Computer room air conditioning operation state control method and system

Abstract

The present invention relates to the field of air conditioning technology, and specifically to a method and system for controlling the operating state of a computer room air conditioner, the method comprising: inputting parameter data at the current moment into a temperature prediction model to obtain predicted temperature data at the next moment; wherein the parameter data includes the actual temperature in the computer room and the target temperature; obtaining the current predicted difference between the predicted temperature data and the target temperature; in response to the current predicted difference being greater than or equal to a threshold, evaluating the temperature prediction model to obtain an evaluation result; the evaluation result is the similarity between the historical actual temperature data and the corresponding historical predicted temperature data; when the evaluation result is greater than a set value, controlling and adjusting the current operating state of the computer room air conditioner; otherwise, repeating the training according to the comprehensive loss function to update the temperature prediction model. That is, the scheme of the present invention can improve the accuracy of the control of the operating state of the computer room air conditioner.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning, and more specifically, to a method and system for controlling the operating state of a computer room air conditioner. Background Art

[0002] With the advent of the big data era, major telecommunications companies and IT companies have established large-scale communication rooms. In order to keep the temperature of the communication room constant, the air conditioner in the room works in a constant temperature cooling mode for a long time, which causes a great waste of energy and increases the cost of the enterprise. Therefore, optimizing the operation state control method of the air conditioner in the communication room can not only ensure that the equipment in the room can be in a good environment, bringing huge benefits to the enterprise, but also ensure that the air conditioner can work in the best working state. Therefore, it is particularly important to control the operation state of the air conditioner in the room.

[0003] In the prior art, such as the patent application document with application publication number CN113865055A and invention name “computer room temperature control method and device”, it is disclosed that a temperature sensor device is set to obtain the sampling temperature of each temperature control area, and compare it with the temperature threshold, determine that the temperature control area is the first temperature control area, and determine the adjacent temperature area of ​​the first temperature control area, and control the air conditioner in the adjacent temperature area, thereby realizing coordinated control of the air conditioners in adjacent areas, thereby achieving the purpose of reliable and energy-saving operation of the computer room air conditioner.

[0004] However, it should be noted that the above method requires the deployment of a large number of sensors and other hardware facilities indoors. In addition, the room temperature has a lag, making it difficult to collect accurate data. Therefore, it is difficult to achieve timely and effective control of the air-conditioning temperature and fully achieve the purpose of energy-saving operation of the air-conditioning.

[0005] Therefore, it is particularly important to effectively and timely control the air conditioning temperature in the computer room. Summary of the invention

[0006] In order to solve one or more of the above-mentioned technical problems, the present invention proposes a method and system for controlling the operating status of a computer room air conditioner, which is used to solve the problem in the prior art that the computer room air conditioner temperature cannot be accurately controlled in a timely and effective manner, and it is difficult to achieve energy-saving operation of the air conditioner; to this end, the present invention provides solutions in the following two aspects.

[0007] In a first aspect, the present invention provides a method for controlling the operating state of a computer room air conditioner, comprising the following steps:

[0008] Input the parameter data at the current moment into the temperature prediction model to obtain the predicted temperature data at the next moment; wherein the parameter data includes the actual temperature and the target temperature in the computer room;

[0009] Get the current predicted difference between the predicted temperature data and the target temperature;

[0010] In response to the current prediction difference being greater than or equal to a threshold, the temperature prediction model is evaluated to obtain an evaluation result; the evaluation result is the similarity between the historical actual temperature data and the corresponding historical predicted temperature data; when the evaluation result is greater than a set value, the current computer room air conditioning operation state is controlled and adjusted; otherwise, the training is repeated according to the comprehensive loss function to update the temperature prediction model;

[0011] Comprehensive loss function for: , is the cross entropy loss, is the similarity, It is the absolute value of the difference between the historical actual temperature difference and the historical predicted temperature difference, wherein the historical actual temperature difference represents the difference change between the historical actual temperature data and the target temperature; the historical predicted temperature difference represents the difference change between the historical predicted temperature data and the target temperature.

[0012] The above scheme predicts the temperature in the computer room at the current moment by using a pre-set temperature prediction model, and compares the difference between the predicted temperature data and the target temperature with the threshold value, so as to timely and effectively control and adjust the operating status of the air conditioner in the current computer room; at the same time, since the prediction effect of the temperature prediction model affects the predicted temperature at future moments, the temperature prediction model is also evaluated in the present invention to determine the prediction effect of the temperature prediction model, and determine whether to adjust the air conditioner or update the temperature prediction model based on the prediction effect. When the temperature prediction model is updated, a comprehensive loss function is constructed by introducing the similarity between the historical actual temperature data and the historical predicted temperature data and their respective difference changes, so as to retrain the temperature prediction model and realize the update of the model. The updated temperature prediction model can be used to more accurately control and adjust the air conditioner while improving the efficiency of the temperature regulation of the computer room air conditioner, so as to achieve the purpose of energy-saving operation of the air conditioner.

[0013] In one embodiment, before obtaining the similarity, a process of screening the historical actual temperature data and the corresponding historical predicted temperature data is also included:

[0014] Input the historical parameter data in any time period into the temperature prediction model to obtain the historical predicted temperature data in the next time period;

[0015] The average of the differences between each historical predicted temperature and the target temperature in the historical predicted temperature data is taken as the historical predicted temperature difference;

[0016] The historical predicted temperature data when the historical predicted temperature difference is less than the threshold value is selected, and the historical actual temperature data at the time corresponding to the historical predicted temperature data is obtained.

[0017] In the above scheme, the temperature data at the time when the air-conditioning operation state adjustment is not required is selected, which can improve the prediction effect of the updated temperature prediction model, and thus improve the accuracy of temperature prediction at future times.

[0018] In one embodiment, the historical actual temperature difference is an average of the differences between each historical actual temperature and the target temperature in the historical actual temperature data.

[0019] In one embodiment, when updating the temperature prediction model, when the number of updates reaches a set number, the updating is stopped, and the final temperature prediction model when the updating is stopped is obtained;

[0020] The new predicted temperature data for the next moment is obtained based on the final temperature prediction model, and the difference between the new predicted temperature data and the target temperature is used as the new predicted difference. When the new predicted difference is less than the threshold, the current operating state of the air conditioner in the computer room is kept unchanged. Otherwise, the staff is reminded.

[0021] In the above scheme, by setting the number of times to update the temperature prediction model, the air-conditioning operation state can be adjusted timely and effectively.

[0022] In one embodiment, the specific process of controlling and adjusting the current operating state of the computer room air conditioner is as follows:

[0023] When the predicted temperature data is lower than the target temperature, the predicted temperature data is adjusted upward according to the set adjustment amount to obtain the adjusted temperature value; when the predicted temperature data is higher than the target temperature, the predicted temperature data is adjusted downward according to the set adjustment amount to obtain the adjusted temperature value.

[0024] In the above scheme, by analyzing the predicted temperature data and the target temperature and setting the corresponding control strategy, the operating status of the computer room air conditioner can be controlled more finely.

[0025] In one embodiment, in response to the current prediction difference being less than a threshold, the current operating state of the computer room air conditioner is kept unchanged.

[0026] In one embodiment, the similarity is calculated using a DTW algorithm.

[0027] In one embodiment, the parameter data also includes outdoor temperature of the computer room, indoor cabinet temperature of the computer room, indoor humidity information of the computer room, and indoor wind speed information of the computer room.

[0028] In the above solution, when predicting the temperature in the machine room, the accuracy of the predicted temperature can be improved by introducing data from multiple angles for temperature prediction.

[0029] In a second aspect, the present invention provides a computer room air conditioner operation state control system, comprising:

[0030] processor;

[0031] The memory stores computer instructions for controlling the operation status of the computer room air conditioner. When the computer instructions are executed by the processor, the system executes the above-mentioned method for controlling the operation status of the computer room air conditioner.

[0032] The beneficial effects of the present invention are:

[0033] The solution of the present invention firstly uses a temperature prediction model to predict the temperature in the computer room at the current moment, and based on the analysis of the predicted temperature data, determines whether to control and adjust the operating status of the air conditioner in the current computer room; when adjustment is required, it is also necessary to consider the effect of the air conditioner adjustment and the influence of the prediction effect of the temperature prediction model. Therefore, the temperature prediction model is subsequently evaluated to determine the prediction effect of the temperature prediction model, and determines whether to continue to adjust the air conditioner or update the temperature prediction model based on the prediction effect. That is, the solution of the present invention can more accurately control and adjust the air conditioner and achieve the purpose of energy-saving operation of the air conditioner while improving the efficiency of temperature adjustment of the computer room air conditioner. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0035] Figure 1 The flowchart schematically shows the steps of the method for controlling the operating state of the computer room air conditioner in this embodiment;

[0036] Figure 2 The structural block diagram of the computer room air conditioner operation status control system in this embodiment is schematically shown. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0038] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0039] Figure 1 The flowchart schematically shows the steps of the method for controlling the operating status of the computer room air conditioner in this embodiment.

[0040] Taking a communication room as an example, the method for controlling the operating status of the air conditioner in the room provided in this embodiment is introduced.

[0041] Specifically, Figure 1 As shown, the computer room air conditioner operating state control method provided in this embodiment includes the following steps:

[0042] In step S1, the parameter data at the current moment is input into the temperature prediction model to obtain the predicted temperature data at the next moment.

[0043] In this embodiment, parameter data at the current moment are collected, wherein the parameter data include the outdoor temperature of the computer room, the indoor temperature of the computer room, the cabinet temperature of the computer room, the indoor humidity information of the computer room, the indoor wind speed information of the computer room, and the target temperature of the air conditioner in the computer room.

[0044] Specifically, the above parameter data can be obtained by installing a temperature sensor outside the computer room to collect the outdoor temperature of the computer room at equal time intervals; installing a temperature sensor at a suitable position inside the computer room to collect the actual temperature data inside the computer room at equal time intervals; installing a temperature sensor on the surface of the cabinet inside the computer room to detect the cabinet temperature of the computer room at different positions, calculating the temperature average, and using the temperature average as the cabinet temperature inside the computer room; installing a humidity sensor at a suitable position inside the computer room to collect the indoor humidity information of the computer room at equal time intervals; installing a wind speed sensor inside the computer room to collect the indoor wind speed information of the computer room at equal time intervals; in this embodiment, the target temperature of the air conditioner in the computer room is also obtained. The equal time intervals mentioned above are sampling intervals, and the sampling intervals can be 1 minute or 5 minutes.

[0045] In this embodiment, only the actual temperature data in the computer room can be collected to perform subsequent temperature prediction model training and temperature prediction in the computer room. Of course, as other implementation methods, all the data in the above parameter data can also be used in this embodiment to make the training of the temperature prediction model more accurate.

[0046] The temperature prediction model in this embodiment adopts a recurrent neural network model.

[0047] Specifically, the training process of the temperature prediction model in this embodiment is:

[0048] Build a recurrent neural network model, such as an RNN network model;

[0049] Obtain a sample data set; wherein the sample data set is obtained by obtaining parameter data within a historical set time period.

[0050] The sample data is input into the recurrent neural network model for training, and the cross entropy loss is used to calculate the difference. The parameters of the network model are adjusted using the gradient descent algorithm until the value of the cross entropy loss between the output prediction result and the true result is less than the difference threshold, thus obtaining a trained temperature prediction model.

[0051] The difference threshold mentioned above may be 0 or a value close to 0, such as the difference threshold being 0.1.

[0052] In this embodiment, after obtaining the trained temperature prediction model, the parameter data at the current moment is input into the temperature prediction model to obtain the predicted temperature data at the next moment of the current moment, thereby realizing the prediction of the temperature in the computer room.

[0053] At step S2, the current predicted difference between the predicted temperature data and the target temperature is obtained; in response to the current predicted difference being greater than or equal to a threshold, the temperature prediction model is evaluated to obtain an evaluation result; the evaluation result is the similarity between the historical actual temperature data and the corresponding historical predicted temperature data; when the evaluation result is greater than a set value, the current operating state of the computer room air conditioner is controlled and adjusted; otherwise, the training is repeated according to the comprehensive loss function to update the temperature prediction model.

[0054] In this embodiment, based on the predicted temperature data at the next moment obtained in step S1, the current predicted difference between the predicted temperature data and the target temperature in the computer room is calculated to determine the operating state of the computer room air conditioner, that is, when the predicted difference is less than a threshold, the operating state of the computer room air conditioner is kept unchanged. The threshold can be set to 2°C, and of course it can be set according to actual conditions.

[0055] When the current prediction difference is greater than or equal to the threshold, there may be two situations: one is the quality of the prediction effect of the trained temperature prediction model, and the other is that the operating status of the air conditioner in the computer room is not good. Therefore, based on the above two situations, the temperature prediction model needs to be evaluated in this embodiment, which specifically includes the following steps: inputting the historical parameter data set in any historical time period into the temperature prediction model to obtain the historical predicted temperature data in the next time period; obtaining the historical actual temperature data at the corresponding moment of the historical predicted temperature data, calculating the similarity between the historical predicted temperature data and the corresponding historical actual temperature data, and using the similarity as the evaluation result.

[0056] The above-mentioned evaluation of the temperature prediction model is carried out using historical parameter data, that is, by obtaining the parameter data of the historical set time period and evenly dividing the parameter data within the set time period to obtain multiple time periods, where the time periods are arranged in chronological order, and each time period includes multiple consecutive moments, and each moment corresponds to a parameter data.

[0057] For example, if the historical setting time period is 12 hours and the sampling interval is 1 minute or 5 minutes, then 12 hours can be divided into 12 time periods, that is, 1 hour is one time period, and then the parameter data in each time period is obtained. Of course, this embodiment is not limited to the above example, and it is also set according to actual conditions.

[0058] It should be noted that any historical time period mentioned above is a random time period in the set time period, and the historical predicted temperature data of the next time period of any historical time period can be obtained through the trained temperature prediction model.

[0059] Since the next time period of any historical time period belongs to the set time period, the next time period also corresponds to historical actual temperature data, wherein the historical actual temperature data is obtained through collection. Therefore, the prediction effect of the temperature prediction model can be judged by comparing the similarity between the historical actual temperature data of the next time period and the historical predicted temperature data.

[0060] Exemplarily, the second time period in the historical setting time period of 12h, i.e., 9:00-9:59, can be randomly selected. At this time, the actual temperature value data in the computer room can be obtained. Then, the actual temperature data of the second time period is used as the input of the trained temperature prediction model, and the predicted temperature data of the third time period (10:00-10:59) can be obtained. At this time, the third time period (10:00-10:59) also corresponds to the collected actual temperature data. Therefore, the actual temperature data collected in the third time period can be compared with the predicted temperature data to evaluate the prediction effect of the temperature prediction model. The similarity calculation method mentioned above can use the dynamic time warping (DTW) algorithm, and of course, the cosine similarity can also be used. The set value is 0.9, and of course it can also be set according to experience, such as 0.8.

[0061] It should be noted that before obtaining the similarity, a process of screening the historical predicted temperature data and the corresponding historical actual temperature data is also included:

[0062] Input the historical parameter data set in any time period into the trained temperature prediction model to obtain the historical predicted temperature data in the next time period;

[0063] The average of the differences between each historical predicted temperature and the target temperature in the historical predicted temperature data is taken as the historical predicted temperature difference;

[0064] The historical predicted temperature data when the historical predicted temperature difference is less than the threshold value is selected, and the historical actual temperature data at the time corresponding to the historical predicted temperature data is obtained.

[0065] The purpose of the temperature data screening mentioned above is to select the temperature data at the moment when the air-conditioning operation status adjustment is not required, so as to improve the accuracy of the optimized temperature prediction model. This is because if the temperature data that needs to be controlled and adjusted is used, then the actual temperature used subsequently is the temperature after interference adjustment, and there will be errors in the evaluation of the temperature prediction model.

[0066] In this embodiment, after the similarity is determined, it is necessary to compare the similarity with a set value, that is, when the similarity is greater than the set value, the temperature prediction model does not need to be optimized; otherwise, the temperature prediction model is optimized.

[0067] In one embodiment, when the temperature prediction model does not need to be optimized, it proves that the operation state of the computer room air conditioner is not good. At this time, it is necessary to control and adjust the operation state of the computer room air conditioner. The specific control strategy is:

[0068] When the predicted temperature data is lower than the target temperature, the predicted temperature data is adjusted upward according to the set adjustment amount to obtain the adjusted temperature value; when the predicted temperature data is higher than the target temperature, the predicted temperature data is adjusted downward according to the set adjustment amount to obtain the adjusted temperature value. The set adjustment amount can be determined according to the difference between the target temperature and the predicted temperature data; of course, it can also be adjusted according to the set value, such as the set adjustment amount can be 2°C or 3°C.

[0069] The control strategy described above can finely control the operating state of the computer room air conditioner; it should be noted that the adjusted temperature value in this embodiment is used to pre-adjust the temperature at the next moment of the current moment.

[0070] In one embodiment, the process of updating the temperature prediction model is as follows:

[0071] Obtain historical predicted temperature differences and historical actual temperature differences;

[0072] Calculate the absolute value of the difference between the historical predicted temperature difference and the historical actual temperature difference;

[0073] According to the similarity, cross entropy loss and absolute value of difference, a comprehensive loss function is obtained;

[0074] Repeated training is performed using a comprehensive loss function to update the temperature prediction model.

[0075] Among them, the comprehensive loss function is: ;in, is the comprehensive loss function, is the cross entropy loss, is the similarity, is the absolute value of the difference.

[0076] In this embodiment, when updating the trained temperature prediction model, the similarity between the two historical predicted temperature data and the corresponding historical actual temperature data is used as a supervisory signal to construct a supervised learning task. That is, the similarity is used as part of the loss function in the active learning algorithm, and a comprehensive loss function is defined to guide the temperature prediction model to better fit the real data; that is, in this embodiment, similarity and the absolute value of the difference are introduced to improve the cross entropy loss, realize the optimization of the temperature prediction model, and obtain a temperature prediction model with better prediction effect.

[0077] Furthermore, in this embodiment, when updating the temperature prediction model, a stop condition needs to be set, wherein the stop condition is: when the number of updates reaches a set number, the update is stopped to avoid failure to adjust the air conditioner operation state in time. The set number is 2, and of course it can be set according to actual conditions.

[0078] When the update is stopped, the final temperature prediction model at the time of stopping the update is also obtained, and the new predicted temperature data for the next moment is obtained based on the final temperature prediction model. The difference between the new predicted temperature data and the target temperature is used as the new prediction difference. When the new prediction difference is less than the threshold, the current operating status of the air conditioner in the computer room is kept unchanged. Otherwise, the staff is reminded or the operating status of the air conditioner is controlled and adjusted.

[0079] In the above embodiment, the control and adjustment of the air-conditioning operation state can be performed according to the above control strategy; of course, reminders can also be given to the staff, and the control and adjustment can be performed based on the staff's experience.

[0080] The solution of the present invention can optimize the operating state of the air-conditioning system, improve the energy efficiency and benefits of the air-conditioning system in the computer room, and enhance the adaptability and intelligence level of the air-conditioning system based on the analysis of the collected temperature parameter data, humidity data and other parameter data inside and outside the computer room.

[0081] Figure 2 The structural block diagram of the computer room air conditioner operation status control system in this embodiment is schematically shown.

[0082] The present invention also provides a computer room air conditioning operation status control system. Figure 2As shown, the control system includes a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the computer room air conditioner operating state control method according to the first aspect of the present invention is implemented.

[0083] The control system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0084] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0085] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for controlling the operating state of a computer room air conditioner, characterized in that: The following steps are involved: Input the parameter data at the current moment into the temperature prediction model to obtain the predicted temperature data at the next moment; The parameter data includes the actual temperature and target temperature in the computer room; Get the current predicted difference between the predicted temperature data and the target temperature; In response to the current prediction difference being greater than or equal to a threshold, the temperature prediction model is evaluated to obtain an evaluation result; the evaluation result is the similarity between the historical actual temperature data and the corresponding historical predicted temperature data; when the evaluation result is greater than a set value, the current computer room air conditioning operation state is controlled and adjusted; On the contrary, the training is repeated according to the comprehensive loss function to update the temperature prediction model; Comprehensive loss function for: , is the cross entropy loss, is the similarity, is the absolute value of the difference between the historical actual temperature difference and the historical predicted temperature difference, wherein the historical actual temperature difference represents the difference change between the historical actual temperature data and the target temperature; the historical predicted temperature difference represents the difference change between the historical predicted temperature data and the target temperature; Before obtaining the similarity, the method further includes a process of screening the historical actual temperature data and the corresponding historical predicted temperature data: inputting the historical parameter data in any time period into the temperature prediction model to obtain the historical predicted temperature data in the next time period; taking the average of the difference between each historical predicted temperature and the target temperature in the historical predicted temperature data as the historical predicted temperature difference; selecting the historical predicted temperature data when the historical predicted temperature difference is less than a threshold value, and obtaining the historical actual temperature data at the corresponding moment of the historical predicted temperature data; When updating the temperature prediction model, when the number of updates reaches the set number, the updating is stopped, and the final temperature prediction model when the updating is stopped is obtained; the new predicted temperature data at the next moment is obtained based on the final temperature prediction model, and the difference between the new predicted temperature data and the target temperature is used as the new prediction difference. When the new prediction difference is less than the threshold, the current operating status of the air conditioner in the computer room is kept unchanged, otherwise, the staff is reminded.

2. The computer room air conditioner operating state control method according to claim 1, characterized in that: The historical actual temperature difference is the average of the differences between each historical actual temperature and the target temperature in the historical actual temperature data.

3. The computer room air conditioner operating state control method according to claim 1, characterized in that: The specific process of controlling and adjusting the current operating state of the computer room air conditioner is as follows: When the predicted temperature data is lower than the target temperature, the predicted temperature data is adjusted upward according to the set adjustment amount to obtain the adjusted temperature value; when the predicted temperature data is higher than the target temperature, the predicted temperature data is adjusted downward according to the set adjustment amount to obtain the adjusted temperature value.

4. The computer room air conditioner operating state control method according to claim 1, characterized in that: In response to the current prediction difference being less than a threshold, the current operating state of the computer room air conditioner is kept unchanged.

5. The computer room air conditioner operating state control method according to claim 1, characterized in that: The parameter data also includes the outdoor temperature of the computer room, the cabinet temperature in the computer room, the indoor humidity information of the computer room, and the indoor wind speed information of the computer room.

6. The computer room air conditioning operation status control system is characterized by: include: processor; A memory storing computer instructions for controlling the operating state of a computer room air conditioner. When the computer instructions are executed by the processor, the system executes the method for controlling the operating state of a computer room air conditioner according to any one of claims 1 to 5.

Images