Control method, program product, equipment and system based on multiple air conditioners

Abstract

The embodiment of the invention discloses a control method based on multiple air conditioners, a program product, equipment and a system. The method comprises the steps that target air conditioner parameters related to the temperature of a target space are obtained; an air conditioner control model indicating the relation between air conditioner control parameters and target space temperatures is obtained, the air conditioner control parameters comprise the target air conditioner parameters of the multiple air conditioner devices, and the target space temperatures comprise the temperatures of the multiple temperature measurement and control points in the target space; based on the air conditioner control model, determining an optimal air conditioner control parameter combination and an optimal temperature value of each temperature measurement and control point; correlation grouped data between all the temperature measurement and control points and the target air conditioner parameters of the multiple pieces of air conditioner equipment are obtained; and based on the optimal air conditioner control parameter combination, the optimal temperature value of each temperature measurement and control point and the correlation grouped data, the multiple air conditioner devices are controlled.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning, and in particular to a control method based on multiple air conditioners, a computer program product, a control device based on multiple air conditioners, and an air conditioning system. Background Art

[0002] The indoor environment is a coupled field of temperature field and wind field. The two fields are highly coupled and synergistically affect the indoor temperature. To analyze the indoor temperature, the coupled field must be decoupled first, so as to study the influence of temperature field and wind field on temperature separately.

[0003] In the process of realizing the invention, the inventors found that there are at least the following technical problems in the prior art: in actual situations, it is very complicated to physically model the indoor ambient temperature and the air conditioning system, and it is very difficult to decouple. Even if a physical model is established, its robustness is very poor, and the anti-interference ability and effect of the physical model under different working conditions are also very different. Moreover, in a large space, there are multiple air conditioning equipments, and each temperature measurement and control point may only be related to one or more air conditioning equipments. If all air conditioning equipments are adjusted, it will not only cause uneven indoor temperature, but also increase energy consumption. Summary of the invention

[0004] In order to improve the existing technical problems, the embodiments of the present invention provide a control method based on multiple air conditioners, a computer program product, a control device based on multiple air conditioners and an air-conditioning system, which can save energy for the air-conditioning system as a whole, realize precise temperature control, and also realize a closed-loop control effect, thereby improving the stability and accuracy of the entire air-conditioning system.

[0005] The technical solution of the embodiment of the present invention is achieved as follows:

[0006] In a first aspect, a control method based on multiple air conditioners is provided, comprising: obtaining a target air-conditioning parameter correlated with the temperature of a target space; obtaining an air-conditioning control model indicating the relationship between the air-conditioning control parameter and the target space temperature, wherein the air-conditioning control parameter includes the target air-conditioning parameters of multiple air-conditioning devices, and the target space temperature includes the temperature of multiple temperature measurement and control points in the target space; based on the air-conditioning control model, determining an optimal air-conditioning control parameter combination and an optimal temperature value of each temperature measurement and control point; obtaining correlation grouping data between each temperature measurement and control point and the target air-conditioning parameters of multiple air-conditioning devices; and controlling the multiple air-conditioning devices based on the optimal air-conditioning control parameter combination, the optimal temperature value of each temperature measurement and control point, and the correlation grouping data.

[0007] In a second aspect, a computer program product is provided, including a computer program, wherein the computer program is executed by a processor to implement the control method based on multiple air conditioners provided in any embodiment of the present application.

[0008] In a third aspect, a control device based on multiple air conditioners is provided, comprising a memory for storing a computer program; and a processor for executing the computer program to implement a control method based on multiple air conditioners provided in any embodiment of the present application.

[0009] In a fourth aspect, an air-conditioning system is provided, comprising a multi-air-conditioning based control device provided in any embodiment of the present application, and at least one air-conditioning device communicatively connected to the control device.

[0010] The control method based on multiple air conditioners, computer program product, control device based on multiple air conditioners and air conditioning system provided by the embodiments of the present application have at least the following beneficial effects:

[0011] The embodiment of the present application obtains target air-conditioning parameters that can affect the temperature of the target space, and establishes an air-conditioning control model of the temperature relationship between the target air-conditioning parameters and multiple temperature measurement and control points in the target space temperature, so that the temperatures of the corresponding multiple temperature measurement and control points can be predicted based on the values ​​of the target air-conditioning parameters of the multiple air-conditioning devices obtained; then, based on the air-conditioning control model, the optimal air-conditioning control parameter combination and the optimal temperature value of each temperature measurement and control point are found, wherein the optimal air-conditioning control parameter combination can make the temperature of each temperature measurement and control point reach the optimal value, and the correlation grouping data between each temperature measurement and control point and the target air-conditioning parameters of the multiple air-conditioning devices are obtained, and the target air-conditioning parameters of the air-conditioning devices most associated with each temperature measurement and control point can be determined through the correlation grouping data, and then the parameter values ​​of the target air-conditioning parameters of the air-conditioning devices most associated with each temperature measurement and control point can be obtained according to the optimal air-conditioning control parameter combination. Based on the parameter values ​​of the target air-conditioning parameters of the air-conditioning devices most associated with each temperature measurement and control point, the air-conditioning devices most associated with each temperature measurement and control point are controlled, so that the air-conditioning system as a whole can be saved, and the temperature of the temperature measurement and control point can be accurately controlled, and a closed-loop control effect can also be achieved, thereby improving the stability and accuracy of the entire air-conditioning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram of an optional application scenario of a control method based on multiple air conditioners in an embodiment;

[0013] Figure 2 is a schematic diagram of an air conditioning system in a target space in an embodiment;

[0014] Figure 3 is a flow chart of a control method based on multiple air conditioners in one embodiment;

[0015] Figure 4 is a schematic diagram of predicting the temperature of a target space based on target air-conditioning parameters in one embodiment;

[0016] Figure 5 1. is a schematic diagram of a flow chart of calculating an optimal air conditioning control parameter combination and an optimal temperature value in a control method based on multiple air conditioners in one embodiment;

[0017] Figure 6 is a schematic diagram of a control device based on multiple air conditioners in one embodiment;

[0018] Figure 7 Schematic diagram of the structure of a control device in one embodiment. DETAILED DESCRIPTION

[0019] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art of the technical field of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the scope of protection of the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0021] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it should be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0022] See also Figure 1 , is a schematic diagram of an optional application scenario of the control method based on multiple air conditioners provided in an embodiment of the present application, and the application scenario diagram includes a control device 100 based on multiple air conditioners (hereinafter referred to as the control device 100) and multiple air conditioners 200. Multiple air conditioners 200 are installed at a position in the environment of the target space. The control device 100 is used to execute the control method based on multiple air conditioners provided in an embodiment of the present application, and control the operation of each air conditioner 200.

[0023] like Figure 2 As shown, Figure 2 Schematic diagram of the air conditioning system in the target space in one embodiment, air conditioning equipment 200 includes air conditioning 01, air conditioning 02, ..., air conditioning k, air conditioning k+1, air conditioning k+2, ..., air conditioning n, each air conditioning equipment corresponds to a cold channel temperature setting value, for example, the cold channel temperature corresponding to air conditioning 01 is T01, the cold channel temperature corresponding to air conditioning 02 is T02, and the cold channel temperature corresponding to air conditioning n is Tn. A plurality of temperature measurement and control points are set in the target space to monitor the temperature of the target space. When the target space is relatively large, for a temperature measurement and control point, it may only be related to the air conditioning parameters of one or more air conditioning equipment associated with it.

[0024] See also Figure 3 , which is a control method based on multiple air conditioners provided in an embodiment of the present application, can be applied to Figure 1 The control device 100 shown includes the following steps:

[0025] S11. Obtain target air-conditioning parameters that are correlated with the temperature of the target space.

[0026] In this embodiment, there are many air conditioning parameters for controlling the air conditioner, such as but not limited to: fan speed, water valve opening, compressor frequency, cooling capacity, circulating air volume, noise level, etc. However, among these air conditioning parameters, not every air conditioning parameter will greatly affect the temperature of the target space, so it is necessary to screen out the target air conditioning parameters from multiple space parameters. Among them, the target air conditioning parameters indicate the air conditioning parameters that are correlated with the temperature of the target space. The target air conditioning parameters include but are not limited to: fan speed, water valve opening, compressor frequency, etc.

[0027] After determining the target air conditioning parameters, the temperature of the target space can be predicted based on the target air conditioning parameters. A regression model of the target air conditioning parameters and the target space temperature can be established based on historical data to predict the target space temperature. For example, a regression model of two target air conditioning parameters and the target space temperature can be established, such as Figure 4 As shown, Figure 4 FIG. 1 is a schematic diagram of predicting the temperature of a target space based on target air-conditioning parameters in an embodiment. Figure 4 It can be seen that the two target air conditioning parameters, as the input of the key influencing factors, have little difference between the prediction of the target space temperature and the actual target space temperature, that is, there is an obvious correlation between the two target air conditioning parameters and the target space temperature, such as Figure 4 The red line in the figure is the contour line of the predicted target space temperature and the actual target space temperature.

[0028] S12: Obtain an air conditioning control model indicating the relationship between the air conditioning control parameters and the target space temperature.

[0029] In this embodiment, the air conditioning control parameters include the target air conditioning parameters of multiple air conditioning devices, and the target space temperature includes the temperatures of multiple temperature measurement and control points in the target space. The air conditioning control model can be used to predict the temperatures of multiple temperature measurement and control points based on the target air conditioning parameters of multiple air conditioning devices. The air conditioning control model can be a model pre-trained based on historical data, that is, the parameters in the air conditioning control model have been solidified. As long as a group of target air conditioning parameter values ​​of multiple air conditioning devices are input, the temperatures of multiple temperature measurement and control points corresponding to the group of target air conditioning parameter values ​​can be predicted by the air conditioning control model.

[0030] S13. Based on the air conditioning control model, determine the optimal air conditioning control parameter combination and the optimal temperature value of each temperature measurement and control point.

[0031] In this embodiment, the independent variables in the air conditioning control model include the target air conditioning parameters of multiple air conditioning devices, and the dependent variables in the air conditioning control model include the temperatures of multiple temperature measurement and control points. Therefore, an optimization objective function can be established based on the air conditioning control model, and then a set of optimal air conditioning control parameter combinations that optimize the optimization objective function can be found using a parameter optimization method. Based on the optimal air conditioning control parameter combination, the input data of the air conditioning control model is formed, and the air conditioning control model can output the optimal temperature values ​​of each temperature measurement and control point corresponding to the optimal air conditioning control parameter combination.

[0032] The parameter optimization method includes but is not limited to particle swarm optimization, genetic algorithm, and ant colony algorithm. The parameter optimization method can be used to obtain a set of optimal air conditioning control parameter combinations that converge the optimization objective function. The optimal air conditioning control parameter combination includes multiple optimal target air conditioning parameters of multiple air conditioning equipment.

[0033] S14, obtaining correlation grouping data between each temperature measurement and control point and the target air-conditioning parameters of the plurality of air-conditioning equipment.

[0034] In this embodiment, there are multiple air-conditioning devices in the target space, and the temperature measurement and control points are distributed in different positions. When the target space is large, the measured value that affects one temperature measurement and control point may be only one or more target air-conditioning parameters of one or more air-conditioning devices. Therefore, the correlation between each temperature measurement and control point and each target air-conditioning parameter of each air-conditioning device can be analyzed based on the historical collection data of the target space, so as to obtain correlation grouping data. For one temperature measurement and control point, the target air-conditioning parameters of the associated air-conditioning device are grouped into one group. For one target air-conditioning parameter of an air-conditioning device, the associated temperature measurement and control points can also be grouped into one group. Therefore, according to the correlation values ​​between each temperature measurement and control point and the target air-conditioning parameters of the multiple air-conditioning devices, multiple groups can be obtained. That is, the correlation grouping data can include multiple groups.

[0035] S15. Control the plurality of air-conditioning devices based on the optimal air-conditioning control parameter combination, the optimal temperature value of each temperature measurement and control point, and the correlation grouping data.

[0036] In this embodiment, since the correlation grouping data indicates the target air-conditioning parameters of the air-conditioning equipment associated with each temperature measurement and control point, for a temperature measurement and control point, the target air-conditioning parameters of a strongly associated air-conditioning equipment can be obtained from the correlation grouping data corresponding to the temperature measurement and control point, and then the parameter values ​​of the strongly associated target air-conditioning parameters can be obtained from the optimal air-conditioning control parameter combination. Based on the optimal temperature value corresponding to the temperature measurement and control point and the parameter values ​​of the strongly associated target air-conditioning parameters, the air-conditioning equipment corresponding to the strongly associated target air-conditioning parameters is controlled to accurately control the temperature of the temperature measurement and control point, thereby achieving a closed-loop control effect, thereby improving the stability and accuracy of the entire air-conditioning system.

[0037] In the above embodiment, target air-conditioning parameters that can affect the temperature of the target space are obtained, and an air-conditioning control model of the temperature relationship between the target air-conditioning parameters and the temperature of multiple temperature measurement and control points in the target space temperature is established, so that the temperatures of the corresponding multiple temperature measurement and control points can be predicted based on the values ​​of the target air-conditioning parameters of the multiple air-conditioning devices obtained; then, based on the air-conditioning control model, the optimal air-conditioning control parameter combination and the optimal temperature value of each temperature measurement and control point are found, wherein the optimal air-conditioning control parameter combination can make the temperature of each temperature measurement and control point reach the optimal value, and the correlation grouping data between each temperature measurement and control point and the target air-conditioning parameters of the multiple air-conditioning devices are obtained, and the target air-conditioning parameters of the air-conditioning devices most associated with each temperature measurement and control point can be determined through the correlation grouping data, and then the parameter values ​​of the target air-conditioning parameters of the air-conditioning devices most associated with each temperature measurement and control point can be obtained according to the optimal air-conditioning control parameter combination. Based on the parameter values ​​of the target air-conditioning parameters of the air-conditioning devices most associated with each temperature measurement and control point, the air-conditioning devices most associated with each temperature measurement and control point are controlled, so that the air-conditioning system can be saved as a whole, the temperature of the temperature measurement and control point can be accurately controlled, and a closed-loop control effect can be achieved, thereby improving the stability and accuracy of the entire air-conditioning system.

[0038] In some embodiments, obtaining a target air-conditioning parameter correlated with the target space temperature includes:

[0039] Acquire a first historical data set, the first historical data set comprising a plurality of groups of first data samples, each group of first data samples comprising air-conditioning parameters of a plurality of space equipment in the target space and temperatures of a plurality of corresponding temperature measurement and control points;

[0040] Based on the first historical data set, calculating a first correlation value between each temperature measurement and control point and an air-conditioning parameter of each air-conditioning device;

[0041] The target air-conditioning parameter is determined from the air-conditioning parameters based on the first correlation value.

[0042] In this embodiment, when the air-conditioning system in the target space is operating normally, multiple groups of first data samples are collected, and for a temperature measurement and control point, the correlation value with each air-conditioning parameter of each air-conditioning device is calculated respectively, and the calculation of the above correlation value is performed for each temperature measurement and control point respectively. Based on the correlation value, the air-conditioning parameter corresponding to the value whose correlation value is higher than the preset correlation value or whose correlation value is within the preset correlation interval is taken as the target air-conditioning parameter. Therefore, by calculating the first correlation value between each temperature measurement and control point and the air-conditioning parameter of each air-conditioning device, the target air-conditioning parameter with a greater correlation with the temperature of the target space can be screened out according to the correlation value, and the temperature of the target space can be adjusted by controlling the air-conditioning parameter with a greater correlation later.

[0043] In the above embodiment, a historical data set of the target space air-conditioning system is obtained, and a first correlation value between each temperature measurement and control point and the air-conditioning parameters of each air-conditioning device is calculated based on the historical data set. The target air-conditioning parameters that have a greater correlation with the temperature of the target space are screened out based on the correlation value. This facilitates precise control of the temperature of the target space based on the target air-conditioning parameters, which can save energy on the air-conditioning system as a whole, achieve precise control of the temperature of the temperature measurement and control point, and achieve a closed-loop control effect, thereby improving the stability and accuracy of the entire air-conditioning system.

[0044] In some embodiments, the air conditioning control model is a pre-trained air conditioning control model, and obtaining the air conditioning control model indicating the relationship between the air conditioning control parameter and the target space temperature includes:

[0045] Acquire a training sample data set, wherein each training sample in the training sample data set includes target air conditioning parameter values ​​of multiple air conditioning devices, each training sample corresponds to a training label, and the training label is the temperature values ​​of multiple temperature measurement and control points corresponding to the target air conditioning parameter values ​​of the multiple air conditioning devices;

[0046] Build an initial air conditioning control model;

[0047] Acquire training samples from the training sample data set to form sample input data of the air-conditioning control model in the current training iteration, and output the temperature values ​​of multiple temperature measurement and control points in the current training iteration through the air-conditioning control model in the current training iteration; calculate the loss value in the current training iteration based on the temperature values ​​of the multiple temperature measurement and control points in the current training iteration and the training labels corresponding to the training samples, and judge whether the current training iteration meets the training iteration termination condition based on the loss value in the current training iteration; if the current training iteration does not meet the training iteration termination condition, return to continue training, and if the current training iteration meets the training iteration termination condition, use the air-conditioning control model after stopping the iteration as the pre-trained air-conditioning control model.

[0048] In this embodiment, when the air conditioning system in the target space is in historical operation, training samples are collected, and the training sample data set is also obtained based on the historical operation data of the target space. The training sample data set includes training sample data under various working conditions. In this way, when the air conditioning control model is trained based on the deep learning method, the air conditioning control model can learn the mapping relationship characteristics between the air conditioning control parameters and the target space temperature under different working conditions during the training process. After the training is completed, the pre-trained air conditioning control model can accurately predict the target space temperature, thereby avoiding the problem of inaccuracy in the indoor temperature estimation of the physical model in the prior art under different working conditions and incomplete parameters. The iteration termination conditions include but are not limited to the loss value in the current training iteration being less than the preset error value, and the number of iterations exceeding the preset number. When calculating the loss value in the current training iteration, based on the loss function, the loss value between the temperature values ​​of multiple temperature measurement and control points in the current training iteration and the training labels corresponding to the training samples is calculated, wherein the loss function is not limited to the variance function and the cross entropy loss function.

[0049] In the above embodiment, training samples under different working conditions are obtained to form a training sample data set. During the training process, the air-conditioning control model learns the characteristics of the training samples under different working conditions. After the training is completed, the air-conditioning control model can accurately predict the target space temperature, which can improve the robustness of the model, thereby improving the stability and accuracy of the control of the entire air-conditioning system.

[0050] Figure 5 This is a flow chart of calculating the optimal air conditioning control parameter combination and the optimal temperature value in a control method based on multiple air conditioners in one embodiment, wherein step S13 specifically includes:

[0051] S131, constructing an optimization objective function for optimizing air-conditioning control parameters.

[0052] In this embodiment, the optimization objective function is used to find the optimal air conditioning control parameter combination, and the optimization objective function is based on minimizing the temperature non-uniformity coefficient and the total power of the air conditioner. The minimization of the temperature non-uniformity coefficient is used to measure whether the temperature of multiple temperature measurement and control points in the target space is uniform. The smaller the minimized temperature non-uniformity coefficient is, the more uniform the temperature of the multiple temperature measurement and control points is. The total power of the air conditioner is used to measure the energy consumption of the air conditioning system. The lower the total power of the air conditioner, the lower the energy consumption, and the higher the total power of the air conditioner, the higher the energy consumption. Therefore, by seeking the optimal air conditioning control parameter combination of the optimization objective function, the temperature of each temperature measurement and control point of the air conditioning system can be made more uniform, and energy consumption can also be reduced.

[0053] In an optional embodiment, the optimization objective function is:

[0054] min:ω1K t +ω2P ac_total

[0055]

[0056] Where ω1 is the temperature non-uniformity coefficient K t The weight of the total target, ω2 is the total power of the air conditioner P ac_total The weight of the total target, T min is the minimum indoor temperature limit, T s is the set temperature that the target space is expected to reach, where

[0057]

[0058] T ave is the average value of multiple temperature measurement and control points, T i is the temperature of the i-th temperature measurement and control point, and n is the total number of temperature measurement and control points in the target space.

[0059] S132, using an iterative calculation method to calculate the current air conditioning control parameter combination of the current iteration, forming input data of the air conditioning control model based on the current air conditioning control parameter combination, and outputting the temperatures of multiple temperature measurement and control points corresponding to the current air conditioning control parameter combination through the air conditioning control model.

[0060] In this embodiment, the target air conditioning parameters of multiple air conditioning devices can be initialized first to obtain an initial air conditioning control parameter combination, and based on the initial air conditioning control parameter combination, the current air conditioning control parameter combination of the current iteration is iteratively calculated using an iterative calculation method. This includes but is not limited to particle swarm optimization, genetic algorithm, and ant colony algorithm. Since the air conditioning control model is a pre-trained model, in each iteration, the input data of the air conditioning control model is formed based on the updated air conditioning control parameter combination, and the temperature of multiple temperature measurement and control points corresponding to the current air conditioning control parameter combination can be predicted and output.

[0061] S133: Calculate the total air-conditioning power corresponding to the current air-conditioning control parameter combination.

[0062] In this embodiment, the current air-conditioning control parameter combination in each iteration process includes target air-conditioning parameters of multiple air-conditioning devices, which, combined with other air-conditioning parameters, can calculate the total air-conditioning power of the air-conditioning system in the target space.

[0063] S134. Calculate the current objective function value based on the optimization objective function, the temperatures of multiple temperature measurement and control points corresponding to the current air conditioning control parameter combination and the current total air conditioning power.

[0064] In this embodiment, the step S134 specifically includes:

[0065] Calculate the current minimized temperature non-uniformity coefficient based on the temperatures of multiple temperature measurement and control points corresponding to the current air conditioning control parameter combination;

[0066] Based on the optimization objective function, the current minimized temperature non-uniformity coefficient and the current total air-conditioning power, a current objective function value is calculated.

[0067] By using the above specific formula for optimizing the objective function, the current objective function value in the current iteration process can be calculated.

[0068] S135. Based on the current objective function value, determine whether the current iteration satisfies the iteration termination condition. If the current iteration does not satisfy the iteration termination condition, return to continue the iterative calculation. If the current iteration satisfies the iteration termination condition, use the air conditioning control parameter combination after stopping the iteration as the optimal air conditioning control parameter combination.

[0069] S136, forming input data of the air-conditioning control model based on the optimal air-conditioning control parameter combination, and outputting the optimal temperature value of each temperature measurement and control point through the air-conditioning control model.

[0070] In the above embodiment, an optimization objective function based on minimizing the temperature non-uniformity coefficient and the total air-conditioning power is constructed, and the optimal air-conditioning control parameter combination is found by optimizing the objective function. When the optimization objective function converges, the optimal air-conditioning control parameter combination can be obtained. The optimal air-conditioning control parameter combination can make the temperatures of multiple temperature measurement and control points more uniform, and can make the overall energy consumption of the target space relatively low, thereby improving the control stability and accuracy of the entire air-conditioning system.

[0071] In some embodiments, the obtaining of correlation grouping data between each temperature measurement and control point and the target air-conditioning parameters of the plurality of air-conditioning devices comprises:

[0072] Acquire a second historical data set, the second historical data set comprising a plurality of groups of second data samples, each group of second data samples comprising target air-conditioning parameters of a plurality of space equipment in the target space and temperatures of a plurality of corresponding temperature measurement and control points;

[0073] Based on the second historical data set, calculating the correlation value between each temperature measurement and control point and the target air-conditioning parameter of each air-conditioning equipment;

[0074] Based on the relevance value, the relevance grouping data is determined.

[0075] In an optional implementation, the calculating, based on the second historical data set, the correlation value between each temperature measurement and control point and the target air-conditioning parameter of each air-conditioning device includes:

[0076] Based on the second historical data set, the correlation value between each temperature measurement and control point and the target air-conditioning parameter of each air-conditioning device is calculated using a correlation calculation formula, wherein the correlation calculation formula is as follows:

[0077]

[0078] where ρ ij is the temperature T of the i-th temperature measurement and control point i and the target air conditioning parameter F of the jth air conditioner j The correlation, cov(F j ,T i ) is T i With F j The covariance between j is the standard deviation of the target parameter of the jth air conditioner, σ i is the variance of the temperature of the i-th temperature measurement and control point.

[0079] In this embodiment, the second historical data set and the first historical data set can be the same data set or different data sets. When the air-conditioning system in the target space is operating normally, multiple sets of second historical data sets are collected. For a temperature measurement and control point, the correlation value between the target space parameters of each air-conditioning device is calculated. If there is a target space parameter whose correlation value meets the preset correlation condition, it means that the temperature measurement and control point is correlated with the target space parameter that meets the preset correlation condition. The larger the correlation value, the greater the correlation with the temperature measurement and control point. If there is no target space parameter whose correlation value meets the preset correlation condition, it means that the temperature measurement and control point is not highly correlated with the target space parameters of each air-conditioning device.

[0080] In this way, by calculating the correlation value between each temperature measurement and control point and the target air-conditioning parameter of each air-conditioning device, and analyzing these correlation values ​​through a thermal map, a temperature measurement and control point and its corresponding target space parameter that meets the preset correlation condition can be grouped together, thereby obtaining correlation grouping data, so that each temperature measurement and control point can be matched with the target air-conditioning parameter of the associated air-conditioning device, which is convenient for subsequent precise control of the corresponding temperature measurement and control point. For example, for a temperature measurement and control point A, the correlation grouping data of the temperature measurement and control point A that can be obtained includes the correlation value between the temperature measurement and control point A and the fan speed of the air-conditioning device B1, the correlation value between the temperature measurement and control point A and the fan speed of the air-conditioning device B3, and the correlation value between the temperature measurement and control point A and the water valve opening of the air-conditioning device B4. That is, the temperature measurement and control point A is related to the fan speed of the air-conditioning device B1, the fan speed of the air-conditioning device B3, and the water valve opening of the air-conditioning device B4. If the correlation value between the fan speed of the temperature measurement and control point A and the air-conditioning device B1 is the largest, it means that the temperature measurement and control point A is most strongly correlated with the fan speed of the air-conditioning device B1.

[0081] In the above embodiment, by analyzing the correlation values ​​between each temperature measurement and control point and the target air-conditioning parameters of each air-conditioning equipment through historical data sets, a temperature measurement and control point and its corresponding target space parameters that meet the preset correlation conditions can be grouped together to obtain correlation grouping data. In this way, each temperature measurement and control point can be matched with the target air-conditioning parameters of the associated air-conditioning equipment, which facilitates the subsequent precise control of the corresponding temperature measurement and control points, thereby improving the stability and accuracy of the control of the entire air-conditioning system.

[0082] In some embodiments, the correlation grouping data includes multiple groups of data, each group of data includes a correlation value of at least one target air-conditioning parameter of an air-conditioning device associated with a temperature measurement and control point, and / or each group of data includes a correlation value of a target air-conditioning parameter of an air-conditioning device and multiple temperature measurement and control points.

[0083] In this embodiment, for the i-th temperature measurement and control point, the correlation set D of the i-th temperature measurement and control point to the n air conditioners is obtained. i ={ρ i1 ,ρ i2 ,ρ i3 ,...ρ in}, from D i The air conditioner corresponding to the maximum correlation value is selected as the air conditioner with the highest correlation with the i-th temperature measurement and control point, and the temperature control of the current temperature measurement and control point i is the responsibility of the j-th air conditioner. Furthermore, based on each air conditioner group, for the j-th air conditioner, all temperature measurement and control points with the strongest correlation with the j-th air conditioner are selected to obtain the set A j ={ρ 1j ,ρ 2j ,ρ 3j ,...ρ kj}, where k represents the number of all temperature measurement and control points that are most relevant to the jth air conditioner.

[0084] In the above embodiment, by analyzing the correlation value between each temperature measurement and control point and the target air-conditioning parameter of each air-conditioning equipment, a temperature measurement and control point and its corresponding target space parameter that meets the preset correlation condition can be grouped together to obtain correlation grouping data. In this way, each temperature measurement and control point can be matched with the target air-conditioning parameter of the associated air-conditioning equipment, which facilitates the subsequent precise control of the corresponding temperature measurement and control point, thereby improving the stability and accuracy of the control of the entire air-conditioning system.

[0085] In some embodiments, the controlling of the plurality of air conditioning devices based on the optimal air conditioning control parameter combination, the optimal temperature value of each temperature measurement and control point, and the correlation grouping data includes:

[0086] For any temperature measurement and control point, obtaining the target air-conditioning parameter with the strongest correlation with the any temperature measurement and control point from the correlation grouped data;

[0087] From the optimal temperature values ​​of each temperature measurement and control point, the optimal temperature value corresponding to any temperature measurement and control point is obtained, and the optimal temperature value corresponding to any temperature measurement and control point is used as the cold channel temperature setting value of the air-conditioning equipment corresponding to the target air-conditioning parameter with the strongest correlation with any temperature measurement and control point;

[0088] From the optimal air-conditioning control parameter combination, the parameter value of the target air-conditioning parameter that is most closely associated with any of the temperature measurement and control points is obtained, and based on the obtained parameter value, the air-conditioning equipment corresponding to the target air-conditioning parameter that is most closely associated with any of the temperature measurement and control points is controlled.

[0089] In this embodiment, for example, taking the target air conditioning parameter as the fan speed as an example, the fan speeds of the multiple air conditioners in the optimal air conditioning control parameter combination are F0={F 10 , F 20 , ..., F n0}, the optimal temperature is T0={T 10 , T 20 , ..., T m0}, where m is the number of temperature measurement points and n is the number of air conditioning equipment. m} to represent the actual observed temperature of m temperature control points. For example, for A2 corresponding to the second air conditioner, the maximum correlation value is selected from A2. The temperature control point corresponding to the maximum value is the seventh temperature control point T7. Then find F from F0. 20 , according to F 20 Control the fan speed of the second air conditioner and find the optimal temperature value T of the seventh temperature measurement and control point from T0 70 , T 70 As the cold channel temperature setting value of the second air conditioner. In this way, by controlling the fan speed of the second air conditioner, the seventh temperature measurement and control point can be accurately controlled. It can be understood that for an i-th temperature measurement and control point, the corresponding D i Set, find the target air-conditioning parameters of the air-conditioning equipment that is strongly associated with the i-th temperature measurement and control point. For example, by analyzing the D7 set corresponding to the 7th temperature measurement and control point, the fan speed of the second air conditioner can also be found.

[0090] In an optional implementation, controlling the air-conditioning equipment corresponding to the target air-conditioning parameter having the strongest correlation with any temperature measurement and control point according to the acquired parameter value includes:

[0091] Determine the acquired parameter value as the limit value of the target air-conditioning parameter of the air-conditioning equipment that is most closely associated with any of the temperature measurement and control points; and / or

[0092] The limit adjustment amount of the target air-conditioning parameter of the air-conditioning equipment that is most closely associated with any of the temperature measurement and control points shall not exceed a preset adjustment ratio.

[0093] In this embodiment, considering safety and system stability, for example, a preset adjustment ratio (such as 5%) is set for the fan, that is, the adjustment amount of the lower limit speed of the fan shall not exceed 5%.

[0094] In the above embodiment, the target air-conditioning parameters of the air-conditioning equipment most associated with each temperature measurement and control point can be determined by correlation grouping data, and then the parameter values ​​of the target air-conditioning parameters of the air-conditioning equipment most associated with each temperature measurement and control point can be obtained according to the optimal air-conditioning control parameter combination. Based on the parameter values ​​of the target air-conditioning parameters of the air-conditioning equipment most associated with each temperature measurement and control point, the air-conditioning equipment most associated with each temperature measurement and control point is controlled, which can save energy on the air-conditioning system as a whole, achieve precise control of the temperature of the temperature measurement and control point, and achieve a closed-loop control effect, thereby improving the stability and accuracy of the entire air-conditioning system.

[0095] In some embodiments, the method further comprises:

[0096] Determining whether the air conditioning system in the target air conditioner is stable;

[0097] If the air-conditioning system in the target air-conditioner is unstable, the control method based on multiple air-conditioners provided in the embodiment of the present application is executed.

[0098] In this embodiment, it can be determined whether the state parameters of the air conditioning system meet the preset state conditions. If the state parameters of the air conditioning system meet the preset state conditions, it means that the air conditioning system tends to be stable. The preset state conditions include but are not limited to the temperature difference of each temperature measurement and control point being less than the preset temperature value, the total power of the air conditioning system being lower than the preset power value, etc.

[0099] On the other hand, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the control method based on multiple air conditioners described in any embodiment of the present application.

[0100] Among them, in the computer program product, the optional implementation form of the program module architecture of the computer program that implements each step of the method can be a control device based on multiple air conditioners. Figure 6On the other hand, the embodiment of the present application provides a control device based on multiple air conditioners, including: a control method based on multiple air conditioners, characterized in that it includes: an acquisition module 61, used to acquire a target air-conditioning parameter that is correlated with the temperature of a target space; the acquisition module 61 is also used to acquire an air-conditioning control model indicating the relationship between the air-conditioning control parameter and the target space temperature, wherein the air-conditioning control parameter includes the target air-conditioning parameters of multiple air-conditioning devices, and the target space temperature includes the temperatures of multiple temperature measurement and control points in the target space; a determination module 62 is used to determine an optimal air-conditioning control parameter combination and an optimal temperature value of each temperature measurement and control point based on the air-conditioning control model; the determination module 62 is also used to acquire correlation grouping data between each temperature measurement and control point and the target air-conditioning parameters of multiple air-conditioning devices; a control module 63 is used to control the multiple air-conditioning devices based on the optimal air-conditioning control parameter combination, the optimal temperature value of each temperature measurement and control point and the correlation grouping data.

[0101] Optionally, the acquisition module 61 is further used for:

[0102] Acquire a first historical data set, the first historical data set comprising a plurality of groups of first data samples, each group of first data samples comprising air-conditioning parameters of a plurality of space equipment in the target space and temperatures of a plurality of corresponding temperature measurement and control points;

[0103] Based on the first historical data set, calculating a first correlation value between each temperature measurement and control point and an air-conditioning parameter of each air-conditioning device;

[0104] The target air-conditioning parameter is determined from the air-conditioning parameters based on the first correlation value.

[0105] Optionally, the acquisition module 61 is further used for:

[0106] Acquire a training sample data set, wherein each training sample in the training sample data set includes target air conditioning parameter values ​​of multiple air conditioning devices, each training sample corresponds to a training label, and the training label is the temperature values ​​of multiple temperature measurement and control points corresponding to the target air conditioning parameter values ​​of the multiple air conditioning devices;

[0107] Build an initial air conditioning control model;

[0108] Acquire training samples from the training sample data set to form sample input data of the air-conditioning control model in the current training iteration, and output the temperature values ​​of multiple temperature measurement and control points in the current training iteration through the air-conditioning control model in the current training iteration; calculate the loss value in the current training iteration based on the temperature values ​​of the multiple temperature measurement and control points in the current training iteration and the training labels corresponding to the training samples, and judge whether the current training iteration meets the training iteration termination condition based on the loss value in the current training iteration; if the current training iteration does not meet the training iteration termination condition, return to continue training, and if the current training iteration meets the training iteration termination condition, use the air-conditioning control model after stopping the iteration as the pre-trained air-conditioning control model.

[0109] Optionally, the determination module 62 is further configured to:

[0110] Constructing an optimization objective function for optimizing air conditioning control parameters;

[0111] Calculate the current air conditioning control parameter combination of the current iteration by using an iterative calculation method, form input data of the air conditioning control model based on the current air conditioning control parameter combination, and output the temperatures of multiple temperature measurement and control points corresponding to the current air conditioning control parameter combination through the air conditioning control model;

[0112] Calculate the total air conditioning power corresponding to the current air conditioning control parameter combination;

[0113] Calculate the current objective function value based on the optimization objective function, the temperatures of multiple temperature measurement and control points corresponding to the current air conditioning control parameter combination and the current air conditioning total power;

[0114] Based on the current objective function value, determine whether the current iteration meets the iteration termination condition, if the current iteration does not meet the iteration termination condition, return to continue iterative calculation; if the current iteration meets the iteration termination condition, the air conditioning control parameter combination after stopping the iteration is used as the optimal air conditioning control parameter combination;

[0115] The input data of the air conditioning control model is formed based on the optimal air conditioning control parameter combination, and the optimal temperature value of each temperature measurement and control point is output through the air conditioning control model.

[0116] Optionally, the determination module 62 is further configured to:

[0117] Calculate the current minimized temperature non-uniformity coefficient based on the temperatures of multiple temperature measurement and control points corresponding to the current air conditioning control parameter combination;

[0118] Based on the optimization objective function, the current minimized temperature non-uniformity coefficient and the current total air-conditioning power, a current objective function value is calculated.

[0119] Optionally, the optimization objective function is:

[0120] min:ω1K t +ω2P ac_total

[0121]

[0122] Where ω1 is the temperature non-uniformity coefficient K t The weight of the total target, ω2 is the total power of the air conditioner P ac_total The weight of the total target, T min is the minimum indoor temperature limit, T s is the set temperature that the target space is expected to reach, where

[0123]

[0124] T ave is the average value of multiple temperature measurement and control points, T i is the temperature of the i-th temperature measurement and control point, and n is the total number of temperature measurement and control points in the target space.

[0125] Optionally, the determination module 62 is further configured to:

[0126] Acquire a second historical data set, the second historical data set comprising a plurality of groups of second data samples, each group of second data samples comprising target air-conditioning parameters of a plurality of space equipment in the target space and temperatures of a plurality of corresponding temperature measurement and control points;

[0127] Based on the second historical data set, calculating the correlation value between each temperature measurement and control point and the target air-conditioning parameter of each air-conditioning equipment;

[0128] Based on the relevance value, relevance grouping data is determined.

[0129] Optionally, the determination module 62 is further configured to:

[0130] Based on the second historical data set, the correlation value between each temperature measurement and control point and the target air-conditioning parameter of each air-conditioning device is calculated using a correlation calculation formula, wherein the correlation calculation formula is as follows:

[0131]

[0132] where ρ ij is the temperature T of the i-th temperature measurement and control point i and the target air conditioning parameter F of the jth air conditioner j The correlation, cov(F j ,T i ) is T i With F j The covariance between j is the standard deviation of the target parameter of the jth air conditioner, σ iis the variance of the temperature of the i-th temperature measurement and control point.

[0133] Optionally, the correlation grouping data includes multiple groups of data, each group of data includes a correlation value of at least one target air-conditioning parameter of an air-conditioning device associated with a temperature measurement and control point, and / or each group of data includes a correlation value of a target air-conditioning parameter of an air-conditioning device and multiple temperature measurement and control points.

[0134] Optionally, the control module 63 is further configured to include:

[0135] For any temperature measurement and control point, obtaining the target air-conditioning parameter with the strongest correlation with the any temperature measurement and control point from the correlation grouped data;

[0136] From the optimal temperature values ​​of each temperature measurement and control point, the optimal temperature value corresponding to any temperature measurement and control point is obtained, and the optimal temperature value corresponding to any temperature measurement and control point is used as the cold channel temperature setting value of the air-conditioning equipment corresponding to the target air-conditioning parameter with the strongest correlation with any temperature measurement and control point;

[0137] From the optimal air-conditioning control parameter combination, the parameter value of the target air-conditioning parameter that is most closely associated with any of the temperature measurement and control points is obtained, and based on the obtained parameter value, the air-conditioning equipment corresponding to the target air-conditioning parameter that is most closely associated with any of the temperature measurement and control points is controlled.

[0138] It should be noted that the structure provided in the embodiment of the present application does not constitute a limitation on the control device based on multiple air conditioners, and the various modules can be implemented in whole or in part by software, hardware, and a combination thereof. The above modules can be embedded in or independent of the controller in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the controller can call and execute the operations corresponding to the above modules. In other embodiments, the control device based on multiple air conditioners may include more or fewer modules than shown in the figure.

[0139] See also Figure 7 On the other hand, the present application provides a control device 100, which includes a memory 3011 of one or more computer-readable storage media and a processor 3012 of one or more processing cores. Those skilled in the art will understand that Figure 7 The control device structure shown in the figure does not constitute a limitation on the control device 100, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently. The memory 3011 stores a computer program, and when the computer program is executed by the processor 3012, the processor 3012 executes the control method based on multiple air conditioners provided in any of the above embodiments of the present application.

[0140] The processor 3012 is the control center of the control device, which uses various interfaces and lines to connect various parts of the entire computer device, and executes various functions of the computer device and processes data by running or executing software programs and / or modules stored in the memory 3011, and calling data stored in the memory 3011. Optionally, the processor 3012 may include one or more processing cores; preferably, the processor 3012 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user pages and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 3012.

[0141] The memory 3011 can be used to store software programs and modules. The processor 3012 executes various functional applications and data processing by running the software programs and modules stored in the memory 3011. The memory 3011 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 3011 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 3011 may also include a memory controller to provide the processor 3012 with access to the memory 3011.

[0142] On the other hand, an embodiment of the present application further provides an air-conditioning system, comprising a multi-air-conditioning based control device provided by any of the above embodiments of the present application, and at least one air-conditioning device communicatively connected to the control device.

[0143] On the other hand, an embodiment of the present application further provides a storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the control method based on multiple air conditioners provided in any of the above embodiments of the present application.

[0144] Those skilled in the art can understand that all or part of the processes in the methods provided in the above embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0145] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A control method based on multiple air conditioners, characterized in that: include: Obtain target air conditioning parameters that are correlated with the temperature of the target space; Acquire an air conditioning control model indicating a relationship between an air conditioning control parameter and a target space temperature, wherein the air conditioning control parameter includes the target air conditioning parameters of a plurality of air conditioning devices, and the target space temperature includes the temperatures of a plurality of temperature measurement and control points in the target space; Based on the air conditioning control model, determining the optimal air conditioning control parameter combination and the optimal temperature value of each temperature measurement and control point; Acquire correlation group data between each temperature measurement and control point and the target air-conditioning parameters of the plurality of air-conditioning devices; Based on the optimal air-conditioning control parameter combination, the optimal temperature value of each temperature measurement and control point and the correlation grouping data, the multiple air-conditioning devices are controlled.

2. The control method based on multiple air conditioners according to claim 1, characterized in that: The step of obtaining the target air conditioning parameter correlated with the target space temperature includes: Acquire a first historical data set, the first historical data set comprising a plurality of groups of first data samples, each group of first data samples comprising air-conditioning parameters of a plurality of space equipment in the target space and temperatures of a plurality of corresponding temperature measurement and control points; Based on the first historical data set, calculating a first correlation value between each temperature measurement and control point and an air-conditioning parameter of each air-conditioning device; The target air-conditioning parameter is determined from the air-conditioning parameters based on the first correlation value.

3. The control method based on multiple air conditioners according to claim 1, characterized in that: The air conditioning control model is a pre-trained air conditioning control model, and the air conditioning control model for obtaining the relationship between the air conditioning control parameter indicating the relationship between the target space temperature includes: Acquire a training sample data set, wherein each training sample in the training sample data set includes target air conditioning parameter values ​​of multiple air conditioning devices, each training sample corresponds to a training label, and the training label is the temperature values ​​of multiple temperature measurement and control points corresponding to the target air conditioning parameter values ​​of the multiple air conditioning devices; Build an initial air conditioning control model; Acquire training samples from the training sample data set to form sample input data of the air-conditioning control model in the current training iteration, and output the temperature values ​​of multiple temperature measurement and control points in the current training iteration through the air-conditioning control model in the current training iteration; calculate the loss value in the current training iteration based on the temperature values ​​of the multiple temperature measurement and control points in the current training iteration and the training labels corresponding to the training samples, and judge whether the current training iteration meets the training iteration termination condition based on the loss value in the current training iteration; if the current training iteration does not meet the training iteration termination condition, return to continue training, and if the current training iteration meets the training iteration termination condition, use the air-conditioning control model after stopping the iteration as the pre-trained air-conditioning control model.

4. The control method based on multiple air conditioners according to claim 1, characterized in that: Determining the optimal air conditioning control parameter combination and the optimal temperature value of each temperature measurement and control point based on the air conditioning control model includes: Constructing an optimization objective function for optimizing air conditioning control parameters; Calculate the current air conditioning control parameter combination of the current iteration by using an iterative calculation method, form input data of the air conditioning control model based on the current air conditioning control parameter combination, and output the temperatures of multiple temperature measurement and control points corresponding to the current air conditioning control parameter combination through the air conditioning control model; Calculate the total air conditioning power corresponding to the current air conditioning control parameter combination; Calculate the current objective function value based on the optimization objective function, the temperatures of multiple temperature measurement and control points corresponding to the current air conditioning control parameter combination and the current air conditioning total power; Based on the current objective function value, determine whether the current iteration meets the iteration termination condition, if the current iteration does not meet the iteration termination condition, return to continue iterative calculation; if the current iteration meets the iteration termination condition, use the air conditioning control parameter combination after stopping the iteration as the optimal air conditioning control parameter combination; The input data of the air conditioning control model is formed based on the optimal air conditioning control parameter combination, and the optimal temperature value of each temperature measurement and control point is output through the air conditioning control model.

5. The control method based on multiple air conditioners according to claim 4, characterized in that: The calculating of the current objective function value based on the optimization objective function, the temperatures of the multiple temperature measurement and control points corresponding to the current air conditioning control parameter combination and the current air conditioning total power comprises: Calculate the current minimized temperature non-uniformity coefficient based on the temperatures of multiple temperature measurement and control points corresponding to the current air conditioning control parameter combination; Based on the optimization objective function, the current minimized temperature non-uniformity coefficient and the current total air-conditioning power, a current objective function value is calculated.

6. The control method based on multiple air conditioners according to claim 5, characterized in that: The optimization objective function is: min:ω1K t +ω2P ac_total Where ω1 is the temperature non-uniformity coefficient K t The weight of the total target, ω2 is the total power of the air conditioner P ac_total The weight of the total target, T min is the minimum indoor temperature limit, T s is the set temperature that the target space is expected to reach, where T ave is the average value of multiple temperature measurement points, T i is the temperature of the i-th temperature measurement and control point, and n is the total number of temperature measurement and control points in the target space.

7. The control method based on multiple air conditioners according to claim 1, characterized in that: The step of obtaining correlation grouping data between each temperature measurement and control point and the target air conditioning parameters of the plurality of air conditioning equipments comprises: Acquire a second historical data set, the second historical data set comprising a plurality of groups of second data samples, each group of second data samples comprising target air-conditioning parameters of a plurality of space equipment in the target space and temperatures of a plurality of corresponding temperature measurement and control points; Based on the second historical data set, calculating the correlation value between each temperature measurement and control point and the target air-conditioning parameter of each air-conditioning equipment; Based on the relevance value, relevance grouping data is determined.

8. The control method based on multiple air conditioners according to claim 4, characterized in that: The calculating, based on the second historical data set, the correlation value between each temperature measurement and control point and the target air-conditioning parameter of each air-conditioning device comprises: Based on the second historical data set, the correlation value between each temperature measurement and control point and the target air-conditioning parameter of each air-conditioning device is calculated using a correlation calculation formula, wherein the correlation calculation formula is as follows: where ρ ij is the temperature Ti of the i-th temperature measurement and control point and the target air conditioning parameter F of the j-th air conditioner j The correlation, cov(F j , T i ) is T i With F j The covariance between j is the standard deviation of the target parameter of the jth air conditioner, σ i is the variance of the temperature of the i-th temperature measurement and control point.

9. The control method based on multiple air conditioners according to claim 1, characterized in that: The correlation grouping data includes multiple groups of data, each group of data includes a correlation value of at least one target air-conditioning parameter of an air-conditioning device associated with a temperature measurement and control point, and / or each group of data includes a correlation value of a target air-conditioning parameter of an air-conditioning device and multiple temperature measurement and control points.

10. The control method based on multiple air conditioners according to claim 9, characterized in that: The controlling of the plurality of air conditioning devices based on the optimal air conditioning control parameter combination, the optimal temperature value of each temperature measurement and control point and the correlation grouping data comprises: For any temperature measurement and control point, obtaining the target air-conditioning parameter with the strongest correlation with the any temperature measurement and control point from the correlation grouped data; From the optimal temperature values ​​of each temperature measurement and control point, the optimal temperature value corresponding to any temperature measurement and control point is obtained, and the optimal temperature value corresponding to any temperature measurement and control point is used as the cold channel temperature setting value of the air-conditioning equipment corresponding to the target air-conditioning parameter with the strongest correlation with any temperature measurement and control point; From the optimal air-conditioning control parameter combination, the parameter value of the target air-conditioning parameter that is most closely associated with any of the temperature measurement and control points is obtained, and based on the obtained parameter value, the air-conditioning equipment corresponding to the target air-conditioning parameter that is most closely associated with any of the temperature measurement and control points is controlled.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the control method based on multiple air conditioners as claimed in any one of claims 1 to 10 is implemented.

12. A control device based on multiple air conditioners, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the control method based on multiple air conditioners as claimed in any one of claims 1 to 10.

13. An air conditioning system, characterized in that: include: A control device based on multiple air conditioners as described in claim 12, and at least one air conditioner device communicatively connected to the control device.

Images