Terminal air conditioning energy saving regulation method and device, electronic equipment, readable storage medium and computer program product

Abstract

The application discloses an end air conditioning energy-saving regulation and control method and device, electronic equipment, readable storage medium and computer program product, and belongs to the technical field of intelligent control. The method comprises the following steps: acquiring historical supply air temperatures of M air conditioners and historical cold channel temperatures of N cold channel temperature sensors in a preset time period; selecting a corresponding relevant cold channel for each air conditioner based on the historical temperature collection data, wherein the relevant cold channel comprises a plurality of cold channel temperature sensors; acquiring real-time cold channel temperatures of the N cold channel temperature sensors; calculating a real-time cold channel temperature mean of the relevant cold channel corresponding to each air conditioner based on the real-time cold channel temperatures of the N cold channel temperature sensors; selecting an air conditioner to be regulated and controlled from the M air conditioners according to a preset screening condition, wherein the real-time cold channel temperature mean of the relevant cold channel corresponding to the air conditioner to be regulated and controlled at least meets the preset screening condition; and performing temperature rising regulation and control on the air conditioner to be regulated and controlled.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and in particular to a method, device, electronic device, readable storage medium, and computer program product for energy-saving control of terminal air conditioning. Background Technology

[0002] With the rapid development of information technology, the energy consumption of data centers has become increasingly prominent, especially the energy consumption of cooling systems, which accounts for a significant proportion. Traditional cooling methods often suffer from overcooling or undercooling, leading to energy waste or equipment overheating. Therefore, how to achieve energy saving through precise temperature control has become a focus of industry attention.

[0003] To address the aforementioned issues, existing machine learning algorithms are as follows: Taking 20 precision air conditioners, arranged in two rows of eight cold aisles each, with four temperature sensors in each aisle, resulting in a total of 64 cold aisle temperatures, as an example, the goal is to ensure that the temperatures of all 64 cold aisles do not exceed the limit when controlling the precision air conditioners. Therefore, 64 predictive models are needed to predict the control parameters of the 20 precision air conditioners and the temperatures of the 64 cold aisles. By increasing the air supply temperature of the air conditioners, the models are invoked to determine whether the cold aisle temperatures are exceeding the limit.

[0004] The existing solutions described above have the following problems: (1) Too many models: 64 independent models need to be built to predict the temperature of each cold aisle, which will greatly increase the complexity of model management and maintenance. Each model needs to be trained, validated and tuned separately, which not only increases the consumption of computing resources, but may also make it difficult to guarantee the consistency between models. In addition, it is difficult to guarantee that the accuracy of each model meets the accuracy requirements.

[0005] (2) Data management and processing complexity: Each model needs to process a large amount of input data, including control parameters of 20 precision air conditioners and temperature data of 64 cold aisles. The data preprocessing, feature engineering and model training processes become very cumbersome, increasing the complexity of data management and processing.

[0006] (3) Difficulty in model training and updating: Due to the large number of models, training and updating these models requires a lot of time and computing resources. In practical applications, it may not be possible to update the models in a timely manner to reflect the latest environmental changes, resulting in a decrease in prediction accuracy.

[0007] (4) Complex system integration: Integrating 64 models into a unified control system results in high system integration complexity. This may increase the difficulty of system development and debugging, and prolong the project implementation cycle. Summary of the Invention

[0008] This application provides a terminal air conditioning energy-saving control method, device, electronic device, readable storage medium, and computer program product, which can solve the problems in the prior art where the large number of models not only increases the consumption of computing resources but also increases the complexity of data management and processing, as well as the problems of decreased prediction accuracy and increased difficulty in system integration and development due to the difficulty of model training and updating.

[0009] To solve the above-mentioned technical problems, this application is implemented as follows: Firstly, a method for energy-saving control of terminal air conditioning is provided, including: Acquire historical temperature data for a preset time period. The historical temperature data includes: historical air supply temperature of M air conditioners and historical cold aisle temperature of N cold aisle temperature sensors, where M and N are positive integers. Based on the historical temperature data, a corresponding cold aisle is selected for each air conditioner. The corresponding cold aisle includes multiple cold aisle temperature sensors, and the historical cold aisle temperature of the corresponding cold aisle is correlated with the historical air supply temperature of the air conditioner corresponding to the corresponding cold aisle. Obtain the real-time cold aisle temperature of N cold aisle temperature sensors, and calculate the average real-time cold aisle temperature of the relevant cold aisle corresponding to each air conditioner based on the real-time cold aisle temperature of N cold aisle temperature sensors. According to preset screening criteria, air conditioners to be controlled are selected from M air conditioners, wherein the real-time average cold aisle temperature of the relevant cold aisle corresponding to the air conditioner to be controlled at least meets the preset screening criteria. The air conditioner to be regulated is heated.

[0010] Secondly, a terminal air conditioning energy-saving control device is provided, comprising: The data acquisition module is used to acquire historical temperature data over a preset time period. The historical temperature data includes: historical air supply temperatures of M air conditioners and historical cold aisle temperatures of N cold aisle temperature sensors. The correlation analysis module is used to select a corresponding cold channel for each air conditioner based on the historical temperature data. The corresponding cold channel includes multiple cold channel temperature sensors, and the historical cold channel temperature of the corresponding cold channel is correlated with the historical air supply temperature of the air conditioner corresponding to the corresponding cold channel. The mean calculation module is used to obtain the real-time cold aisle temperature of N cold aisle temperature sensors, and calculate the mean real-time cold aisle temperature of the relevant cold aisle corresponding to each air conditioner based on the real-time cold aisle temperature of N cold aisle temperature sensors. The air conditioner screening module is used to screen out the air conditioners to be controlled from M air conditioners according to preset screening conditions, wherein the real-time average cold aisle temperature of the relevant cold aisle corresponding to the air conditioner to be controlled at least meets the preset screening conditions. The control module is used to control the temperature of the air conditioner to be controlled.

[0011] Thirdly, an electronic device is provided, comprising a processor and a memory, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the above-described terminal air conditioning energy-saving control method.

[0012] Fourthly, a readable storage medium is provided, wherein at least one computer program is stored in the readable storage medium, the computer program being loaded and executed by a processor to implement the above-described terminal air conditioning energy-saving control method.

[0013] Fifthly, a computer program product is provided, the computer program product comprising at least one computer program, the computer program being loaded and executed by a processor to implement the terminal air conditioning energy-saving control method provided in the various optional implementations described above.

[0014] The terminal air conditioning energy-saving control method, device, electronic equipment, readable storage medium, and computer program product provided in this application embodiment select the most relevant cold aisle temperature for each air conditioner based on cold aisle temperature correlation analysis and distance priority principle, ensuring that the selected relevant cold aisle temperature sensors can more accurately reflect the impact of each air conditioner's outlet air temperature. Then, by using the real-time cold aisle temperature and safe temperature threshold of the relevant cold aisle, the precise air conditioner requiring control is accurately located, thereby avoiding resource waste. Furthermore, this application embodiment calculates the average real-time cold aisle temperature of the corresponding relevant cold aisle of the air conditioner, replacing multiple models with a single index. This simplifies the complex system that originally required 64 independent models into a unified logic or a small number of models, thereby reducing system complexity and the difficulty of model management and maintenance.

[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] Figure 1 A flowchart of a terminal air conditioning energy-saving control method provided in an exemplary embodiment of this application is shown; Figure 2This invention provides a flowchart illustrating how a corresponding cold aisle is selected for each air conditioner based on historical temperature data, according to an exemplary embodiment of this application. Figure 3 A flowchart illustrating the process of obtaining the average real-time cold aisle temperature of each air conditioner corresponding to its respective cold aisle, provided in an exemplary embodiment of this application, is shown. Figure 4 This application illustrates a flowchart of an exemplary embodiment of the process for selecting an air conditioner to be controlled from M air conditioners. Figure 5 A block diagram of a terminal air conditioning energy-saving control device provided in an exemplary embodiment of this application is shown; Figure 6 A structural block diagram of an electronic device provided in an exemplary embodiment of this application is shown. Detailed Implementation

[0018] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0019] To address the problems in existing technologies where an excessive number of models not only increases the consumption of computing resources but also increases the complexity of data management and processing, and where difficulties in model training and updating lead to decreased prediction accuracy and increased complexity in system integration and development, this application provides a terminal air conditioning energy-saving control method and device.

[0020] The execution subject of this method can be various types of computing devices, or it can be an application or app installed on a computing device. The computing device can be a user terminal such as a mobile phone, tablet computer, or smart wearable device, or it can be a server. The server can be a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing, consisting of a large number of computers and network servers.

[0021] For ease of description, this application uses a server as the execution subject of the method in its embodiments to illustrate the method. Those skilled in the art will understand that this embodiment uses a server as an example to describe the method, which is merely an illustrative example and does not limit the scope of protection of the corresponding claims.

[0022] The terminal air conditioning energy-saving control method provided in this application is a terminal energy-saving scheme based on cold aisle temperature correlation analysis and distance priority principle. It dynamically adjusts the operating parameters of the cooling system by real-time monitoring and analysis of the cold aisle temperature distribution to achieve precise cooling control. Specifically, this method utilizes temperature sensors arranged in the cold aisle to collect temperature data in real time and identifies areas or equipment with abnormal temperatures through data analysis algorithms. Based on this data, the data center control system can automatically adjust the temperature setpoint of the air conditioning equipment to ensure that cold air is accurately delivered to the equipment requiring cooling, thereby avoiding unnecessary energy consumption.

[0023] Figure 1 A flowchart illustrating an exemplary embodiment of this application of a terminal air conditioning energy-saving control method is shown. Figure 1 As shown, the terminal air conditioning energy-saving control method mainly includes the following steps (S101-S105): S101. Obtain historical temperature data for a preset time period. The historical temperature data includes: historical air supply temperature of M air conditioners and historical cold aisle temperature of N cold aisle temperature sensors, where M and N are positive integers. In this embodiment, a scenario is illustrated using 20 precision air conditioners, 2 rows of cold aisles, 8 cold aisles per row, and 4 temperature sensors per cold aisle, for a total of 64 cold aisle temperature sensors. In this scenario, M=20 and N=64.

[0024] The preset time period includes six months or more to obtain richer research data. Historical temperature data of more than six months is collected, including the historical supply air temperature (control parameters) of 20 air conditioners and the historical cold aisle temperature of 64 cold aisle temperature sensors of more than six months.

[0025] In practice, these historical temperature data are stored in a DataFrame data structure, with each row representing a data record at a point in time, and the columns representing the historical air supply temperature of 20 air conditioners and the historical cold aisle temperature of 64 cold aisle temperature sensors.

[0026] These historical temperature data provide a foundation for subsequent analysis and model building. The rich data helps to more accurately explore the relationship between air conditioning control parameters and cold aisle temperature.

[0027] S102. Select the corresponding relevant cold aisle for each air conditioner based on historical temperature data. The relevant cold aisle includes multiple cold aisle temperature sensors. The historical cold aisle temperature of the relevant cold aisle is correlated with the historical air supply temperature of the air conditioner corresponding to the relevant cold aisle. As an optional implementation method in this embodiment, Pearson correlation analysis is used to analyze the correlation between the historical cold aisle temperature of the relevant cold aisle and the historical air supply temperature of the air conditioner corresponding to the relevant cold aisle.

[0028] like Figure 2 As shown in the exemplary embodiment of this application, the terminal air conditioning energy-saving control method selects the corresponding relevant cold channel for each air conditioner based on historical temperature data, including the following steps (S201-S202): S201. Calculate the correlation coefficient between the historical supply air temperature of each air conditioner and the historical cold aisle temperature of each cold aisle temperature sensor using Pearson correlation analysis. In this embodiment, Pearson correlation analysis is used to analyze the correlation coefficient between the historical cold aisle temperatures of 64 cold aisle temperature sensors and the historical air supply temperatures of 20 air conditioners. Specifically, `df.corr(method='pearson')` can be called to return a symmetric DataFrame, where each element represents the Pearson correlation coefficient between two columns (a historical cold aisle temperature column and a historical air supply temperature column for the air conditioner). The correlation coefficient ranges from -1 to 1, where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no linear correlation.

[0029] S202. Select the cold aisle temperature sensor with the highest correlation coefficient for each air conditioner as the corresponding cold aisle for each air conditioner.

[0030] The correlation coefficients between each air conditioner and 64 historical cold aisle temperatures are ranked, and the top-ranked cold aisle temperature sensors for each air conditioner are selected as the relevant cold aisles. The initial preset number can be set according to actual control needs, and this application does not limit this. For example, based on the correlation coefficient ranking, the top 4 cold aisle temperature sensors with the highest correlation coefficients for each air conditioner can be selected.

[0031] like Figure 2 As shown in another exemplary embodiment of this application, the terminal air conditioning energy-saving control method, which selects a corresponding relevant cold channel for each air conditioner based on historical temperature data, further includes: S203. Obtain the second-to-last preset number of cold aisles that are closest to each air conditioner; S204. After deduplicating and merging the first preset number of cold aisles and the second preset number of cold aisles, they are used as the relevant cold aisles for each air conditioner.

[0032] In this embodiment, to ensure operational security, based on the distance priority principle, a preset number of cold aisle temperature sensors closest to each air conditioner are deduplicated and used as the corresponding relevant cold aisles. The second preset number can be set according to actual control needs; this application does not impose any restrictions on this. For example, when selecting the two closest cold aisle temperature sensors for an air conditioner, it's possible that these sensors overlap with the top four cold aisle temperature sensors selected in step S202 based on their correlation coefficients. In such cases, the remaining cold aisle temperature sensors after deduplication are used as the final determined relevant cold aisles for that air conditioner. This screening method comprehensively considers correlation and distance factors, preventing the omission of critical areas and selecting the cold aisle temperatures most relevant to each air conditioner, ensuring that the selected cold aisle temperature sensors more accurately reflect the impact of each air conditioner's outlet air temperature. Through cold aisle temperature correlation analysis and the distance priority principle, the complex system that originally required 64 independent models is simplified into a unified logic or a small number of models, thereby reducing system complexity and the difficulty of model management and maintenance.

[0033] In one application example, after performing Pearson correlation analysis on the historical temperature data, it was found that for air conditioner A, the correlation coefficients with cold aisle temperature sensors C1, C2, C3, and C4 were 0.8, 0.75, 0.7, and 0.65, respectively, ranking in the top four. Meanwhile, the two cold aisle sensors closest to air conditioner A are C5 and C6. Since C5 overlaps with C2, C1, C2, C3, C4, and C6 were ultimately selected as the cold aisle temperatures associated with air conditioner A. The other 19 air conditioners were screened using the same method.

[0034] S103. Obtain the real-time cold aisle temperature from N cold aisle temperature sensors. Based on the real-time cold aisle temperature from the N cold aisle temperature sensors, calculate the average real-time cold aisle temperature of the relevant cold aisle for each air conditioner. like Figure 3 As shown in another exemplary embodiment of this application, the terminal air conditioning energy-saving control method obtains the real-time cold aisle temperatures of N cold aisles, and calculates the average real-time cold aisle temperature of the relevant cold aisle corresponding to each air conditioner based on the real-time cold aisle temperatures of the N cold aisles, including the following steps: S301. Obtain the real-time cold aisle temperature of N cold aisle temperature sensors within a first preset time period, and calculate the average cold aisle temperature of each cold aisle temperature sensor within the first preset time period, wherein the average cold aisle temperature is obtained by calculating the average of the real-time cold aisle temperatures within the first preset time period. In one application example, the first preset duration is 1 hour, and real-time cold aisle temperature data from 64 cold aisle temperature sensors are retrieved for 1 hour. Assuming that cold aisle temperature sensor C1 has 60 real-time cold aisle temperature data records at 1 hour, the average of the overall data is calculated to obtain the average cold aisle temperature of C1. The average cold aisle temperatures of the other 63 cold aisle temperature sensors are obtained in the same way. Therefore, by averaging the overall data, data oscillations can be reduced.

[0035] Specifically, in one application example, the data is averaged using df.mean(), which returns a Series format where the index is the column name (64 cold aisle temperature sensors) and the value is the average cold aisle temperature of the corresponding sensor.

[0036] S302. Based on the average cold aisle temperature of each cold aisle within a first preset time period, calculate the average real-time cold aisle temperature of the relevant cold aisle corresponding to each air conditioner, wherein the average real-time cold aisle temperature of the air conditioner is obtained by calculating the average cold aisle temperature of the relevant cold aisle corresponding to the air conditioner.

[0037] In one application example, assuming that the relevant cold aisles of air conditioner A are C2, C3, C4, and C6, in step S301, the average cold aisle temperatures of C2, C3, C4, and C6 within a first preset time period are obtained. The average of these four values ​​is then taken to obtain the real-time average cold aisle temperature k of the corresponding relevant cold aisles of air conditioner A. The real-time average cold aisle temperature k of the corresponding relevant cold aisles of 20 air conditioners is obtained in this way. In this embodiment, a single comprehensive value k is used to represent the cold aisle temperature of each air conditioner, replacing multiple models with a single index, reducing the number of models from 64 to 20 comprehensive indices. For example, the real-time average cold aisle temperature k of the four associated cold aisle temperature sensors of air conditioner A replaces four independent models, thereby simplifying the model and reducing the complexity of data processing.

[0038] S104. Select the air conditioner to be controlled from M air conditioners according to the preset screening conditions, wherein the real-time average cold aisle temperature of the relevant cold aisle corresponding to the air conditioner to be controlled at least meets the preset screening conditions. In this embodiment, as an optional implementation, before selecting the air conditioner to be controlled from the M air conditioners, the method provided in this application embodiment further includes: obtaining the real-time air supply temperature of the M air conditioners within a second preset time period, and calculating the average air supply temperature of each air conditioner within the second preset time period.

[0039] In one application example, the second preset duration can be 1 hour, retrieving real-time air supply temperature data from 20 air conditioners over one hour. Assuming air conditioner A has 60 time points of air supply temperature data records within one hour, the average of these data points is calculated to obtain the average air supply temperature of air conditioner A. The average air supply temperatures of the other 19 air conditioners are obtained in the same way. Therefore, by averaging the overall data, data oscillations can be reduced.

[0040] like Figure 4 As shown, as an optional implementation method in this application embodiment, selecting the air conditioner to be controlled from M air conditioners according to preset screening conditions includes the following steps: S401. Mark the air conditioners among the M air conditioners whose average supply air temperature is less than the safe temperature threshold, and use the marked air conditioners as the S air conditioners to be screened.

[0041] In this embodiment, the preset screening conditions include whether the average supply air temperature is less than a safe temperature threshold. For example, the safe temperature threshold can be set to 23.5℃. This temperature setting is to ensure a certain safety margin during regulation and avoid excessive regulation leading to excessively high temperatures. First, S air conditioners with an average supply air temperature less than the safe temperature threshold are initially screened out, which narrows down the range of air conditioners to be regulated and improves screening efficiency for further screening.

[0042] Specifically, in one application example, the data is averaged using df.mean(), which returns a Series format where the index is the column name (20 air conditioners) and the value is the average air supply temperature of the corresponding air conditioner.

[0043] S402. Sort the average real-time cold aisle temperature of the relevant cold aisle corresponding to the S air conditioners to be screened in ascending order, where S is a positive integer and S≤M; S403. Select the air conditioners whose real-time cold aisle temperature average is ranked in the top three of a preset number as the air conditioners to be controlled.

[0044] In this embodiment, the preset screening criteria further include: the third preset number of air conditioners whose real-time cold aisle temperature average is ranked first. This third preset number can be set according to actual control needs, and this application does not impose any restrictions on it. For example, three air conditioners to be controlled can be selected based on business requirements (the actual number can be determined according to the specific business scenario). In step S302, the comprehensive real-time cold aisle temperature average k of each air conditioner is obtained, and these k values ​​are sorted in ascending order. Specifically, the selection principle is to select the three air conditioners corresponding to the top three k values ​​in ascending order according to the real-time cold aisle temperature average k, and to ensure that the air conditioner's supply air temperature is less than 23.5℃. If this condition is not met, the search continues until three air conditioners that meet the requirements are found. This screening logic combines the air conditioner's supply air temperature and the real-time cold aisle temperature average, which can accurately identify the air conditioners that most need control, improving the effectiveness of control.

[0045] In one application example, at the current moment, it is found that the average supply air temperature of 10 air conditioners is less than 23.5℃. After sorting the average real-time cold aisle temperature k of these 10 air conditioners in ascending order, the top three air conditioners with the highest average real-time cold aisle temperature k and satisfying that the average supply air temperature is less than 23.5℃ are selected. Let's assume that these three air conditioners are air conditioner A, air conditioner B, and air conditioner C.

[0046] This application utilizes correlation analysis and distance priority principles to select relevant cold channels for each air conditioner, and then accurately locates the precision air conditioner that needs to be controlled by using the real-time cold channel temperature and safe temperature threshold of the relevant cold channels, thereby avoiding resource waste.

[0047] S105, performs temperature control on the air conditioner to be regulated.

[0048] As an optional implementation method in this embodiment, the temperature control of the air conditioner to be controlled includes: adjusting the temperature of the air conditioner to be controlled according to a preset safe temperature control value. Specifically, the safe temperature control value can be set according to actual control needs, and this application does not limit it. For example, the safe temperature control value can be set to 0.5℃, and the control of air conditioners A, B, and C can be adjusted by 0.5℃ respectively. For example, the supply air temperature of air conditioner A can be adjusted from 23℃ to 23.5℃, the supply air temperature of air conditioner B from 22℃ to 22.5℃, and the supply air temperature of air conditioner C from 22.5℃ to 23℃. In specific implementation, the cold aisle temperature of 64 cold aisle temperature sensors is also monitored in real time to ensure that it does not exceed the safe temperature threshold. If a cold aisle temperature is found to be close to or exceed the set safe temperature threshold during the control process, the supply air temperature of the air conditioner is adjusted in time to ensure the stable and safe temperature environment of the entire data center. This embodiment ensures that the cold aisle temperature does not exceed the limit through precise control and real-time monitoring, while avoiding over-control, thus achieving energy-saving effects.

[0049] The terminal air conditioning energy-saving control method provided in this application uses cold aisle temperature correlation analysis and distance priority principles to select the cold aisle temperature most relevant to each air conditioner, ensuring that the selected relevant cold aisle temperature sensors can more accurately reflect the impact of each air conditioner's outlet air temperature. Then, by using the real-time cold aisle temperature and safe temperature threshold of the relevant cold aisle, the precise air conditioner requiring control is accurately located, thereby avoiding resource waste. Furthermore, this application embodiment calculates the average real-time cold aisle temperature of the corresponding relevant cold aisle of the air conditioner, replacing multiple models with a single index. This simplifies the complex system that originally required 64 independent models into a unified logic or a small number of models, thereby reducing system complexity and the difficulty of model management and maintenance.

[0050] An exemplary embodiment of this application provides a terminal air conditioning energy-saving control device 10. Figure 5 This illustration shows a structural block diagram of a terminal air conditioning energy-saving control device 10 provided in an exemplary embodiment of this application. The aforementioned terminal air conditioning energy-saving control device 10 is applied to the control system of a data center and can achieve the following: Figures 1-4 All or part of the contents of any of the embodiments shown. The following is only a brief description of the structure and function of the terminal air conditioning energy-saving control device 10. For other matters not covered, please refer to the relevant descriptions in the above-described terminal air conditioning energy-saving control method. The embodiments of the terminal air conditioning energy-saving control device 10 correspond to the embodiments of the above-described terminal air conditioning energy-saving control method. All implementation processes and methods of the above-described method embodiments can be applied to the embodiments of the terminal air conditioning energy-saving control device 10 and can achieve the same technical effect.

[0051] like Figure 5 As shown, the terminal air conditioning energy-saving control device 10 includes: a data acquisition module 100, a correlation analysis module 200, a mean calculation module 300, a screen module for air conditioners to be controlled 400, and a control module 500, wherein: The data acquisition module 100 is used to acquire historical temperature data for a preset time period. The historical temperature data includes: historical air supply temperature of M air conditioners and historical cold aisle temperature of N cold aisle temperature sensors. The correlation analysis module 200 is used to select the corresponding relevant cold aisle for each air conditioner based on historical temperature data. The relevant cold aisle includes multiple cold aisle temperature sensors, and the historical cold aisle temperature of the relevant cold aisle is correlated with the historical air supply temperature of the air conditioner corresponding to the relevant cold aisle. The mean calculation module 300 is used to obtain the real-time cold aisle temperature of N cold aisle temperature sensors, and calculate the mean real-time cold aisle temperature of the relevant cold aisle for each air conditioner based on the real-time cold aisle temperature of N cold aisle temperature sensors. The air conditioner screening module 400 is used to screen out the air conditioners to be controlled from M air conditioners according to preset screening conditions, wherein the real-time average cold aisle temperature of the relevant cold aisle corresponding to the air conditioner to be controlled at least meets the preset screening conditions. The control module 500 is used to control the temperature of the air conditioner to be controlled.

[0052] In this embodiment, a scenario is illustrated using 20 precision air conditioners, 2 rows of cold aisles, 8 cold aisles per row, and 4 temperature sensors per cold aisle, for a total of 64 cold aisle temperature sensors. In this scenario, M=20 and N=64. The preset time period includes six months or more to obtain richer research data. The data acquisition module 100 collects historical temperature data for more than six months, including the historical supply air temperature (control parameters) of the 20 air conditioners for more than six months and the historical cold aisle temperature of the 64 cold aisle temperature sensors for more than six months.

[0053] As an optional implementation method in this embodiment, the correlation analysis module 200 uses Pearson correlation analysis to analyze the correlation between the historical cold aisle temperature of the relevant cold aisle and the historical air supply temperature of the air conditioner corresponding to the relevant cold aisle.

[0054] As an optional implementation method in this embodiment, the correlation analysis module 200 selects the corresponding relevant cold channel for each air conditioner based on historical temperature data in the following way: using Pearson correlation analysis to calculate the correlation coefficient between the historical air supply temperature of each air conditioner and the historical cold channel temperature of each cold channel temperature sensor; and selecting the first preset number of cold channel temperature sensors with the highest correlation coefficient for each air conditioner as the corresponding relevant cold channel for each air conditioner.

[0055] In addition, the correlation analysis module 200 selects the corresponding cold channel for each air conditioner based on historical temperature data in the following way: obtain the second-most preset number of cold channel temperature sensors that are closest to each air conditioner; and merge the first-most preset number of cold channel temperature sensors and the second-most preset number of cold channel temperature sensors after deduplication to obtain the corresponding cold channel for each air conditioner.

[0056] The embodiments of this application take into account correlation and distance factors to prevent missing key areas, screen out the cold aisle temperature most relevant to each air conditioner, and ensure that the selected cold aisle temperature sensor can more accurately reflect the influence of the air outlet temperature of each air conditioner.

[0057] As an optional implementation in this embodiment, the average calculation module 300 obtains the real-time cold aisle temperatures of N cold aisles in the following manner, and calculates the average real-time cold aisle temperature of the relevant cold aisle corresponding to each air conditioner based on the real-time cold aisle temperatures of the N cold aisles: The real-time cold aisle temperatures of N cold aisle temperature sensors are obtained within a first preset time period, and the average cold aisle temperature of each cold aisle temperature sensor within the first preset time period is calculated. The average cold aisle temperature is obtained by calculating the average of the real-time cold aisle temperatures within the first preset time period. Based on the average cold aisle temperature of each cold aisle within a first preset time period, the average real-time cold aisle temperature of the relevant cold aisle corresponding to each air conditioner is calculated. The average real-time cold aisle temperature of the air conditioner is obtained by calculating the average cold aisle temperature of the relevant cold aisle corresponding to the air conditioner.

[0058] In one application example, the first preset duration is 1 hour, and real-time cold aisle temperature data from 64 cold aisle temperature sensors are retrieved for 1 hour. Assuming that cold aisle temperature sensor C1 has 60 real-time cold aisle temperature data records at 1 hour, the average of the overall data is calculated to obtain the average cold aisle temperature of C1. The average cold aisle temperatures of the other 63 cold aisle temperature sensors are obtained in the same way. Therefore, by averaging the overall data, data oscillations can be reduced.

[0059] In one application example, assuming that the relevant cold aisles of air conditioner A are C2, C3, C4, and C6, in step S301, the average cold aisle temperatures of C2, C3, C4, and C6 within a first preset time period are obtained. The average of these four values ​​is then taken to obtain the real-time average cold aisle temperature k for the corresponding relevant cold aisle of air conditioner A. The real-time average cold aisle temperature k for the corresponding relevant cold aisles of all 20 air conditioners is obtained in this manner.

[0060] In this embodiment, by calculating the real-time average cold aisle temperature of the corresponding cold aisle of the air conditioner, a single index is used to replace multiple models, simplifying the complex system that originally required 64 independent models into a unified logic or a small number of models, thereby reducing system complexity and reducing the difficulty of model management and maintenance.

[0061] In this embodiment, as an optional implementation, the mean calculation module 300 is further used to obtain the real-time air supply temperature of M air conditioners within a second preset time period, and to calculate the average air supply temperature of each air conditioner within the second preset time period.

[0062] In one application example, the second preset duration can be 1 hour, retrieving real-time air supply temperature data from 20 air conditioners over one hour. Assuming air conditioner A has 60 time points of air supply temperature data records within one hour, the average of these data points is calculated to obtain the average air supply temperature of air conditioner A. The average air supply temperatures of the other 19 air conditioners are obtained in the same way. Therefore, by averaging the overall data, data oscillations can be reduced.

[0063] As an optional implementation method in this application embodiment, the air conditioner screening module 400 selects the air conditioner to be controlled from M air conditioners according to preset screening conditions in the following manner: Mark the air conditioners among the M air conditioners whose average supply air temperature is lower than the safe temperature threshold, and designate the marked air conditioners as S air conditioners to be screened; sort the real-time cold aisle temperature average of the relevant cold aisle corresponding to the S air conditioners to be screened in ascending order, where S is a positive integer and S≤M; select the air conditioners whose real-time cold aisle temperature average ranks in the top three preset numbers as the air conditioners to be controlled.

[0064] In this embodiment, the preset screening conditions include whether the average supply air temperature is less than a safe temperature threshold. For example, the safe temperature threshold can be set to 23.5℃. This temperature setting is to ensure a certain safety margin during regulation and avoid excessive regulation leading to excessively high temperatures. First, S air conditioners with an average supply air temperature less than the safe temperature threshold are initially screened out, which narrows down the range of air conditioners to be regulated and improves screening efficiency for further screening.

[0065] In this embodiment, the preset screening criteria further include: the third preset number of air conditioners ranked in the top three by the real-time average cold aisle temperature. This third preset number can be set according to actual control needs, and this application does not impose any restrictions on it. For example, three air conditioners to be controlled can be selected based on business requirements (the actual number can be determined according to the specific business scenario). The selection principle is to select the three air conditioners corresponding to the top three k values ​​in ascending order of the real-time average cold aisle temperature k, and to ensure that the air conditioner's supply air temperature is less than 23.5℃. If this condition is not met, the search continues until three air conditioners that meet the requirements are found. This screening logic combines the air conditioner's supply air temperature and the real-time average cold aisle temperature, enabling precise identification of the air conditioners most in need of control and improving the effectiveness of control.

[0066] This application utilizes correlation analysis and distance priority principles to select relevant cold channels for each air conditioner, and then accurately locates the precision air conditioner that needs to be controlled by using the real-time cold channel temperature and safe temperature threshold of the relevant cold channels, thereby avoiding resource waste.

[0067] As an optional implementation method in this embodiment, the control module 500 controls the temperature of the air conditioner to be controlled by adjusting it in the following way: adjusting the temperature of the air conditioner to be controlled according to a preset safe temperature control value. Specifically, the safe temperature control value can be set according to actual control needs, and this application does not limit it. For example, the safe temperature control value can be set to 0.5℃, and the air conditioners A, B and C can be controlled by adding 0.5℃ respectively.

[0068] The terminal air conditioning energy-saving control device provided in this application embodiment selects the cold aisle temperature most relevant to each air conditioner based on cold aisle temperature correlation analysis and distance priority principle, ensuring that the selected relevant cold aisle temperature sensors can more accurately reflect the impact of each air conditioner's outlet air temperature. Then, by using the real-time cold aisle temperature and safe temperature threshold of the relevant cold aisle, the device precisely locates the precision air conditioner requiring control, thereby avoiding resource waste. Furthermore, this application embodiment calculates the average real-time cold aisle temperature of the corresponding relevant cold aisle of the air conditioner, replacing multiple models with a single index. This simplifies the complex system, which originally required 64 independent models, into a unified logic or a small number of models, thereby reducing system complexity and the difficulty of model management and maintenance.

[0069] Figure 6 A structural block diagram of an electronic device 1000 illustrating an exemplary embodiment of this application is shown. The electronic device 1000 can be implemented as the aforementioned terminal air conditioning energy-saving control device, which can be configured in electronic devices such as smartphones, tablets, laptops, desktop computers, smartwatches, televisions, or servers.

[0070] Typically, electronic device 1000 includes a processor 1001 and a memory 1002.

[0071] Processor 1001 may include one or more processing cores, such as a quad-core processor, a deca-core processor, etc. Processor 1001 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1001 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1001 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 1001 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0072] The memory 1002 may include one or more computer-readable storage media, which may be non-transitory. The memory 1002 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1002 is used to store at least one instruction, which is executed by the processor 1001 to implement all or part of the steps in the terminal air conditioning energy-saving control method shown in the method embodiments of this application.

[0073] Those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on the electronic device 1000, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0074] In one exemplary embodiment, a readable storage medium is also provided, which stores a program or instructions that, when executed by a processor, implement all or part of the steps in the above-described terminal air conditioning energy-saving control method. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, or optical data storage device, etc.

[0075] In one exemplary embodiment, a computer program product is also provided, comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform the aforementioned... Figures 1 to 5 All or part of the steps of the terminal air conditioning energy-saving control method shown in any embodiment.

[0076] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the claims.

[0077] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for energy-saving control of terminal air conditioning, characterized in that, include: Acquire historical temperature data for a preset time period. The historical temperature data includes: historical air supply temperature of M air conditioners and historical cold aisle temperature of N cold aisle temperature sensors, where M and N are positive integers. Based on the historical temperature data, a corresponding cold aisle is selected for each air conditioner. The corresponding cold aisle includes multiple cold aisle temperature sensors, and the historical cold aisle temperature of the corresponding cold aisle is correlated with the historical air supply temperature of the air conditioner corresponding to the corresponding cold aisle. Obtain the real-time cold aisle temperature of N cold aisle temperature sensors, and calculate the average real-time cold aisle temperature of the relevant cold aisle corresponding to each air conditioner based on the real-time cold aisle temperature of N cold aisle temperature sensors. According to preset screening conditions, air conditioners to be controlled are selected from M air conditioners. The average real-time cold aisle temperature of the relevant cold aisle corresponding to the air conditioner to be controlled at least meets the preset screening conditions. The preset screening conditions include that the average air supply temperature of the air conditioner is less than the safe temperature threshold. The average air supply temperature is the average real-time air supply temperature of the air conditioner within a second preset time period. The air conditioner to be regulated is heated.

2. The method according to claim 1, characterized in that, The step of selecting a corresponding cold aisle for each air conditioner based on the historical temperature data includes: Pearson correlation analysis was used to calculate the correlation coefficient between the historical supply air temperature of each air conditioner and the historical cold aisle temperature of each cold aisle temperature sensor. For each air conditioner, select the first preset number of cold aisle temperature sensors with the highest correlation coefficient as the corresponding cold aisle for each air conditioner.

3. The method according to claim 2, characterized in that, The step of selecting a corresponding cold aisle for each air conditioner based on the historical temperature data also includes: Obtain the second preset number of cold aisle temperature sensors that are closest to each of the aforementioned air conditioners; The first preset number of cold aisle temperature sensors and the second preset number of cold aisle temperature sensors are deduplicated and merged to form the relevant cold aisle for each air conditioner.

4. The method according to claim 1, characterized in that, The step of acquiring the real-time cold aisle temperatures of N cold aisle temperature sensors, and calculating the average real-time cold aisle temperature of the relevant cold aisle for each air conditioner based on the real-time cold aisle temperatures of the N cold aisle temperature sensors, includes: The real-time cold aisle temperatures of N cold aisle temperature sensors are obtained within a first preset time period, and the average cold aisle temperature of each cold aisle temperature sensor within the first preset time period is calculated, wherein the average cold aisle temperature is obtained by calculating the average of the real-time cold aisle temperatures within the first preset time period. Based on the average cold aisle temperature of each of the cold aisle temperature sensors within the first preset time period, the real-time average cold aisle temperature of the relevant cold aisle corresponding to each air conditioner is calculated, wherein the real-time average cold aisle temperature of the air conditioner is obtained by calculating the average cold aisle temperature of the relevant cold aisle corresponding to the air conditioner.

5. The method according to claim 1, characterized in that, The step of selecting the air conditioner to be controlled from the M air conditioners according to preset screening criteria includes: Sort the average real-time cold aisle temperature of the relevant cold aisle corresponding to the S air conditioners to be screened in ascending order, where S is a positive integer and S≤M; The air conditioners whose average real-time cold aisle temperature ranks among the top three preset numbers are selected as the air conditioners to be controlled.

6. The method according to claim 5, characterized in that, The average air supply temperature of the air conditioner to be controlled meets the preset screening conditions. Before selecting the air conditioner to be controlled from the M air conditioners, the method further includes: obtaining the real-time air supply temperature of the M air conditioners within a second preset time period, and calculating the average air supply temperature of each air conditioner within the second preset time period; Before sorting the real-time cold aisle temperature averages of the S air conditioners to be screened in ascending order, the method includes: Air conditioners with an average supply air temperature lower than the safe temperature threshold among the M air conditioners are marked, and the marked air conditioners are selected as the S air conditioners to be screened.

7. The method according to claim 1, characterized in that, The method of regulating the temperature of the air conditioner to be regulated includes: regulating the temperature of the air conditioner to be regulated according to a preset safe temperature regulation value.

8. A terminal air conditioning energy-saving control device, characterized in that, include: The data acquisition module is used to acquire historical temperature data over a preset time period. The historical temperature data includes: historical air supply temperatures of M air conditioners and historical cold aisle temperatures of N cold aisle temperature sensors. The correlation analysis module is used to select a corresponding cold channel for each air conditioner based on the historical temperature data. The corresponding cold channel includes multiple cold channel temperature sensors, and the historical cold channel temperature of the corresponding cold channel is correlated with the historical air supply temperature of the air conditioner corresponding to the corresponding cold channel. The mean calculation module is used to obtain the real-time cold aisle temperature of N cold aisle temperature sensors, and calculate the mean real-time cold aisle temperature of the relevant cold aisle corresponding to each air conditioner based on the real-time cold aisle temperature of N cold aisle temperature sensors. The air conditioner screening module is used to screen out the air conditioners to be controlled from M air conditioners according to preset screening conditions. The average real-time cold aisle temperature of the relevant cold aisle corresponding to the air conditioner to be controlled at least meets the preset screening conditions. The preset screening conditions include that the average air supply temperature of the air conditioner is less than a safe temperature threshold. The average air supply temperature is the average real-time air supply temperature of the air conditioner within a second preset time period. The control module is used to control the temperature of the air conditioner to be controlled.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the steps of the terminal air conditioning energy-saving control method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions, which, when executed by a processor, implement the steps of the terminal air conditioning energy-saving control method as described in any one of claims 1-7.

11. A computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the steps of the terminal air conditioning energy-saving control method as described in any one of claims 1 to 7.

Images