Method and apparatus for air conditioner control, air conditioner, storage medium

Abstract

The application 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 a schedule of a prediction day and a leading index parameter into the label prediction model to obtain a target clustering label; and performing load prediction according to a target derivation model corresponding to the target clustering label. Since the schedule of the prediction day and the leading index parameter can be obtained before system operation, the load prediction can be performed without waiting for actual environmental parameters generated by the system operation, so that the system can timely perform the load prediction. The application further discloses a device for controlling the air conditioner, an air conditioner and a storage medium.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent household appliances, for example to a method and device for air conditioner control, an air conditioner and a storage medium. BACKGROUND

[0002] At present, the energy consumption of building air conditioning systems accounts for nearly half of the overall operation energy consumption of buildings, and overcooling often occurs in commercial office buildings, which not only wastes energy but also affects the comfort experience. This phenomenon mainly arises from the high delay in the prediction of real-time load changes by central air conditioning systems, and even if the optimal control strategy is pushed, the regulation and control is not timely. In order to solve this problem, advanced control is introduced into the control strategy of central air conditioning systems, but in order for the advanced control to have a good effect, a relatively accurate load prediction value must be obtained.

[0003] The related technology discloses a load prediction method based on meteorological similar days, including the following steps: S10, statistics of measured load data and corresponding meteorological data; S20, data preprocessing, including elimination of missing data and abnormal data; data normalization is performed on the load data after elimination; S30, clustering, according to the meteorological data, the load day is divided into different categories, forming the meteorological similar day; S40, based on each time of known load in the category to which the meteorological similar day belongs, a support vector machine prediction model is established; S50, the support vector machine prediction model is trained; S60, the meteorological data of the day to be predicted is input into the trained support vector machine prediction model, and the load prediction of the day to be predicted is obtained. Based on the clustering analysis, a regression prediction model is established by using a support vector machine, the penalty parameter and the kernel function parameter of the model are optimized based on the idea of cross-validation, 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 at least the following problems exist in the related technology:

[0005] Although the related technology improves the accuracy of load prediction to some extent, in actual application, the system can only perform load prediction after the actual environmental parameters are generated by system operation, and the problem of untimely system regulation and control still exists, resulting in poor user experience.

[0006] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present application, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] The following presents a simplified summary of some aspects of the disclosed embodiments in order to provide a basic understanding of such embodiments. This summary is not an extensive overview of the embodiments described in detail in the following detailed description, and is intended neither to identify key or critical elements of all embodiments nor to delineate the scope of any of the embodiments. Its sole purpose is to present some aspects of the disclosed embodiments in a simplified form as a prelude to the more detailed description that is presented later.

[0008] The embodiments of the present disclosure provide a method and device for air conditioner control, an air conditioner and a storage medium, so as to avoid the situation that the load prediction cannot be performed until the actual environmental parameters are generated after the system is operated, and enable the system to timely perform the load prediction.

[0009] In some embodiments, the method comprises: training a neural network model according to historical data acquired in advance to obtain a label prediction model; inputting a schedule of a prediction day and a leading indicator parameter into the label prediction model to obtain a target clustering label; and performing load prediction according to a target derivation model corresponding to the target clustering label.

[0010] In some embodiments, the device comprises: a processor and a memory storing program instructions, wherein the processor is configured to execute the method for air conditioner control when executing the program instructions.

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

[0012] an air conditioner body;

[0013] The device for air conditioner control is installed in the air conditioner body.

[0014] In some embodiments, the storage medium stores program instructions, and the program instructions perform the method for air conditioner control when executed.

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

[0016] The neural network model is trained according to the historical data acquired in advance to obtain the label prediction model, the schedule of the prediction day and the leading indicator parameter are input into the label prediction model to obtain the target clustering label, and finally the load prediction is performed according to the target derivation model corresponding to the target clustering label. Since the schedule of the prediction day and the leading indicator parameter can be acquired before the system is operated, the load prediction can be performed without waiting for the actual environmental parameters generated after the system is operated, so that the system can timely perform the load prediction.

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

[0018] One or more embodiments are illustrated by way of example in the figures that are not intended to be limiting of the embodiments. Like numbers refer to like elements throughout the drawings, which are not necessarily to scale, and in which:

[0019] Figure 1 is a schematic diagram of one method for air conditioner control provided by embodiments of the present disclosure;

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

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

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

[0023] Figure 5 is a schematic diagram of one apparatus for air conditioner control provided by embodiments of the present disclosure;

[0024] Figure 6 is a schematic diagram of one air conditioner provided by embodiments of the present disclosure. DETAILED DESCRIPTION

[0025] In order to enable every detailed understanding of the features and technical contents of the embodiments of the present disclosure, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the drawings for reference only, and not to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, through multiple details, a sufficient understanding of the disclosed embodiments is provided. However, one or more embodiments can still be implemented without these details. In other cases, for the sake of simplicity of the drawings, well-known structures and devices can be simplified.

[0026] The terms "first", "second", and the like in the description and claims of the present disclosure and the above drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0027] Unless otherwise specified, the term "a plurality of" means two or more.

[0028] In the embodiments of the present disclosure, the character " / " represents an "or" relationship between the objects before and after it. For example, A / B means A or B.

[0029] The term "and / or" is a description of an association relationship between objects, which means that there can be three relationships. For example, A and / or B means that there are three relationships of A or B, or A and B.

[0030] The term "corresponding" can refer to an association relationship or a binding relationship. A and B correspond to each other means that there is an association relationship or a binding relationship between A and B.

[0031] In the embodiments of the present disclosure, the smart home appliance refers to a home appliance product formed after introducing microprocessors, sensor technology, and network communication technology into home appliances, and has the characteristics of intelligent control, intelligent sensing, and intelligent application. The operation process of the smart home appliance often depends on the application and processing of modern technologies such as the Internet of Things, the Internet, and electronic chips. For example, the smart home appliance can realize remote control and management of the smart home appliance by the user through connection with electronic devices.

[0032] In the embodiments of the present disclosure, the terminal device refers to an electronic device with wireless connection function. The terminal device can be connected to the smart home appliance as described above through the Internet, or can be directly connected to the smart home appliance as described above through Bluetooth, Wi-Fi, and the like. In some embodiments, the terminal device is, for example, a mobile device, a computer, or a built-in vehicle device in a hovercar, or any combination thereof. The mobile device may, for example, include a mobile phone, a smart home device, a wearable device, a smart mobile device, a virtual reality device, or any combination thereof, wherein the wearable device may, for example, include a smart watch, a smart bracelet, a pedometer, and the like.

[0033] Currently, the energy consumption of building air conditioning system accounts for nearly half of the overall operation energy consumption of the building, and overcooling often occurs in commercial office buildings, which not only wastes energy but also affects the comfort experience. This phenomenon mainly arises from the high delay in the prediction of real-time load changes by the central air conditioning system, and even if the optimal control strategy is pushed, the regulation and control are not timely. In order to solve this problem, lead control is introduced into the control strategy of the central air conditioning system, but in order for the lead control to have a good effect, a relatively accurate load prediction value must be obtained. The related technology discloses a load prediction method based on meteorological similar days, including the following steps: S10, statistics of measured load data and corresponding meteorological data; S20, data preprocessing, including elimination of missing data and abnormal data; data normalization is performed on the load data after elimination; S30, clustering, according to the meteorological data, the load day is divided into different categories to form the meteorological similar day; S40, based on each time of the known load in the category to which the meteorological similar day belongs, a support vector machine prediction model is established; S50, the support vector machine prediction model is trained; S60, the meteorological data of the day to be predicted is input into the trained support vector machine prediction model to obtain the load prediction of the day to be predicted. On the basis of cluster analysis, a regression prediction model is established by using a support vector machine, based on the idea of cross-validation, the penalty parameter and the kernel function parameter of the model are optimized, the prediction error is reduced, and the prediction accuracy is improved. Although the related technology improves the accuracy of load prediction to some extent, in actual application, the system must wait for the actual environmental parameters generated by the system operation to perform load prediction, and the problem of untimely system regulation and control still exists, resulting in poor user experience.

[0034] In combination Figure 1 The embodiment of the present disclosure provides a method for controlling an air conditioner, which comprises the following steps:

[0035] S01, the air conditioner trains a neural network model according to historical data obtained in advance to obtain a label prediction model.

[0036] S02, the air conditioner inputs the schedule of the prediction day and the lead indicator parameter into the label prediction model to obtain a target clustering label.

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

[0038] The leading indicator data includes: average temperature, chilled water set temperature, cooling water set temperature, main machine start-stop time, whether it is a weekday, month number, light intensity, etc. The temperature and light intensity of the prediction day can be given by the open interface of the weather forecast, the chilled water set temperature, the cooling water set temperature, and the main machine start-stop time are generally common parameters in the group control schedule and are easy to obtain, and the month number and whether it is a weekday can be obtained through simple logical judgment. The above leading indicator parameters can be obtained before the air conditioner main machine is started on the prediction day.

[0039] The method for air conditioner control provided by the embodiment of the present disclosure is used to train the neural network model according to the historical data obtained in advance, obtain the label prediction model, input the schedule of the prediction day and the leading indicator parameters into the label prediction model, obtain the target clustering label, and finally perform load prediction according to the target derivation model corresponding to the target clustering label. Since the schedule of the prediction day and the leading indicator parameters can be obtained before the system runs, it is not necessary to wait for the actual environmental parameters generated by the system running to perform load prediction, so that the system can timely perform load prediction.

[0040] In combination with Figure 2 The embodiment of the present disclosure provides a method for air conditioner control, which comprises:

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

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

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

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

[0045] The air conditioner trains a neural network model according to historical data to obtain a label prediction model, including: collecting historical data of the air conditioner, including temperature, humidity, wind speed and other parameters, and corresponding labels, that is, power consumption of the air conditioner. The original historical data is converted into a data format suitable for training by using data cleaning, feature extraction, data normalization and other methods. According to the characteristics and labels of the data set, a neural network model is constructed. Here, different neural network structures and activation functions, as well as optimization algorithms and loss functions, can be selected. Then, the data set is divided into a training set, a validation set and a test set, and the commonly used ratio is 6:2:2. Then the training set is used to train the neural network model, and the validation set is used for validation. By continuously adjusting the model parameters and hyperparameters, the accuracy of the model is improved. Finally, the model is evaluated, and the performance of the model is evaluated on the test set, and 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 converges and meets the judgment condition, the model is determined as the label prediction model.

[0046] The label prediction model is updated at intervals.

[0047] The method for controlling the air conditioner provided by the embodiments of the present disclosure is used. The air conditioner exports historical data from a cloud historical database, and trains a neural network model according to the historical data to obtain a label prediction model. In this way, the label prediction model is trained by the historical data, so that the prediction of the cluster label can be performed before the load prediction on the prediction day, and the target cluster label matched is obtained to improve the accuracy of the load prediction.

[0048] In combination with Figure 3 The embodiments of the present disclosure provide a method for controlling an air conditioner, including:

[0049] S01, the air conditioner trains a neural network model according to the historical data obtained in advance to obtain a label prediction model.

[0050] S31, the air conditioner obtains the scheduling and the lead indicator parameter of the prediction day before the air conditioner starts.

[0051] S32, the air conditioner inputs the scheduling and the lead indicator parameter into the label prediction model to output a target cluster label.

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

[0053] The method for air conditioner control provided by the embodiment of the present disclosure is used to obtain the schedule and the leading indicator parameter of the prediction day before the air conditioner starts, input the schedule and the leading indicator parameter into the label prediction model, and output the target clustering label. The load prediction is not needed after the air conditioner runs, and the schedule and the leading indicator parameter of the prediction day are obtained in advance before the air conditioner starts, the label prediction model is called to determine the target clustering label, so that the regulation and control is more timely.

[0054] In combination with Figure 4 The embodiment of the present disclosure provides a method for air conditioner control, which comprises the following steps:

[0055] S01, the air conditioner trains the neural network model according to the historical data obtained in advance to obtain a label prediction model.

[0056] S02, the air conditioner inputs the schedule and the leading indicator parameter of the prediction day into the label prediction model to obtain a target clustering label.

[0057] S41, the air conditioner queries a target derivation model corresponding to the target clustering label.

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

[0059] The method for air conditioner control provided by the embodiment of the present disclosure is used to query the target derivation model corresponding to the target clustering label by the air conditioner, and input the load of the previous time into the target derivation model to obtain the predicted load of the current time. Since the target clustering label is obtained by inputting the schedule and the leading indicator parameter of the prediction day into the label prediction model, the target derivation model is matched with the target clustering label, so that the target derivation model can be matched with the situation of the prediction day. On this basis, only the load of the previous time is needed to be input into the target derivation model, so that the load of the next time can be accurately predicted, and the load of the whole day of the prediction day can be accurately predicted by the target derivation model.

[0060] Optionally, the method for air conditioner control further comprises: the air conditioner performs adaptive clustering on the per-day load sequence according to an adaptive unsupervised clustering algorithm to obtain a plurality of clustering labels; and the air conditioner determines a derivation model of each clustering label according to the per-day load sequence of each clustering label.

[0061] In this way, the air conditioner performs adaptive clustering on the daily load sequence according to the adaptive unsupervised clustering algorithm, obtains multiple clustering labels, and respectively determines a derivation model of each clustering label according to the daily load sequence of each clustering label. Since the clustering center and the upper and lower limits of each category sequence are generated after clustering, the adaptive clustering can consider the performance degradation of the system, so that the result is closer to the true value. At the same time, in subsequent prediction, the upper and lower limits obtained by adaptive clustering are helpful to eliminate abnormal values of prediction, and can ensure that the predicted value is within a reasonable range to a certain extent. Adaptive unsupervised clustering is to update the sequence data source in a rolling manner and classify by combining unsupervised learning method. Since the definition of the clustering label is uncertain before the task starts, the adaptive unsupervised clustering algorithm can well improve the robustness of clustering.

[0062] Optionally, before the air conditioner obtains multiple clustering labels by performing adaptive clustering on the daily load sequence according to the adaptive unsupervised clustering algorithm, the air conditioner further includes: the air conditioner pre-processes the cooling load data; and the air conditioner converts the pre-processed single-point load sequence into the daily load sequence.

[0063] In this way, the air conditioner pre-processes the cooling load data and converts the pre-processed single-point load sequence into the daily load sequence. Since the sensor for collecting environmental parameters always has problems of calibration and precision, and always causes delay through internal calculation and protocol transmission and data storage, and causes relatively abnormal time sequence data when the device starts and stops, the cooling load data is pre-processed through the daily load sequence, so that the daily load sequence after the cooling load data pre-processing is more accurate, thereby making the derivation model of each clustering label more accurate and improving the accuracy of load prediction.

[0064] Optionally, the air conditioner pre-processes the cooling load data, including: the air conditioner obtains the cooling load data from a data source; and the air conditioner pre-processes the cooling load data by sequentially performing 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 a data source and pre-processes the cooling load data by sequentially performing missing and over-limit processing, abnormal segment positioning, abnormal segment reconstruction and smoothing processing, so that the daily load sequence after the cooling load data pre-processing is more accurate, thereby making the derivation model of each clustering label more accurate and improving the accuracy of load prediction.

[0066] In actual application process, the air conditioner obtains the cooling load data from the data source, processes the abnormal data in the cooling load data through a simple statistical method, such as a box plot, an equal distance outlier detection, a Li Sanqi test and the like. Then, the abnormal time sequence data, i.e. an abnormal segment, to be reconstructed is located according to the start and stop time of the equipment. After locating the abnormal segment to be reconstructed, it is judged 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 segment. If the mechanism model of the associated equipment is not available, a statistical method, singular value decomposition or a machine learning interpolation method and the like are adopted to reconstruct the value of the abnormal segment. Finally, the reconstructed data is filtered and smoothed, so as to complete 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 dates; and the air conditioner sorts the load sequence of each date according to time to obtain the daily load sequence.

[0068] Optionally, after the air conditioner sorts the load sequence of each date according to time to obtain the daily load sequence, the air conditioner can further 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 dates, and sorts the load sequence of each date according to time to obtain the daily load sequence, which facilitates subsequent clustering processing of the daily load sequence according to the adaptive unsupervised clustering algorithm, thereby avoiding repeated modeling of regular items for load prediction.

[0070] Optionally, the air conditioner performs adaptive clustering on the daily load sequence according to the adaptive unsupervised clustering algorithm to obtain a plurality of clustering labels, including: the air conditioner inputs the daily load sequence into an unsupervised clustering model to output clustering labels, clustering centers, sequence upper limits and sequence lower limits.

[0071] Optionally, after the air conditioner inputs the daily load sequence into the unsupervised clustering model to output clustering labels, clustering centers, sequence upper limits and sequence lower limits, the air conditioner can further perform clustering visualization operation on the clustering results of the unsupervised clustering model, and associate the daily load sequence with the clustering results after the visualization operation. Finally, the air conditioner can further analyze the clustering results through a regression analysis method.

[0072] In this way, adaptive clustering can consider the performance degradation of the system and make the result closer to the true value due to the generation of cluster centers and the upper and lower limits of the sequence corresponding to each cluster label after clustering. Meanwhile, the upper and lower limits obtained by adaptive clustering are helpful for removing abnormal values in load prediction, which ensures the load prediction result within a reasonable range to a certain extent. Adaptive unsupervised clustering is to update the sequence data source in a rolling manner and classify by combining unsupervised learning method. Since the definition of the cluster label is uncertain before the task starts, adaptive unsupervised clustering can well improve the robustness of clustering.

[0073] Optionally, the air conditioner determines the derivation 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 length 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 derivation formula model of each cluster label according to the step length, the input data set and the 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 derivation formula model of each cluster label respectively; the air conditioner determines whether the derivation formula model of each cluster label reaches convergence; and the air conditioner determines that the derivation formula model reaching convergence as the derivation model of the corresponding cluster label.

[0074] The form of the derivation formula model can be a parameter equation of a defined expression, for example, autoregressive (AR), moving average (MA), autoregressive moving average (ARMA), cubic exponential smoothing (Holt-Winters), and other commonly used time series simple models.

[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 as to match the derivation model with the change of the daily load sequence of each cluster label. Each cluster label is regarded as a unit, and each unit is trained separately to obtain the derivation model, thereby improving the accuracy of load prediction.

[0076] In combination with Figure 5 As shown in FIG. 10, the embodiment of the present disclosure provides a device 300 for air conditioner control, which includes a processor 301 and a memory 101. Optionally, the device can also include a communication interface 102 and a bus 103. The processor 301, the communication interface 102, and the memory 101 can complete mutual communication through the bus 103. The communication interface 102 can be used for information transmission. The processor 301 can call the logical instructions in the memory 101 to execute the method for air conditioner control of the above-mentioned embodiments.

[0077] In addition, the logic instructions in the memory 101 described above can be implemented in the form of a software function unit and sold or used as an independent product, which can be stored in a computer readable storage medium.

[0078] The memory 101 as a computer readable storage medium can be used to store software programs, computer executable programs, such as program instructions / modules corresponding to the method in the embodiments of the present disclosure. The processor 301 executes the program instructions / modules stored in the memory 101, thereby performing functional applications and data processing, that is, implementing the method for air conditioner control in the above embodiments.

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

[0080] In combination Figure 6 As shown in the figure, the embodiments of the present disclosure provide an air conditioner 100, which includes an air conditioner body and the above-mentioned device 200 (300) for air conditioner control. The device 200 (300) for air conditioner control is installed on the air conditioner body. The installation relationship described herein is not limited to being placed in the air conditioner, but also includes installation connection with other components of the air conditioner, including but not limited to physical connection, electrical connection or signal transmission connection, etc. Those skilled in the art can understand that the device 200 (300) for air conditioner control can be adapted to a feasible air conditioner body, and thus realize other feasible embodiments.

[0081] The embodiments of the present disclosure provide a storage medium, which stores computer executable instructions, and the computer executable instructions are set to execute the above-mentioned method for air conditioner control.

[0082] The storage medium described above can be a transitory storage medium or a non-transitory storage medium.

[0083] The technical solutions of the embodiments of the present disclosure can be embodied in the form of a software product. The 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 disclosed in the embodiments of the present disclosure. The aforementioned storage medium can be a non-transitory storage medium, including: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes, or can be a transitory storage medium.

[0084] The above description and drawings sufficiently illustrate the embodiments of the present disclosure to enable one skilled in the art to practice them. Other embodiments can include structural, logical, electrical, process, and other changes. The embodiments represent only a few of the possible variations. Individual components and functions are optional unless explicitly required, and the order of operations can be changed. Parts and features of some embodiments can be included in or replace parts and features of other embodiments. Also, the words used in this application are used only to describe the embodiments and not to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly requires otherwise, the singular forms "a," "an," and "the" are intended to include the plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listed items. In addition, when used in this application, the term "comprise" and its variations "comprises" and / or comprises" and the like mean the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. Without more limitations, the element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, or device including the stated element. In this document, each embodiment focuses on the differences from other embodiments, and the same or similar parts between embodiments can be referred to each other. For the method, product, etc. disclosed in the embodiments, if it corresponds to the method part disclosed in the embodiments, the relevant part can be referred to the description of the method part.

[0085] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods for each specific application to realize the described functions, but such implementation should not be considered beyond 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 above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0086] 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 above-described device embodiments are only schematic, for example, the division of the units can only be a logical function division, and actual implementation can have another division manner, for example, a plurality of 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 the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms. The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to implement the embodiments. In addition, each functional unit in the embodiments of the present disclosure can be integrated in one processing unit, or each unit can be a physically independent unit, or two or more units can be integrated in one unit.

[0087] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

Claims

1. A method for air conditioner control, characterized by, The method comprises the following steps: training a neural network model according to historical data obtained in advance to obtain a label prediction model; inputting a schedule of a prediction day and a leading index parameter into the label prediction model to obtain a target clustering label; performing load prediction according to a target derivation model corresponding to the target clustering label; wherein the leading index parameter comprises average temperature, chilled water set temperature, cooling water set temperature, main machine start-stop time, whether it is a working day, month number, and light intensity, and the temperature and light intensity of the prediction day are given by an open interface of a weather forecast; the load prediction according to the target derivation model corresponding to the target clustering label comprises: querying the target derivation model corresponding to the target clustering label; inputting a load at a previous time into the target derivation model to obtain a predicted load at a current time.

2. The method of claim 1, wherein, The method comprises the following steps: exporting historical data from a cloud historical database; training a neural network model according to the historical data to obtain a label prediction model.

3. The method of claim 1, wherein, The method comprises the following steps: obtaining the schedule of the prediction day and the leading index parameter before starting the air conditioner; inputting the schedule and the leading index parameter into the label prediction model to output the target clustering label.

4. The method according to any one of claims 1 to 3, characterized in that, The method further comprises the following steps: performing adaptive clustering on a day-by-day load sequence according to an adaptive unsupervised clustering algorithm to obtain a plurality of clustering labels; determining a derivation model of each clustering label according to the day-by-day load sequence of each clustering label.

5. The method of claim 4, wherein, Before the step of performing adaptive clustering on the day-by-day load sequence according to the adaptive unsupervised clustering algorithm to obtain a plurality of clustering labels, the method further comprises the following steps: preprocessing the cold load data; converting the single-point load sequence after preprocessing into a day-by-day load sequence.

6. The method of claim 5, wherein, The method comprises the following steps: obtaining the cold load data from a data source; preprocessing the cold load data in the order of missing and out-of-limit processing, abnormal segment positioning, abnormal segment reconstruction, and smoothing processing.

7. An apparatus for air conditioner control comprising a processor and a memory having stored therein program instructions, the apparatus characterized by: The processor is configured to execute the method for air conditioner control according to any one of claims 1 to 6 when the program instructions are run.

8. An air conditioner characterized by comprising: The device comprises: an air conditioner body; the device for air conditioner control according to claim 7 is installed on the air conditioner body.

9. A storage medium storing program instructions, characterized in that, The program instructions are run to execute the method for air conditioner control according to any one of claims 1 to 6.

Images