Air conditioner control method and device, air conditioner and storage medium

Abstract

The invention relates to the technical field of intelligent household appliances, and discloses a method for controlling an air conditioner, which comprises the following steps: training a neural network model according to historical data obtained in advance to obtain a label prediction model; inputting the schedule of the prediction day and the preceding index parameter into a label prediction model to obtain a target clustering label; and performing load prediction according to a target derivation model corresponding to the target clustering tag. Since the schedule of the prediction day and the preceding index parameters can be obtained before the system runs, the load prediction can be carried out without waiting for the actual environmental parameters generated by the system running, and the system can carry out load prediction in time. The invention further discloses a device for controlling the air conditioner, the air conditioner and a storage medium.

Description

Technical Field

[0001] The present application relates to the technical field of smart home appliances, for example, to a method and device for controlling an air conditioner, an air conditioner, and a storage medium. Background Art

[0002] At present, the energy consumption of building air conditioning systems accounts for nearly half of the overall energy consumption of building operations. Overcooling often occurs in commercial office buildings, wasting energy while affecting the comfort experience. This phenomenon mainly stems from the high delay in the central air conditioning system's prediction of real-time load changes. Even if the optimal control strategy is pushed, the regulation is not timely. In order to solve this problem, advance control is introduced into the control strategy of the central air conditioning system, but in order for advance control to have a better effect, a more accurate load forecast value must be obtained.

[0003] Related technology discloses a load forecasting method based on meteorologically similar days, including the following steps: S10, statistically measured load data and corresponding meteorological data; S20, data preprocessing, including the elimination of missing data and abnormal data; data normalization of the load data after elimination; S30, clustering, classifying load days into different categories according to meteorological data to form meteorologically similar days; S40, establishing a support vector machine prediction model based on each moment of the known load in the category to which the meteorologically similar days belong; S50, training the support vector machine prediction model; S60, inputting the meteorological data of the day to be predicted into the trained support vector machine prediction model to obtain the load forecast of the day to be predicted. Based on cluster analysis, a regression prediction model is constructed using a support vector machine, and based on the idea of ​​cross-validation, the penalty parameters and kernel function parameters of the model are optimized, the prediction error is reduced, and the prediction accuracy is improved.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] Although the use of relevant technologies has improved the accuracy of load forecasting to a certain extent, in actual application, the system must wait for the system to run and generate actual environmental parameters before it can make load forecasts. There is still the problem of untimely system regulation, resulting in poor user experience.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] The embodiments of the present disclosure provide a method and device for controlling an air conditioner, an air conditioner, and a storage medium to avoid the situation where load forecasting must be performed only after the system is running and actual environmental parameters are generated, so that the system can perform load forecasting in a timely manner.

[0009] In some embodiments, the method includes: training a neural network model based on pre-acquired historical data to obtain a label prediction model; inputting the schedule and leading indicator parameters of the prediction day into the label prediction model to obtain a target cluster label; and performing load forecasting based on a target derivation model corresponding to the target cluster label.

[0010] In some embodiments, the device includes: a processor and a memory storing program instructions, and the processor is configured to execute the above-mentioned method for controlling an air conditioner when executing the above-mentioned program instructions.

[0011] In some embodiments, the air conditioner comprises:

[0012] Air conditioner body;

[0013] The above-mentioned device for controlling the air conditioner is installed on the air conditioner body.

[0014] In some embodiments, the storage medium stores program instructions, and when the program instructions are executed, the above-mentioned method for controlling the air conditioner is executed.

[0015] The method and device for controlling an air conditioner, the air conditioner, and the storage medium provided in the embodiments of the present disclosure can achieve the following technical effects:

[0016] The neural network model is trained based on the historical data acquired in advance to obtain the label prediction model, and the schedule and leading indicator parameters of the forecast day are input into the label prediction model to obtain the target cluster label. Finally, the load forecast is performed based on the target derivation model corresponding to the target cluster label. Since the schedule and leading indicator parameters of the forecast day can be obtained before the system is operated, the load forecast can be performed without waiting for the actual environmental parameters to be generated by the system operation, so that the system can perform load forecasting in a timely manner.

[0017] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0019] Figure 1 is a schematic diagram of a method for controlling an air conditioner provided by an embodiment of the present disclosure;

[0020] Figure 2 is a schematic diagram of another method for controlling an air conditioner provided by an embodiment of the present disclosure;

[0021] Figure 3 is a schematic diagram of another method for controlling an air conditioner provided by an embodiment of the present disclosure;

[0022] Figure 4 is a schematic diagram of another method for controlling an air conditioner provided by an embodiment of the present disclosure;

[0023] Figure 5 is a schematic diagram of a device for controlling an air conditioner provided by an embodiment of the present disclosure;

[0024] Figure 6 It is a schematic diagram of an air conditioner provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0026] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0027] Unless otherwise stated, the term "plurality" means two or more.

[0028] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0029] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0030] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0031] In the embodiments of the present disclosure, smart home appliances refer to home appliances that are formed by introducing microprocessors, sensor technology, and network communication technology into home appliances. They have the characteristics of intelligent control, intelligent perception, and intelligent application. The operation process of smart home appliances often relies on the application and processing of modern technologies such as the Internet of Things, the Internet, and electronic chips. For example, smart home appliances can be connected to electronic devices to enable users to remotely control and manage the smart home appliances.

[0032] In the disclosed embodiments, the terminal device refers to an electronic device with a wireless connection function. The terminal device can communicate with the above-mentioned smart home appliances by connecting to the Internet, or can communicate with the above-mentioned smart home appliances directly through Bluetooth, WiFi, etc. In some embodiments, the terminal device is, for example, a mobile device, a computer, or a vehicle-mounted device built into a hover car, or any combination thereof. Mobile devices may include, for example, mobile phones, smart home devices, wearable devices, smart mobile devices, virtual reality devices, etc., or any combination thereof, wherein wearable devices include, for example: smart watches, smart bracelets, pedometers, etc.

[0033] At present, the energy consumption of building air conditioning systems accounts for nearly half of the overall energy consumption of building operations. Overcooling often occurs in commercial office buildings, wasting energy while affecting the comfort experience. This phenomenon mainly stems from the high delay in the central air conditioning system's prediction of real-time load changes. Even if the optimal control strategy is pushed, the regulation is not timely. In order to solve this problem, advance control is introduced into the control strategy of the central air conditioning system, but in order for advance control to have a better effect, a more accurate load forecast value must be obtained. The related art discloses a load forecasting method based on meteorological similar days, which includes the following steps: S10, statistical measured load data and corresponding meteorological data; S20, data preprocessing, including the elimination of missing data and abnormal data; data normalization of the load data after elimination; S30, clustering, dividing the load days into different categories according to the meteorological data to form meteorological similar days; S40, establishing a support vector machine prediction model based on each moment of the known load in the category to which the meteorological similar day belongs; S50, training the support vector machine prediction model; S60, inputting the meteorological data of the day to be predicted into the trained support vector machine prediction model to obtain the load forecast of the day to be predicted. On the basis of cluster analysis, a regression prediction model is constructed using a support vector machine, and based on the idea of ​​cross-validation, the penalty parameters and kernel function parameters of the model are optimized, the prediction error is reduced, and the prediction accuracy is improved. Although the use of related technologies has improved the accuracy of load forecasting to a certain extent, in actual application, the system must wait for the system to run to generate actual environmental parameters before the system can perform load forecasting. There is still a problem of untimely system regulation, resulting in poor user experience.

[0034] Combination Figure 1 As shown, the embodiment of the present disclosure provides a method for controlling an air conditioner, comprising:

[0035] S01, the air conditioner trains a neural network model based on pre-acquired historical data to obtain a label prediction model.

[0036] S02, the air conditioner inputs the schedule and leading indicator parameters of the forecast day into the label prediction model to obtain the target cluster label.

[0037] S03, the air conditioner performs load forecasting according to a target derivation model corresponding to the target cluster label.

[0038] Among them, the leading indicator data include: average temperature, chilled water set temperature, cooling water set temperature, host start and stop time, whether it is a working day, number of months, light intensity, etc. Among them, the temperature and light intensity of the forecast day can be given by the open interface of the weather forecast, the chilled water set temperature, cooling water set temperature, host start and stop time, etc. are generally common parameters in the group control schedule for easy acquisition, and the number of months and whether it is a working day can be obtained through simple logical judgment. The above leading indicator parameters can all be obtained before the air conditioner host is turned on on the forecast day.

[0039] By adopting the method for controlling an air conditioner provided by the embodiment of the present disclosure, a neural network model is trained according to the historical data acquired in advance to obtain a label prediction model, and the schedule and leading indicator parameters of the prediction day are input into the label prediction model to obtain the target cluster label, and finally load prediction is performed according to the target derivation model corresponding to the target cluster label. Since the schedule and leading indicator parameters of the prediction day can be obtained before the system is run, load prediction can be performed without waiting for the actual environmental parameters to be generated by the system operation, so that the system can perform load prediction in a timely manner.

[0040] Combination Figure 2 As shown, the embodiment of the present disclosure provides a method for controlling an air conditioner, comprising:

[0041] S21, the air conditioner exports historical data from the cloud historical database.

[0042] S22, the air conditioner trains a neural network model based on historical data to obtain a label prediction model.

[0043] S02, the air conditioner inputs the schedule and leading indicator parameters of the forecast day into the label prediction model to obtain the target cluster label.

[0044] S03, the air conditioner performs load forecasting according to a target derivation model corresponding to the target cluster label.

[0045] Among them, the air conditioner trains the neural network model based on historical data to obtain a label prediction model, including: collecting historical data of the air conditioner, including parameters such as temperature, humidity, wind speed, and corresponding labels, that is, the power consumption of the air conditioner. The original historical data is converted into a data format suitable for training by using methods such as data cleaning, feature extraction, and data normalization. According to the characteristics and labels of the data set, a neural network model is constructed. Different neural network structures and activation functions, as well as optimization algorithms and loss functions can be selected here. Then the data set is divided into a training set, a validation set, and a test set, and the ratio usually used is 6:2:2. Then the neural network model is trained using the training set and verified on the validation set. The model parameters and hyperparameters are continuously adjusted to improve the accuracy of the model. Finally, the model is evaluated, and the performance of the model is evaluated on the test set. Various indicators, such as mean square error (MSE) and mean absolute error (MAE), are calculated to determine whether the model converges to evaluate the performance of the model. When the model convergence meets the judgment conditions, it is determined that the model is changed to a label prediction model.

[0046] Among them, the label prediction model is updated at set time intervals.

[0047] By using the method for controlling an air conditioner provided by the embodiment of the present disclosure, the air conditioner exports historical data from a cloud historical database, and trains a neural network model based on the historical data to obtain a label prediction model. In this way, the label prediction model is obtained through historical data training, so that cluster labels can be predicted before load forecasting on the forecast day, thereby obtaining matching target cluster labels to improve the accuracy of load forecasting.

[0048] Combination Figure 3 As shown, the embodiment of the present disclosure provides a method for controlling an air conditioner, comprising:

[0049] S01, the air conditioner trains a neural network model based on pre-acquired historical data to obtain a label prediction model.

[0050] S31, the air conditioner obtains the schedule and leading indicator parameters of the forecast day before starting the air conditioner.

[0051] S32, the air conditioner inputs the scheduling and leading indicator parameters into the label prediction model and outputs the target cluster label.

[0052] S03, the air conditioner performs load forecasting according to a target derivation model corresponding to the target cluster label.

[0053] By adopting the method for controlling an air conditioner provided by the embodiment of the present disclosure, the air conditioner obtains the schedule and leading indicator parameters of the forecast day before starting the air conditioner, inputs the schedule and leading indicator parameters into the label prediction model, and outputs the target cluster label. There is no need to wait until the air conditioner is running before performing load prediction. Before the air conditioner is started, the schedule and leading indicator parameters of the forecast day can be obtained in advance, and the label prediction model can be called to determine the target cluster label, so that the regulation is more timely.

[0054] Combination Figure 4 As shown, the embodiment of the present disclosure provides a method for controlling an air conditioner, comprising:

[0055] S01, the air conditioner trains a neural network model based on pre-acquired historical data to obtain a label prediction model.

[0056] S02, the air conditioner inputs the schedule and leading indicator parameters of the forecast day into the label prediction model to obtain the target cluster label.

[0057] S41, the air conditioner queries the target inference model corresponding to the target cluster label.

[0058] S42, the air conditioner inputs the load at the previous moment into the target derivation model to obtain the predicted load at the current moment.

[0059] Using the method for air conditioner control provided by the embodiment of the present disclosure, the air conditioner queries the target derivation model corresponding to the target cluster label, and inputs the load of the previous moment into the target derivation model to obtain the predicted load of the current moment. Since the target cluster label is obtained by inputting the label prediction model through the forecast day schedule and the leading indicator parameters of the forecast day, the target derivation model can be matched with the situation of the forecast day by matching the target derivation model corresponding to the target cluster label. On this basis, it is only necessary to input the load of the previous moment into the target derivation model to accurately predict the load of the next moment, and the load of the whole day of the forecast day can be accurately predicted through the target derivation model.

[0060] Optionally, the method for controlling an air conditioner further includes: the air conditioner adaptively clusters the daily load sequence according to an adaptive unsupervised clustering algorithm to obtain multiple cluster labels; the air conditioner determines a derivation model for each cluster label according to the daily load sequence of each cluster label.

[0061] In this way, the air conditioner adaptively clusters the daily load sequence according to the adaptive unsupervised clustering algorithm to obtain multiple cluster labels, and determines the derivation model of each cluster label according to the daily load sequence of each cluster label. Since cluster centers and upper and lower limits of the sequence of each category will be generated after clustering, adaptive clustering can take into account the performance attenuation of the system and make the results closer to the true value. At the same time, in subsequent predictions, the upper and lower limits obtained by adaptive clustering are very helpful in clearing the outliers of the prediction, and can ensure that the predicted value is within a reasonable range to a certain extent. Adaptive unsupervised clustering is to classify by rolling update of the sequence data source combined with unsupervised learning method. Since the definition of cluster labels is uncertain before the task starts, the adaptive unsupervised clustering algorithm can well improve the robustness of clustering.

[0062] Optionally, the air conditioner adaptively clusters the daily load sequence according to an adaptive unsupervised clustering algorithm to obtain multiple clustering labels, and further includes: the air conditioner preprocesses the cooling load data; the air conditioner converts the preprocessed single-point load sequence into a daily load sequence.

[0063] In this way, the air conditioner preprocesses the cooling load data and converts the preprocessed single-point load sequence into a daily load sequence. Since the sensors that collect environmental parameters will always have calibration and accuracy problems, and will always cause delays through internal calculations, protocol transmission, and data storage, and will bring relatively abnormal time series data when the equipment is started and stopped, by preprocessing the cooling load data on the daily load sequence, the daily load sequence after preprocessing the cooling load data can be made more accurate, thereby making the derivation model of each cluster label more accurate and improving the accuracy of load prediction.

[0064] Optionally, the air conditioner preprocesses the cooling load data, including: the air conditioner obtains the cooling load data from the data source; the air conditioner preprocesses the cooling load data by missing and over-limit processing, abnormal segment positioning, abnormal segment reconstruction and smoothing processing.

[0065] In this way, the air conditioner obtains the cooling load data from the data source, and pre-processes the cooling load data in sequence through missing and over-limit processing, abnormal segment positioning, abnormal segment reconstruction and smoothing processing, so that the daily load sequence after pre-processing of the cooling load data is more accurate, thereby making the derivation model of each clustering label more accurate, thereby improving the accuracy of load prediction.

[0066] In actual application, the air conditioner obtains cooling load data from the data source, and processes abnormal data in the cooling load data through simple statistical methods, such as box plot, equidistant outlier detection, Li Sanzhi test and other methods. Then, the abnormal time series data that needs to be reconstructed is located according to the start and stop time of the equipment, that is, the abnormal fragment. After locating the abnormal fragment that needs to be reconstructed, it is determined whether the mechanism model of the associated equipment is available. If the mechanism model of the associated equipment is available, the mechanism model of the associated equipment is applied to reconstruct the value of the abnormal fragment; if the mechanism model of the associated equipment is not available, the value of the abnormal fragment is reconstructed by using statistical methods, singular value decomposition or machine learning interpolation methods, and finally the reconstructed data is filtered and smoothed, thereby completing the cooling load data preprocessing process.

[0067] Optionally, the air conditioner converts the preprocessed single-point load sequence into a daily load sequence, including: the air conditioner classifies the preprocessed single-point load sequence according to date; the air conditioner sorts the load sequence of each date according to time to obtain a daily load sequence.

[0068] The air conditioner sorts the load sequence of each date according to time to obtain the daily load sequence. The air conditioner can also merge the load sequence of each date according to a set time interval and merge the load sequence of each date into a complete daily load sequence.

[0069] In this way, the air conditioner classifies the preprocessed single-point load sequence according to date, and sorts the load sequence of each date according to time to obtain a daily load sequence, which is convenient for subsequent clustering processing of the daily load sequence according to the adaptive unsupervised clustering algorithm, thereby avoiding repeated modeling of regular items for load forecasting.

[0070] Optionally, the air conditioner adaptively clusters the daily load sequence according to an adaptive unsupervised clustering algorithm to obtain multiple clustering labels, including: the air conditioner inputs the daily load sequence into an unsupervised clustering model, and outputs clustering labels, cluster centers, sequence upper limits and sequence lower limits.

[0071] Among them, the air conditioner will input the unsupervised clustering model according to the daily load sequence. After outputting the cluster label, cluster center, sequence upper limit and sequence lower limit, the clustering results of the unsupervised clustering model can also be clustered and visualized, and the daily load sequence can be associated with the clustering results after the visualization operation. Finally, the clustering results can be analyzed by regression analysis method.

[0072] In this way, since cluster centers and upper and lower limits of the sequence corresponding to each cluster label will be generated after clustering, adaptive clustering can take into account the performance degradation of the system and make the results closer to the true value. At the same time, in subsequent predictions, the upper and lower limits obtained by adaptive clustering are very helpful in removing abnormal values ​​in load forecasting, and to a certain extent ensure that the load forecasting results are within a reasonable range. Adaptive unsupervised clustering is to classify by rolling update of sequence data sources combined with unsupervised learning methods. Since the definition of cluster labels is uncertain before the task starts, adaptive unsupervised clustering can greatly improve the robustness of clustering.

[0073] Optionally, the air conditioner determines the inference model of each cluster label according to the daily load sequence of each cluster label, including: the air conditioner obtains the daily load sequence of each cluster label; the air conditioner determines the step size according to the error standard of the daily load sequence of each cluster label, and divides the input data set and the output data set; the air conditioner determines the inference model of each cluster label according to the step size, input data set and output data set of the daily sequence of each cluster label; the air conditioner divides the daily load sequence of each cluster label into a training data set and a test data set, and trains the inference model of each cluster label respectively; the air conditioner determines whether the inference model of each cluster label has reached convergence; the air conditioner determines that the inference model that has reached convergence is the inference model of the corresponding cluster label.

[0074] Among them, the inference model can be in the form of a parametric equation with a defined expression, for example, commonly used simple time series models such as autoregression (AR), moving average (MA), autoregression moving average (ARMA), and triple exponential smoothing (Holt-Winters).

[0075] In this way, the air conditioner determines the derivation model corresponding to each cluster label according to the daily load sequence of each cluster label, so that the derivation model can match the change of the daily load sequence of each cluster label. All daily load sequences of each cluster label are regarded as units, and each unit is trained separately to obtain the derivation model, which improves the accuracy of load forecasting.

[0076] Combination Figure 5 As shown, the embodiment of the present disclosure provides a device 300 for controlling an air conditioner, including a processor 301 and a memory 101. Optionally, the device may also include a communication interface 102 and a bus 103. The processor 301, the communication interface 102, and the memory 101 may communicate with each other through the bus 103. The communication interface 102 may be used for information transmission. The processor 301 may call the logic instructions in the memory 101 to execute the method for controlling an air conditioner of the above embodiment.

[0077] In addition, the logic instructions in the memory 101 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0078] The memory 101 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 301 executes the function application and data processing by running the program instructions / modules stored in the memory 101, that is, the method for controlling the air conditioner in the above embodiment is implemented.

[0079] The memory 101 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 101 may include a high-speed random access memory and may also include a non-volatile memory.

[0080] Combination Figure 6 As shown, an embodiment of the present disclosure provides an air conditioner 100, including: an air conditioner body, and the above-mentioned device 200 (300) for controlling the air conditioner. The device 200 (300) for controlling the air conditioner is installed in the air conditioner body. The installation relationship described here is not limited to placement inside the air conditioner, but also includes installation connections with other components of the air conditioner, including but not limited to physical connection, electrical connection or signal transmission connection, etc. It can be understood by those skilled in the art that the device 200 (300) for controlling the air conditioner can be adapted to a feasible air conditioner body, thereby realizing other feasible embodiments.

[0081] An embodiment of the present disclosure provides a storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the above-mentioned method for controlling an air conditioner.

[0082] The above-mentioned storage medium may be a transient storage medium or a non-transient storage medium.

[0083] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0084] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe 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, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of 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 groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0085] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0086] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which 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 may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0087] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for controlling an air conditioner, characterized in that: include: Train the neural network model based on the historical data acquired in advance to obtain a label prediction model; Input the schedule and leading indicator parameters of the forecast day into the label prediction model to obtain the target cluster label; Load forecasting is performed based on the target derivation model corresponding to the target cluster labels.

2. The method according to claim 1, characterized in that The step of training a neural network model based on pre-acquired historical data to obtain a label prediction model includes: Export historical data from the cloud historical database; Based on historical data, the neural network model is trained to obtain the label prediction model.

3. The method according to claim 1, characterized in that The scheduling and leading indicator parameters of the forecast day are input into the label forecasting model to obtain the target cluster label, including: Obtain the schedule and leading indicator parameters for the forecast day before the air conditioner is started; The scheduling and leading indicator parameters are input into the label prediction model, and the target cluster label is output.

4. The method according to claim 1, characterized in that: The load forecasting is performed according to the target derivation model corresponding to the target clustering label, including: Query the target inference model corresponding to the target cluster label; The load at the previous moment is input into the target derivation model to obtain the predicted load at the current moment.

5. The method according to any one of claims 1 to 4, characterized in that: Also includes: According to the adaptive unsupervised clustering algorithm, the daily load series are adaptively clustered to obtain multiple cluster labels; The derivation model of each cluster label is determined according to the daily load sequence of each cluster label.

6. The method according to claim 5, characterized in that Before the adaptive clustering of the daily load sequence is performed according to the adaptive unsupervised clustering algorithm to obtain multiple clustering labels, the method further includes: Preprocess cooling load data; The preprocessed single-point load series is converted into a daily load series.

7. The method according to claim 6, characterized in that The preprocessing of cooling load data includes: Get cooling load data from data source; The cooling load data is preprocessed by means of missing and over-limit processing, abnormal segment location, abnormal segment reconstruction and smoothing processing.

8. A device for controlling an air conditioner, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for controlling an air conditioner according to any one of claims 1 to 7 when running the program instructions.

9. An air conditioner, characterized in that: include: Air conditioner body; The device for controlling an air conditioner according to claim 8 is installed in the air conditioner body.

10. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the method for controlling an air conditioner according to any one of claims 1 to 7 is executed.

Images