, the initial energy consumption optimization instruction is adjusted until the difference between the energy-saving index information and the preset energy-saving index reference information meets the preset difference requirement.

[0020] In one embodiment, the adjusting the adjusted energy consumption optimization instruction according to the coordination relationship between the server cabinets to obtain the energy consumption optimization instruction for each server cabinet includes:

[0021] Determining operation matching degree information and collaborative efficiency information according to the energy consumption distribution information of each of the server cabinets;

[0022] According to the operation matching degree information and the collaborative efficiency information, the adjusted energy consumption optimization instruction is adjusted to obtain the energy consumption optimization instruction for each of the server cabinets.

[0023] In one embodiment, the method further comprises:

[0024] Obtaining energy consumption distribution information of a sample server cabinet under a preset cabinet working condition, and obtaining refrigeration equipment control information of the sample server cabinet;

[0025] According to the energy consumption distribution information of the sample server cabinet under the preset cabinet working condition and the refrigeration equipment control information, the energy consumption optimization model to be trained is trained to obtain the pre-built multiple energy consumption optimization models.

[0026] In one embodiment, the obtaining of energy consumption distribution information of a server cabinet to be controlled includes:

[0027] The energy consumption distribution information at the current moment is used as the target energy consumption information, and the energy consumption distribution information at the historical moment is used as the historical energy consumption information; the historical moment is the moment before the current moment;

[0028] Determine the average energy consumption information corresponding to the historical moment according to the historical energy consumption information;

[0029] Determining the average energy consumption information corresponding to the current moment according to the average energy consumption information corresponding to the historical moment and the target energy consumption information;

[0030] Determine sampling frequency information according to the average energy consumption information corresponding to the current moment;

[0031] The energy consumption distribution information of the server cabinet to be controlled is obtained according to the sampling frequency information.

[0032] In a second aspect, the present application also provides a server cabinet control device, including:

[0033] An information acquisition module, used to acquire energy consumption distribution information of a server cabinet to be controlled, and cabinet operating condition information of the server cabinet;

[0034] A model acquisition module, used to acquire a target energy consumption optimization model matching the server cabinet from a plurality of pre-built energy consumption optimization models according to the cabinet working condition information;

[0035] The equipment control module is used to input the energy consumption distribution information into the target energy consumption optimization model to obtain energy consumption optimization instructions for the server cabinet; the energy consumption optimization instructions are used to control the refrigeration equipment set in the server cabinet to perform refrigeration processing according to the energy consumption optimization instructions.

[0036] In a third aspect, the present application further provides an energy consumption management system. The energy consumption management system comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the above method are implemented.

[0037] In a fourth aspect, the present application further provides a server cabinet. The server cabinet comprises a U position detection system, a management module and the above energy consumption management system; wherein:

[0038] The U-position detection system is used to obtain the U-position distribution information and the equipment U-position occupancy information of the server cabinet;

[0039] The energy consumption management system is used to obtain energy consumption optimization instructions for the server cabinet;

[0040] The management module is used to adjust the setting position and working status of each device in the server cabinet according to the U-position distribution information, the device U-position occupancy information and the energy consumption optimization instruction for the server cabinet.

[0041] In a fifth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the steps of the above method when executed by a processor.

[0042] In a sixth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0043] The server cabinet control method, device, energy consumption management system, server cabinet, computer-readable storage medium and computer program product obtain energy consumption distribution information of the server cabinet to be controlled and cabinet operating condition information of the server cabinet, and obtain a target energy consumption optimization model matching the server cabinet from a plurality of pre-built energy consumption optimization models according to the cabinet operating condition information, thereby accurately determining a target energy consumption optimization model matching the server cabinet from a plurality of pre-built energy consumption optimization models according to the cabinet operating condition classification of the server cabinet, inputting the energy consumption distribution information into the target energy consumption optimization model, and obtaining an energy consumption optimization model for the server cabinet. Energy consumption optimization instructions are generated to analyze the energy consumption distribution information of the server cabinet through the target energy consumption optimization model, and energy consumption optimization instructions for the server cabinet are accurately generated, so as to use the energy consumption optimization instructions to control the refrigeration equipment set in the server cabinet to perform refrigeration processing according to the energy consumption optimization instructions. The energy consumption optimization model can be determined based on the cabinet working condition of the server cabinet, and then the energy consumption optimization model can be used to analyze the energy consumption distribution of the server cabinet, and energy consumption optimization instructions for controlling the refrigeration equipment set in the server cabinet are generated, so as to use the energy consumption optimization instructions to regulate the refrigeration equipment, optimize the resource allocation in the server cabinet, and then improve the control efficiency of the server cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A schematic diagram of a flow chart of a server cabinet control method in an embodiment;

[0046] Figure 2 is a schematic diagram of an energy consumption management system in one embodiment;

[0047] Figure 3 is a schematic diagram of a server cabinet in one embodiment;

[0048] Figure 4 A schematic diagram of a U-position detection process in an embodiment;

[0049] Figure 5 is a schematic diagram of an intelligent integrated cabinet in one embodiment;

[0050] Figure 6 A schematic diagram of a process of energy consumption management in an embodiment;

[0051] Figure 7is a structural block diagram of a server cabinet control device in one embodiment;

[0052] Figure 8 The figure is a diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] In an exemplary embodiment, Figure 1 As shown, a server cabinet control method is provided, and the method is applied to an energy consumption management system in a server cabinet as an example for description, including the following steps S102 to S106. Among them:

[0055] Step S102: acquiring energy consumption distribution information of the server cabinet to be controlled and cabinet operating condition information of the server cabinet.

[0056] Among them, the server cabinet may refer to an installation box used to combine installation panels, plug-ins, plug-in boxes, electronic components, devices and mechanical parts and components to form an integral installation box.

[0057] Among them, the energy consumption distribution information may refer to information characterizing the energy consumption of each area / device in the server cabinet. In actual applications, the internal space of the server cabinet may be divided into several areas, and the energy consumption of the equipment in each area may be used to determine the energy consumption distribution information of the server cabinet.

[0058] Among them, the cabinet working condition information may refer to information characterizing the working status of the server cabinet. In actual applications, the working status of the server cabinet may be pre-classified into several cabinet working condition classifications, each cabinet working condition classification may characterize a working status, and the cabinet working condition information may include the cabinet working condition classification.

[0059] As an example, a server cabinet is provided with several sensors, and the energy consumption management system can determine the energy consumption information of each area / device in the server cabinet to be controlled based on the sensor information collected by the sensors, and then the energy consumption management system can determine the energy consumption distribution information based on the energy consumption information of each area / device in the server cabinet. The energy consumption management system can perform feature recognition on the sensor information collected by several sensors set in the server cabinet, extract features related to the cabinet working condition, and determine the cabinet working condition information of the server cabinet based on the features related to the cabinet working condition. In actual applications, the energy consumption management system can obtain the sensor information collected by several sensors set in the server cabinet under the preset cabinet working condition, combine the sensor information under the preset cabinet working condition and the preset cabinet working condition, establish the correlation between the features related to the cabinet working condition and the preset cabinet working condition, and pre-construct the cabinet working condition recognition model. In a specific implementation, the energy consumption management system can input sensor information into a cabinet operating condition identification model. The cabinet operating condition identification model can be used to extract features related to the cabinet operating condition from the sensor information, and determine the cabinet operating condition based on the features related to the cabinet operating condition, so as to perform cabinet operating condition identification based on the sensor information.

[0060] Step S104: acquiring a target energy consumption optimization model matching the server cabinet from a plurality of pre-built energy consumption optimization models according to the cabinet operating condition information.

[0061] The energy consumption optimization model may refer to information for determining the control instructions of the refrigeration equipment (such as air conditioners, etc.) in the server cabinet according to the energy consumption distribution information of the server cabinet. In practical applications, each cabinet working condition may have a corresponding energy consumption optimization model. In a specific implementation, the target energy consumption optimization model matched by the server cabinet may refer to an energy consumption optimization model in which the cabinet working condition in the pre-built multiple energy consumption optimization models is the same as the cabinet working condition represented by the cabinet working condition information of the server cabinet.

[0062] As an example, the energy consumption management system pre-builds multiple energy consumption optimization models according to the control instructions of the server cabinet for the refrigeration equipment in the server cabinet under different preset working conditions, and each energy consumption optimization model can correspond to a preset working condition. In practical applications, the energy consumption management system can obtain the target energy consumption optimization model matching the server cabinet from the pre-built multiple energy consumption optimization models according to the cabinet working condition information of the server cabinet. For example, the energy consumption management system can compare the cabinet working condition information of the server cabinet with the working conditions corresponding to the pre-built multiple energy consumption optimization models one by one, and use the energy consumption optimization model with the same working condition as the working condition represented by the cabinet working condition information of the server cabinet in the pre-built multiple energy consumption optimization models as the target energy consumption optimization model matching the server cabinet.

[0063] Step S106: input the energy consumption distribution information into the target energy consumption optimization model to obtain energy consumption optimization instructions for the server cabinet.

[0064] The energy consumption optimization instruction may refer to an instruction / command for controlling the refrigeration equipment provided in the server cabinet to perform refrigeration processing according to the energy consumption optimization instruction. In actual applications, the energy consumption optimization instruction may be used to adjust the working state of the refrigeration equipment.

[0065] As an example, the energy consumption management system can input the energy consumption distribution information of the server cabinet into the target energy consumption optimization model that matches the server cabinet. Since the target energy consumption optimization model can be constructed / trained based on the control instructions of the server cabinet for the refrigeration equipment in the server cabinet under different preset working conditions, the target energy consumption optimization model can analyze the energy consumption distribution information of the server cabinet and generate refrigeration equipment control instructions that can be used as energy consumption optimization instructions for the server cabinet. After that, the energy consumption management system can control the refrigeration equipment installed in the server cabinet according to the energy consumption optimization instructions for the server cabinet to perform cooling processing according to the energy consumption optimization instructions.

[0066] In the above-mentioned server cabinet control method, by obtaining the energy consumption distribution information of the server cabinet to be controlled and the cabinet operating condition information of the server cabinet, according to the cabinet operating condition information, a target energy consumption optimization model matching the server cabinet is obtained from multiple pre-built energy consumption optimization models, so that according to the classification of the cabinet operating condition of the server cabinet, the target energy consumption optimization model matching the server cabinet is accurately determined from multiple pre-built energy consumption optimization models, and the energy consumption distribution information is input into the target energy consumption optimization model to obtain energy consumption optimization instructions for the server cabinet, so that the energy consumption distribution information of the server cabinet is analyzed by the target energy consumption optimization model, and the energy consumption optimization instructions for the server cabinet are accurately generated, so as to use the energy consumption optimization instructions to control the refrigeration equipment set in the server cabinet to perform refrigeration processing according to the energy consumption optimization instructions, and the energy consumption optimization model can be first determined based on the cabinet operating condition of the server cabinet, and then the energy consumption optimization model is used to analyze the energy consumption distribution of the server cabinet, and the energy consumption optimization instructions for controlling the refrigeration equipment set in the server cabinet are generated, so that the energy consumption optimization instructions are used to regulate the refrigeration equipment, optimize the resource configuration in the server cabinet, and thus improve the control efficiency of the server cabinet.

[0067] In an exemplary embodiment, there are multiple server cabinets; energy consumption distribution information is input into a target energy consumption optimization model to obtain energy consumption optimization instructions for the server cabinets, including: inputting the energy consumption distribution information of each server cabinet into the target energy consumption optimization model to obtain initial energy consumption optimization instructions for each server cabinet; adjusting the initial energy consumption optimization instructions of each server cabinet according to the energy consumption distribution information of each server cabinet to obtain adjusted energy consumption optimization instructions for each server cabinet; adjusting the adjusted energy consumption optimization instructions according to the collaborative relationship between each server cabinet to obtain energy consumption optimization instructions for each server cabinet.

[0068] The initial energy consumption optimization instruction may refer to an instruction / command output by the target energy consumption optimization model after analyzing the energy consumption distribution information and used to control the refrigeration equipment.

[0069] The adjusted energy consumption optimization instruction may refer to an instruction / command for controlling the refrigeration equipment obtained after the initial energy consumption optimization instruction is adjusted.

[0070] As an example, if there are multiple server cabinets to be controlled, the refrigeration equipment control instructions output by the target energy consumption optimization model matching each server cabinet can be used as the initial energy consumption optimization instructions. After obtaining the initial energy consumption optimization instructions, the energy consumption management system can also adjust the initial energy consumption optimization instructions of each server cabinet according to the difference between the energy consumption distribution information of each server cabinet and the preset energy consumption, and obtain the adjusted energy consumption optimization instructions for each server cabinet. In actual applications, if there is a collaborative relationship between multiple server cabinets to be controlled, the energy consumption management system can also analyze the degree of collaboration between the server cabinets according to the collaborative relationship between the server cabinets, adjust the adjusted energy consumption optimization instructions, and obtain the energy consumption optimization instructions for each server cabinet.

[0071] In this embodiment, by inputting the energy consumption distribution information of each server cabinet into the target energy consumption optimization model, an initial energy consumption optimization instruction for each server cabinet is obtained; the initial energy consumption optimization instruction of each server cabinet is adjusted according to the energy consumption distribution information of each server cabinet, and an adjusted energy consumption optimization instruction for each server cabinet is obtained; the adjusted energy consumption optimization instruction is adjusted according to the coordination relationship between each server cabinet, and an energy consumption optimization instruction for each server cabinet is obtained. This can fully analyze the energy consumption distribution information of the server cabinet and the coordination relationship between the server cabinets, and finely adjust the initial energy consumption optimization instruction output by the target energy consumption optimization model to obtain accurate energy consumption optimization instructions, thereby improving the accuracy of the energy consumption optimization instructions and improving the control efficiency of the server cabinet.

[0072] In some embodiments, the initial energy consumption optimization instructions of each server cabinet are adjusted according to the energy consumption distribution information of each server cabinet to obtain the adjusted energy consumption optimization instructions for each server cabinet, including: obtaining the preset energy consumption information corresponding to the cabinet working condition information; according to the difference between the preset energy consumption information and the energy consumption distribution information, adjusting the initial energy consumption optimization instructions to obtain the adjusted energy consumption optimization instructions for each server cabinet.

[0073] The preset energy consumption information may refer to information representing the preset energy consumption of each area in the server cabinet under the working condition corresponding to the cabinet working condition information.

[0074] As an example, since the cabinet operating condition information can represent a specific operating condition in the preset operating condition classification, the energy consumption management system can determine the preset energy consumption information corresponding to the cabinet operating condition information based on the operating condition corresponding to the cabinet operating condition information. The preset energy consumption information can be used as an optimal energy consumption information. The energy consumption management system can then analyze the difference between the preset energy consumption information and the energy consumption distribution information, and further fine-tune the initial energy consumption optimization instructions based on the difference between the preset energy consumption information and the energy consumption distribution information to obtain adjusted energy consumption optimization instructions for each server cabinet.

[0075] In this embodiment, by obtaining the preset energy consumption information corresponding to the cabinet operating condition information; adjusting the initial energy consumption optimization instructions according to the difference between the preset energy consumption information and the energy consumption distribution information, and obtaining the adjusted energy consumption optimization instructions for each server cabinet, it is possible to fully analyze the difference between the preset energy consumption information and the energy consumption distribution information, finely adjust the initial energy consumption optimization instructions, improve the accuracy of the energy consumption optimization instructions, and thus improve the control efficiency of the server cabinet.

[0076] In some embodiments, the initial energy consumption optimization instruction is adjusted according to the difference between the preset energy consumption information and the energy consumption distribution information, including: determining energy-saving adjustment reference information according to the difference between the preset energy consumption information and the energy consumption distribution information; controlling the refrigeration equipment in the server cabinet according to the energy-saving adjustment reference information, and determining the energy-saving index information of the server cabinet; adjusting the initial energy consumption optimization instruction according to the difference between the energy-saving index information and the preset energy-saving index reference information, until the difference between the energy-saving index information and the preset energy-saving index reference information meets the preset difference requirement.

[0077] The energy-saving adjustment reference information may refer to information used to control the working state of a refrigeration device provided in a server cabinet. In practical applications, the energy-saving adjustment reference information may be used as an energy-saving adjustment suggestion.

[0078] The energy-saving index information may refer to pre-set information used to characterize the energy-saving degree of the server cabinet. In actual applications, the energy-saving index information may include but is not limited to energy consumption information, production efficiency information, and equipment life information.

[0079] Among them, the preset energy-saving index reference information may refer to pre-set information used to determine whether the energy-saving degree of the server cabinet meets the preset energy-saving requirements. In actual applications, the preset energy-saving index reference information may include but is not limited to the minimum energy consumption, maximum production efficiency and standard value of equipment life.

[0080] The preset difference requirement may refer to information for determining whether the difference between the energy-saving index information and the preset energy-saving index reference information is less than or equal to a preset threshold.

[0081] As an example, the energy consumption management system can first determine the energy-saving adjustment reference information based on the difference between the preset energy consumption information and the energy consumption distribution information, and then the energy consumption management system can control the refrigeration equipment in the server cabinet according to the energy-saving adjustment reference information, and determine the energy consumption information, production efficiency information, equipment life information and other energy-saving index information of the server cabinet after controlling the refrigeration equipment according to the energy-saving adjustment reference information. After that, the energy consumption management system can obtain the preset energy-saving index reference information corresponding to the energy-saving index information, and analyze the difference between the energy-saving index information and the preset energy-saving index reference information. If the difference between the energy-saving index information and the preset energy-saving index reference information meets the preset difference requirement, the energy consumption management system can use the initial energy consumption optimization instruction as the adjusted energy consumption optimization instruction. If the difference between the energy-saving index information and the preset energy-saving index reference information does not meet the preset difference requirement, the energy consumption management system can adjust the initial energy consumption optimization instruction according to the difference between the energy-saving index information and the preset energy-saving index reference information until the difference between the energy-saving index information and the preset energy-saving index reference information meets the preset difference requirement.

[0082] For example: the energy consumption management system can adjust the initial energy consumption optimization instruction according to the difference between the energy-saving index information and the preset energy-saving index reference information to obtain the adjusted energy consumption optimization instruction. Then the energy consumption management system can control the refrigeration equipment in the server cabinet according to the adjusted energy consumption optimization instruction and re-acquire the energy consumption distribution information of the server cabinet. Then the energy consumption management system can determine the new energy-saving adjustment reference information according to the difference between the energy consumption distribution information at this time and the preset energy consumption information. The energy consumption management system can control the refrigeration equipment in the server cabinet according to the new energy-saving adjustment reference information and determine the new energy-saving index information of the server cabinet after controlling the refrigeration equipment according to the new energy-saving adjustment reference information. Then the energy consumption management system can analyze the new energy-saving information. The difference between the indicator information and the preset energy-saving indicator reference information, if the difference between the new energy-saving indicator information and the preset energy-saving indicator reference information meets the preset difference requirements, the energy consumption management system can use the adjusted energy consumption optimization instruction at this time as the final adjusted energy consumption optimization instruction, if the difference between the new energy-saving indicator information and the preset energy-saving indicator reference information does not meet the preset difference requirements, the energy consumption management system can adjust the adjusted energy consumption optimization instruction at this time to obtain a new adjusted energy consumption optimization instruction, and return to execute the step of controlling the refrigeration equipment in the server cabinet according to the adjusted energy consumption optimization instruction, until the difference between the energy-saving indicator information and the preset energy-saving indicator reference information meets the preset difference requirements, and the final adjusted energy consumption optimization instruction is obtained. It can be understood that adjusting the initial energy consumption optimization instruction according to the difference between the energy-saving indicator information and the preset energy-saving indicator reference information can be regarded as a multi-objective optimization problem: with minimizing energy consumption, maximizing production efficiency, and maintaining equipment life as optimization goals, continuously adjusting the initial energy consumption optimization instruction can obtain the final adjusted energy consumption optimization instruction.

[0083] In this embodiment, energy-saving adjustment reference information is determined based on the difference between preset energy consumption information and energy consumption distribution information; the refrigeration equipment in the server cabinet is controlled based on the energy-saving adjustment reference information, and the energy-saving index information of the server cabinet is determined; according to the difference between the energy-saving index information and the preset energy-saving index reference information, the initial energy consumption optimization instruction is adjusted until the difference between the energy-saving index information and the preset energy-saving index reference information meets the preset difference requirement. Based on the difference between the energy-saving index information of the server cabinet and the preset energy-saving index reference information, the initial energy consumption optimization instruction can be finely adjusted to improve the accuracy of the energy consumption optimization instruction, thereby improving the control efficiency of the server cabinet.

[0084] In some embodiments, the adjusted energy consumption optimization instructions are adjusted according to the collaborative relationship between each server cabinet to obtain energy consumption optimization instructions for each server cabinet, including: determining operation matching information and collaborative efficiency information according to the energy consumption distribution information of each server cabinet; adjusting the adjusted energy consumption optimization instructions according to the operation matching information and collaborative efficiency information to obtain energy consumption optimization instructions for each server cabinet.

[0085] The operation matching degree information may refer to information on whether the workload distribution between the server cabinets that cooperate with each other is balanced.

[0086] The collaborative efficiency information may refer to information on the system operating efficiency of a server cabinet cluster system composed of server cabinets that collaborate with each other.

[0087] As an example, the energy consumption management system can determine the cabinet energy consumption information of each server cabinet based on the energy consumption distribution information of each server cabinet, and compare the cabinet energy consumption information of any two server cabinets to determine the energy consumption difference between the cabinet energy consumption information of different server cabinets. The energy consumption management system can determine the operation matching information based on the energy consumption difference and the preset energy consumption difference threshold. The energy consumption management system can determine the system energy consumption of the server cabinet cluster system composed of each server cabinet based on the energy consumption distribution information of each server cabinet, and determine the collaborative efficiency information based on the system energy consumption and the preset system energy consumption. Afterwards, the energy consumption management system can adjust the adjusted energy consumption optimization instructions based on the difference between the operation matching information and the preset operation matching reference information and the difference between the collaborative efficiency information and the preset collaborative efficiency reference information to obtain energy consumption optimization instructions for each server cabinet.

[0088] In this embodiment, the operation matching information and the collaborative efficiency information are determined according to the energy consumption distribution information of each server cabinet; the adjusted energy consumption optimization instructions are adjusted according to the operation matching information and the collaborative efficiency information to obtain energy consumption optimization instructions for each server cabinet. The operation matching degree and the collaborative efficiency between each server cabinet can be fully analyzed, and the adjusted energy consumption optimization instructions can be fine-tuned based on the operation matching degree and the collaborative efficiency, thereby improving the accuracy of the energy consumption optimization instructions and thus improving the control efficiency of the server cabinet.

[0089] In some embodiments, the above method also includes: obtaining energy consumption distribution information of the sample server cabinet under preset cabinet operating conditions, and obtaining refrigeration equipment control information of the sample server cabinet; training the energy consumption optimization model to be trained according to the energy consumption distribution information and refrigeration equipment control information of the sample server cabinet under preset cabinet operating conditions, and obtaining multiple pre-built energy consumption optimization models.

[0090] The refrigeration equipment control information may refer to information used to characterize the working status of the refrigeration equipment installed in the server cabinet. In actual applications, the refrigeration equipment control information may include but is not limited to temperature, working gear, working time, etc.

[0091] As an example, in order to build an energy consumption optimization model, the energy consumption management system can obtain the energy consumption distribution information of the sample server cabinet under the preset cabinet working conditions, and obtain the refrigeration equipment control information of the sample server cabinet, and then train the energy consumption optimization model to be trained based on the energy consumption distribution information and refrigeration equipment control information of the sample server cabinet under the preset cabinet working conditions, so that the energy consumption optimization model to be trained can fully learn the correlation between the energy consumption distribution information under different cabinet working conditions and the refrigeration equipment control information of the sample server cabinet, and obtain multiple pre-built energy consumption optimization models.

[0092] In this embodiment, by obtaining the energy consumption distribution information of a sample server cabinet under a preset cabinet operating condition, and obtaining the refrigeration equipment control information of the sample server cabinet; according to the energy consumption distribution information and refrigeration equipment control information of the sample server cabinet under the preset cabinet operating condition, the energy consumption optimization model to be trained is trained to obtain multiple pre-built energy consumption optimization models. The energy consumption optimization model to be trained can be based on samples such as the energy consumption distribution and refrigeration equipment control information to obtain a pre-built energy consumption optimization model, thereby improving the accuracy of the energy consumption optimization instructions output by the energy consumption optimization model, thereby improving the control efficiency of the server cabinet.

[0093] In some embodiments, energy consumption distribution information of a server cabinet to be controlled is obtained, including: taking the energy consumption distribution information at the current moment as the target energy consumption information, and taking the energy consumption distribution information at the historical moment as the historical energy consumption information; determining the average energy consumption information corresponding to the historical moment based on the historical energy consumption information; determining the average energy consumption information corresponding to the current moment based on the average energy consumption information corresponding to the historical moment and the target energy consumption information; determining the sampling frequency information based on the average energy consumption information corresponding to the current moment; and obtaining the energy consumption distribution information of the server cabinet to be controlled based on the sampling frequency information.

[0094] Among them, the historical moments may include moments before the current moment.

[0095] The average energy consumption information may refer to an average value representing the energy consumption information of the server cabinet over a period of time.

[0096] The sampling frequency information may refer to information of the acquisition frequency used to characterize the energy consumption distribution information of the server cabinet.

[0097] As an example, the energy consumption management system can use the energy consumption distribution information of the server cabinet at the current moment as the target energy consumption information, and use the energy consumption distribution information of the server cabinet at the historical moment as the historical energy consumption information. Then, the energy consumption management system can determine the average energy consumption information corresponding to the historical moment based on the historical energy consumption information, and determine the average energy consumption information corresponding to the current moment based on the average energy consumption information corresponding to the historical moment and the target energy consumption information. Then, the energy consumption management system can determine the sampling frequency information based on the difference between the target energy consumption information and the average energy consumption information corresponding to the current moment, and obtain the energy consumption distribution information of the server cabinet to be controlled based on the sampling frequency information. For example, if the total number of sampling times at the current moment can be expressed as n, the target energy consumption information can be expressed as E d , the average energy consumption information corresponding to the historical moment can be expressed as E p1 , then the average energy consumption information E corresponding to the current moment p2 It can be expressed as (E p1 *(n-1)+E d ) / n, sampling frequency information f s It can be expressed as k*|E d -E p2 | α , where k can be a preset parameter and the value of α depends on f s With E d -E p2 Is there a linear relationship between them? If α is 1, then f s With E d -E p2 There is a linear relationship between them. If α is not 1, then f s With E d -E p2 There is a non-linear relationship between them.

[0098] In this embodiment, the energy consumption distribution information at the current moment is used as the target energy consumption information, and the energy consumption distribution information at the historical moment is used as the historical energy consumption information; the average energy consumption information corresponding to the historical moment is determined according to the historical energy consumption information; the average energy consumption information corresponding to the current moment is determined according to the average energy consumption information corresponding to the historical moment and the target energy consumption information; the sampling frequency information is determined according to the average energy consumption information corresponding to the current moment; the energy consumption distribution information of the server cabinet to be controlled is obtained according to the sampling frequency information, and the sampling frequency of the energy consumption distribution information can be adaptively adjusted according to the energy consumption distribution of the server cabinet in different time periods, the data collection method can be flexibly adjusted, and resource utilization is optimized.

[0099] In some embodiments, Figure 2As shown, a schematic diagram of an energy consumption management system is provided. The energy consumption management system can be used as an energy consumption monitoring system. The energy consumption management system can include an acquisition module, a calculation module, a judgment module, a control module and an intelligent management module. The acquisition module integrates high-precision current sensors, voltage sensors, power sensors, temperature sensors, wind speed sensors, etc., which are used to monitor the energy consumption and environmental conditions of the server in the cabinet in real time, including parameters such as power, current, voltage, temperature and humidity, and upload the data to the management system for energy management and optimization. The calculation module is used to receive parameters such as temperature and humidity in the cabinet, the number of equipment, U-position information, and real-time power consumption of the server, calculate the real-time power consumption distribution information of the cabinet and send it to the judgment module. The judgment module is used to receive the real-time power consumption distribution of the cabinet, and combine the machine learning algorithm to build an energy consumption optimization model with multi-model fusion:

[0100]

[0101]

[0102]

[0103]

[0104] ,

[0105] Among them, x can represent the total load (such as energy consumption) of the first area (such as the upper area) of the server cabinet, y can represent the total load (such as energy consumption) of the second area (such as the middle area) of the server cabinet, z can represent the total load (such as energy consumption) of the third area (such as the lower area) of the server cabinet, θ can represent the total load (such as total energy consumption) of the server cabinet, ω can represent the cooling strategy (such as energy consumption optimization instruction), and the cooling strategy can be determined by the load of each area of ​​the cabinet and the total load and the preset cabinet working condition. The control module is used to receive the cooling strategy adoption instruction sent by the judgment module to complete the fine control of the air supply of the air conditioner. The intelligent management module integrates data processing and communication functions, and can link and uniformly manage and control the camera, energy consumption management system and U-position detection system in the cabinet: judge the cabinet shelf rate through U-position detection and image recognition, and process energy consumption information based on the energy consumption monitoring module to rationally allocate resources and intelligent air conditioning control, thereby realizing the fine management of the intelligent computer room. The energy consumption management system can compare the real-time power consumption distribution information of the cabinet with the preset cabinet operating conditions to determine which cooling strategy should be adopted, thereby completing the fine control of air conditioning and cooling, and achieving the purpose of precise energy saving.

[0106] In some embodiments, Figure 3As shown, a schematic diagram of a server cabinet is provided, and the server cabinet includes a U-position detection system, a management module and an energy consumption management system; wherein the U-position detection system is used to obtain the U-position distribution information and the equipment U-position occupancy information of the server cabinet.

[0107] In practical applications, such as Figure 4 The figure shows a flow diagram of U-position detection. The U-position detection system can obtain the internal image of the cabinet through the camera installed on the inside of the server cabinet door; determine the target ROI area based on the internal image of the cabinet; correct the target ROI area to obtain the target correction image; perform U-position segmentation processing on the target correction image based on the preset template to obtain the U-position distribution corresponding to the target correction image; determine the U-position occupancy range of the equipment based on the target correction image, and combine the U-position sensor signal to improve the recognition accuracy, and determine the size, quantity and free U-position distribution of the equipment on the rack in the target cabinet, the installation status of the blind plate and other information according to the U-position range and U-position distribution of the equipment. The U-position detection system can accurately detect the U-position occupancy of the server in the cabinet, which is conducive to the efficient use of the cabinet space.

[0108] The energy management system is used to obtain energy optimization instructions for server cabinets. The energy management system has in-depth energy analysis and real-time optimization capabilities, and can dynamically adjust the operating parameters of equipment in the cabinet to achieve energy saving.

[0109] The management module is used to adjust the setting position and working status of each device in the server cabinet according to the U-position distribution information, the equipment U-position occupancy information and the energy consumption optimization instructions for the server cabinet. The management module can also be used to monitor the equipment in the cabinet in real time, so that users can promptly understand the operating status inside the cabinet.

[0110] In practical applications, the server cabinet can be used as an intelligent integrated cabinet. The cabinet body of the intelligent integrated cabinet is made of high-strength metal material, which has good heat dissipation performance and stability. The camera inside the intelligent integrated cabinet has night vision function and monitors the status inside the cabinet in real time. The acquisition equipment of the intelligent integrated cabinet can monitor the operating status of the server in the cabinet in real time. The images collected by the acquisition equipment are transmitted to the monitoring center through the network, and the management personnel can view them at any time. Figure 5 As shown, a schematic diagram of an intelligent integrated cabinet is provided. The acquisition module, calculation module, judgment module, control module and intelligent management module in the intelligent integrated cabinet can constitute an energy consumption monitoring system / energy consumption management system. The camera, U-position sensor and processing unit can constitute a U-position detection system. In a specific implementation, the intelligent integrated cabinet can also be provided with a management module. The management module can adjust the setting position and working state of each device in the server cabinet according to the U-position distribution information, the equipment U-position occupancy information and the energy consumption optimization instruction for the server cabinet. It can be understood that the processing unit can realize the function of the management module.

[0111] In one of the exemplary embodiments, the server cabinet can link the cabinet camera, energy management system and U-position detection system through the built-in intelligent control system. By integrating high-precision sensors, image recognition technology, machine learning algorithms and other advanced technologies, it can capture real-time information such as the distribution of vacant U-positions in the cabinet, the installation status of blind panels, the size, quantity, energy consumption and operating status of equipment in the cabinet, analyze the real-time power consumption distribution of the cabinet to match the optimal cooling strategy and synchronously adjust the air supply and cooling of the air conditioner, promptly detect abnormal operation of equipment and issue an alarm, effectively improving the green and intelligent management level of the computer room.

[0112] like Figure 6 As shown in the figure, a schematic diagram of the process of energy consumption management is provided. Taking a row of cabinets (4 cabinets + 2 inter-row air conditioners) as an example, high-precision current sensors, voltage sensors, power sensors, temperature sensors, wind speed sensors, U-position sensors and vibration sensors are first installed at the corresponding positions of each cabinet and air conditioner to ensure that all sensors can work stably and are connected to the energy consumption monitoring module: the energy consumption monitoring module is installed at the power inlet of the cabinet, and the energy consumption of the server in the cabinet is monitored in real time through the sensor. The energy consumption monitoring module transmits the monitored data to the intelligent control system through the communication interface; it is connected to the U-position detection module: the sensor installed on each U position of the cabinet is used to detect the occupancy of the server. The U-position detection module transmits the detected data to the intelligent control system for the management and optimization of the cabinet space. Then configure the system parameters to ensure normal interaction between the modules. The sensor collects parameters such as the distribution of free U positions in the cabinet, the installation of blind panels, the size, quantity, energy consumption and operating status of the equipment in the cabinet at a preset frequency, and cleans the collected raw data. The data synchronization and calibration submodule ensures that the data collected by different sensors are synchronized in time, and uses a linear calibration algorithm to calibrate the data, that is, y=ax+b. The data acquisition frequency setting submodule analyzes the statistical characteristics of the equipment energy consumption data, identifies the key time points and conditions for energy consumption changes, that is, equipment startup and load changes, and dynamically sets the adaptive sampling frequency adjustment according to the changing characteristics of the energy consumption data and key collection points, that is:

[0113] .

[0114] Among them, f s is the sampling frequency, E d is the energy consumption value of the equipment in the cabinet collected at the current moment, E p is the average energy consumption, E p The calculation expression can be expressed as:

[0115] .

[0116] Where n is the number of sampling times.

[0117] Extract features from energy consumption information, such as extracting energy consumption features under different operating conditions, energy consumption trends under different loads, etc., and store the processed data in the system database for subsequent analysis and modeling. The energy consumption management system can build a hierarchical model in combination with machine learning algorithms, and provide customized cooling strategies based on the power consumption distribution and the preset cabinet working conditions. For example: extract features related to working condition identification from the original sensor data, annotate the training data set, clarify the working condition category corresponding to each sample, and thus build a working condition identification model. According to the control information of the refrigeration equipment of the server cabinet under different working conditions, the decision tree model is constructed and optimized, and the energy consumption optimization model corresponding to each working condition can be pre-trained. The pre-trained energy consumption optimization model is stored in the model library. According to the identified working conditions, the corresponding energy consumption optimization model is selected from the model library for energy consumption prediction and optimization. The judgment module can select the corresponding cooling strategy according to the different working conditions of the cabinet.

[0118] The control module can receive the cooling strategy adoption instruction sent by the judgment module to complete the fine control of the air supply of the air conditioner. The control module can also integrate data such as energy consumption, and predict energy consumption optimization instructions through the pre-trained energy consumption optimization model. For example, by comparing the power consumption distribution with the preset cabinet working condition, the difference between the current energy consumption and the optimal energy consumption of the preset working condition is calculated, and the reasons for the difference are analyzed, such as equipment operating status, environmental parameters, load changes, etc. If a certain equipment is found to be abnormal in the current operating status, the system will generate energy-saving adjustment suggestions for adjusting the air conditioner fan speed and temperature set point, define the optimization goals as minimizing energy consumption, maximizing production efficiency, and maintaining equipment life, and set corresponding weights. Based on the multi-objective optimization problem, a preliminary energy-saving adjustment strategy is generated, such as switching the air conditioner operation mode or adjusting the air conditioner working time, and evaluating the impact on energy consumption, production efficiency and equipment life. According to the evaluation results, the preliminary strategy is optimized and the optimal energy-saving adjustment suggestion is selected. The intelligent integrated cabinet is also connected to the monitoring center through the network to realize remote monitoring management and cabinet air conditioning group control functions, thereby realizing energy consumption management integration. Managers can access the intelligent control system through the network to view the operating status, energy consumption and U-position occupancy of the servers in the cabinet, and perform corresponding operations and management. For the entire row of cabinets in the same row, the cooling mode time, air supply mode time and fan speed of the air conditioner are adjusted by comprehensively considering the conditions of each device to achieve overall energy consumption reduction.

[0119] The intelligent management module of the energy management system can analyze the operation matching and coordination efficiency between equipment and cabinets, evaluate the coordination status between equipment by calculating the matching index and coordination efficiency ratio, and establish an energy consumption optimization model based on equipment operating parameters and coordination relationships. It can provide energy-saving solutions based on the model optimization results, and continuously monitor and correct the model.

[0120] In this embodiment, the energy consumption optimization model based on machine learning can provide customized energy-saving adjustment suggestions according to different working conditions. In addition, the energy consumption management system continuously optimizes the model and algorithm through user feedback and continuous monitoring of actual energy consumption changes of equipment, ensures the accuracy and applicability of energy-saving suggestions, improves the control efficiency of server cabinets, and thus improves the energy efficiency of server cabinets.

[0121] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0122] Based on the same inventive concept, the embodiment of the present application also provides a server cabinet control device for implementing the server cabinet control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more server cabinet control device embodiments provided below can refer to the limitations of the server cabinet control method above, and will not be repeated here.

[0123] In an exemplary embodiment, Figure 7 As shown, a server cabinet control device is provided, including: an information acquisition module 702, a model acquisition module 704 and a device control module 706, wherein:

[0124] The information acquisition module 702 is used to acquire the energy consumption distribution information of the server cabinet to be controlled and the cabinet working condition information of the server cabinet.

[0125] The model acquisition module 704 is used to acquire a target energy consumption optimization model matching the server cabinet from a plurality of pre-built energy consumption optimization models according to the cabinet operating condition information.

[0126] The device control module 706 is used to input the energy consumption distribution information into the target energy consumption optimization model to obtain energy consumption optimization instructions for the server cabinet; the energy consumption optimization instructions are used to control the refrigeration equipment set in the server cabinet to perform refrigeration processing according to the energy consumption optimization instructions.

[0127] In one of the exemplary embodiments, there are multiple server cabinets; the device control module 706 is specifically used to input the energy consumption distribution information of each server cabinet into the target energy consumption optimization model to obtain initial energy consumption optimization instructions for each server cabinet; adjust the initial energy consumption optimization instructions of each server cabinet according to the energy consumption distribution information of each server cabinet to obtain adjusted energy consumption optimization instructions for each server cabinet; adjust the adjusted energy consumption optimization instructions according to the collaborative relationship between each server cabinet to obtain energy consumption optimization instructions for each server cabinet.

[0128] In one of the exemplary embodiments, the device control module 706 is specifically used to obtain preset energy consumption information corresponding to the cabinet operating condition information; the preset energy consumption information represents the preset energy consumption of each area in the server cabinet under the operating condition corresponding to the cabinet operating condition information; according to the difference between the preset energy consumption information and the energy consumption distribution information, the initial energy consumption optimization instruction is adjusted to obtain the adjusted energy consumption optimization instruction for each server cabinet.

[0129] In one of the exemplary embodiments, the device control module 706 is specifically used to determine energy-saving adjustment reference information based on the difference between the preset energy consumption information and the energy consumption distribution information; the energy-saving adjustment reference information is used to control the working state of the refrigeration equipment set in the server cabinet; the refrigeration equipment in the server cabinet is controlled according to the energy-saving adjustment reference information, and the energy-saving index information of the server cabinet is determined; according to the difference between the energy-saving index information and the preset energy-saving index reference information, the initial energy consumption optimization instruction is adjusted until the difference between the energy-saving index information and the preset energy-saving index reference information meets the preset difference requirement.

[0130] In one of the exemplary embodiments, the device control module 706 is specifically used to determine the operation matching information and the collaborative efficiency information based on the energy consumption distribution information of each of the server cabinets; according to the operation matching information and the collaborative efficiency information, the adjusted energy consumption optimization instructions are adjusted to obtain energy consumption optimization instructions for each of the server cabinets.

[0131] In one of the exemplary embodiments, the above-mentioned device also includes a model construction module, which is specifically used to obtain energy consumption distribution information of a sample server cabinet under a preset cabinet operating condition, and obtain refrigeration equipment control information of the sample server cabinet; according to the energy consumption distribution information of the sample server cabinet under the preset cabinet operating condition and the refrigeration equipment control information, the energy consumption optimization model to be trained is trained to obtain the pre-constructed multiple energy consumption optimization models.

[0132] In one of the exemplary embodiments, the information acquisition module 702 is specifically used to use the energy consumption distribution information at the current moment as the target energy consumption information, and use the energy consumption distribution information at the historical moment as the historical energy consumption information; the historical moment is the moment before the current moment; based on the historical energy consumption information, determine the average energy consumption information corresponding to the historical moment; based on the average energy consumption information corresponding to the historical moment and the target energy consumption information, determine the average energy consumption information corresponding to the current moment; based on the average energy consumption information corresponding to the current moment, determine the sampling frequency information; and acquire the energy consumption distribution information of the server cabinet to be controlled based on the sampling frequency information.

[0133] Each module in the server cabinet control device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0134] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a server cabinet control method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0135] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0136] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0137] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0138] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0139] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0140] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0141] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0142] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A server cabinet control method, characterized in that: Applications to the method include: Obtaining energy consumption distribution information of a server cabinet to be controlled and cabinet operating condition information of the server cabinet; According to the cabinet operating condition information, a target energy consumption optimization model matching the server cabinet is obtained from a plurality of pre-built energy consumption optimization models; The energy consumption distribution information is input into the target energy consumption optimization model to obtain an energy consumption optimization instruction for the server cabinet; the energy consumption optimization instruction is used to control the refrigeration equipment provided in the server cabinet to perform refrigeration processing according to the energy consumption optimization instruction.

2. The method according to claim 1, characterized in that The number of the server cabinets is multiple; the energy consumption distribution information is input into the target energy consumption optimization model to obtain energy consumption optimization instructions for the server cabinets, including: Inputting the energy consumption distribution information of each of the server cabinets into the target energy consumption optimization model to obtain an initial energy consumption optimization instruction for each of the server cabinets; Adjusting the initial energy consumption optimization instruction of each server cabinet according to the energy consumption distribution information of each server cabinet to obtain an adjusted energy consumption optimization instruction for each server cabinet; The adjusted energy consumption optimization instruction is adjusted according to the coordination relationship between the server cabinets to obtain the energy consumption optimization instruction for each server cabinet.

3. The method according to claim 2, characterized in that The step of adjusting the initial energy consumption optimization instructions of each server cabinet according to the energy consumption distribution information of each server cabinet to obtain the adjusted energy consumption optimization instructions for each server cabinet includes: Acquire preset energy consumption information corresponding to the cabinet operating condition information; the preset energy consumption information represents the preset energy consumption of each area in the server cabinet under the operating condition corresponding to the cabinet operating condition information; According to the difference between the preset energy consumption information and the energy consumption distribution information, the initial energy consumption optimization instruction is adjusted to obtain an adjusted energy consumption optimization instruction for each of the server cabinets.

4. The method according to claim 3, characterized in that The adjusting the initial energy consumption optimization instruction according to the difference between the preset energy consumption information and the energy consumption distribution information includes: Determining energy-saving adjustment reference information according to the difference between the preset energy consumption information and the energy consumption distribution information; the energy-saving adjustment reference information is used to control the working state of the refrigeration equipment provided in the server cabinet; Controlling the refrigeration equipment in the server cabinet according to the energy-saving adjustment reference information, and determining the energy-saving index information of the server cabinet; According to the difference between the energy-saving index information and the preset energy-saving index reference information, the initial energy consumption optimization instruction is adjusted until the difference between the energy-saving index information and the preset energy-saving index reference information meets the preset difference requirement.

5. The method according to claim 2, characterized in that: The adjusting the adjusted energy consumption optimization instruction according to the coordination relationship between the server cabinets to obtain the energy consumption optimization instruction for each server cabinet includes: Determining operation matching degree information and collaborative efficiency information according to the energy consumption distribution information of each of the server cabinets; According to the operation matching degree information and the collaborative efficiency information, the adjusted energy consumption optimization instruction is adjusted to obtain the energy consumption optimization instruction for each of the server cabinets.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining energy consumption distribution information of a sample server cabinet under a preset cabinet working condition, and obtaining refrigeration equipment control information of the sample server cabinet; According to the energy consumption distribution information of the sample server cabinet under the preset cabinet working condition and the refrigeration equipment control information, the energy consumption optimization model to be trained is trained to obtain the pre-built multiple energy consumption optimization models.

7. The method according to claim 1, characterized in that The obtaining of energy consumption distribution information of the server cabinet to be controlled includes: The energy consumption distribution information at the current moment is used as the target energy consumption information, and the energy consumption distribution information at the historical moment is used as the historical energy consumption information; the historical moment is the moment before the current moment; Determine the average energy consumption information corresponding to the historical moment according to the historical energy consumption information; Determining the average energy consumption information corresponding to the current moment according to the average energy consumption information corresponding to the historical moment and the target energy consumption information; Determine sampling frequency information according to the average energy consumption information corresponding to the current moment; The energy consumption distribution information of the server cabinet to be controlled is obtained according to the sampling frequency information.

8. A server cabinet control device, characterized in that: The device comprises: An information acquisition module, used to acquire energy consumption distribution information of a server cabinet to be controlled, and cabinet operating condition information of the server cabinet; A model acquisition module, used to acquire a target energy consumption optimization model matching the server cabinet from a plurality of pre-built energy consumption optimization models according to the cabinet working condition information; The equipment control module is used to input the energy consumption distribution information into the target energy consumption optimization model to obtain energy consumption optimization instructions for the server cabinet; the energy consumption optimization instructions are used to control the refrigeration equipment set in the server cabinet to perform refrigeration processing according to the energy consumption optimization instructions.

9. An energy consumption management system, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A server cabinet, characterized in that: It includes a U-position detection system, a management module and an energy consumption management system as claimed in claim 9; wherein, The U-position detection system is used to obtain the U-position distribution information and the equipment U-position occupancy information of the server cabinet; The energy consumption management system is used to obtain energy consumption optimization instructions for the server cabinet; The management module is used to adjust the setting position and working status of each device in the server cabinet according to the U-position distribution information, the device U-position occupancy information and the energy consumption optimization instruction for the server cabinet.

11. A computer-readable storage medium having a computer program stored thereon, 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.

12. 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