Method, device and equipment for controlling multi-split air conditioning system and storage medium

Abstract

The invention relates to the technical field of intelligent air conditioners, and discloses a method, device and equipment for controlling a multi-split air conditioning system and a storage medium. The method comprises the steps that current state environment parameters of the multi-split air conditioning system are obtained; based on a system model between the air conditioner state environment parameters and the controllable parameters and a comfort model between the controllable parameters and the tail end indoor comfort, a current fitness function is estimated according to the current state environment parameters and the tail end target comfort; and according to the optimal solution of the current fitness function, a current control parameter value is determined, and according to the current control parameter value, the multi-split air conditioning system is controlled to operate. Thus, the actual load requirement of the tail end in the multi-split air conditioning system is accurately fed back, more accurate load supply is further provided, it is guaranteed that the outdoor unit of the multi-split air conditioning system operates in an efficient interval to the maximum extent, the control stability of the multi-split air conditioning system is improved, and additional energy consumption for stable regulation and control is also reduced.

Description

Technical Field

[0001] This application relates to the technical field of intelligent air conditioners, for example, to methods, devices, equipment, and storage media for controlling multi-connected air conditioner systems. Background Art

[0002] As a type of central air conditioner system, a multi-connected air conditioner system adopts the form of one or more outdoor units driving multiple indoor units. With the development of central air conditioner systems, multi-connected air conditioner systems have gradually occupied an important position in the market scale of central air conditioner systems due to their convenient design and installation, and the ability to independently control multiple terminals. Under the background of carbon peaking and carbon neutrality, the energy-saving and comfortable operation of multi-connected air conditioners has always been the focus of research. However, due to the characteristics of multi-terminal independent and flexible regulation of multi-connected air conditioner systems, the control of the overall system belongs to a non-linear optimization problem with multiple inputs and outputs. And due to the variability of free control of the indoor units at the terminals and the variable working conditions, it is almost impossible to optimize and solve the overall system using theoretical methods.

[0003] Currently, according to the changes in the suction / exhaust of the multi-connected outdoor unit during actual operation and the corresponding threshold settings, the frequency of the air conditioner outdoor unit can be controlled, and the corresponding unit addition and subtraction can be completed. That is, through the changes in the suction / exhaust pressure, the load demand at the terminal is mapped indirectly. Such a control strategy cannot precisely control and integrate the actual needs of the entire multi-connected air conditioner system, and to a large extent, it cannot accurately meet the comfort requirements of the terminals and improve the energy-saving potential. Moreover, only regulating the entire multi-connected air conditioner system according to the real-time changes in the suction / exhaust pressure will cause instability in the control of the entire multi-connected air conditioner system due to short-term regulation at the terminals at certain moments, resulting in additional energy consumption for stable regulation.

[0004] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] To provide a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a comprehensive review, nor is it intended to identify key / important elements or delineate the scope of protection of these embodiments, but rather serves as a prelude to the following detailed description.

[0006] Embodiments of the present disclosure provide a method, device, air conditioner, and storage medium for multi-connected air conditioner control to solve the technical problem of additional energy waste caused by the inability of traditional multi-connected air conditioner systems to accurately reflect the terminal load demand and comprehensively consider the load distribution within a time period during the control process.

[0007] In some embodiments, the method includes:

[0008] Obtain the current state environment parameters of the multi-connected air-conditioning system;

[0009] Based on the system model between the air-conditioning state environment parameters and the controllable parameters, and the comfort model between the controllable parameters and the indoor comfort at the end, estimate the current fitness function according to the current state environment parameters and the target comfort at the end;

[0010] Determine the current control parameter value according to the optimal solution of the current fitness function, and control the operation of the multi-connected air-conditioning system according to the current control parameter value.

[0011] In some embodiments, the device includes:

[0012] An acquisition module configured to obtain the current state environment parameters of the multi-connected air-conditioning system;

[0013] An estimation module configured to estimate the current fitness function based on the system model between the air-conditioning state environment parameters and the controllable parameters, and the comfort model between the controllable parameters and the indoor comfort at the end, according to the current state environment parameters and the target comfort at the end;

[0014] An optimal control module configured to determine the current control parameter value according to the optimal solution of the current fitness function, and control the operation of the multi-connected air-conditioning system according to the current control parameter value.

[0015] In some embodiments, the device for controlling the multi-connected air-conditioning system includes a processor and a memory storing program instructions, and the processor is configured to execute the above method for controlling the multi-connected air-conditioning system when executing the program instructions.

[0016] In some embodiments, the device includes a device body; the above device for controlling the multi-connected air-conditioning system is installed on the device body.

[0017] In some embodiments, the storage medium stores program instructions, and the program instructions execute the above method for controlling the multi-connected air-conditioning system when running.

[0018] The method, device and air conditioner for controlling the multi-connected air-conditioning system provided by the embodiments of the present disclosure can achieve the following technical effects:

[0019] After obtaining the current state environment parameters of the multi-connected air-conditioning system, according to the system model between the air-conditioning state environment parameters and the controllable parameters, as well as the comfort model between the controllable parameters and the terminal indoor comfort, the current fitness function matching the current state environment parameters and the terminal target comfort can be estimated. And after determining the current control parameter value according to the optimal solution of the current fitness function, the corresponding air-conditioning operation is carried out. In this way, the comfort requirements of the terminal can be accurately met, that is, the actual load demand at the terminal in the multi-connected air-conditioning system can be accurately fed back, and then a more accurate load supply can be provided, ensuring that the outdoor unit of the multi-connected air-conditioning system operates in the high-efficiency range to the greatest extent, improving the control stability of the multi-connected air-conditioning system, and reducing the additional energy consumption for stable regulation.

[0020] The above general description and the following description are only exemplary and explanatory, and are not used to limit this application. Brief Description of the Drawings

[0021] One or more embodiments are exemplarily illustrated by the corresponding drawings. These exemplary illustrations and the drawings do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation, and among them:

[0022] Figure 1 is a schematic structural diagram of a system for controlling a multi-connected air-conditioning system provided by an embodiment of the present disclosure;

[0023] Figure 2 is a schematic flowchart of a process for obtaining sample data provided by an embodiment of the present disclosure;

[0024] Figure 3 is a schematic diagram of the relationship between state environment parameters of a multi-connected air-conditioning system under a refrigeration mode working condition provided by an embodiment of the present disclosure;

[0025] Figure 4 is a schematic diagram of the construction of a comfort model in a multi-connected air-conditioning system provided by an embodiment of the present disclosure;

[0026] Figure 5 is a schematic flowchart of a method for controlling a multi-connected air-conditioning system provided by an embodiment of the present disclosure;

[0027] Figure 6 is a schematic flowchart of a method for controlling a multi-connected air-conditioning system provided by an embodiment of the present disclosure;

[0028] Figure 7 is a schematic structural diagram of a device for controlling a multi-connected air-conditioning system provided by an embodiment of the present disclosure;

[0029] Figure 8It is a schematic structural diagram of a control device for a multi-connected air-conditioning system provided by an embodiment of the present disclosure;

[0030] Figure 9 It is a schematic diagram of a device provided by an embodiment of the present disclosure. Specific embodiments

[0031] In order to be able to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. The attached drawings are for reference and illustration only, and are not intended to limit the embodiments of the present disclosure. In the following technical description, for the sake of explanation, multiple details are provided to provide a full understanding of the disclosed embodiments. However, one or more embodiments can still be implemented without these details. In other cases, well-known structures and devices can be shown in a simplified manner to simplify the drawings.

[0032] In the embodiments of the present disclosure, terms such as "first" and "second" in the specification, claims and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data used can be interchanged under appropriate circumstances so as to implement the embodiments of the present disclosure described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion.

[0033] Unless otherwise stated, the term "plurality" means two or more.

[0034] In the embodiments of the present disclosure, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B.

[0035] The term "and / or" is an associative relationship describing an object, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B these three relationships.

[0036] The multi-connected air-conditioning system includes: one or more outdoor units and multiple indoor units located at the indoor end. For the multi-connected air-conditioning system, there are sensors at multiple positions inside at the factory stage. These sensors include but are not limited to: outdoor unit suction pressure sensor, exhaust pressure sensor, compressor frequency sensor, indoor unit temperature sensor, etc. After the multi-connected air-conditioning system is installed and put into operation, a large amount of historical data of the sensors will be generated. These historical data can be the historical state environment parameter data of the air-conditioning system, and these historical state environment parameter data can be stored in the cloud server.

[0037] In the embodiments of the present disclosure, based on sample data including historical state environment parameter data of an air conditioner, training is performed to obtain a system model between the state environment parameters and controllable parameters of the air conditioner, and a comfort model between the controllable parameters and the indoor comfort level at the end. In this way, after obtaining the current state environment parameters of the multi-connected air conditioner, according to the system model and the comfort model, the current fitness function matching the current state environment parameters and the target indoor comfort level at the end can be estimated, and according to the optimal solution of the current fitness function, the current control parameter value is determined, and then the corresponding air conditioner operation is performed. Thus, the comfort requirements at the end can be accurately met. That is, the actual load demand at the end in the multi-connected air conditioner system is accurately fed back, and then a more accurate load supply is provided, improving the stability of the control of the multi-connected air conditioner system and reducing the additional energy consumption for stable regulation.

[0038] Figure 1 It is a schematic structural diagram of a system for controlling a multi-connected air conditioner system provided by an embodiment of the present disclosure. As Figure 1 shown, the system for controlling the multi-connected air conditioner system includes: a cloud server 100 and a multi-connected air conditioner system 200. The multi-connected air conditioner system includes: an outdoor unit 211, an outdoor unit 212,..., and indoor units 221, 222,....

[0039] The multi-connected air conditioner system 200 can communicate with the cloud server 100. In this way, during the operation of the multi-connected air conditioner system 200, through configured multi-point sensors, the state environment parameters of the air conditioner system can be monitored, including: suction pressure (low pressure) Ps, discharge pressure (high pressure) Pd, compressor frequency f, outdoor temperature, each indoor temperature at the end, outdoor unit power Pow, refrigeration (heating) capacity Q, etc. Among them, the state environment parameters monitored at a certain moment are the current state environment parameters. Of course, during the operation of the multi-connected air conditioner system 200 or after the end of this operation, the monitored state environment parameters can be sent to the cloud server 100 for storage, that is, the cloud server 100 stores the historical state environment parameter data of the air conditioner system.

[0040] In the embodiments of the present disclosure, either the cloud server 100 or the multi-connected air conditioner system 200 can be trained based on the historical state environment parameter data of the air conditioner system by using a matching model (such as a mechanism model, a data-driven model, etc.) to obtain a system model between the state environment parameters and controllable parameters of the air conditioner, and a comfort model between the controllable parameters and the indoor comfort level at the end.

[0041] Thus, a system model and a comfort model are obtained. The cloud server 100 or the multi-connected air-conditioning system 200 acquires the current state environment parameters of the multi-connected air-conditioning system. Then, based on the system model and the comfort model, the current fitness function matching the current state environment parameters and the end target comfort can be estimated. Then, according to the optimal solution of the current fitness function, the current control parameter value is determined, and the multi-connected air-conditioning system is controlled according to the current control parameter value. Thus, the comfort requirements of the end can be accurately met, that is, the actual load requirements at the end in the multi-connected air-conditioning system are accurately fed back, and then a more accurate load supply is provided, improving the control stability of the multi-connected air-conditioning system and reducing the additional energy consumption for stable regulation.

[0042] For the control of the multi-connected air-conditioning system, model training needs to be performed on the historical state environment parameter data of the air-conditioning system to obtain a system model between the air-conditioning state environment parameters and the controllable parameters, and a comfort model between the controllable parameters and the indoor comfort at the end.

[0043] The cloud server stores the historical state environment parameter data of the air-conditioning system, but the quality and format of these data do not necessarily meet the requirements of subsequent model training. Therefore, in order to ensure the accuracy of subsequent model training and the applicability of subsequent applications, these historical data need to be integrated and preprocessed. That is, in some embodiments, the historical state environment parameter data corresponding to a set time period can be acquired and subjected to interpolation completion and alignment processing to obtain the sample data for model training. For example: for a multi-connected air-conditioning system with a short running time, the corresponding historical state environment parameter data is not much. Therefore, all the historical state environment parameter data can be determined as the historical state environment parameter data corresponding to the set time period. For the case where there is a large amount of historical state environment parameter data, considering the attenuation problem of the multi-connected air-conditioning system running over time and the computing power expenditure, the historical state environment parameter data corresponding to a recent time period can be selected as the historical state environment parameter data corresponding to the set time period.

[0044] Figure 2 It is a schematic flowchart of a process for obtaining sample data provided by an embodiment of the present disclosure. As Figure 2 shown, the process of performing interpolation completion and alignment processing to obtain the sample data for model training may include:

[0045] Step 201: Acquire the historical state environment parameter data corresponding to the set time period.

[0046] The historical state environment parameter data corresponding to a certain time period can be used as the historical state environment parameter data corresponding to the set time period.

[0047] Step 202: Determine the threshold range corresponding to each state environment parameter.

[0048] Step 203: Determine whether there is status environmental parameter data outside the corresponding threshold range? If so, execute Step 204; otherwise, execute Step 205.

[0049] Step 204: Perform interpolation processing on the status environmental parameter data outside the corresponding threshold range. Then proceed to Step 205.

[0050] In some embodiments, interpolation processing can be performed on the status environmental parameter data outside the corresponding threshold range based on statistical methods. Of course, other interpolation methods can also be applied here, without strict limitations.

[0051] Step 205: Determine whether there are outliers in the historical status environmental parameter data through the corresponding box plot? If so, execute Step 206; otherwise, execute Step 207.

[0052] Step 206: Perform interpolation processing on the outliers, and then proceed to Step 207.

[0053] Similarly, statistical methods can be selected but are not limited to for performing interpolation processing on the outliers.

[0054] Step 207: Perform time alignment processing on the historical status environmental parameter data.

[0055] For the convenience of subsequent model training and application, the historical status environmental parameter data is aligned to the nearest time. For example, for the data collected and stored at 13:01:35, after time alignment processing, it becomes data at 13:01:30; for the data collected and stored at 13:02:05, the alignment processing results in data at 13:02:00.

[0056] Step 208: Determine the historical status environmental parameter data after interpolation completion and alignment processing as the sample data for model training.

[0057] It can be seen that the historical status environmental parameter data after interpolation completion and alignment processing can meet the requirements of model training. That is, the cloud server or the multi-connected air-conditioning system obtains the sample data for model training. Thus, based on the sample data, model training can be carried out to obtain the corresponding system model and comfort model.

[0058] Among them, for a multi-connected air-conditioning system, the component with the largest energy consumption proportion in the overall system is the outdoor unit of the multi-connected air-conditioning system. The operating state of the outdoor unit of the multi-connected air-conditioning system determines the amount of cooling capacity provided by the system and the level of the overall energy consumption of the system. Therefore, in order to explore the energy-saving potential of the multi-connected system at the decision-making level, it is necessary to study the mapping relationship between the operating state of the multi-connected outdoor unit and some decision control parameters. Under the condition of meeting the cooling capacity demand and the end comfort level during the prediction period, an optimal operating state is achieved, that is, an efficient operation with the minimum energy consumption. By establishing a system model between the air-conditioning state environment parameters and the controllable parameters, the relationship between the cooling capacity of the outdoor unit and the energy consumption can be mapped.

[0059] The main operating state parameters of the outdoor unit of the multi-connected air-conditioning system include: suction / discharge pressure, compressor frequency, cooling capacity, energy consumption, etc. These operating state parameters belong to the state environment parameters of the multi-connected air-conditioning system. Therefore, it is necessary to establish a model between each or multiple operating state parameters and the corresponding controllable parameters, that is, it is necessary to establish models for multiple state environment parameters, and the mutual influence relationship needs to be considered when establishing the models for each state environment parameter, and corresponding boundary conditions are set.

[0060] Therefore, the system model between the air-conditioning state environment parameters and the controllable parameters includes models for multiple state environment parameters. In some embodiments, it may include: determining the first input parameters corresponding to the first state environment parameter of the multi-connected air-conditioning system, and the first correlation relationship between the first state environment parameter and other state environment parameters, where the first input parameters include one or more controllable parameters; according to the first input parameters and the first correlation relationship, performing model training on the sample data including the historical state environment parameter data of the air-conditioning system to obtain the first state environment parameter model in the system model.

[0061] Figure 3 It is a schematic diagram of the relationship between state environment parameters of a multi-connected air-conditioning system provided by an embodiment of the present disclosure under the cooling mode condition. As Figure 3 shown, the controllable parameters under the cooling mode are the low pressure Ps and the compressor frequency f. From Figure 3 the relationship shown, it can be seen that it is necessary to establish the relationship between the three parameters of the high pressure Pd, the cooling capacity Q, and the outdoor unit power Pow and these two target control parameters. Moreover, there is also a mutual correlation relationship between the three parameters of the high pressure Pd, the cooling capacity Q, and the outdoor unit power Pow.

[0062] When building a model for high-pressure Pd (exhaust pressure), that is, when the environmental parameters of the first state are high-pressure Pd, the corresponding first input parameters are determined to include: low-pressure Ps and compressor frequency f, and the first correlation relationship between high-pressure Pd and outdoor temperature outTemp is also determined. Considering the subsequent demand for time-series prediction, possible first input parameters may also include other time-series values, etc. Then, based on the first correlation relationship among low-pressure Ps, compressor frequency f, and parameters such as outdoor temperature outTemp, a suitable model (such as a mechanism model, a data-driven model, etc.) is selected, and the sample data is used for model training to obtain the high-pressure Pd model F(Ps, f, OutTemp,...) in the system model.

[0063] Similarly, the cooling capacity Q of the outdoor unit of the multi-connected air-conditioning system can be determined as the environmental parameter of the first state. The corresponding first input parameters include: low-pressure Ps and compressor frequency f, and the first correlation relationship among the cooling capacity Qd, high-pressure Pd, indoor temperature indoorTemp, outdoor temperature outTemp, etc. is also determined. Similarly, considering the subsequent demand for time-series prediction, possible first input parameters may also include other time-series values, etc. Thus, according to the first input parameters and the first correlation relationship, a suitable model (such as a mechanism model, a data-driven model, etc.) is selected, and the sample data is used for model training to obtain the cooling capacity Q model F(Ps, f, Pd, indoorTemp, OutTemp,...) in the system model.

[0064] Of course, the power Pow of the outdoor unit of the multi-connected air-conditioning system can also be determined as the environmental parameter of the first state. The corresponding first input parameters include: low-pressure Ps and compressor frequency f, and the first correlation relationship between the power Pow of the outdoor unit and high-pressure Pd and other parameters is also determined. Similarly, considering the subsequent demand for time-series prediction, possible first input parameters may also include other time-series values, etc. Thus, according to the first input parameters and the first correlation relationship, a suitable model (such as a mechanism model, a data-driven model, etc.) is selected, and the sample data is used for model training to obtain the

[0065] Based on the relationships between these three models and the controllable parameters, the time-series state changes of each parameter of the outdoor unit of the multi-connected air-conditioning system are mapped when the set value of the target controllable parameter changes. Thus, different combinations of controllable parameter values can be selected to obtain the optimal comprehensive time-series energy efficiency while meeting the load demand and comfort within the time period. The above examples are only one of the modeling methods for the environmental parameters of the multi-connected air-conditioning system. In the embodiments of the present disclosure, the modeling methods and model inputs for each environmental parameter are not limited.

[0066] The energy-saving control operation of a multi-connected air-conditioning system needs to be carried out on the premise of meeting the indoor comfort of the terminal. Therefore, when changing the values of the controllable parameters of the outdoor unit, it is necessary to be able to meet the comfort of the terminal. In order to clearly understand the mapping relationship between indoor comfort and the changes in these controllable parameter values, a comfort model between the controllable parameters and the indoor comfort of the terminal needs to be established. The state environment parameters that can directly affect the indoor terminal comfort mainly include: indoor temperature, indoor humidity, wind speed, CO2 concentration, fresh air volume, etc. And the adjustment of the controllable parameter values of the outdoor unit will directly affect the changes in, for example, indoor temperature and indoor humidity. Therefore, in some embodiments, a first mapping relationship between the controllable parameters and the terminal temperature and humidity parameters is constructed. And, a second mapping relationship between the terminal temperature and humidity parameters and the indoor comfort of the terminal is constructed; according to the first mapping relationship and the second mapping relationship, and using the sample data including the historical state environment parameter data of the air-conditioning system, model training is carried out to obtain the comfort model. That is, a mapping model between the controllable parameters and the indoor temperature and indoor humidity can be established, and the outputs of these models are used as the inputs of the mapping model between the state environment parameters and the indoor comfort of the terminal.

[0067] Figure 4 It is a schematic diagram of the construction of a comfort model in a multi-connected air-conditioning system provided by an embodiment of the present disclosure. As Figure 4 shown, the controllable parameters include: low pressure Ps and compressor frequency f. In this way, including the controllable parameters and the load supply quantity output from the controllable parameter values, etc., a mapping relationship with the indoor temperature and humidity is constructed, that is, the first mapping relationship. Then, the indoor temperature and humidity are determined, as well as other state environment parameters, such as: CO2 concentration, fresh air related parameters, wind speed, temperature field uniformity, PMV, etc., and the second mapping relationship with the indoor comfort of the terminal is determined. Thus, according to the first mapping relationship and the second mapping relationship, and using the above-obtained sample data, model training is carried out to obtain the comfort model. That is, the indoor temperature, indoor humidity, CO2 concentration, fresh air related parameters, wind speed, temperature field uniformity, PMV, etc. can be used as inputs to establish a comfort model. And, during the model training process, when calculating the comfort using the sample data including the historical state environment parameter data of the air-conditioning system, the weight coefficients between the various parameters can be flexibly adjusted according to the actual working conditions to calculate the corresponding comfort.

[0068] After the cloud server or the multi-connected air-conditioning system stores the system model between the air-conditioning state environmental parameters and the controllable parameters, and the comfort model between the controllable parameters and the indoor comfort at the end, it can, through the linkage between the state environmental parameters in each model, predict in advance the changes in the supply amount of the outdoor unit load, energy efficiency, and indoor comfort at the end caused by the change of the controllable parameters. Thus, under the condition of ensuring the indoor comfort at the end, the solution can be obtained for maintaining the efficient operation (i.e., minimum energy consumption) of the entire multi-connected air-conditioning system during the time period. That is, the corresponding control parameter values can be obtained through the optimal solution combination of the sequence, and the corresponding multi-connected air-conditioning system can be controlled.

[0069] Figure 5 It is a schematic flowchart of a method for controlling a multi-connected air-conditioning system provided by an embodiment of the present disclosure. As Figure 5 shown, the process for controlling a multi-connected air-conditioning system includes:

[0070] Step 501: Obtain the current state environmental parameters of the multi-connected air-conditioning system.

[0071] The multi-connected air-conditioning system is configured with sensors at multiple points. Therefore, the state environmental parameters of the multi-connected air-conditioning system can be monitored, including: the operating state parameters of the outdoor unit, such as: the suction pressure (low pressure) Ps, the discharge pressure (high pressure) Pd, the compressor frequency f, the power of the outdoor unit Pow, the cooling capacity Q, etc., and the environmental parameters where the air-conditioning system is located, such as: the outdoor temperature, the indoor temperature of each end, the air quality, etc. The current moment corresponds to the current state environmental parameters.

[0072] Step 502: Based on the system model between the air-conditioning state environmental parameters and the controllable parameters, and the comfort model between the controllable parameters and the indoor comfort at the end, estimate the current fitness function according to the current state environmental parameters and the target indoor comfort at the end.

[0073] In the embodiment of the present disclosure, the optimal solution can be obtained under the condition of ensuring the indoor comfort at the end and maintaining the efficient operation (i.e., minimum energy consumption) of the entire multi-connected air-conditioning system, and the corresponding control parameter values can be obtained. To solve such an optimization problem, methods such as optimization based on a heuristic algorithm and model-based reinforcement learning can be used but are not limited to these.

[0074] Among them, the heuristic algorithms include: genetic algorithm, simulated annealing, ant colony algorithm, particle swarm algorithm, etc. The core of the optimization based on the heuristic algorithm is the setting of the fitness function. By abstracting the optimization task into the corresponding fitness function, and according to the change combination of the controllable parameters within the corresponding threshold range, the optimal combination solution that can meet the corresponding constraints is sought.

[0075] Therefore, in some embodiments, the system model between the air-conditioning state environmental parameters and the controllable parameters, as well as the comfort model between the controllable parameters and the terminal indoor comfort can be called, and the current fitness function can be estimated according to the current state environmental parameters and the terminal target comfort.

[0076] By solving the optimization problem, the current time step and the corresponding current control parameter value can be obtained. The general time step can be 5 minutes, 8 minutes, 10 minutes, etc. In some embodiments, only the fitness function corresponding to one time step can be estimated. For example: if the input parameter of the system model is the current state environmental parameter, then based on the current state environmental parameter, a power index expression can be estimated based on the system model, and a comfort index expression matching the current state environmental parameter and the terminal target comfort can be estimated based on the comfort model. Thus, the current fitness function can be obtained according to the power index expression and the comfort index expression.

[0077] However, in some embodiments, the control of the multi-connected device should not be too frequent. Therefore, it may be necessary to consider the changes in the room load and outdoor environmental parameters, etc. in the future period of time. In this way, it may be necessary to consider the fitness functions corresponding to two or more time steps.

[0078] In some embodiments, the power and comfort are considered simultaneously in the fitness function to ensure that the minimum energy consumption is achieved within the recommended comfort range of the indoor terminal. Therefore, estimating the current fitness function includes: based on the current state environmental parameter and the system model, estimating one or more power index expressions corresponding to each time step respectively, and adding the weights of each power index expression according to the set power weight coefficient to obtain the total power index expression; based on the current state environmental parameter and the terminal target comfort, estimating one or more comfort index expressions corresponding to each time step respectively based on the comfort model, and adding the weights of each comfort index expression according to the set comfort weight coefficient to obtain the total comfort index expression; performing a subtraction operation on the total power index expression and the total comfort index expression to obtain the current fitness function.

[0079] For example, the coverage period should not be too short, but considering the problem of the accuracy decline of the model prediction for too long, therefore, the fitness functions corresponding to three time steps can be estimated.

[0080]

[0081]

[0082] Fitness function = J Pow -J com (3)

[0083] Wherein, J Pow is the power exponent, ω 1i is the power weight coefficient, f pow is the mapping model of power, X i is the input parameter at the i-th time step of the power mapping model, Pow max is the maximum power of the outdoor unit of the multi-connected air conditioner; J com is the comfort index, ω 2i is the comfort weight coefficient, f com is the mapping model of comfort, R i is the input parameter at the i-th time step of the comfort mapping model, Com ref is the recommended value of indoor terminal comfort.

[0084] The power Pow model F(Ps, f, Pd,...) in the system model can be called, and the input parameters corresponding to each time step are input, including: the current state environment parameters and the estimated state environment parameters corresponding to the next two time steps, and the corresponding power exponent expression can be obtained and Therefore, according to the set power weight coefficients ω 11 、ω 12 and ω 13 , the power exponent expressions are weighted and added to obtain the total power exponent expression J Pow .

[0085] Similarly, the comfort model is called, and the input parameters corresponding to each time step are input, including: the current state environment parameters and the terminal target comfort, and the estimated state environment parameters and the terminal target comfort corresponding to the next two time steps. Therefore, the corresponding comfort index expressions can be obtained, which are respectively and Therefore, according to the set comfort weight coefficients ω 21 、ω 22 and ω 23 , the comfort index expressions are weighted and added to obtain the total comfort index expression J com .

[0086] Therefore, the current fitness function = J Pow -J com .

[0087] The model prediction of the fitness function will have a decrease in accuracy as the time step increases. Therefore, in some embodiments, the weight coefficients can be attenuated. That is, ω 11 、ω 12 , and ω 13 decrease in sequence. Similarly, ω 21 、ω22 and ω 23 also decrease in turn. It is necessary to ensure that ω 11 + ω 12 + ω 13 = 1, which also applies to ω 21 , ω 22 and ω 23 .

[0088] Step 503: Determine the current control parameter values according to the optimal solution of the current fitness function, and control the operation of the multi-connected air-conditioning system according to the current control parameter values.

[0089] The optimal solution of the current fitness function can be solved by a heuristic algorithm. According to the change combinations of the controllable parameters within the corresponding threshold ranges, seek the optimal combined solution that can meet the corresponding constraints. Therefore, in some embodiments, determining the current control parameter values includes: determining the boundary ranges of the control parameter values and intermediate variable values corresponding to the current fitness function; obtaining the intermediate variable values of the current fitness function and the corresponding optimal solutions through a heuristic algorithm; when the variable values and the corresponding optimal solutions are respectively within the corresponding boundary ranges, determine the optimal solutions as the corresponding current control parameter values.

[0090] Of course, when the variable values and the corresponding optimal solutions are not all within the corresponding boundary ranges, it is also necessary to re-determine the boundary ranges of the control parameter values and intermediate variable values corresponding to the current fitness function, and then continue to find the optimal solution until the variable values and the corresponding optimal solutions are respectively within the corresponding boundary ranges.

[0091] It can be seen that in the embodiments of the present disclosure, after obtaining the current state environment parameters of the multi-connected air-conditioning system, according to the system model between the air-conditioning state environment parameters and the controllable parameters, and the comfort model between the controllable parameters and the terminal indoor comfort, the current fitness function matching the current state environment parameters and the terminal target comfort can be estimated. And according to the optimal solution of the current fitness function, after determining the current control parameter values, the corresponding air-conditioning operation is performed. In this way, the comfort requirements of the terminal can be accurately met, that is, the actual load requirements at the terminal in the multi-connected air-conditioning system can be accurately fed back, and then a more accurate load supply can be provided, ensuring that the outdoor unit of the multi-connected air-conditioning system operates in the efficient range to the greatest extent, improving the control stability of the multi-connected air-conditioning system, and also reducing the additional energy consumption for stable regulation. And when estimating the current fitness function, the load requirements in the future time period are considered, and the load supply amounts and indoor comfort in each time period are balanced, so as to ensure that the outdoor unit of the multi-connected system operates in the efficient range to the greatest extent.

[0092] Next, the operation process will be integrated into specific embodiments to illustrate the multi-connected air-conditioning control process provided by the embodiments of the present invention.

[0093] In one embodiment of the present disclosure, as Figure 1 shown, the cloud server can communicate with the multi-connected air conditioning system. Moreover, after the cloud server obtains the historical state environment parameter data corresponding to the set time period, performs interpolation completion and alignment processing, and obtains the sample data for model training, it uses a matching model (such as a mechanism model, a data-driven model, etc.) to perform model training on the sample data, and respectively obtains the system model between the air conditioning state environment parameters and the controllable parameters, and the comfort model between the controllable parameters and the terminal indoor comfort.

[0094] Figure 6 FIG. is a schematic flowchart of a method for controlling a multi-connected air conditioning system provided by an embodiment of the present disclosure. As Figure 6 shown, the process of the multi-connected air conditioning control system includes:

[0095] Step 601: The cloud server obtains the current operating state parameters of the outdoor unit in the multi-connected air conditioning system and the current environment parameters in the terminal indoor of the multi-connected air conditioning system, and obtains the current state environment parameters.

[0096] The current state environment parameters include: the current operating state parameters of the outdoor unit, such as: current low pressure, current compressor frequency, current outdoor unit power, current cooling capacity, etc., and also include: the current environment parameters in the terminal indoor, such as: current indoor temperature, current outdoor temperature, current indoor humidity, current indoor CO 2 concentration, etc. The current state environment parameters of the multi-connected air conditioning system can be obtained through the multi-point sensors configured in the multi-connected air conditioning system and through local weather stations, etc.

[0097] Step 602: Based on the system model between the air conditioning state environment parameters and the controllable parameters, and the comfort model between the controllable parameters and the terminal indoor comfort, the cloud server estimates the current fitness function matching three time steps, as well as the boundary ranges corresponding to the control parameter values and the intermediate variable values respectively according to the current state environment parameters and the terminal target comfort.

[0098] The current fitness function matching three time steps can be estimated through formulas (1), (2), and (3).

[0099] Step 603: Through a heuristic algorithm, the cloud server obtains the intermediate variable value of the current fitness function and the corresponding optimal solution.

[0100] Step 604: Determine whether the intermediate variable value and the corresponding optimal solution are respectively within the corresponding boundary ranges? If so, execute Step 605, otherwise, return to Step 602.

[0101] If the intermediate variable values and the corresponding optimal solutions are not all within the corresponding boundary ranges, then 602 needs to be returned to reproduce the estimation of the current fitness function, as well as the boundary ranges corresponding to the control parameter values and the intermediate variable values respectively.

[0102] Step 605: The cloud server determines the optimal solutions as the corresponding current control parameter values respectively.

[0103] Step 606: The cloud server sends the current control parameter values to the multi-connected air-conditioning system for corresponding operation.

[0104] It can be seen that in this embodiment, after the cloud server obtains the current state environment parameters of the multi-connected air-conditioning system, it can estimate the current fitness function that matches the current state environment parameters and the terminal target comfort according to the system model between the air-conditioning state environment parameters and the controllable parameters, and the comfort model between the controllable parameters and the terminal indoor comfort. Then, according to the optimal solution of the current fitness function, the current control parameter values are determined and the corresponding air-conditioning operation is carried out. In this way, the comfort requirements of the terminal can be accurately met, that is, the actual load requirements at the terminal in the multi-connected air-conditioning system are accurately fed back, and then a more accurate load supply is provided, ensuring that the outdoor unit of the multi-connected air-conditioning system operates in the efficient range to the greatest extent, improving the stability of the control of the multi-connected air-conditioning system, and also reducing the additional energy consumption for stable regulation.

[0105] According to the above process for multi-connected air-conditioning control, a device for multi-connected air-conditioning control can be constructed.

[0106] Figure 7 It is a schematic structural diagram of a device for controlling a multi-connected air-conditioning system provided by an embodiment of the present disclosure. As Figure 7 shown, the device 700 for controlling a multi-connected air-conditioning system includes: an acquisition module 710, an estimation module 720, and an optimal control module 730.

[0107] The acquisition module 710 is configured to acquire the current state environment parameters of the multi-connected air-conditioning system.

[0108] The estimation module 720 is configured to estimate the current fitness function based on the system model between the air-conditioning state environment parameters and the controllable parameters, and the comfort model between the controllable parameters and the terminal indoor comfort, according to the current state environment parameters and the terminal target comfort.

[0109] The optimal control module 730 is configured to determine the current control parameter values according to the optimal solution of the current fitness function, and control the operation of the multi-connected air-conditioning system according to the current control parameter values.

[0110] In some embodiments, it further includes:

[0111] The first training module is configured to determine a first input parameter corresponding to the first state environment parameter of the multi-connected air conditioning system, and a first correlation relationship between the first state environment parameter and other state environment parameters, where the first input parameter includes one or more controllable parameters; perform model training on sample data including the historical state environment parameter data of the air conditioning system according to the first input parameter and the first correlation relationship to obtain the first state environment parameter model in the system model.

[0112] In some embodiments, it further includes:

[0113] The second training module is configured to construct a first mapping relationship between the controllable parameter and the terminal temperature and humidity parameter, and construct a second mapping relationship between the terminal temperature and humidity parameter and the terminal indoor comfort level; perform model training on sample data including the historical state environment parameter data of the air conditioning system according to the first mapping relationship and the second mapping relationship to obtain the comfort model.

[0114] In some embodiments, it further includes:

[0115] The preprocessing module is configured to obtain the historical state environment parameter data corresponding to the set time period, and perform interpolation completion and alignment processing to obtain the sample data for model training.

[0116] In some embodiments, the prediction module 720 includes:

[0117] The power prediction unit is configured to, according to the current state environment parameter, based on the system model, predict the power index expressions corresponding to one or more time steps respectively, and perform weighted addition on each power index expression according to the set power weight coefficient to obtain the total power index expression.

[0118] The comfort prediction unit is configured to, according to the current state environment parameter and the terminal target comfort level, based on the comfort model, predict the comfort index expressions corresponding to one or more time steps respectively, and perform weighted addition on each comfort index expression according to the set comfort weight coefficient to obtain the total comfort index expression.

[0119] The fitness prediction unit is configured to perform a subtraction operation on the total power index expression and the total comfort index expression to obtain the current fitness function.

[0120] In some embodiments, the optimal control module 730 is specifically configured to determine the boundary ranges of the control parameter values and intermediate variable values corresponding to the current fitness function; obtain the intermediate variable values of the current fitness function and the corresponding optimal solutions through a heuristic algorithm; in the case where the variable values and the corresponding optimal solutions are respectively within the corresponding boundary ranges, determine the optimal solutions as the corresponding current control parameter values.

[0121] It can be seen that in this embodiment, after training the system model between the air-conditioning state environmental parameters and the controllable parameters, and the comfort model between the controllable parameters and the terminal indoor comfort, the device for multi-connected air-conditioning control can, after obtaining the current state environmental parameters of the multi-connected air-conditioning, estimate the current fitness function that matches the current state environmental parameters and the terminal target comfort according to the system model and the comfort model, and determine the current control parameter value according to the optimal solution of the current fitness function, and then perform the corresponding air-conditioning operation. Thus, the comfort requirements of the terminal can be accurately met, that is, the actual load requirements at the terminal in the multi-connected air-conditioning system can be accurately fed back, and further a more accurate load supply can be provided, improving the stability of the multi-connected air-conditioning system control and reducing the additional energy consumption for stable regulation.

[0122] Combined with Figure 8 , this embodiment of the present disclosure provides a device 800 for multi-connected air-conditioning system control, including:

[0123] A processor 1000 and a memory 1001, and may further include a communication interface 1002 and a bus 1003. Among them, the processor 1000, the communication interface 1002, and the memory 1001 can complete mutual communication through the bus 1003. The communication interface 1002 can be used for information transmission. The processor 1000 can call the logic instructions in the memory 1001 to execute the method for multi-connected air-conditioning system control in the above embodiment.

[0124] In addition, when the logic instructions in the above-mentioned memory 1001 are implemented in the form of software function units and sold or used as an independent product, they can be stored in a computer-readable storage medium.

[0125] The memory 1001, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as the program instructions / modules corresponding to the methods in this embodiment of the present disclosure. The processor 1000 executes functional applications and data processing by running the program instructions / modules stored in the memory 1001, that is, implements the method for multi-connected air-conditioning system control in the above method embodiment.

[0126] The memory 1001 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the terminal device, etc. In addition, the memory 1001 may include a high-speed random access memory and may also include a non-volatile memory.

[0127] An embodiment of the present disclosure provides a control device for a multi-connected air-conditioning system, including: a processor and a memory storing program instructions, where the processor is configured to execute a multi-connected air-conditioning control method when executing the program instructions.

[0128] Combined with Figure 9 , an embodiment of the present disclosure provides a device 900, which can be a cloud server or a device in a multi-connected air-conditioning system, including: a device body, and the above-mentioned control device 700 (800) for the multi-connected air-conditioning system. The control device 700 (800) for the multi-connected air-conditioning system is installed on the device body. The installation relationship described here not only includes being placed inside the product, but also includes installation connections with other components of the product, including but not limited to physical connections, electrical connections, or signal transmission connections, etc. Those skilled in the art can understand that the control device 700 (800) for the multi-connected air-conditioning system can be adapted to a feasible device body, thereby implementing other feasible embodiments.

[0129] An embodiment of the present disclosure provides a storage medium storing program instructions, and when the program instructions are running, they execute the method for multi-connected air-conditioning control as described above.

[0130] An embodiment of the present disclosure provides a computer program product, where the computer program product includes a computer program stored on a storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer is made to execute the above-mentioned multi-connected air-conditioning control method.

[0131] The above storage medium can be a transient computer-readable storage medium or a non-transient computer-readable storage medium.

[0132] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The foregoing storage medium can be a non-transient storage medium, including: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes, or it can also be a transient storage medium.

[0133] The above description and drawings fully illustrate the embodiments of the present disclosure, enabling those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. Embodiments merely represent possible variations. Unless explicitly required, individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of the present disclosure includes the entire scope of the claims and all available equivalents of the claims. When used in this application, although terms such as "first", "second", etc. may be used in this application to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, without changing the meaning of the description, the first element may be called the second element, and similarly, the second element may be called the first element, as long as all occurrences of the "first element" are consistently renamed and all occurrences of the "second element" are consistently renamed. The first element and the second element are both elements, but they may not be the same element. Moreover, the terms used in this application are only for describing the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to also include the plural forms. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations including one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groupings of these. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, or device comprising the element. In this document, each embodiment may focus on the differences from other embodiments, and the same or similar parts among the embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, the relevant parts may refer to the description of the method part.

[0134] Those skilled in the art will realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner can depend on the specific application and design constraints of the technical solution. The skilled person can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present disclosure. The skilled person can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0135] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to implement this embodiment. Additionally, in the embodiments of the present disclosure, the functional units can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0136] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of code, or a portion thereof that contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending upon the functionality involved. In the description corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending upon the functionality involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for controlling a multi-connected air conditioning system, characterized in that, it includes: Obtain the current state environment parameters of the multi-connected air conditioning system; Based on the system model between the air conditioning state environment parameters and the controllable parameters, and the comfort model between the controllable parameters and the terminal indoor comfort, estimate the current fitness function according to the current state environment parameters and the terminal target comfort; According to the optimal solution of the current fitness function, determine the current control parameter value, and control the operation of the multi-connected air conditioning system according to the current control parameter value.

2. The method according to claim 1, characterized in that, it further includes: Determine the first input parameter corresponding to the first state environment parameter of the multi-connected air conditioning system, and the first correlation relationship between the first state environment parameter and other state environment parameters, wherein the first input parameter includes one or more controllable parameters; According to the first input parameter and the first correlation relationship, perform model training on the sample data including the historical state environment parameter data of the air conditioning system to obtain the first state environment parameter model in the system model.

3. The method according to claim 1, characterized in that, it further includes: Construct the first mapping relationship between the controllable parameters and the terminal temperature and humidity parameters, and construct the second mapping relationship between the terminal temperature and humidity parameters and the terminal indoor comfort; According to the first mapping relationship and the second mapping relationship, perform model training on the sample data including the historical state environment parameter data of the air conditioning system to obtain the comfort model.

4. The method according to claim 2 or 3, characterized in that, before performing the model training, it further includes: Obtain the historical state environment parameter data corresponding to the set time period, and perform interpolation, complementation and alignment processing to obtain the sample data for model training.

5. The method according to claim 1, characterized in that, the estimating the current fitness function includes: According to the current state environment parameters, based on the system model, estimate the power index expressions corresponding to one or more time steps respectively, and according to the set power weight coefficient, add the weights of each power index expression to obtain the total power index expression; According to the current state environment parameters and the terminal target comfort, based on the comfort model, estimate the comfort index expressions corresponding to one or more time steps respectively, and according to the set comfort weight coefficient, add the weights of each comfort index expression to obtain the total comfort index expression; Perform a subtraction operation on the total power index expression and the total comfort index expression to obtain the current fitness function.

6. The method according to any one of claims 1-3, 5, characterized in that, the determining the current control parameter value includes: Determine the boundary ranges of the control parameter values and intermediate variable values corresponding to the current fitness function; Through the heuristic algorithm, obtain the intermediate variable values of the current fitness function and the corresponding optimal solutions; In the case where the variable values and the corresponding optimal solutions are respectively within the corresponding boundary ranges, determine the optimal solutions as the corresponding current control parameter values.

7. A device for controlling a multi-connected air conditioning system, characterized in that, it includes: An acquisition module, configured to acquire the current state environment parameters of a multi-connected air-conditioning system; An estimation module, configured to estimate a current fitness function according to the current state environment parameters and the end target comfort level, based on a system model between the air-conditioning state environment parameters and controllable parameters, and a comfort model between the controllable parameters and the end indoor comfort level; An optimal control module, configured to determine a current control parameter value according to the optimal solution of the current fitness function, and control the operation of the multi-connected air-conditioning system according to the current control parameter value.

8. A device for controlling a multi-connected air-conditioning system, the device comprising a processor and a memory storing program instructions, wherein, the processor is configured to execute the method for controlling a multi-connected air-conditioning system according to any one of claims 1 to 6 when executing the program instructions.

9. A device, wherein, it includes: a device body; The device for multi-connected air-conditioning control according to claim 7 or 8 is installed on the device body.

10. A storage medium storing program instructions, wherein, the program instructions, when running, execute the method for controlling a multi-connected air-conditioning system according to any one of claims 1 to 6.

Images