Air conditioning control method, device, electronic equipment and storage medium

By clustering analysis of the historical data of air conditioners, determining the regulation strategy and conducting unified regulation, the existing air conditioner control methods are solved, and the efficiency and energy saving effect of existing air conditioner control methods in large buildings is achieved, achieving more efficient air conditioner management.

CN118189361BActive Publication Date: 2024-11-12WUHAN SAN FRAN ELECTRONICS CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202410521744.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-28
Publication Date
2024-11-12
Estimated Expiration
2044-04-28

AI Technical Summary

Technical Problem

The existing air conditioner control methods cannot take into account the control efficiency, energy saving effect and user comfort. Especially in large buildings, when controlling each air conditioner separately or controlling each floor/building in a unified manner, the data volume and logic are large, resulting in Energy saving effect and user comfort cannot be guaranteed.

Method used

By clustering analysis of the historical use data of the air conditioner in multiple target control areas, a cluster of control areas is obtained, and the corresponding air conditioner control strategy is determined based on each cluster, and the air conditioner in the cluster is uniformly regulated to reduce real-time monitoring and processing data improve control efficiency.

Benefits of technology

While ensuring the energy-saving effect and user comfort in each air conditioning control area, the amount of data monitored and processed in real time is greatly reduced, and the efficiency and accuracy of air conditioning control is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118189361B_ABST
    Figure CN118189361B_ABST
Patent Text Reader

Abstract

The present application relates to the field of air conditioning control technology, and specifically provides an air conditioning control method, device, electronic device and storage medium, including: clustering analysis of the historical air conditioning usage data of the target control area to obtain clustering results; the clustering results include multiple control area clusters; determining the air conditioning control strategy corresponding to each control area cluster; and uniformly controlling the air conditioners in the corresponding control area cluster according to the air conditioning control strategy. Since the control area cluster is obtained by clustering analysis of the historical air conditioning usage data of the target control area, multiple target control areas in each control area cluster have similar historical air conditioning usage data; based on the air conditioning control strategy corresponding to each control area cluster, the air conditioners in the control area cluster are uniformly controlled, which can ensure the energy saving effect / user comfort of each air conditioning control area while greatly reducing the relevant data that needs to be monitored and processed in real time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of air conditioning control technology, and more specifically, to an air conditioning control method, device, electronic device and storage medium. Background Art

[0002] The existing air conditioning control method mainly monitors the objective environmental factors and historical usage behavior of the air conditioner in real time, and controls the air conditioner according to the real-time monitoring data.

[0003] For large buildings with multiple air conditioners (each air conditioner corresponds to a different control area), each air conditioner is usually controlled individually based on the existing air conditioner control method; or the air conditioners in each floor / building are controlled uniformly. Individual control of each air conditioner can achieve better energy-saving effects / user comfort, but individual control requires real-time monitoring and processing of a large amount of data, and the control logic is cumbersome; and in the case of unified control, the energy-saving effect / user comfort of each air conditioner control area cannot be guaranteed. Summary of the invention

[0004] In view of this, the purpose of the embodiments of the present application is to provide an air conditioning control method, device, electronic device and storage medium to solve the technical problem that the existing air conditioning control method cannot take into account both control efficiency and energy saving effect / user comfort.

[0005] In a first aspect, an embodiment of the present application provides an air conditioning control method, which is used to control the air conditioning in a target building including multiple target control areas, and the method includes:

[0006] Performing cluster analysis on the historical air-conditioning usage data of the target control area to obtain a clustering result; wherein the historical air-conditioning usage data includes: at least one of the ambient temperature data, ambient humidity data, control area temperature data, control area humidity data, air-conditioning control data and air-conditioning power consumption data of the target control area within a target historical time period; the clustering result includes a plurality of control area clusters, each of which includes a plurality of the target control areas;

[0007] Determining an air conditioning control strategy corresponding to each of the control area clusters;

[0008] The air conditioners in the corresponding control area cluster are uniformly controlled according to the air conditioner control strategy.

[0009] In the above implementation process, the air conditioning control method obtains clustering results by clustering analysis on the historical air conditioning usage data of the target control area; wherein the clustering results include multiple control area clusters; determines the air conditioning control strategy corresponding to each of the control area clusters; and uniformly controls the air conditioners in the corresponding control area clusters according to the air conditioning control strategy. The control area cluster is obtained by clustering analysis on the historical air conditioning usage data of the target control area, and multiple target control areas in the control area cluster have similar historical air conditioning usage data; based on the air conditioning control strategy corresponding to each control area cluster, the air conditioners in the control area cluster are uniformly controlled, which can ensure the energy-saving effect / user comfort of each air conditioning control area while greatly reducing the relevant data that needs to be monitored and processed in real time. The technical problem that the existing air conditioning control method cannot take into account both control efficiency and energy-saving effect / user comfort is solved.

[0010] Optionally, in an embodiment of the present application, determining the air conditioning control strategy corresponding to each of the control area clusters includes: determining a central control area within each of the control area clusters and a central air conditioning control strategy corresponding to the central control area; and determining the central air conditioning control strategy as the air conditioning control strategy corresponding to the control area cluster.

[0011] In the above implementation process, by determining the central air conditioning control strategy corresponding to the central control area in each control area cluster, and determining the central air conditioning control strategy as the air conditioning control strategy corresponding to the control area cluster, the air conditioners in the control area cluster can be uniformly controlled according to the central air conditioning control strategy. In the process of realizing "uniform control of the air conditioners in the control area cluster", only the air conditioning data of the central control area needs to be monitored and processed, which greatly reduces the relevant data that needs to be monitored and processed during the air conditioning control process, thereby improving the control efficiency of the air conditioner.

[0012] Optionally, in an embodiment of the present application, the clustering result also includes: a central control area within each of the control area clusters; the clustering analysis is performed on the air-conditioning historical usage data of the target control area to obtain the clustering result, including: performing K clustering analysis on the air-conditioning historical usage data to obtain a preset number of the control area clusters and the central control area within each control area cluster.

[0013] In the above implementation process, the historical air-conditioning usage data of the target control area is clustered and analyzed by means of K cluster analysis. While obtaining the clustering results, the central control area within each control area cluster can be more reasonably determined, and the control accuracy of the air-conditioning within the control area cluster can be further improved to obtain better energy-saving effects / user comfort.

[0014] Optionally, in an embodiment of the present application, the method for determining the preset number includes: determining an initial number range of the preset number; wherein the initial number range includes multiple initial numbers; calculating clustering parameters corresponding to each of the initial numbers; wherein the clustering parameters include at least one of a silhouette coefficient, a covariance coefficient, an error square sum coefficient, and an intermittent statistic; and determining the preset number within the initial number range based on the clustering parameters.

[0015] In the above implementation process, according to the clustering parameters corresponding to each initial number, the value of the preset number (i.e., the number of clusters of the control area cluster in the results of the clustering analysis) can be determined more accurately, thereby improving the accuracy of the clustering analysis results to obtain better energy-saving effects / user comfort.

[0016] Optionally, in an embodiment of the present application, before performing K cluster analysis on the air conditioner historical usage data, performing cluster analysis on the air conditioner historical usage data of the target control area further includes: performing density cluster analysis on the air conditioner historical usage data based on a preset density threshold and a minimum cluster threshold to obtain core point data, boundary point data and noise point data;

[0017] The K clustering analysis is performed on the air conditioner historical usage data to obtain a preset number of control area clusters and a central control area within each control area cluster, including: performing a K clustering analysis on the core point data and the boundary point data to obtain a preset number of control area clusters and a central control area within each control area cluster.

[0018] In the above implementation process, by performing density clustering analysis on the historical air-conditioning usage data, core point data, boundary point data and noise point data with low density are obtained; K clustering analysis is performed on the core point data and boundary point data after removing the noise point data, so as to obtain more accurate clustering analysis results, so as to obtain better energy-saving effect / user comfort.

[0019] Optionally, in an embodiment of the present application, after performing density clustering analysis on the air-conditioning historical usage data based on a preset density threshold and a minimum cluster threshold to obtain core point data, boundary point data and noise point data, the method further includes: determining an independent air-conditioning control strategy corresponding to each of the noise point data; and independently controlling the air-conditioning within the target control area corresponding to the corresponding noise point data based on the independent air-conditioning control strategy.

[0020] In the above implementation process, for the air conditioners in the target control area corresponding to the noise point data with lower density, independent air conditioning control strategies are adopted to independently control them to ensure the air conditioning control effect and obtain better energy saving effect / user comfort.

[0021] Optionally, in an embodiment of the present application, clustering analysis is performed on the historical usage data of the air conditioner in the target control area to obtain clustering results, including: preprocessing the historical usage data of the air conditioner to obtain preprocessed data within a unit time; wherein the preprocessed data includes: at least one of the daily average temperature of the environment, the daily average humidity of the environment, the daily average temperature of the control area, the daily average humidity of the control area, the daily average control data and the daily average electricity consumption data per unit area; cluster analysis is performed on the preprocessed data to obtain the clustering results.

[0022] In the above implementation process, by preprocessing the historical air-conditioning usage data, the preprocessed data within a unit time is obtained; the influence of the delay of the air-conditioning system on the historical air-conditioning usage data can be eliminated, thereby obtaining a more accurate clustering result.

[0023] In a second aspect, an embodiment of the present application provides an air conditioning control device, the device comprising:

[0024] A cluster analysis module, configured to perform cluster analysis on the historical air-conditioning usage data of the target control area to obtain a clustering result; wherein the historical air-conditioning usage data includes: at least one of the ambient temperature data, ambient humidity data, control area temperature data, control area humidity data, air-conditioning control data and air-conditioning power consumption data of the target control area within a target historical time period; the clustering result includes a plurality of control area clusters, each of which includes a plurality of the target control areas;

[0025] A control strategy determination module, used to determine the air conditioning control strategy corresponding to each of the control area clusters;

[0026] The air conditioning control module is used to uniformly control the air conditioners in the corresponding control area cluster according to the air conditioning control strategy.

[0027] Optionally, in an embodiment of the present application, the control strategy determination module is specifically used to: determine a central control area within each of the control area clusters and a central air conditioning control strategy corresponding to the central control area; and determine the central air conditioning control strategy as the air conditioning control strategy corresponding to the control area cluster.

[0028] Optionally, in an embodiment of the present application, the clustering results also include: a central control area within each of the control area clusters; the clustering analysis module is specifically used to: perform K clustering analysis on the air-conditioning historical usage data to obtain a preset number of the control area clusters and a central control area within each control area cluster.

[0029] Optionally, in an embodiment of the present application, the device also includes: a preset quantity determination module, used to determine an initial quantity range of the preset quantity; wherein the initial quantity range includes multiple initial quantities; calculate clustering parameters corresponding to each of the initial quantities; wherein the clustering parameters include at least one of a silhouette coefficient, a covariance coefficient, an error square sum coefficient and an intermittent statistic; based on the clustering parameters, determine the preset quantity within the initial quantity range.

[0030] Optionally, in an embodiment of the present application, the cluster analysis module is specifically used to: perform density cluster analysis on the air-conditioning historical usage data based on a preset density threshold and a minimum cluster threshold to obtain core point data, boundary point data and noise point data; and perform K cluster analysis on the core point data and the boundary point data to obtain a preset number of the control area clusters and the central control area within each control area cluster.

[0031] Optionally, in an embodiment of the present application, the device also includes: the control strategy determination module, which is also used to determine the independent air-conditioning control strategy corresponding to each of the noise point data; the air-conditioning control module is also used to independently control the air-conditioning in the target control area corresponding to the corresponding noise point data based on the independent air-conditioning control strategy.

[0032] Optionally, in an embodiment of the present application, the cluster analysis module is specifically used to: preprocess the historical air-conditioning usage data to obtain preprocessed data within a unit time; wherein the preprocessed data includes: at least one of the daily average temperature of the environment, the daily average humidity of the environment, the daily average temperature of the control area, the daily average humidity of the control area, the daily average control data and the daily average electricity consumption data per unit area; perform cluster analysis on the preprocessed data to obtain the clustering results.

[0033] In a third aspect, an embodiment of the present application further provides an electronic device; the electronic device includes:

[0034] Memory;

[0035] processor;

[0036] The memory stores a computer program executable by the processor, and when the computer program is executed by the processor, the air conditioning control method described in any one of the first aspects is performed.

[0037] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the air conditioning control method as described in any one of the first aspects is executed.

[0038] The beneficial effects of the present application are: obtaining clustering results by clustering analysis of the historical air-conditioning usage data of the target control area; wherein the clustering results include multiple control area clusters; determining the air-conditioning control strategy corresponding to each of the control area clusters; and uniformly controlling the air-conditioning in the corresponding control area cluster according to the air-conditioning control strategy. The control area cluster is obtained by clustering analysis of the historical air-conditioning usage data of the target control area, and multiple target control areas in the control area cluster have similar historical air-conditioning usage data; based on the air-conditioning control strategy corresponding to each control area cluster, the air-conditioning in the control area cluster is uniformly controlled, which can ensure the energy-saving effect / user comfort of each air-conditioning control area while greatly reducing the relevant data that needs to be monitored and processed in real time. It solves the technical problem that the existing air-conditioning control method cannot take into account both control efficiency and energy-saving effect / user comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A schematic diagram of a flow chart of an air conditioning control method provided in an embodiment of the present application;

[0041] Figure 2 A numerical schematic diagram of clustering parameters corresponding to different initial numbers provided in an embodiment of the present application;

[0042] Figure 3 A schematic diagram of the structure of an air conditioning control device provided in an embodiment of the present application;

[0043] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0046] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0047] See also Figure 1 The flowchart of an air conditioning control method provided by an embodiment of the present application is shown. The air conditioning control method is used to control the air conditioning in a target building including multiple target control areas, and the air conditioning control method may include the following steps:

[0048] S101, performing cluster analysis on the historical air-conditioning usage data of the target control area to obtain a clustering result; wherein the historical air-conditioning usage data includes: at least one of the ambient temperature data, ambient humidity data, control area temperature data, control area humidity data, air-conditioning control data and air-conditioning power consumption data of the target control area within a target historical time period; the clustering result includes a plurality of control area clusters, each of which includes a plurality of the target control areas;

[0049] S102, determining an air conditioning control strategy corresponding to each of the control area clusters;

[0050] S103: uniformly control the air conditioners in the corresponding control area cluster according to the air conditioner control strategy.

[0051] Among them, in step 101, the number of target control areas can be 10, 80, 200 or other reasonable values; the target building can be a school, an office building or an intelligent building, etc.; the number of air conditioners in a single target control area can be 1, 3 or other reasonable values; this application does not make specific restrictions on this. The historical use data of the air conditioner can include only the power consumption data of the air conditioner; it can also include the ambient temperature data, the temperature data of the control area and the power consumption data of the air conditioner; or it can include the ambient humidity data, the humidity data of the control area and the power consumption data of the air conditioner; it can also include the ambient temperature data, the ambient humidity data, the temperature data of the control area, the humidity data of the control area, the air conditioner control data and the power consumption data of the air conditioner. The air conditioner control data may include: the wind force size of the air conditioner, the working mode (which may include cooling, heating, humidification, etc.), the working temperature and other parameters; the air conditioner power consumption data may include parameters such as the working time period or the power consumption. The clustering method used for clustering analysis of the historical use data of the air conditioner in the target control area can be: density-based clustering analysis (for example, DBSCAN clustering algorithm) or partition-based clustering analysis (for example, K-means clustering algorithm), etc.

[0052] In step 102, the air conditioning control strategy corresponding to the control area cluster may be determined based on any target control area in the control area cluster, or the air conditioning historical usage data in multiple target control areas. For example, the target control area in the center area of ​​the control area cluster may be determined based on the location of the target control area, and the air conditioning control strategy corresponding to the control area cluster may be determined based on the air conditioning historical usage data of the target control area in the center area.

[0053] Among them, in step 103, the control area cluster obtained by cluster analysis includes multiple target control areas with relatively similar air-conditioning historical usage data; based on the air-conditioning control strategy, the air-conditioners in the corresponding control area clusters are uniformly controlled, which can ensure the energy-saving effect / user comfort of each air-conditioning control area while greatly reducing the relevant data that needs to be monitored and processed in real time.

[0054] It can be seen that the air conditioning control method provided in the embodiment of the present application obtains clustering results by clustering analysis on the air conditioning historical usage data of the target control area; wherein the clustering results include multiple control area clusters; determining the air conditioning control strategy corresponding to each of the control area clusters; and uniformly controlling the air conditioners in the corresponding control area clusters according to the air conditioning control strategy. Among them, the control area cluster is obtained by clustering analysis on the air conditioning historical usage data of the target control area, and multiple target control areas in the control area cluster have similar air conditioning historical usage data; based on the air conditioning control strategy corresponding to each control area cluster, the air conditioners in the control area cluster are uniformly controlled, which can ensure the energy-saving effect / user comfort of each air conditioning control area while greatly reducing the relevant data that needs to be monitored and processed in real time. It solves the technical problem that the existing air conditioning control method cannot take into account both control efficiency and energy-saving effect / user comfort.

[0055] In addition, S101, performing cluster analysis on the historical air-conditioning usage data of the target control area to obtain clustering results, may also include: performing cluster analysis on the historical air-conditioning usage data and future air-conditioning usage demand data of the target control area to obtain the clustering results.

[0056] Among them, the future air conditioning use demand data may include: air conditioning use time period demand, power consumption demand, use temperature range demand, etc. Based on the above method, by clustering the air conditioning data of all target control areas (which may include air conditioning historical use data and future air conditioning use demand data), the air conditioning data analysis from room latitude (taking the target control area as room as an example) to building latitude (taking the target building as building as an example) is completed, and the comprehensive analysis of air conditioning data from point to surface is realized, so as to efficiently and accurately complete the air conditioning control in each target control area.

[0057] In some optional embodiments, S102, determining the air conditioning control strategy corresponding to each of the control area clusters, includes: determining a central control area within each of the control area clusters and a central air conditioning control strategy corresponding to the central control area; determining the central air conditioning control strategy as the air conditioning control strategy corresponding to the control area cluster.

[0058] Among them, the central control area can be determined according to the spatial position of the target control area in the control area cluster, or according to the similarity between the air conditioning historical usage data in any two or more target control areas in the control area cluster; and the air conditioning control strategy corresponding to the central control area is determined as the air conditioning control strategy corresponding to the control area cluster. The specific implementation method of "determining the central control area according to the similarity between the air conditioning historical usage data in any two target control areas in the control area cluster" may include: determining the sum of the similarities between the designated target control area and the air conditioning historical usage data of any other target control areas (taking the target control area including the first control area, the second control area and the third control area as an example, the sum of the similarities corresponding to the first control area refers to the sum of "the similarity between the air conditioning historical usage data of the first control area and the second control area" and "the similarity between the air conditioning historical usage data of the first control area and the third control area"); the designated target control area with the largest sum of similarities is determined as the above-mentioned central control area.

[0059] In some optional embodiments, the clustering result also includes: a central control area within each of the control area clusters; S101, performing cluster analysis on the air-conditioning historical usage data of the target control area to obtain a clustering result, including: performing K clustering analysis on the air-conditioning historical usage data to obtain a preset number of the control area clusters and the central control area within each control area cluster.

[0060] Among them, the control area clusters and the central control area within each control area cluster can be obtained through K cluster analysis. K cluster analysis can divide the target control area into a preset number of clusters (i.e., control area clusters) through an iterative process, and the data points (i.e., air conditioner historical usage data) within each cluster (i.e., control area cluster) have high similarity. The preset number can be 3, 5, 8 or other reasonable values; specifically, the specific value of the preset number in the K cluster analysis can be determined based on clustering parameters (e.g., silhouette coefficient, covariance coefficient, error square sum coefficient, and intermittent statistics, etc.) or the inflection point method.

[0061] In some optional embodiments, the method for determining the above-mentioned preset number includes: determining an initial number range of the preset number; wherein the initial number range includes multiple initial numbers; calculating clustering parameters corresponding to each of the initial numbers; wherein the clustering parameters include at least one of a silhouette coefficient, a covariance coefficient, an error square sum coefficient and an intermittent statistic; and determining the preset number within the initial number range based on the clustering parameters.

[0062] The clustering parameters may include the silhouette coefficient and the covariance coefficient, or may include the error square sum coefficient, or may include the silhouette coefficient, the covariance coefficient, the error square sum coefficient, and the interval statistic at the same time. The initial number range may be [2, 8], or [3, 6] or other reasonable numerical ranges. The covariance coefficient refers to the ratio of the covariance within the regulatory region cluster to the covariance between the regulatory region clusters.

[0063] Please refer to Figure 2 , Figure 2 A numerical schematic diagram of clustering parameters corresponding to different initial numbers provided in an embodiment of the present application. Figure 2 The numerical diagram shown corresponds to the case where "the initial number range is [2, 7], and the clustering parameters include the silhouette coefficient, covariance coefficient, error square sum coefficient, and intermittent statistic". By calculating the values ​​of each clustering parameter when the initial number is 2, 3, 4, 5, 6, and 7 respectively (wherein the calculation method of the silhouette coefficient, covariance coefficient, error square sum coefficient, and intermittent statistic can be implemented based on the existing corresponding coefficient calculation method); and making the calculated clustering parameters into the following Figure 2 The data graph shown can more easily observe the initial data with the best clustering effect, and use the initial number with the best clustering effect as the above preset number. Specifically, the closer the silhouette coefficient is to 1, the better the clustering effect; the clustering effect corresponding to the inflection point (i.e., the sudden slowdown in the rate of decline) in the covariance coefficient and the error square sum coefficient is better; and the clustering effect corresponding to the initial number when the interval statistic is positive for the first time is the best. Combined with Figure 2 The clustering parameters shown in can determine that when the preset number is 3, the best clustering effect can be obtained. It should be noted that Figure 2 It is only a numerical diagram of clustering parameters shown as an example. The specific numerical values ​​of clustering parameters need to be determined according to the actual target control area and historical air-conditioning usage data.

[0064] In some optional embodiments, before performing K cluster analysis on the air conditioner historical usage data, S101, performing cluster analysis on the air conditioner historical usage data of the target control area, also includes: performing density cluster analysis on the air conditioner historical usage data based on a preset density threshold and a minimum cluster threshold to obtain core point data, boundary point data and noise point data; performing K cluster analysis on the air conditioner historical usage data to obtain a preset number of control area clusters and the central control area within each control area cluster, includes: performing K cluster analysis on the core point data and the boundary point data to obtain a preset number of control area clusters and the central control area within each control area cluster.

[0065] Among them, the density clustering analysis of the historical air-conditioning usage data can be realized based on DBSCAN (Density-Based Spatial Clustering of Applications with Noise), OPTICS (Ordering Points to Identify the Clustering Structure) or DENCLUE (DENsity CLUE) algorithms. The preset density threshold and the minimum cluster threshold can be determined or adjusted according to the actual application parameters such as the type of target building, the number of target control areas, and the historical air-conditioning usage data. The minimum cluster threshold refers to the number of objects (data points corresponding to the historical air-conditioning usage data in the target control area) contained in a certain area in the clustering space is not less than the minimum cluster threshold; the preset density threshold refers to the neighborhood distance threshold of the sample (including multiple data points corresponding to the historical air-conditioning usage data). By performing density clustering analysis on the historical usage data of the air conditioner, the historical usage data of the air conditioner is divided into core point data, boundary point data and noise point data with lower density; then, by performing K clustering analysis on the core point data and boundary point data after removing the noise point data, the quality of the clustering analysis is improved to obtain more accurate clustering analysis results, thereby improving the energy saving effect / user comfort that can be achieved by the air conditioning control method.

[0066] Among them, for the case of implementing density clustering analysis of historical air conditioner usage data based on the DBSCAN algorithm, the preset density threshold can be the neighborhood radius when defining density. Each historical air conditioner usage data can be corresponded to a historical data point; determine the preset density threshold and the minimum cluster threshold; randomly select a first data point from the historical data points; determine the first number of historical data points in the area with the first data point as the center and the preset density threshold as the radius; if the first number is greater than or equal to the minimum cluster threshold, determine the first data point as the core point data; and determine "the historical data points in the area with the first data point as the center and the preset density threshold as the radius" as the neighborhood of the first data point.

[0067] If the first data point is less than the minimum cluster threshold, it is determined that the first data point is not core point data; determine whether the first data point is in the neighborhood of other data points; if the first data point is in the neighborhood of any other data point, determine that the first data point is a boundary data point; if the first data point is not in the neighborhood of all other data points, determine that the first data point is a noise data point.

[0068] In some optional embodiments, after performing density clustering analysis on the air-conditioning historical usage data based on a preset density threshold and a minimum cluster threshold to obtain core point data, boundary point data and noise point data, the method further includes: determining an independent air-conditioning control strategy corresponding to each of the noise point data; and independently controlling the air-conditioning in the target control area corresponding to the corresponding noise point data based on the independent air-conditioning control strategy.

[0069] Among them, for the air conditioners in the target control area corresponding to the noise point data with lower density, the independent air conditioner control strategy corresponding to the air conditioners in the target control area can be determined based on the historical use data of the air conditioners, and the real-time environmental data of the air conditioners in the corresponding target control area can be monitored separately. According to the real-time environmental data and the independent air conditioner control strategy, the control of the "air conditioners in the target control area corresponding to the noise point data with lower density" can be achieved to obtain better energy saving effect / user comfort. For application scenarios where the requirements for energy saving effect or user comfort are not very high, the "target control area corresponding to the noise point data" can also be divided into the above-mentioned control area cluster, and the air conditioners in the corresponding control area cluster can be uniformly controlled based on the air conditioner control strategy.

[0070] In some optional embodiments, clustering analysis is performed on the historical air-conditioning usage data of the target control area to obtain clustering results, including: preprocessing the historical air-conditioning usage data to obtain preprocessed data within a unit time; wherein the preprocessed data includes: at least one of the daily average temperature of the environment, the daily average humidity of the environment, the daily average temperature of the control area, the daily average humidity of the control area, the daily average control data and the daily average electricity consumption data per unit area; cluster analysis is performed on the preprocessed data to obtain the clustering results.

[0071] Among them, by preprocessing the historical use data of the air conditioner, the preprocessed data within a unit time is obtained; the influence of the delay of the air conditioning system on the historical use data of the air conditioner can be eliminated, thereby obtaining a more accurate clustering result. In the case where the historical use data of the air conditioner includes ambient temperature data, ambient humidity data, temperature data of the control area, humidity data of the control area, air conditioning control data and air conditioning power consumption data, the use data of the air conditioner in the historical time period can be obtained, specifically, the use data of the corresponding air conditioner in the past year, or in July or December of last year. Taking the historical use data of the air conditioner including the ambient temperature data, ambient humidity data, temperature data of the control area, humidity data of the control area, air conditioning control data and air conditioning power consumption data of the corresponding air conditioner in July of last year as an example, the obtained ambient temperature data, ambient humidity data, temperature data of the control area, humidity data of the control area, etc. can be averaged to one day, and the air conditioning control data (for example, wind speed, air conditioning working temperature, etc.) can also be averaged to one day. For air-conditioning power consumption data, such as power consumption, the air-conditioning load per unit area can be calculated first (specifically, it can be the air-conditioning load per unit area in the target control area in each time period of the day), each time period may include 8:00 a.m. to 9:00 a.m., 9:00 a.m. to 10:00 a.m., 10:00 a.m. to 11:00 a.m., 11:00 a.m. to 12:00 noon, 12:00 noon to 1:00 p.m., 1:00 p.m. to 2:00 p.m. and other time periods; then the air-conditioning load of each day is averaged using stack processing to obtain the daily average power consumption per unit area.

[0072] Optionally, in an embodiment of the present application, after preprocessing the historical air-conditioning usage data to obtain the preprocessed data within a unit time, clustering analysis is performed on the historical air-conditioning usage data of the target control area to obtain clustering results, which may also include: performing principal component analysis on the preprocessed data to obtain principal component data in the preprocessed data; performing cluster analysis on the principal component data to obtain the clustering results.

[0073] Among them, the principal component analysis of the preprocessed data can be realized based on the PCA principal component analysis method. The preprocessed data is reduced in dimension by the principal component analysis method, and the mutual influencing factors between the preprocessed data are eliminated, so as to reduce the data dimension for cluster analysis while retaining the key data, and improve the accuracy of the cluster analysis results.

[0074] Please refer to Figure 3 , Figure 3 A schematic diagram of the structure of an air conditioning control device provided in an embodiment of the present application. The air conditioning control device comprises:

[0075] The cluster analysis module 201 is used to perform cluster analysis on the historical air-conditioning usage data of the target control area to obtain a clustering result; wherein the historical air-conditioning usage data includes: at least one of the ambient temperature data, ambient humidity data, control area temperature data, control area humidity data, air-conditioning control data and air-conditioning power consumption data of the target control area within a target historical time period; the clustering result includes a plurality of control area clusters, each of which includes a plurality of the target control areas;

[0076] A control strategy determination module 202, used to determine the air conditioning control strategy corresponding to each of the control area clusters;

[0077] The air conditioning control module 203 is used to uniformly control the air conditioners in the corresponding control area cluster according to the air conditioning control strategy.

[0078] It should be understood that the air conditioning control device corresponds to the above-mentioned air conditioning control method embodiment and can execute the various steps involved in the above-mentioned method embodiment. The specific functions of the air conditioning control device can be found in the description above. To avoid repetition, the detailed description is appropriately omitted here. The air conditioning control device includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the device.

[0079] Please refer to Figure 4 , Figure 4 The present invention provides a schematic diagram of the structure of an electronic device 300 provided in an embodiment of the present application. The electronic device 300 includes: a memory 302 and a processor 301; the memory 302 stores a computer program executable by the processor 301, and when the computer program is executed by the processor 301, the air conditioning control method described in any one of the first aspects is executed.

[0080] The memory 302 and the processor 301 may be interconnected and communicate with each other via a communication bus 303 and / or other forms of connection mechanisms (not shown). The memory 302 stores a computer program executable by the processor 301, and when the computer program is executed by the processor 301, the air conditioning control method described in the first aspect above is executed.

[0081] The embodiment of the present application further provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by the processor 301, the air conditioning control method described in the first aspect above is executed.

[0082] Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0083] In several embodiments provided by the embodiments of the present application, it should be understood that the disclosed device / system and method can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a part of the module, program segment or code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0084] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0085] The above description is only an optional implementation manner of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the embodiments of the present application, which should be covered within the protection scope of the embodiments of the present application.

Claims

1. An air conditioning control method, characterized in that: The method is used to control the air conditioning in a target building including a plurality of target control areas, and the method comprises: Performing cluster analysis on the historical air-conditioning usage data of the target control area to obtain a clustering result; wherein the historical air-conditioning usage data includes: ambient temperature data, ambient humidity data, at least one of control area temperature data and control area humidity data of the target control area within a target historical time period, air-conditioning power consumption data, and air-conditioning control data; the clustering result includes a plurality of control area clusters, each of which includes a plurality of the target control areas; Determining an air conditioning control strategy corresponding to each of the control area clusters; Performing unified control of the air conditioners in the corresponding control area cluster according to the air conditioner control strategy; The cluster analysis of the historical air-conditioning usage data of the target control area to obtain the clustering result includes: preprocessing the historical air-conditioning usage data to obtain the preprocessing data within a unit time; wherein the preprocessing data includes: the daily average temperature of the environment, the daily average humidity of the environment, the daily average temperature of the control area and the daily average humidity of the control area, at least one of the daily average electricity consumption data per unit area and the daily average control data; performing principal component analysis on the preprocessing data to obtain the principal component data in the preprocessing data; performing cluster analysis on the principal component data to obtain the clustering result; Wherein, the determining of the air conditioning control strategy corresponding to each of the control area clusters includes: determining a central control area within each of the control area clusters and a central air conditioning control strategy corresponding to the central control area; determining the central air conditioning control strategy as the air conditioning control strategy corresponding to the control area cluster; Among them, the determination of the central control area within each of the control area clusters and the central air-conditioning control strategy corresponding to the central control area includes: determining the central control area according to the similarity between the air-conditioning historical usage data of any two target control areas within each of the control area clusters; the specific implementation method is: determining the sum of the similarities between the air-conditioning historical usage data of the designated target control area within each of the control area clusters and any other target control areas; determining the designated target control area with the largest sum of similarities as the central control area within the control area cluster; and determining the air-conditioning control strategy corresponding to the central control area as the air-conditioning control strategy corresponding to the control area cluster.

2. The method according to claim 1, characterized in that in, The clustering results also include: a central regulatory region within each of the regulatory region clusters; The cluster analysis of the historical air conditioning usage data of the target control area to obtain a clustering result includes: performing a K cluster analysis on the historical air conditioning usage data to obtain a preset number of control area clusters and a central control area in each control area cluster; Wherein, before performing K cluster analysis on the historical air conditioner usage data, performing cluster analysis on the historical air conditioner usage data of the target control area further includes: performing density cluster analysis on the historical air conditioner usage data based on a preset density threshold and a minimum cluster threshold to obtain core point data, boundary point data and noise point data; The performing K cluster analysis on the historical air conditioner usage data to obtain a preset number of the control area clusters and a central control area in each control area cluster includes: performing K cluster analysis on the core point data and the boundary point data to obtain a preset number of the control area clusters and a central control area in each control area cluster; Among them, after performing density clustering analysis on the air-conditioning historical usage data based on the preset density threshold and the minimum cluster threshold to obtain core point data, boundary point data and noise point data, the method also includes: determining an independent air-conditioning control strategy corresponding to each of the noise point data; and independently controlling the air-conditioning in the target control area corresponding to the corresponding noise point data based on the independent air-conditioning control strategy.

3. The method according to claim 2, characterized in that in, The method for determining the preset number includes: Determining an initial quantity range of the preset quantity; wherein the initial quantity range includes a plurality of initial quantities; Calculating a clustering parameter corresponding to each of the initial quantities; wherein the clustering parameter includes at least one of a silhouette coefficient, a covariance coefficient, a square error coefficient, and an intermittent statistic; The preset number within the initial number range is determined according to the clustering parameter.

4. An air conditioning control device, characterized in that: The device comprises: A cluster analysis module, configured to perform cluster analysis on the historical air-conditioning usage data of the target control area to obtain a clustering result; wherein the historical air-conditioning usage data includes: the ambient temperature data, ambient humidity data, at least one of the control area temperature data and the control area humidity data of the target control area within the target historical time period, the air-conditioning control data, and the air-conditioning power consumption data; the clustering result includes a plurality of control area clusters, each of which includes a plurality of the target control areas; A control strategy determination module, used to determine the air conditioning control strategy corresponding to each of the control area clusters; An air conditioning control module, used to uniformly control the air conditioners in the corresponding control area cluster according to the air conditioning control strategy; The cluster analysis module is further used to: pre-process the historical air-conditioning usage data to obtain pre-processed data within a unit time; wherein the pre-processed data includes: at least one of the daily average temperature of the environment, the daily average humidity of the environment, the daily average temperature of the control area and the daily average humidity of the control area, the daily average electricity consumption data per unit area and the daily average control data; perform principal component analysis on the pre-processed data to obtain principal component data in the pre-processed data; perform cluster analysis on the principal component data to obtain the clustering result; The control strategy determination module is specifically used to: determine the central control area within each of the control area clusters and the central air conditioning control strategy corresponding to the central control area; determine the central air conditioning control strategy as the air conditioning control strategy corresponding to the control area cluster; Among them, the determination of the central control area within each of the control area clusters and the central air-conditioning control strategy corresponding to the central control area includes: determining the central control area according to the similarity between the air-conditioning historical usage data of any two target control areas within each of the control area clusters; the specific implementation method is: determining the sum of the similarities between the air-conditioning historical usage data of the designated target control area within each of the control area clusters and any other target control areas; determining the designated target control area with the largest sum of similarities as the central control area within the control area cluster; and determining the air-conditioning control strategy corresponding to the central control area as the air-conditioning control strategy corresponding to the control area cluster.

5. An electronic device, characterized in that: The electronic device comprises: Memory; processor; The memory stores a computer program executable by the processor, and when the computer program is executed by the processor, the method according to any one of claims 1 to 3 is performed.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 3 is executed.

Citation Information

Patent Citations

  • Variable refrigerant flow system with zone grouping

    CN114096786A

  • Constant-temperature intelligent analysis method for heating equipment based on multi-modal perception

    CN114971426A

  • Air conditioner load cluster participation demand response income distribution method based on interactive adjustment

    CN117628663A

  • Method and apparatus for human detection in images

    US20180157904A1

  • Variable refrigerant flow system with zone grouping

    US20220042705A1