Data center air conditioner control method and air conditioner control system

Abstract

The invention discloses a data center air conditioner control method and an air conditioner control system, and relates to the technical field of air conditioner control. The method comprises the steps that the real-time electricity consumption of each array cabinet is obtained, the total electricity consumption of a machine room is determined, and the load power of the machine room is determined based on the total electricity consumption; determining the total cooling capacity output of the air conditioner according to the load variable quantity of the load power and a temperature set value in a preset period; and on the basis of the total cooling capacity output, operation parameters of the air conditioner are determined, and the air conditioner is controlled to operate according to the operation parameters. According to the method, the power utilization data of the machine room is converted into the heat representation, so that rapid and accurate heat management is realized, the air conditioning system of the data center can adjust cold supply in real time according to the actual load of the machine room, and the instant cold supply requirement of the data center is met.

Description

Technical Field

[0001] The present application relates to the field of air conditioning control technology, and in particular to a data center air conditioning control method and an air conditioning control system. Background Art

[0002] The air conditioning system of a traditional data center usually controls the opening of the water valve and the speed of the fan based on the deviation between the supply air temperature and the return air temperature and the set value, using the PID (Proportional Integral Derivative) control principle to achieve temperature control in the computer room area. However, with the widespread application of artificial intelligence big models, the basic model of data center business is also changing.

[0003] For example, in the intelligent computing center, which uses GPU (Graphics Processing Unit) servers as the main equipment, the power of a single cabinet has been significantly increased, from 4-6kW in traditional computer rooms to 10-15kW or even higher. The actual operation of the intelligent computing center shows that when the GPU server is in standby mode, the power consumption is about 20-30% of the rated power. However, when the intelligent computing center starts to perform training tasks, all GPUs will quickly reach full load, and the load of a single cabinet can reach 80-90% of the rated value.

[0004] The air conditioning system of a traditional data center usually installs temperature sensors inside the air conditioning equipment and adjusts the room temperature through a long-distance supply and return air mode. Therefore, when the temperature of the room rises rapidly due to the training tasks performed by the intelligent computing center, the cooling response of the air conditioning system of the traditional data center will be significantly delayed and cannot immediately meet the cooling demand of the equipment in the room. Summary of the invention

[0005] The main purpose of this application is to provide a data center air conditioning control method and an air conditioning control system, aiming to solve the technical problem that the traditional air conditioning system has a delayed cooling response and cannot immediately meet the cooling demand of the equipment in the data center computer room.

[0006] To achieve the above object, an embodiment of the present application provides a data center air conditioning control method, the data center air conditioning control method comprising: Obtain the real-time power consumption of each cabinet, determine the total power consumption of the computer room, and determine the load power of the computer room based on the total power consumption; Determining the total cooling output of the air conditioner according to the load change of the load power within a preset period and the temperature setting value; Based on the total cooling output, operating parameters of the air conditioner are determined, and the air conditioner is controlled to operate according to the operating parameters.

[0007] In one embodiment, the step of determining the total cooling output of the air conditioner according to the load change amount of the load power within a preset period and the temperature setting value includes: Acquire the current of each of the first cabinets, and calculate the current load of each of the first cabinets based on the current; Based on the current load, determine the average load of the cabinets in the equipment room at present, and use the average load as a reference load; When the real-time load of the computer room is higher than the reference load, calculating the load change within a preset period; The total cooling capacity output of the air conditioner is determined according to the load change.

[0008] In one embodiment, the step of determining the total cooling output of the air conditioner according to the load change further includes: According to the load variation interval in which the load variation is located, determining the range of cooling capacity required to offset the heat in different load variation intervals; Obtaining the basic cooling capacity and temperature setting value of the current computer room; The total cooling output of the air conditioner is determined within the cooling capacity range according to the basic cooling capacity and the temperature setting value.

[0009] In one embodiment, after the step of determining the total cooling output of the air conditioner in the cooling capacity range according to the basic cooling capacity and the temperature setting value, the method further comprises: If the total cooling capacity output is greater than the basic cooling capacity, controlling the air conditioner to increase the cooling capacity; If the total cooling output is less than the basic cooling capacity, the air conditioner is controlled to reduce the cooling capacity.

[0010] In one embodiment, the step of determining the operating parameters of the air conditioner based on the total cooling output, and controlling the air conditioner to operate according to the operating parameters includes: According to the total cooling output and in combination with the refrigeration performance curve of the air conditioner, searching for initial operating parameters of the air conditioner corresponding to the total cooling output; Obtaining real-time temperature data of the equipment room and determining the temperature gradient and temperature change trend; adjusting the initial operating parameters according to the temperature gradient and the temperature change trend to obtain the operating parameters of the air conditioner; The operating parameters are sent to the air conditioner, and the air conditioner is driven to operate according to the operating parameters.

[0011] In one embodiment, the step of determining the operating parameters of the air conditioner based on the total cooling output, and controlling the air conditioner to operate according to the operating parameters, further includes: Use the prediction model to predict the power consumption data and temperature data within the preset time period in the future; Determining the cooling demand change trend of the computer room according to the prediction result of the prediction model; The operating parameters of the air conditioner are determined according to the cooling demand change trend and the temperature setting value.

[0012] In one embodiment, after the step of determining the operating parameters of the air conditioner according to the cooling demand change trend and the temperature setting value, the step further includes: transmitting the operating parameters to the air conditioner; Acquire system feedback data of the air conditioner running based on the operating parameters; Based on the system feedback data, the prediction model is iteratively trained through a neural network to optimize the prediction model; Based on the optimized prediction model, the step of using the prediction model to predict the power consumption data and temperature data within a preset time period in the future is jumped to execution.

[0013] In one embodiment, the data center air conditioning control method further includes: Establish two groups of communication connections, the first group of communication connections is the communication connection from the air conditioner to the controller, and the second group of communication connections is the communication connection from the electric meter of the cabinet to the controller; The communication connection uses a shielded twisted pair cable, and the communication connection includes serial port communication, network port communication, and a combination of the serial port communication and the network port communication.

[0014] An embodiment of the present application provides an air-conditioning control system, which includes a controller and a communication system between the controller, a power distribution cabinet and an air conditioner. The controller includes a wall-mounted type or a rack-mounted type, wherein the rack-mounted type can be installed with a cabinet, and the wall-mounted type has an IP65 protection function. The controller implements the steps of the data center air-conditioning control method as described above.

[0015] An embodiment of the present application also provides an air conditioning control system, which further includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the data center air conditioning control method as described above.

[0016] The embodiment of the present application discloses a data center air conditioning control method, which determines the total power consumption of the computer room by obtaining the real-time power consumption of each cabinet, and determines the load power of the computer room based on the total power consumption; determines the total cooling output of the air conditioner according to the load change amount and the temperature setting value of the load power within a preset period; determines the operating parameters of the air conditioner based on the total cooling output, and controls the air conditioner to operate according to the operating parameters. The present application realizes fast and accurate heat management by converting the power consumption data of the computer room into heat representation, ensuring that the air conditioning system of the data center can adjust the cooling supply according to the actual load of the computer room in real time, and realizes the immediate cooling demand of the data center. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of CPU temperature changes under a traditional air conditioning control strategy of an air conditioning control system involved in an embodiment of the present application; Figure 2 A schematic diagram of CPU temperature change after the air conditioning control system according to the embodiment of the present application changes the air conditioning control strategy; Figure 3 A schematic diagram of serial communication between a precision power distribution cabinet and a precision air conditioner of an air conditioning control system according to an embodiment of the present application; Figure 4 A schematic diagram of a precision power distribution cabinet and a precision air conditioner of an air-conditioning control system according to an embodiment of the present application using network port communication; Figure 5 A schematic diagram of a combination of serial port communication and network port communication used by a precision power distribution cabinet and a precision air conditioner of an air conditioning control system according to an embodiment of the present application; Figure 6 A flow chart of a data center air conditioning control method according to an embodiment of the present application using a controller integrated communication method; Figure 7 A schematic diagram of a wall-mounted control cabinet of an air-conditioning control system according to an embodiment of the present application; Figure 8 It is a flowchart of a first embodiment of a data center air conditioning control method involved in an embodiment of the present application; Fig. 9 This is a brief flowchart of a first embodiment of a data center air conditioning control method according to an embodiment of the present application; Fig.10 This is a flow chart of a second embodiment of a data center air conditioning control method according to an embodiment of the present application; Fig.11 This is a flow chart of a third embodiment of a data center air conditioning control method according to an embodiment of the present application; Fig.12This is a flow chart of a fourth embodiment of a data center air conditioning control method according to an embodiment of the present application; Fig.13 This is a schematic diagram of the structure of the air-conditioning control system involved in the embodiment of the present application.

[0018] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] 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.

[0020] The air conditioning system of a traditional data center usually controls the opening of the water valve and the speed of the fan based on the deviation between the supply air temperature and the return air temperature and the set value, using the PID (Proportional Integral Derivative) control principle to achieve temperature control in the computer room area. However, with the widespread application of artificial intelligence big models, the basic model of data center business is also changing.

[0021] For example, in the intelligent computing center, which uses GPU (Graphics Processing Unit) servers as the main equipment, the power of a single cabinet has been significantly increased, from 4-6kW in traditional computer rooms to 10-15kW or even higher. The actual operation of the intelligent computing center shows that when the GPU server is in standby mode, the power consumption is about 20-30% of the rated power. However, when the intelligent computing center starts to perform training tasks, all GPUs will quickly reach full load, and the load of a single cabinet can reach 80-90% of the rated value.

[0022] The air conditioning system of a traditional data center usually installs temperature sensors inside the air conditioning equipment and adjusts the room temperature through a long-distance air supply and return mode. Therefore, when the intelligent computing center performs training tasks and causes the room temperature to rise rapidly, the cooling output of the air conditioning system of the traditional data center lags significantly behind the heat generated by the CPU (Central Processing Unit) and GPU, causing the temperature of the server CPU / GPU to fluctuate greatly. The CPU temperature change diagram under the traditional air conditioning control strategy is shown in the figure below. Figure 1 shown.

[0023] Therefore, traditional data centers use the PID control principle to control the opening of the water valve and the speed of the fan based on the deviation between the supply air temperature, return air temperature and the set value, which cannot immediately meet the cooling needs of the equipment in the computer room.

[0024] In order to solve the above defects existing in the related art, the embodiment of the present application proposes a data center air conditioning control method, which determines the total power consumption of the computer room by obtaining the real-time power consumption of each cabinet, and determines the load power of the computer room based on the total power consumption; determines the total cooling output of the air conditioner according to the load change and temperature setting value of the load power within a preset period; determines the operating parameters of the air conditioner based on the total cooling output, and controls the air conditioner to operate according to the operating parameters. The present application realizes fast and accurate heat management by converting the power consumption data of the computer room into heat representation, ensuring that the air conditioning system of the data center can adjust the cooling supply according to the actual load of the computer room in real time, and realizes the immediate cooling demand of the data center.

[0025] It should be noted that the execution subject of this embodiment can be an air conditioning control system, or a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an air conditioning control device capable of realizing the above functions, such as an AI controller. The following takes the AI ​​controller (hereinafter referred to as the "controller") as an example to illustrate this embodiment and the following embodiments.

[0026] In order to meet the immediate cooling needs of the data center, the present application also provides an air-conditioning system, which is based on the data acquisition and communication network of the precision power distribution cabinet and the chilled water precision air conditioner, and realizes real-time monitoring of the computer room and intelligent control of the air-conditioning system through the controller integrated communication method.

[0027] This application changes the logic of the air conditioner to control itself based on the supply and return air temperature, and instead uses the actual power consumption of the server as the main control basis. Since the power consumption of the server is almost entirely converted into heat, that is, the actual power consumption of the server, the data collected in real time by the electric meter in the cabinet shall prevail.

[0028] The real-time electricity data collected from the electric meters in the cabinets are analyzed and calculated through the AI ​​big model, and the corresponding operating parameters are output to control the fan and water valve of the air conditioner, and then the output of the air conditioner cooling capacity is controlled in real time to meet the cooling demand of the server in the computer room.

[0029] Since the speed of collecting the power consumption of the server is much higher than the speed of collecting the temperature of the computer room, after changing the control strategy of the air conditioner, no matter how the server load changes, the server CPU / GPU temperature is stable and meets the relevant specifications. The schematic diagram of the CPU temperature change after changing the control strategy of the air conditioner is as follows: Figure 2 shown.

[0030] In this embodiment, the air-conditioning control system adopts a combination of software and hardware. In terms of hardware, an AI controller is deployed on-site in the data room, and network communication is used to access the data collection of the precision distribution cabinet and the data collection of the precision air conditioner, and intelligent control is performed. At the software level, a basic general model is first constructed, and an AI genetic algorithm or a particle swarm algorithm is introduced on the basis of the basic general model. These algorithms are used to optimize the control strategy, that is, by simulating biological genetic processes or the collaborative behavior of particle groups, the best control strategy is continuously searched and optimized. The optimal control strategy will be output to the on-site AI controller. After receiving the instruction, the controller converts it into a specific control action, such as adjusting the compressor speed, fan speed, expansion valve opening, etc. of the air conditioner, so that the air-conditioning control system operates according to the optimized operating parameters.

[0031] After the air conditioning control system runs according to the optimized operating parameters, it will send feedback information. The feedback information includes the actual parameters and status of the air conditioning control system. The prediction model compares the received system feedback information and passes the feedback information to the linear regression neural network. The neural network continuously iterates and optimizes the prediction model by comparing the difference between the actual feedback information and the expected target. In this process, the prediction model can self-learn and enhance, continuously adjust, and then return to the strategy optimization stage again, realizing the continuous iteration and upgrading of the model to better meet the operation requirements of the data center air conditioning control system.

[0032] Furthermore, the air conditioning control system provided in the embodiment of the present application includes a controller and a communication system between the controller, the power distribution cabinet and the air conditioner. The controller supports dual power input to ensure stable power supply of the controller, avoid system interruption due to single power failure, and improve the reliability of the system. The controller is also equipped with a human-machine interface (control panel) to facilitate operators to view parameters, input operation instructions, etc., providing an intuitive and convenient operation method.

[0033] In addition, the controller includes wall-mounted or rack-mounted. The rack-mounted type can be installed in a standard cabinet and integrated with other devices in the cabinet, which is convenient for unified management and maintenance in environments such as data centers. The wall-mounted type has IP65 protection function and can operate normally in harsh environments, such as air-conditioned rooms where dust, water vapor or other pollutants may exist.

[0034] When controlling the air conditioning in the data center, the controller will use its data acquisition function to collect various operating data of the distribution cabinet and the air conditioner, including the voltage, current, power factor and other parameters of the distribution cabinet, as well as the temperature, humidity, compressor status, fan speed, air volume, water valve opening and other information of the air conditioner. Subsequently, according to the data center air conditioning control method, these data are analyzed and processed, and corresponding control strategies are formulated through the prediction model to achieve refined control of the air conditioner and the distribution cabinet, such as adjusting the cooling capacity of the air conditioner, adjusting the fan speed, controlling the power distribution of the distribution cabinet, etc., in order to achieve the purpose of optimizing energy utilization and maintaining stable environmental temperature and humidity.

[0035] It should be noted that in this embodiment and other embodiments, if the controller goes down due to various reasons during the application process, it will not affect the operation of the original automatic control system of the air conditioner, nor will it affect the monitoring of the original dynamic environment system. Even if the controller fails, the original automatic control system of the air conditioner can still operate normally according to its own set procedures and logic, ensuring that the temperature, humidity and other environmental parameters in the machine room will not be out of control due to the failure of the controller, ensuring the basic environmental regulation function. At the same time, the original dynamic environment system can also continue to monitor various parameters in the environment, including monitoring and recording of information such as temperature, humidity, power parameters, and equipment operating status.

[0036] Specifically, in terms of implementation basis, this air conditioning control system deploys a precision power distribution cabinet in the data room and a chilled water precision air conditioner in the air conditioning room. The precision power distribution cabinet is used to collect real-time power data from the electric meter of the column head cabinet. According to different communication requirements, the system is divided into three scenarios to realize data collection and communication: Scenario 1: Both the precision power distribution cabinet and the precision air conditioner use serial communication. Figure 3 , Figure 3 Schematic diagram of serial communication between precision power distribution cabinet and precision air conditioner.

[0037] The 1-N precision air conditioners in the air-conditioning room on the corresponding side of the data room uniformly use RS485 ("hand-in-hand" connection method) interface to communicate with the host computer. The 1-N precision power distribution cabinets in the data room also use RS485 to communicate with the host computer, and the host computer is connected to the network switch of the acquisition system.

[0038] It should be noted that the host computer can be a serial port server or an embedded server and other devices, and its main function is to access the network switch of the acquisition system to achieve real-time collection and monitoring of power data.

[0039] Scenario 2 is that both the precision power distribution cabinet and the precision air conditioner use network port communication. Figure 4 , Figure 4This is a schematic diagram of the network port communication between the precision power distribution cabinet and the precision air conditioner. The 1-N precision air conditioners in the air conditioning room on one side of the data room and the 1-N precision power distribution cabinets in the data room each use RJ45 network ports to communicate with the network switch of the acquisition system.

[0040] Scenario 3 is that the precision power distribution cabinet uses network port communication and the precision air conditioner uses serial port communication. Figure 5 , Figure 5 This is a schematic diagram of the combination of serial port communication and network port communication used by precision power distribution cabinets and precision air conditioners. Among them, the precision power distribution cabinet uses network port communication, and the precision air conditioner uses serial port communication. The 1-N precision power distribution cabinets in the data room use RJ45 network ports to communicate with the network switch of the acquisition system, and the 1-N precision air conditioners in the air conditioning room on the corresponding side of the data room use RS485 to communicate with the host computer, and the host computer is connected to the network switch of the acquisition system.

[0041] It should be noted that in the three communication scenarios in this embodiment, the use of single-sided air supply in the data room is only an optional solution. This embodiment does not limit the air conditioning layout of the air conditioning room in the data room, and double-sided air supply or other air conditioning layout solutions can also be used.

[0042] Collecting electrical data such as current, voltage, and power of the precision distribution cabinet, as well as operating parameters such as the water valve opening and fan speed of the precision air conditioner, provides an important data source and judgment basis for the embodiments of this application. Traditional precision air conditioners use serial communication, which requires data transparent transmission through the host computer to access the acquisition network, and has a certain delay in the training cycle. In addition to selecting serial communication, this embodiment can be optimized to network communication to increase the response speed. Alternatively, a combination of serial communication and network communication can be used. Among them, if network communication is used for data collection of the precision distribution cabinet, it can meet the needs of low latency and fast response.

[0043] Furthermore, the air conditioning control system in this embodiment is used to implement a data center air conditioning control method, which uses a controller integrated communication method, as follows: Two groups of communication connections are established, the first group of communication connections is the communication connection from the air conditioner to the controller, and the second group of communication connections is the communication connection from the electric meter of the cabinet to the controller. The communication connection uses a shielded twisted pair cable, and the communication connection includes serial port communication, network port communication, and a combination of serial port communication and network port communication.

[0044] For example, to help understand the implementation process of the data center air conditioning control method in this embodiment, please refer to Figure 6 , Figure 6 A flow chart of the controller integrated communication method is provided, specifically: In this embodiment, the communication connection includes two groups: the communication connection from the air conditioner to the wall-mounted control cabinet, and the communication connection from the electric meter of the cabinet to the wall-mounted control cabinet. The communication connection is carried out in a hand-in-hand connection mode. The air conditioner end is the P9 terminal of the air conditioner controller, the wall-mounted control cabinet end connected to the air conditioner end is the A2 / B2 terminal of its internal terminal row, the wall-mounted control cabinet end connected to the electric meter end of the cabinet is the A3 / B3 terminal of its internal terminal row, and the electric meter end of the cabinet is the A1 / B1 terminal of the electric meter.

[0045] It should be noted that in electrical engineering, a terminal refers to a wiring terminal, also known as a wiring terminal. The A1 / B1 terminal, A2 / B2 terminal, and A3 / B3 terminal mentioned in this embodiment are only a reference to the name of the interface used for access. In actual applications, there is no limit on the number of interfaces connected to the air conditioner terminal, the wall-mounted control cabinet terminal, and the meter terminal of the electric cabinet.

[0046] In addition, the controller mentioned in the embodiment of the present application is included in the wall-mounted control cabinet. After the wall-mounted control cabinet obtains the power consumption data of each electric meter in the row cabinet, it will perform peak filtering on the power consumption data, and then predict the power consumption data through the prediction model at the software level, so as to obtain the power consumption and environmental data of the current computer room in the future, and then determine the operating parameters of the air conditioner according to the prediction, and send the operating parameters to the air conditioner controller P9. After receiving the operating parameter instruction, the air conditioner controller P9 will accurately adjust the various operating settings of each air conditioner according to the instruction, thereby completing the intelligent regulation of the air conditioning system and realizing the stable control of environmental parameters such as temperature and humidity in the computer room.

[0047] For example, in the connection between the electric meter in the terminal cabinet and the wall-mounted control cabinet, each electric meter in the terminal cabinet is connected to the wall-mounted control cabinet separately, and multiple interfaces will appear. In actual applications, the number of interfaces will vary according to the specific number of devices and connection requirements. Please refer to Figure 7 , Figure 7 Schematic diagram of the wall-mounted control cabinet of the air-conditioning control system.

[0048] exist Figure 7 In the description, the incoming line circuit breaker is the abbreviation of the incoming line air switch, which is a circuit protection device. Incoming line circuit breaker 1 and incoming line circuit breaker 2 are mainly used to control and protect the main power line entering the device or system. A dual power switching device is a device that can automatically or manually switch between two power supplies. A terminal block is an accessory for realizing electrical connection, which is composed of a plurality of terminal blocks. A transformer is a device that uses the principle of electromagnetic induction to change the AC voltage. The controller is the core control component of the wall-mounted control cabinet, which usually includes various electronic components and control circuits to execute and realize the steps of the data center air conditioning control method in this embodiment and the following embodiments.

[0049] The data center air conditioning control method of the first embodiment proposed in this application, please refer to Figure 8 The method comprises steps S10 to S30: Step S10: acquiring the real-time power consumption of each cabinet, determining the total power consumption of the computer room, and determining the load power of the computer room based on the total power consumption.

[0050] Data centers usually contain a large number of high-performance computing devices, which consume a lot of power and generate corresponding heat during operation. Since the power consumption of the equipment is almost entirely converted into heat, the actual power consumption of the equipment can be calculated based on the power data collected in real time by the electric meter in the cabinet.

[0051] The first cabinet is the cabinet at the front of a row of equipment in the computer room. It provides power distribution and management for the equipment in this row. The real-time power consumption of each first cabinet can be obtained through the electric meter or other power monitoring equipment equipped in the first cabinet.

[0052] When the device is started or running, there may be instantaneous current or power peaks. However, these peaks do not represent the stable power of the device and may interfere with the calculation of actual power consumption and air conditioning control. Therefore, it is necessary to perform peak filtering on the collected power data to obtain power data that can reflect the normal operation of the device.

[0053] In this process, multiple algorithms such as sliding window averaging and median filtering can be used to achieve peak filtering. The sliding window averaging method averages the power data within a certain time window, regards the maximum value exceeding a certain threshold as the peak value, and replaces it with the average value within the window, thereby making the power data smoother.

[0054] For example, the electricity data of each cabinet is obtained through the cabinet meter. The sliding window averaging method is used, assuming that the window size is time points, real-time electricity consumption data for each time point , calculate the before and after / Average value of 2 time points ,when Greater than a certain multiple (such as 1.5 times) , it is considered as a peak value and replaced by .

[0055] After obtaining and processing the real-time power consumption of each cabinet, in order to control the power consumption of the entire computer room, it is necessary to summarize the power data of each cabinet to obtain the total power consumption of the computer room. The total power consumption of the computer room reflects the total amount of power consumed by all equipment in the computer room during a certain period of time, and thus reflects the total heat generated by the entire computer room. The controller will then adjust the cooling output of the air conditioner according to the overall load of the computer room to ensure that the temperature in the computer room is maintained within an appropriate range to avoid performance or damage caused by overheating of the equipment.

[0056] In an optional implementation scheme, the real-time power consumption of each cabinet is first collected through the electric meter or other power monitoring equipment equipped in the cabinet. Then, the real-time power consumption is peak filtered to remove the instantaneous high power consumption peak caused by equipment startup, load mutation, etc. Then, the load of each cabinet is determined based on the real-time power consumption data after peak filtering. Then add up the load values ​​of each cabinet to determine the load power of the entire computer room.

[0057] Step S20: determining the total cooling output of the air conditioner according to the load change of the load power within a preset period and the temperature setting value.

[0058] The load change refers to the increase or decrease in the load power of the computer room within a preset period. The load change reflects the change in the operating status of the equipment in the computer room. The temperature setting value is pre-set according to the requirements of the equipment in the computer room for the ambient temperature. Each temperature setting value corresponds to a cooling demand value, which is determined based on the optimal operating temperature range and heat dissipation characteristics of the equipment in the computer room. It is a reference for the cooling capacity corresponding to the operating temperature required to maintain the stable operation of the equipment in the computer room. The total cooling output refers to the cooling capacity that the air conditioner needs to provide within a certain period of time to offset the heat generated by the equipment in the computer room.

[0059] For example, within a preset period of half an hour, the load power of the equipment room is recorded at the beginning as , the load power recorded at the end is , then the load change for .

[0060] In this embodiment, in order to determine the total cooling output of the air conditioner, the change in the operating state of the equipment in the computer room is judged according to the load change in a preset period. If the load change is positive, that is, the load is increased, it indicates that the power of the equipment in the computer room has increased, the heat generated has increased, and more cooling output is required accordingly. If the load change is negative, that is, the load is reduced, it indicates that the power of the equipment in the computer room has decreased, the heat generated has also decreased, and the cooling output of the air conditioner is reduced accordingly.

[0061] In this process, the total cooling output is calculated based on the current total power consumption of the computer room and the basic heat load required by the computer room environment, including the space size, insulation performance and equipment layout of the computer room.

[0062] In an optional implementation, historical load power change data, historical power consumption data of the computer room, actual temperature change data in the computer room, and corresponding air conditioning cooling output values ​​are collected and used as a training set. A deep learning model, such as a neural network, is used to learn and train the data in the training set.

[0063] During the model training process, the model input includes parameters such as the load change within the preset period, the total power consumption of the computer room, and the temperature setting value, and the output is the total cooling output value of the air conditioner. Through continuous training and feedback, the model can learn the changing trend of the computer room load through the load change within the preset period, and thus determine whether to increase or decrease the cooling output. Then, the increase is determined based on the total power consumption and temperature setting value of the computer room. Finally, the model can predict the total cooling output required by the computer room based on the real-time total power consumption, load change, and temperature setting value of the computer room.

[0064] For example, when the load change is positive, it means that the load in the computer room has increased, but the specific increase needs to be judged in combination with the total power consumption. If the total power consumption also increases a lot, it means that the load increase is large, and the air conditioner needs to provide more cooling to cope with it. If the total power consumption does not increase much, it means that the load increase is small, and the cooling output of the air conditioner can be adjusted accordingly.

[0065] In addition, in another optional implementation scheme, the equipment density and heating conditions in different areas of the computer room may be different. Zoning control can be used to divide the computer room into multiple areas, and each area is equipped with an independent cabinet power monitoring device.

[0066] The load power and load change of each area are calculated separately, and the cooling output of the air conditioner in each area is determined specifically according to the temperature setting value of each area.

[0067] Step S30: determining operating parameters of the air conditioner based on the total cooling output, and controlling the air conditioner to operate according to the operating parameters.

[0068] In this embodiment, the real-time total power consumption of the computer room is used as the main basis for the total cooling output of the air conditioner, so as to achieve accurate matching and immediate response of cooling and power. Based on the total cooling output, the operating parameters of the air conditioner can be adjusted through control algorithms such as PID control (proportional-integral-derivative control), fuzzy logic control or machine learning algorithms.

[0069] Specifically, the operating parameters of the air conditioner are determined based on the determined total cooling output and the performance curve of the air conditioner itself. For example, the appropriate speed value is inferred based on the correspondence between the compressor speed and the cooling capacity. By monitoring the temperature conditions at different locations in the computer room and combining the total cooling output, the fan speed is adjusted using the air volume adjustment algorithm to control the fan air volume, thereby achieving uniform distribution of cooling capacity; or the air volume weights of different areas can be set in advance according to the layout of the computer room and the distribution of equipment to ensure that areas with more heat can get more cold air. In addition, the electronic expansion valve technology is used to adjust the expansion valve opening in real time according to the total cooling output and the data fed back by the refrigerant temperature, pressure and other sensors.

[0070] In an optional implementation, the controller can also collect the water valve data of the air conditioner and quickly feed it back to the corresponding control system, such as the BA system (Building Automation System). The water valve data is used as the control basis for the air conditioner's water pump and chiller, thereby improving the response speed of the entire refrigeration system.

[0071] It should be noted that the control system mentioned here can be a central control system connected to the air-conditioning control system, or other equipment responsible for managing and coordinating water pumps, chillers, etc.

[0072] For example, to help understand the implementation process of the data center air conditioning control method in this embodiment, please refer to Fig. 9 , Fig. 9 A brief flow chart of a data center air conditioning control method is provided, specifically: First, real-time power consumption data of multiple cabinets is collected to obtain the real-time power consumption data of each cabinet. Then, peak filtering is started on the collected real-time power consumption data to remove the instantaneous current or power peaks that occur accidentally at the moment of equipment startup or during operation, so that the real-time power consumption data can accurately reflect the power consumption of the equipment under normal operation.

[0073] Next, the load of each cabinet is calculated based on the real-time power consumption data after peak filtering, and the load of all cabinets is calculated. Accumulate the load power of the entire computer room, and then calculate the load change of the computer room within the preset period. .

[0074] Subsequently, the temperature setting value is compared with the room temperature, and the difference between the two is input into the expert PID controller. The expert PID controller outputs a control signal based on the difference, thereby controlling the fan speed and water valve opening, etc., and finally adjusting the room temperature to keep it near the set value.

[0075] In this embodiment, the load power of the computer room is determined by obtaining the real-time power consumption of the cabinet, and the total cooling output of the air conditioner is determined according to the load change and the temperature setting value, thereby determining the air conditioner operating parameters and controlling its operation. The data center air conditioning control method in this embodiment can achieve accurate matching and instant response of cooling capacity and power. Compared with the conventional air conditioning automatic control system, the response time of the air conditioning control system using the method of this embodiment is shortened from minutes (about 2 minutes) to seconds, and can be controlled within 10 seconds, which significantly improves the response speed and control accuracy of the system, and can more quickly and accurately adjust the cooling capacity of the air conditioner according to the actual power consumption of the equipment in the computer room, ensuring that the equipment in the computer room is always in a suitable temperature environment, and improving the stability and reliability of the operation of the computer room.

[0076] Please refer to Fig.10 In the data center air conditioning control method of the second embodiment proposed in this application, step S20 includes steps S21 to S24: Step S21: acquiring the current of each of the first cabinets, and calculating the current load of each of the first cabinets based on the current.

[0077] In this embodiment, the load borne by each terminal cabinet is calculated based on the current of the terminal cabinet and combined with electrical formulas (such as power = voltage × current. When the voltage is relatively stable, the current can approximately reflect the load power). It represents the power load level of the equipment connected to the terminal cabinet.

[0078] By installing current sensors and other equipment on the power supply cabinet, the current data of the power supply cabinet can be obtained in real time. Then, according to the voltage and other parameters of the power supply system in the computer room, the current load of each power supply cabinet can be calculated using the above electrical formula.

[0079] Step S22: Based on the current load, determine the average load of the cabinets in the equipment room at present, and use the average load as a reference load.

[0080] In this embodiment, multiple cabinets in the computer room jointly supply power to the equipment. In order to determine the overall load condition of the computer room, it is necessary to determine a benchmark value that can represent the overall load level of the computer room so as to compare it with the real-time load and determine the changing trend of the computer room load.

[0081] Add the current loads of all the cabinets calculated in the above steps, and then divide it by the number of cabinets to get an average value, which can reflect the average level of cabinet loads in the room. This average value is used as the benchmark load for judging the real-time load changes in the room.

[0082] Step S23: When the real-time load of the computer room is higher than the reference load, the load variation within a preset period is calculated.

[0083] When the real-time load of the computer room is higher than the benchmark load, it indicates that the power consumption of the equipment in the computer room has increased, and the heat generated will also increase accordingly. At this time, it is necessary to calculate the load change so that the total cooling output of the air conditioner can be adjusted according to the load change to maintain the stability of the computer room temperature.

[0084] Step S24: determining the total cooling output of the air conditioner according to the load change.

[0085] In an optional implementation, step S24 further includes steps S241 to S243: Step S241: determining the range of cooling required to offset heat in different load variation intervals according to the load variation interval in which the load variation is located.

[0086] The load variation interval is preset to divide the load variation into different ranges. For example, the load variation can be divided into several intervals such as small range variation, medium range variation, and large range variation based on experience or experimental data, and each interval corresponds to a different load variation amplitude. Among them, each load variation interval corresponds to a range of cooling required to offset the heat, that is, when the load variation is in a certain interval, in order to maintain the temperature of the computer room stable, the range of the total cooling output of the air conditioner is required.

[0087] Step S242: Obtain the basic cooling capacity and temperature setting value of the current computer room.

[0088] Basic cooling capacity refers to the cooling capacity that the computer room itself can provide without relying on active cooling by air conditioning, such as the cooling capacity from the computer room's insulation structure, ventilation system, and natural cooling sources in the environment. It can help lower the temperature in the computer room to a certain extent.

[0089] The basic cooling capacity may also include the cooling capacity corresponding to the operating parameters of the air conditioner currently running in the computer room, that is, the cooling capacity of the air conditioner when the operating parameters are not adjusted.

[0090] Step S243: determining the total cooling output of the air conditioner within the cooling capacity range according to the basic cooling capacity and the temperature setting value.

[0091] In this embodiment, the basic cooling capacity and the desired temperature setting value are known, and the system will select a suitable value in the predetermined cooling capacity range as the total cooling capacity output of the air conditioner. The selection process can comprehensively consider the matching degree between the basic cooling capacity and the actual situation of the current computer room, as well as the cooling capacity adjustment required to achieve the temperature setting value.

[0092] For example, if the actual temperature of the current computer room is higher than the temperature setting value, and the basic cooling capacity is insufficient to adjust the temperature to the setting value, a relatively large value in the cooling capacity range needs to be selected as the total cooling capacity output to ensure that there is enough cooling capacity to lower the temperature of the computer room.

[0093] If the actual temperature of the current computer room is lower than the set temperature value and the basic cooling capacity is relatively large, a smaller value may be selected in the cooling capacity range to avoid over-cooling.

[0094] Specifically, algorithms or rules are used, such as the difference between the basic cooling capacity and the temperature setting value, the current load change trend of the computer room, the heat dissipation conditions of the environment, and other information, to determine the specific value of the total cooling output within the cooling capacity range, so as to ensure that the air-conditioning system can achieve energy saving and efficient operation while meeting the cooling demand of the equipment in the computer room, ensure that the temperature in the computer room is always stable, and ensure that servers and other equipment work in a suitable temperature environment to avoid adverse effects on equipment performance and life due to excessively high or low temperatures.

[0095] Further, step S243 includes steps S244 to S245: Step S244: If the total cooling output is greater than the basic cooling capacity, the air conditioner is controlled to increase the cooling capacity.

[0096] Step S245: If the total cooling output is less than the basic cooling capacity, the air conditioner is controlled to reduce the cooling capacity.

[0097] When there is a load change, whether the load increases or decreases, obtain the basic cooling capacity in the current computer room and compare it with the total cooling output. There will be at least three situations: First, the basic cooling capacity is consistent with the total cooling output, indicating that the load variation is small and there is no need to adjust the operating parameters of the air conditioner.

[0098] Second, if the cooling capacity corresponding to the current operating parameters of the air conditioner is less than the total cooling output, it is necessary to adjust the operating parameters of the air conditioner, such as increasing the compressor speed of the air conditioner, increasing the fan air volume or adjusting the expansion valve opening, so that the cooling capacity is increased to the total cooling output.

[0099] Third, if the cooling capacity corresponding to the current operating parameters of the air conditioner exceeds the total cooling output, the cooling output will be reduced.

[0100] Please refer to Fig.11 In the data center air conditioning control method of the third embodiment proposed in this application, step S30 includes steps S31 to S34: Step S31: according to the total cooling output and in combination with the refrigeration performance curve of the air conditioner, searching for the initial operating parameters of the air conditioner corresponding to the total cooling output.

[0101] After determining the total cooling output of the air conditioner, it needs to be converted into specific air conditioner operating parameters in order to actually operate and control the air conditioner. Since different air conditioners have different cooling performance, it is necessary to find the corresponding operating parameters based on their own cooling performance curves.

[0102] The refrigeration performance curve reflects the cooling capacity that the air conditioner can provide under different operating parameters, and describes the relationship between the cooling capacity of the air conditioner and the operating parameters (such as compressor speed, fan speed, expansion valve opening, etc.).

[0103] According to the calculated total cooling output, using the pre-stored refrigeration performance curve of the air conditioner, a set of operating parameters that meet the total cooling output requirements is found through search or interpolation calculation methods as initial operating parameters.

[0104] For example, if the total cooling output is Q, the corresponding compressor speed, fan speed, expansion valve opening and other parameters are found on the refrigeration performance curve. Using linear interpolation or nonlinear interpolation algorithm, according to the known performance curve data points, a set of parameter combinations closest to Q is found, and these parameter combinations are the initial operating parameters.

[0105] Step S32: Acquire the real-time temperature data of the machine room, and determine the temperature gradient and temperature change trend.

[0106] Step S33: adjusting the initial operating parameters according to the temperature gradient and the temperature change trend to obtain the operating parameters of the air conditioner.

[0107] In this embodiment, the initial operating parameters determined only according to the total cooling output may not fully meet the actual uneven temperature distribution in the computer room. Therefore, the initial operating parameters can be further adjusted according to the data collected by the sensors arranged in the computer room to ensure that the temperature conditions in each area of ​​the computer room can meet the requirements.

[0108] Temperature gradient refers to the temperature difference at different locations in the room, which reflects the spatial distribution of temperature in the room. Factors such as equipment heat dissipation at different locations and airflow organization in the room can cause temperature gradient.

[0109] The temperature change trend refers to the temperature change trend in the computer room over time. It is affected by factors such as equipment operation and air conditioning cooling output, and reflects the dynamic changes in the temperature in the computer room.

[0110] In this embodiment, temperature sensors are arranged in each corner of the computer room, and these sensors collect temperature data at different locations in the computer room in real time. By analyzing these data, when it is found that the temperature gradient is large or the temperature change trend does not meet the requirements, the initial operation parameters are adjusted.

[0111] For example, if the temperature in a certain area of ​​the room is high, you need to increase the fan speed of the air conditioner near that area or adjust the direction of the air outlet to improve the cooling capacity of the corresponding area. If the temperature change trend shows that the temperature rises too fast, you need to adjust the operating parameters of the air conditioner to increase the cooling capacity output.

[0112] During the adjustment process, the control algorithm can be used to adjust the initial operating parameters of the air conditioners in different areas according to the size and direction of the temperature gradient and the temperature change trend.

[0113] Step S34: sending the operating parameters to the air conditioner, and driving the air conditioner to operate according to the operating parameters.

[0114] The operating parameters adjusted by the control algorithm are transmitted to the air conditioner, so that the air conditioner operates according to the new operating parameters, thereby achieving precise control of the temperature of the computer room and ensuring the normal operation and stable performance of the equipment in the computer room.

[0115] It should be noted that the operating parameters include the compressor speed, fan speed, expansion valve opening, the opening status and intensity of the dehumidification or humidification function of the air conditioner, etc.

[0116] Please refer to Fig.12 In the data center air conditioning control method of the fourth embodiment proposed in the present application, step S30 further includes steps S35 to S37: Step S35: using the prediction model to predict the power consumption data and temperature data within a preset time period in the future.

[0117] The operating status of the equipment in the computer room and the environmental changes usually have certain regularity and periodicity. Therefore, we can use historical data to build a prediction model to make a reasonable estimate of the future situation. By analyzing the historical power data and historical environmental data, we can predict the future power consumption and temperature conditions of the computer room so as to plan the operation strategy of the air conditioner in advance. Then, we use the trained prediction model to predict the power consumption and temperature data in the future preset time period.

[0118] Step S36: Determine the change trend of the cooling demand of the computer room according to the prediction result of the prediction model.

[0119] It should be noted that the forecast results include the power consumption data and temperature trend forecast of the computer room in the future preset time period. The cooling demand of the computer room is essentially determined by the balance between the heat generated by the equipment and the heat dissipation of the environment. The increase in power consumption data means that more equipment is running at high load and the heat generation increases. Therefore, based on the power consumption data and combined with the temperature forecast, the trend of cooling demand can be determined.

[0120] When the prediction model predicts that the power consumption of the computer room will gradually increase and the temperature will also rise in the next period of time, it means that the demand for cooling is increasing. Conversely, if the power consumption decreases and the temperature also starts to drop, the demand for cooling will decrease.

[0121] Step S37: determining the operating parameters of the air conditioner according to the cooling demand change trend and the temperature setting value.

[0122] The trend of cooling demand indicates the direction of cooling demand. If cooling demand increases, the air conditioner operating parameters need to be adjusted accordingly to meet the cooling demand, and the cooling power needs to be increased. By adjusting the inverter output frequency and increasing the compressor speed, the refrigerant circulation is accelerated to increase the cooling output. In addition, the air supply volume should also be increased synchronously. By adjusting the fan speed and optimizing the opening degree of the air duct valve, the cold air can be evenly and quickly delivered to every corner of the room.

[0123] In an optional implementation, step S35 may include steps S351-S353: Step S351: Introduce a genetic algorithm or a particle swarm algorithm into the general model, and use the historical electricity data and the historical environmental data as inputs of the general model to train the general model.

[0124] The general model is a basic prediction model that aims to predict a certain future result based on input data. However, the environment of the computer room is relatively complex, and factors such as equipment operation status, power consumption, and ambient temperature affect each other. Therefore, if you want to accurately predict the future power consumption and temperature data of the computer room, it is difficult to achieve the ideal effect if you only rely on the general model. Therefore, the genetic algorithm or particle swarm algorithm is introduced to optimize the general model.

[0125] The historical power consumption data records the power consumption of the computer room at different time periods and under different equipment operating conditions, reflecting the degree of equipment load. The historical environmental data includes information such as the temperature and humidity of the computer room, which can reflect the heat generation and loss in the computer room.

[0126] The historical electricity data and historical environmental data are used as the input of the model, aiming to use the model to find the intrinsic connection between the data and thus predict the expected results.

[0127] Genetic algorithm and particle swarm algorithm are two optimization algorithms that can imitate natural phenomena and improve the performance of the model by searching and iteratively optimizing the solution space.

[0128] Specifically, the genetic algorithm is an algorithm that simulates the biological evolution process and optimizes a set of potential solutions (i.e., model parameters) through operations such as selection, crossover, and mutation. The particle swarm algorithm simulates the social behavior of a flock of birds or a school of fish and searches for the optimal solution by updating the position and velocity of particles.

[0129] The historical data is input into the general model after the optimization algorithm is introduced to obtain the prediction results of the historical data. The prediction results of the historical data include the power consumption data, temperature, humidity, pressure and other parameters of the computer room within a period of time after the historical time point.

[0130] Step S352: Construct a fitness function based on the inverse mean square error between the prediction results of historical data and the historical true values.

[0131] Mean square error is a commonly used indicator to evaluate forecast accuracy, which aims to calculate the average square difference between the predicted value and the actual value.

[0132] In this embodiment, the inverse of the mean square error is used as the fitness function, the purpose of which is to allow the general model after the optimization algorithm is introduced to find the model parameters that minimize the mean square error during the training process. Therefore, using the inverse of the mean square error as the fitness function means that the higher the fitness, the better the model performance. By constructing the fitness function, the performance of the current general model in predicting the data related to the computer room can be evaluated, and then the optimization algorithm can be guided in the direction of improving the prediction accuracy to optimize the general model.

[0133] Step S353: Based on the fitness function, the initial parameters of the general model are optimized and trained to obtain a trained prediction model.

[0134] During the training of the general model, the optimization algorithm will adjust the initial parameters of the general model according to the evaluation results of the fitness function. Taking the genetic algorithm as an example, by selecting individuals (parameter combinations) with higher fitness and performing crossover and mutation operations on them, new individuals are generated, and then iterates continuously, so that the individuals in the population continue to evolve towards a better solution, that is, the parameters of the general model are continuously adjusted, and finally the optimal parameter combination is found.

[0135] For the particle swarm algorithm, the particle position (corresponding to the model parameters) is updated according to the particle's current position, historical optimal position, global optimal position and speed update formula, thereby optimizing the model.

[0136] After the optimization training of the above optimization algorithm, the general model is finally trained into a prediction model that can accurately predict the relevant data of the computer room, so that the power consumption and environmental data of the computer room in the future can be better predicted based on the input real-time power data of the computer room.

[0137] In another optional embodiment, step S37 further includes steps S38 to S41: Step S38: Transmitting the operating parameters to the air conditioner.

[0138] In this embodiment, the current power data and environmental data of the computer room are input into the prediction model trained in the above steps, and then the operating parameters of the air conditioner are determined according to the prediction results of the prediction model.

[0139] Step S39: Obtaining system feedback data of the air conditioner operating based on the operating parameters.

[0140] In this embodiment, when the air conditioner receives the operating parameters and starts to operate, system feedback data is generated. The feedback data includes various information during the actual operation of the air conditioner, such as actual power consumption, current temperature, humidity, cooling or heating efficiency, and total cooling output of the air conditioner.

[0141] Step S40: Based on the system feedback data, the prediction model is iteratively trained through a neural network to optimize the prediction model.

[0142] After obtaining the system feedback data, in order to make the prediction model more accurate and reliable, the neural network is used to iteratively train the prediction model. In this step, the system feedback data is used as input, and the system feedback data is compared with the prediction results of the prediction model. Through the back propagation algorithm and gradient descent of the neural network, the parameters of the prediction model are adjusted according to the feedback data, so that the prediction model can better learn the actual operating rules of the power consumption data and environmental data of the computer room.

[0143] Through multiple iterative training, the parameters of the prediction model are continuously updated, so that the prediction model can gradually reduce the prediction error, thereby optimizing the prediction model and improving its accuracy and reliability in predicting future situations.

[0144] Step S41: Based on the optimized prediction model, jump to the step of using the prediction model to predict the power consumption data and temperature data within a preset time period in the future.

[0145] Since the equipment operating environment of the data center is dynamically changing, it is necessary to continuously make predictions based on the latest power consumption and environmental data in order to make corresponding preparations and adjustments in advance.

[0146] After the optimization of the prediction model is completed, the optimized prediction model is used to continue to predict the power consumption data and temperature data in the next preset time period in the future. Then it continues to provide a basis for subsequent decision-making and control, such as adjusting the operating parameters of the air conditioner to ensure that the computer room environment is always in a stable and suitable state.

[0147] Through the above cycle, the prediction model can be continuously updated and optimized to better adapt to the ever-changing environment and cooling requirements of the data center.

[0148] An embodiment of the present application provides an air-conditioning control system, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the data center air-conditioning control method in the above-mentioned embodiment.

[0149] Reference below Fig.13 , which shows a schematic diagram of the structure of an air conditioning control system suitable for implementing the embodiment of the present application. The air conditioning control system in the embodiment of the present application may include various hardware and software components for implementing the data center air conditioning control method. Fig.13 The air conditioning control system shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0150] like Fig.13As shown, the air conditioning control system may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the air conditioning control system are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the air conditioning control system to communicate with other devices wirelessly or by wire to exchange data. Although the figures show an air conditioning control system with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0151] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0152] The air conditioning control system provided by the present application adopts the data center air conditioning control method in the above embodiment, which can solve the technical problem that the traditional air conditioning system has a delayed cooling response and cannot immediately meet the cooling demand of the equipment in the data center computer room. Compared with the prior art, the beneficial effects of the air conditioning control system provided by the present application are the same as the beneficial effects of the data center air conditioning control method provided by the above embodiment, and the other technical features in the air conditioning control system are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0153] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0154] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0155] An embodiment of the present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the data center air conditioning control method in the above-mentioned embodiment.

[0156] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0157] The computer-readable storage medium may be included in the air-conditioning control system; or may exist independently without being assembled into the air-conditioning control system.

[0158] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the air-conditioning control system, the air-conditioning control system: obtains the real-time power consumption of each row cabinet, determines the total power consumption of the computer room, and determines the load power of the computer room based on the total power consumption; determines the total cooling output of the air conditioner according to the load change of the load power and the temperature setting value within a preset period; determines the operating parameters of the air conditioner based on the total cooling output, and controls the air conditioner to operate according to the operating parameters.

[0159] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0160] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0161] The modules involved in the embodiments described in the present application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0162] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned data center air conditioning control method, and can solve the technical problem that the traditional air conditioning system has a delayed cooling response and cannot immediately meet the cooling demand of the equipment in the data center computer room. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the data center air conditioning control method provided in the above-mentioned embodiment, and will not be repeated here.

[0163] An embodiment of the present application provides a computer program product, including a computer program, which implements the steps of the above-mentioned data center air conditioning control method when executed by a processor.

[0164] The computer program product provided by the present application can solve the technical problem that the traditional air conditioning system has a delayed cooling response and cannot immediately meet the cooling demand of the equipment in the data center computer room. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as the beneficial effects of the data center air conditioning control method provided by the above embodiment, and will not be repeated here.

[0165] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

[0166] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0167] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method.

[0168] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A data center air conditioning control method, characterized in that: The data center air conditioning control method comprises: Obtain the real-time power consumption of each cabinet, determine the total power consumption of the computer room, and determine the load power of the computer room based on the total power consumption; Determining the total cooling capacity output of the air conditioner according to the load change amount of the load power within a preset period and the temperature setting value; Based on the total cooling output, operating parameters of the air conditioner are determined, and the air conditioner is controlled to operate according to the operating parameters.

2. The data center air conditioning control method according to claim 1, characterized in that: The step of determining the total cooling output of the air conditioner according to the load change amount of the load power within the preset period and the temperature setting value comprises: Acquire the current of each of the first cabinets, and calculate the current load of each of the first cabinets based on the current; Based on the current load, determine the average load of the cabinets in the equipment room at present, and use the average load as a reference load; When the real-time load of the computer room is higher than the reference load, calculating the load change within a preset period; The total cooling capacity output of the air conditioner is determined according to the load change.

3. The data center air conditioning control method according to claim 2, characterized in that: The step of determining the total cooling capacity output of the air conditioner according to the load variation further includes: According to the load variation interval in which the load variation is located, determining the range of cooling capacity required to offset the heat in different load variation intervals; Obtaining the basic cooling capacity and temperature setting value of the current computer room; The total cooling output of the air conditioner is determined within the cooling capacity range according to the basic cooling capacity and the temperature setting value.

4. The data center air conditioning control method according to claim 3, characterized in that: After the step of determining the total cooling output of the air conditioner within the cooling capacity range according to the basic cooling capacity and the temperature setting value, the method further includes: If the total cooling output is greater than the basic cooling capacity, controlling the air conditioner to increase the cooling capacity; If the total cooling output is less than the basic cooling capacity, the air conditioner is controlled to reduce the cooling capacity.

5. The data center air conditioning control method according to claim 1, characterized in that: The step of determining the operating parameters of the air conditioner based on the total cooling capacity output, and controlling the air conditioner to operate according to the operating parameters comprises: According to the total cooling output and in combination with the refrigeration performance curve of the air conditioner, searching for initial operating parameters of the air conditioner corresponding to the total cooling output; Obtaining real-time temperature data of the equipment room and determining the temperature gradient and temperature change trend; adjusting the initial operating parameters according to the temperature gradient and the temperature change trend to obtain the operating parameters of the air conditioner; The operating parameters are sent to the air conditioner, and the air conditioner is driven to operate according to the operating parameters.

6. The data center air conditioning control method according to claim 1, characterized in that: The step of determining the operating parameters of the air conditioner based on the total cooling output, and controlling the air conditioner to operate according to the operating parameters, further includes: Use the prediction model to predict the power consumption data and temperature data within the preset time period in the future; Determining the cooling demand change trend of the computer room according to the prediction result of the prediction model; The operating parameters of the air conditioner are determined according to the cooling demand change trend and the temperature setting value.

7. The data center air conditioning control method according to claim 6, characterized in that: After the step of determining the operating parameters of the air conditioner according to the cooling demand change trend and the temperature setting value, the method further includes: transmitting the operating parameters to the air conditioner; Acquire system feedback data of the air conditioner running based on the operating parameters; Based on the system feedback data, the prediction model is iteratively trained through a neural network to optimize the prediction model; Based on the optimized prediction model, the step of using the prediction model to predict the power consumption data and temperature data within a preset time period in the future is jumped to execution.

8. The data center air conditioning control method according to claim 1, characterized in that: The data center air conditioning control method further includes: Establish two groups of communication connections, the first group of communication connections is the communication connection from the air conditioner to the controller, and the second group of communication connections is the communication connection from the electric meter of the cabinet to the controller; The communication connection uses a shielded twisted pair cable, and the communication connection includes serial port communication, network port communication, and a combination of the serial port communication and the network port communication.

9. An air conditioning control system, characterized in that: The air conditioning control system includes a controller and a communication system between the controller, a power distribution cabinet and an air conditioner. The controller includes a wall-mounted type or a rack-mounted type, wherein the rack-mounted type can be installed with a cabinet, and the wall-mounted type has an IP65 protection function. The controller is for implementing the steps of the data center air conditioning control method as described in any one of claims 1 to 8.

10. An air conditioning control system, characterized in that: The air conditioning control system further includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the data center air conditioning control method according to any one of claims 1 to 8.

Images