US20240288191A1

US20240288191A1 - Method for controlling air conditioner, and electronic device and computer-readable storage medium

Info

Publication number: US20240288191A1
Application number: US18/564,029
Authority: US
Inventors: Xing Fang; Yuanyang LI; Jiongpei HU; Jie Yan; Jing Sun; Rui Liang
Original assignee: Shanghai Kong Intelligent Building Co Ltd; GD Midea Heating and Ventilating Equipment Co Ltd
Current assignee: Shanghai Kong Intelligent Building Co Ltd; GD Midea Heating and Ventilating Equipment Co Ltd
Priority date: 2021-09-30
Filing date: 2022-05-06
Publication date: 2024-08-29
Also published as: CN113739390A; WO2023050814A1; EP4328506A4; CN113739390B; EP4328506A1

Abstract

A method includes obtaining temperature data and humidity data of an air conditioner, inputting a mode of the air conditioner, a prediction type of the air conditioner, the temperature data, and the humidity data into a pre-trained prediction model, and controlling a startup or a shutdown of the air conditioner based on a predicted time output by the prediction model. The mode of the air conditioner includes at least one of a cooling mode or a heating mode, the prediction type of the air conditioner includes at least one of a startup-time prediction or a shutdown-time prediction, parameters of the prediction model include an indoor set temperature, an indoor set temperature threshold value, an indoor set humidity, and an indoor set humidity threshold value, and the predicted time includes at least one of a predicted startup time or a predicted shutdown time.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese patent application No. 202111163463.6, filed on Sep. 30, 2021, and entitled “method and apparatus for controlling air conditioner, and electronic device,” the entire contents of which are incorporated herein by reference.

TECHNICAL FIELD

The present application relates to the field of air conditioner technologies, and more particularly, to a method for controlling an air conditioner, an apparatus for controlling an air conditioner, and an electronic device.

BACKGROUND

In a commercial scenario, startup and shutdown of an air conditioner is generally completed through manual operation of property management staff, that is, the property management staff manually turns on the air conditioner before the workers come to the building to work, and manually turns off the air conditioner after the workers leave. With this control method that completely depends on manual control, workers sometimes complain because the air conditioner is not turned on in time, or energy may be wasted because the air conditioner is forgotten to be turned off.
With the promotion and application of a building management system (BMS, which is also referred to as a building automatic control system), the control method of starting up and shutting down the air conditioner manually by the property staff has been partially replaced by a time schedule control of the BMS, that is, startup and shutdown times of the air conditioner are preset in the BMS and the air conditioner is automatically started up or shut down according to the preset startup and shutdown times. However, the time schedule control method still has a certain defect, the startup and shutdown times of the air conditioner in the time schedule is set manually according to experience. If the air conditioner is started up too early, an indoor temperature is too low, and a waste of energy consumption is caused. If an air conditioner system is started up too late, the indoor temperature during the business hours is too high.
Therefore, the two control methods of the air conditioner cannot adjust the startup and shutdown times according to the change of the actual load of the building, and thus there exists problems of large energy consumption, waste of energy and poor thermal comfort of the air conditioner.

SUMMARY

In view of this, the present application provides a method and an apparatus for controlling an air conditioner, and an electronic device, which aims at conserving energy consumption of the air conditioner, an occurrence of waste of energy would not be caused, and a good thermal adaptability is realized.
Some embodiments of the present application provide a method for controlling an air conditioner, which is applied to a controller of the air conditioner. the method for controlling the air conditioner includes: obtaining temperature data and humidity data of the air conditioner, wherein the temperature data includes an indoor temperature and an outdoor temperature, the humidity data includes indoor humidity and outdoor humidity; inputting a mode of the air conditioner, a prediction type of the air conditioner, the temperature data and the humidity data into a pre-trained prediction model of the air conditioner, and outputting a predicted time of the air conditioner; where the mode of the air conditioner includes a cooling mode and/or a heating mode; the prediction type of the air conditioner includes a startup-time prediction and/or a shutdown-time prediction; parameters of the prediction model includes an indoor set temperature, an indoor set temperature threshold value, indoor set humidity and an indoor set humidity threshold value; the predicted time includes a predicted startup time and/or a predicted shutdown time; and controlling a startup or a shutdown of the air conditioner based on the predicted time.
In some optional embodiments of the present application, the step of obtaining the temperature data and the humidity data of the air conditioner may include: obtaining a first current time; and obtaining temperature data and humidity data of the air conditioner, in response to the first current time reaches a preset determination time.
In some optional embodiments of the present application, if the prediction type of the air conditioner is the startup-time prediction, the predicted startup time of the air conditioner may be determined by using a computational formula which is expressed as
$Δ t_{open} = c_{1} \cdot (T_{in} - T_{set} - T_{comp}) + c_{2} \cdot (T_{out} - T_{set} - T_{comp}) + c_{3} \cdot ({RH}_{in} - {RH}_{set} - {RH}_{comp}) + c_{4} ({RH}_{out} - {RH}_{set} - {RH}_{comp});$
where, Δt_openrepresents the predicted startup time, c₁-c₄represent preset coefficients for the startup-time prediction, T_inrepresents the indoor temperature, RH_inrepresents the indoor humidity, T_outrepresents the outdoor temperature, RH_outrepresents the outdoor humidity, T_setrepresents the indoor set temperature, RH_setrepresents the indoor set humidity, T_comprepresents the indoor set temperature threshold value, and RH_comprepresents the indoor set humidity threshold value; in response to the prediction type of the air conditioner is the shutdown-time prediction, the predicted shutdown time of the air conditioner may be determined by using a computational formula which is expressed as:
$Δ t_{close} = d_{1} \cdot (T_{in} - T_{set} - T_{comp}) + d_{2} \cdot (T_{out} - T_{set} - T_{comp}) + d_{3} \cdot ({RH}_{in} - {RH}_{set} - {RH}_{comp}) + d_{4} \cdot ({RH}_{out} - {RH}_{set} - {RH}_{comp});$

- wherein, Δt_closerepresents the predicted shutdown time, d1-d4 represent predetermined coefficients for the shutdown-time prediction.

In some optional embodiments of the present application, after the step of outputting the predicted time of the air conditioner, the method for controlling the air conditioner may further include: using, in response to the predicted time is greater than a preset upper limit value of the startup time or the shutdown time, the upper limit value as the predicted time; or using, in response to the predicted time is less than a lower limit value of the startup time or the shutdown time, the lower limit value as the predicted time.
In some optional embodiments of the present application, the step of controlling the startup or the shutdown of the air conditioner based on the predicted time may include: obtaining a second current time; and calculating a time difference between the second current time and a preset business-open time or a preset close-of-business time, and controlling the air conditioner to be powered on or powered-off, in response to the time difference is smaller than or equal to the predicted startup time or the predicted shutdown time.
In some optional embodiments of the present application, after obtaining the predicted startup time Δt_openis obtained, a time difference Δt between the second current time and the business-open time is calculated in real time and the time difference Δt is compared with the predicted startup time Δt_open, continue to wait if a condition of Δt>Δt_openis met; or a startup instruction is sent to the air conditioner in order that the air conditioner starts to operate if a condition of Δt≤Δt_openis met.
In some optional embodiments of the present application, after the predicted shutdown time Δt_closeis obtained, a time difference Δt between the second current time and the close-of-business time is calculated in real time and the time difference Δt is compared with the predicted shutdown time Δt_close, continue to wait if a condition of Δt>Δt_closeis met; or alternatively, a startup instruction is sent to the air conditioner in order that the air conditioner starts to operate if a condition of Δt≤Δt_closeis met.
In some optional embodiments of the present application, after the step of controlling the startup or the shutdown of the air conditioner based on the predicted time, the method for controlling the air conditioner further includes: determining a temperature-reaching time of the air conditioner; and adjusting the parameters of the prediction model based on the temperature-reaching time.
In some optional embodiments of the present application, the step of determining the temperature-reaching time of the air conditioner includes: determining a startup time of the air conditioner in response to the prediction type of the air conditioner is the startup-time prediction; obtaining a third current time if the indoor temperature is greater than or equal to a sum of the indoor set temperature and the indoor set temperature threshold value; and taking a difference value between the third current time and the startup time as the temperature-reaching time; or alternatively, determining the shutdown time of the air conditioner in response to the prediction type of the air conditioner is the shutdown-time prediction; obtaining a fourth current time if the indoor temperature is less than or equal to a sum of the indoor set temperature and the indoor set temperature threshold value; and taking a difference value between the fourth current time and the shutdown time as the temperature-reaching time.
In some optional embodiments of the present application, the step of adjusting the parameters of the prediction model based on the temperature-reaching time includes: determining a first absolute value of a difference value between the temperature-reaching time and the predicted startup time if the prediction type of the air conditioner is the startup-time prediction, and adjusting the parameters of the prediction model if the first absolute value is greater than a preset first error threshold value; or alternatively, determining a second absolute value of a difference between the temperature-reaching time and the predicted shutdown time in response to the prediction type of the air conditioner is the shutdown-time prediction; and adjusting the parameters of the prediction model in response to the second absolute value is greater than a preset second error threshold value.
In some optional embodiments of the present application, the step of adjusting the parameters of the prediction model based on the temperature-reaching time includes: obtaining historical temperature data and historical humidity data of the air conditioner within a preset time range; and adjusting the parameters of the prediction model based on the historical temperature data and the historical humidity data.
In some optional embodiments of the present application, the controller of the air conditioner is arranged in the air conditioner; as an alternative, the controller of the air conditioner is arranged in a server being in communication connection with the air conditioner.
An apparatus for controlling an air conditioner is further provided in some other embodiments of the present application. The apparatus is applied to a controller of the air conditioner, and may include: a data acquisition module configured to obtain temperature data and humidity data of the air conditioner, where the temperature data includes an indoor temperature and an outdoor temperature, the humidity data comprises indoor humidity and outdoor humidity; a time prediction module configured to input a mode of the air conditioner, a prediction type of the air conditioner, the temperature data and the humidity data into a pre-trained prediction model of the air conditioner, and output a predicted time of the air conditioner, where the mode of the air conditioner includes a cooling mode and/or a heating mode; the prediction type of the air conditioner includes a startup-time prediction and/or a shutdown-time prediction, parameters of the prediction model include an indoor set temperature, an indoor set temperature threshold value, indoor set humidity and an indoor set humidity threshold value, the predicted time includes a predicted startup time and/or a predicted shutdown time; an air conditioner control module configured to control a startup or a shutdown of the air conditioner based on the predicted time.
An electronic device is further provided in some other embodiments of the present application, this electronic device may include a processor and a memory, the memory may store a computer-executable instruction executable by the processor, the processor is configured to execute the computer-executable instruction so as to implement the aforesaid method for controlling the air conditioner.
A computer-readable storage medium is further provided in some other embodiments of the present application. The computer-readable storage medium may store a computer-executable instruction, that, when being invoked and executed by a processor, causes the processor to implement the aforesaid method for controlling the air conditioner.
The embodiments of the present application may at least have the following beneficial effects:
According to the method and the apparatus for controlling the air conditioner and the electronic device provided by the embodiment of the present application, the mode, the prediction type, the temperature data and the humidity data of the air conditioner are input into the pre-trained prediction model of the air conditioner, the predicted time of the air conditioner is output, and the startup or the shutdown of the air conditioner is controlled based on the predicted time. In this way, the predicted startup time and the predicted shutdown time of the air conditioner are predicted through the prediction model, energy consumption of the air conditioner may be saved, an occurrence of waste of energy would not be caused, and the air conditioner has a good thermal adaptability.
Other features and benefits of the present application will be illustrated in the following description. Alternatively, some of the features and benefits may be deduced or unambiguously determined from the description or be obtained by implementing the above-mentioned technical solutions of the present application.
In order to make the above objective, the features and the benefits of the present application to be more obvious and more comprehensible, preferable embodiments are provided as examples below with reference to the accompanying drawings, and are described in detail below.

DESCRIPTION OF THE DRAWINGS

In order to explain the technical solution in the embodiments of the present application or in the related art, a brief introduction regarding the accompanying drawings that need to be used for describing the embodiments or the related art is given below. It is obvious that the accompanying drawings described below are only some embodiments of the present application, for the person of ordinary skill in the art, other drawings may also be obtained according to the current drawings without paying creative labor.

FIG. 1 illustrates a schematic flow diagram of one method for controlling an air conditioner according to one embodiment of the present application;

FIG. 2 illustrates a schematic flow diagram of another method for controlling an air conditioner according to one embodiment of the present application;

FIG. 3 illustrates a schematic diagram of a method for controlling an air conditioner based on a startup-time prediction according to one embodiment of the present application;

FIG. 4 illustrates a schematic diagram of a method for controlling an air conditioner based on a shutdown-time prediction according to one embodiment of the present application;

FIG. 5 illustrates a schematic diagram of a curve of startup time according to one embodiment of the present application;

FIG. 6 illustrates a schematic structural diagram of one apparatus for controlling an air conditioner according to one embodiment of the present application;

FIG. 7 illustrates a schematic structural diagram of another apparatus for controlling an air conditioner according to one embodiment of the present application;

FIG. 8 illustrates a schematic structural diagram of an electronic device according to one embodiment of the present application.

DETAILED DESCRIPTION OF EMBODIMENTS

In order to make the objective, the technical solutions and the benefits of the present application be clearer, the technical solutions in the embodiments of the present application will be described clearly and comprehensively. It is apparent that, the embodiments described below are only some embodiments of the present application, instead of all of the embodiments. Based on the embodiments in the present application, other embodiments which are obtained by a person of ordinary skill in the art without paying creative labors, should all be included in the protection scope of the present application.
Currently, a method for controlling an air conditioner in a public building includes two approaches for controlling startup and shutdown of the air conditioner, that is, manually operating by a property staff and setting a time schedule, both of the two approaches cannot adjust startup time and shutdown time according to the change of the actual load of the building, and problems of large energy consumption, problems of waste of energy and poor thermal comfort of the air conditioner exist. In view of this, a method and an apparatus for controlling an air conditioner, and an electronic device provided in the embodiments of the present application may be applied to a startup and shutdown controller of an air conditioner having a self-learning function, and may calculate a cooling or heating temperature change rate of the air conditioner according to parameters such as indoor and outdoor temperature and humidity of the latest several days, and predict an early startup time or an early shutdown time for the air conditioner according to the temperature change rate, thereby achieving an effect of automatic optimization of the startup and shutdown of the air conditioner without human intervention.
In order to facilitate understanding of the embodiments of the present application, firstly, a method for controlling an air conditioner disclosed in the embodiments of the present application is described in detail.
A method for controlling an air conditioner is provided in one embodiment of the present application, this method is applied to a controller of the air conditioner. With reference to the flow diagram of the method for controlling the air conditioner shown in FIG. 1 , the method for controlling the air conditioner may include the following steps:
In a step of S102, temperature data and humidity data of the air conditioner are obtained.
The temperature data in this embodiment may include an indoor temperature and an outdoor temperature, and the humidity data may include indoor humidity and outdoor humidity. The air conditioner in this embodiment may be a central air-conditioning. As an alternative, the air conditioner may also be other types of air conditioners other than the central air-conditioning. The air conditioner is taken as the central air conditioner as an example in this embodiment, and details are not repeatedly described herein. The controller of the air conditioner may be disposed in the air conditioner, and may also be disposed in a server being in communication connection with the air conditioner. Where, the server may be a cloud server, and may also be a physical server, the server is not limited in this embodiment.
The main function of the air conditioner is to ensure the temperature of the indoor environment by processing indoor cold load or heat load, and the main parameters that affect the cooling or heating rate of the air conditioner is the indoor temperature, the indoor humidity, the outdoor temperature, the outdoor humidity, flow density and heating quantities of devices. Since the flow density and the heating quantities of devices are the parameters being difficult to be obtained. Regarding a commercial office building, it can be considered that the flow density and the heating parameters of devices are fixed parameters before the business hours or before the close of business every day. Therefore, the indoor temperature, the indoor humidity, the outdoor temperature, and the outdoor humidity are the parameters that actually affect the cooling or heating rate of the air conditioner. The outdoor temperature and the outdoor humidity may be directly obtained from a database of the server, and the indoor temperature and the indoor humidity may be collected by a temperature sensor and a humidity sensor arranged in the air conditioner.
In a step of S104, a mode of the air conditioner, a prediction type, the temperature data and the humidity data of the air conditioner are input into a pre-trained prediction model of the air conditioner, and a predicted time of the air conditioner is output.
Where, the mode of the air conditioner in this embodiment may include a cooling mode and/or a heating mode, the prediction type of the air conditioner may include a startup-time prediction and/or a shutdown-time prediction. The parameters of the prediction model of the air conditioner may include: an indoor set temperature, an indoor set temperature threshold value, indoor set humidity, and an indoor set humidity threshold value. The predicted time may include a predicted startup time and/or a predicted shutdown time.
In this embodiment, the startup time and the shutdown time of the air conditioner may be predicted, which are respectively referred to as the predicted startup time and the predicted shutdown time. If the air conditioner is in the startup-time prediction, the predicted startup time may be output, if the air conditioner is in the shutdown-time prediction, the predicted shutdown time may be output. In addition, when the air conditioner is in different modes, the numerical values of the parameters of the prediction model of the air conditioner may be the same or be different, the parameters of the prediction model of the air conditioner are not limited herein.
In a step of S106, the air conditioner is controlled to start up or shut down based on the predicted time.
Thus, after the predicted time is determined, the controller may control the startup or shutdown of the air conditioner according to the predicted time. The output predicted time in this embodiment may be a specific time point, or may be a time duration.
For example, if the controller determines that the predicted startup time is a specific time point 8, the air conditioner may be controlled to start up at the time point 8 o'clock. If the controller determines that the predicted shutdown time is 18 o'clock, the air conditioner may be controlled to shut down at 18 o'clock.
For another example, if the controller determines that the predicted startup time is 1 hour, the air conditioner may be controlled to start up at 8 o'clock according to the time when the employees should come to work and the predicted startup time, after previously determining that the time when the employees should come to work is 9 o'clock.
According to the method for controlling the air conditioner provided in this embodiment of the present application, the mode, the prediction type, the temperature data and the humidity data of the air conditioner are input into the pre-trained prediction model of the air conditioner to output the predicted time of the air conditioner, and the startup or the shutdown of the air conditioner is controlled based on the predicted time. In this way, the predicted startup time and the predicted shutdown time of the air conditioner are predicted through the prediction model, thus, energy consumption of the air conditioner may be saved, an occurrence of waste of energy would not be caused, and the air conditioner has a good thermal adaptability.
Another method for controlling an air conditioner is provided in another embodiment of the present application, this method is implemented on the basis of the aforesaid embodiment. With reference to the flow diagram of the method for controlling the air conditioner shown in FIG. 2 , the method for controlling the air conditioner in this embodiment may include the following steps:
In a step of S202, the temperature data and the humidity data of the air conditioner are obtained.
Regarding the method for the controlling air conditioner based on the startup-time prediction and the method for the controlling air conditioner based on the shutdown-time prediction, reference can be made to schematic diagram of the method for controlling the air conditioner based on the prediction of the startup time as shown in FIG. 3 and the schematic diagram of the method for controlling the air conditioner based on the shutdown-time prediction shown in FIG. 4 . In this embodiment, this embodiment is explained first by taking FIG. 3 as an example, and then is explained by taking FIG. 4 as an example, details of this embodiment will not be repeatedly described again.
As shown in FIG. 3 and FIG. 4 , the temperature data and the humidity data of the air conditioner may be obtained after a time on the time axis reaches a preset determination time. For example, a first current time is obtained, the temperature data and the humidity data of the air conditioner are obtained if the first current time reaches the preset determination time.
As shown in FIG. 3 , a time module in the controller may obtain a first current time t, compare the first current time t with a preset determination time T₀in real time, and continue to wait if the first current time t is less than the preset determination time T₀, or trigger an early startup control if the first current time is equal to the preset determination time T₀(i.e., the first current time reaches the preset determination time).
As shown in FIG. 4 , a time module in the controller may obtain a first current time t, compare the first current time t with a preset determination time T₀in real time, and continue to wait if the first current time t is less than the preset determination time T₀, or trigger an early shutdown control if the first current time is equal to the preset determination time T₀(i.e., the first current time reaches the preset determination time).
In a step of S204, the mode of the air conditioner, the prediction type, the temperature data and the humidity data of the air conditioner are input into a pre-trained prediction model of the air conditioner, and a predicted time of the air conditioner is output.
As mentioned above, for the commercial office building, it can be considered that before the business hours or before the close of business every day, the flow density and the heating quantities of devices are fixed parameters, and the indoor temperature, the indoor humidity, the outdoor temperature and the outdoor humidity are the remaining parameters that actually influence the cooling rate or the heating rate of the air conditioner. For a cooling scenario, it is obvious that, the higher the indoor temperature and the outdoor temperature, the greater the sensible heat load to be processed by the air conditioner, and the longer the required cooling time. The higher the indoor humidity and the outdoor humidity, the greater the latent heat load to be processed by the air conditioner, and the longer the required cooling time. The cooling scenario is in contrast to the heating scenario.
Thus, the predicted startup time of the air conditioner may be represented by the following computational formula:
$Δ t_{open} = f_{1} (T_{in}, {RH}_{in}, T_{out}, {RH}_{out}, T_{set}, {RH}_{set}, T_{comp}, {RH}_{comp}) .$
Where, Δt_openrepresents a predicted startup time, and Δt_openis a time duration rather than a moment of time. T_inrepresents the indoor temperature, RH_inrepresents the indoor humidity, T_outrepresents the outdoor temperature, RH_outrepresents the outdoor humidity, T_setrepresents the indoor set temperature, RH_setrepresents the indoor set humidity, T_comprepresents the indoor set temperature threshold value, and RH_comprepresents the indoor set humidity threshold value.
Herein, it should be noted that, for the indoor set temperature T_set, the cooling mode may be set to 1° C., the heating mode may be set to −1° C. The indoor set temperature T_setreflects a tolerance of a person on the deviation of the indoor temperature. For the indoor set humidity threshold value RH_comp, the cooling mode may be set to 10%, the heating mode may be set to −10%, and the indoor set humidity threshold value RH_compreflects the tolerance of the person on the deviation of the indoor humidity.
The aforesaid function may be expressed as the form of a variety of equations. Considering that the computing power of a controller chip is limited, a form of multivariate linear equation: that is, if the prediction type of the air conditioner is the startup-time prediction, the predicted startup time of the air conditioner is determined by using the following computational formula.
$Δ t_{open} = c_{1} \cdot (T_{in} - T_{set} - T_{comp}) + c_{2} \cdot (T_{out} - T_{set} - T_{comp}) + c_{3} \cdot ({RH}_{in} - {RH}_{set} - {RH}_{comp}) + c_{4} ({RH}_{out} - {RH}_{set} - {RH}_{comp});$
C₁-C₄in the above computational formula is a preset coefficient for the startup-time prediction, and may be preset in the controller:
Early shutdown of the air conditioner is a reverse process of early startup of the air conditioner. The air conditioner is shut down in advance by utilizing the indoor tolerable temperature deviation and humidity deviation, the indoor temperature is maintained till close-of-business time by utilizing cold storage or heat storage of the building. Thus, the energy consumption of the air conditioner is conserved, the early shutdown time of the air conditioner may be represented by the following computational formula expressed below:
$Δ t_{close} = f_{2} (T_{in}, {RH}_{in}, T_{out}, {RH}_{out}, T_{set}, {RH}_{set}, T_{comp}, {RH}_{comp}) .$
In the above formula, Δt_closerepresents a predicted early shutdown time of the air conditioner, and Δt_closeis a time duration rather than a moment of time. Other parameters are the same as the parameters described above:
The aforesaid function is also expanded into the form of multivariate linear equation: that is, in response to the prediction type of the air conditioner is the shutdown-time prediction, the predicted shutdown time of the air conditioner is determined through the following computational formula which is expressed as:
$Δ t_{close} = d_{1} \cdot (T_{in} - T_{set} - T_{comp}) + d_{2} \cdot (T_{out} - T_{set} - T_{comp}) + d_{3} \cdot ({RH}_{in} - {RH}_{set} - {RH}_{comp}) + d_{4} \cdot ({RH}_{out} - {RH}_{set} - {RH}_{comp});$
Where, Δt_closerepresents the predicted shutdown time, d₁-d₄represent the preset coefficients of shutdown-time prediction that can be preset in the controller.
As shown in FIG. 3 , the early startup time is calculated, and the controller may collect and record the indoor temperature and humidity and the outdoor temperature and humidity at the current time, and calculate the early startup time Δt_openaccording to early startup-time prediction equation. However, there exists an upper limit value and a lower limit value for the early startup time, that is, the air conditioner cannot be started up too early or too late. Therefore, if the predicted time is greater than an upper limit value of the preset startup time or the preset shutdown time, the upper limit value is used as the predicted time. If the predicted time is less than the lower limit value of the startup time or the shutdown time, the lower limit value is taken as the predicted time.
Taking the predicted time as time duration as an example, taking the startup as an example, if the predicted startup time is 1 hour, however, the lower limit value of the startup time is 30 minutes, the predicted time is less than the lower limit value of the startup time, so that the lower limit value can be used as the predicted time.
The condition of shutdown is similar to the condition of startup, as shown in FIG. 4 , the early shutdown time is calculated, the controller collects and records indoor temperature and humidity and outdoor temperature and humidity at the current time, and calculates the early startup time Δt_closeaccording to the early startup-time prediction equation. If Δt_closeexceeds an upper limit value Δt_maxof the shutdown time, Δt_close=Δt_max; if Δt_closeis less than the lower limit value Δt_minof the shutdown time, Δt_close=Δt_min.
In a step of S206, the air conditioner is controlled to start up or shut down based on the predicted time.
Taking the predicted time as the time duration as an example. As shown in FIG. 3 and FIG. 4 , when the controller controls the startup or shutdown of the air conditioner, the controller may first perform a step of determining whether the air conditioner is started up, such as obtaining a second current time; and calculating a time difference between the second current time and a preset business-open time or a preset close-of-business time, controlling the air conditioner to be started up or shut down if the time difference is less than or equal to the predicted startup time or the predicted shutdown time.
As shown in FIG. 3 , whether the air conditioner is to be started up is determined. The controller calculates a time difference Δt between the second current time t and the business-open time t_onin real time after the predicted startup time is obtained, and compares the time difference Δt with the predicted startup time Δt_open. If a condition of Δt>Δt_openis met, it indicates that the startup time is not reached currently, and the controller continues to wait; if a condition of Δt≤Δt_openis met, it indicates that the startup time is reached, the controller sends a startup instruction to the air conditioner, so that the air conditioner starts to operate.
As shown in FIG. 4 , whether the air conditioner is to be started up is determined. When the predicted shutdown time Δt_closeis obtained, the controller calculates a time difference Δt between the second current time t and a close-of-business time t_offin real time, and compares the time difference Δt with the Δt_close. If a condition of Δt>Δt_closeis met, it indicates that the shutdown time is not reached currently, and the controller continues to wait; If a condition of Δt≤Δt_closeis met, it indicates that the shutdown time is reached, the controller sends a shutdown instruction to the air conditioner, and the air conditioner stops operation.
In a step of S208, a temperature-reaching time of the air conditioner is determined.
How the controller controls the startup and shutdown of the air conditioner has been described in the above steps. However, the prediction model in the air conditioner may be self-learned, and the parameters thereof may be adjusted. That is, the coefficients in the startup-time prediction equation and the shutdown-time prediction equation of the air conditioner is not fixed. As shown in FIG. 3 and FIG. 4 , whether the parameter needs to be adjusted needs to be determined first, then, the parameters are adjusted. The temperature-reaching time may be determined through the following steps: the step of determining the temperature-reaching time of the air conditioner includes:

- the startup time of the air conditioner is determined, if the prediction type of the air conditioner is the startup-time prediction; a third current time is obtained, if the indoor temperature is greater than or equal to the sum of the indoor set temperature and the indoor set temperature threshold value; the difference value between the third current time and the startup time is used as the temperature-reaching time.

As shown in FIG. 3 , the temperature-reaching time is calculated. The controller may collect the indoor temperature in real time, determine that the indoor temperature is greater than or equal to the sum of the indoor set temperature and the indoor set temperature threshold value, the indoor temperature T_in=indoor set temperature T_set+the indoor set temperature threshold value T_comp. If the indoor temperature is greater than or equal to the sum of the indoor set temperature and the indoor set temperature threshold value, a third current time t₂is recorded, the temperature-reaching time Δt_r=the third current time t₂−the startup time t₁. Otherwise, the controller continues to wait.
In response to the prediction type of the air conditioner is the shutdown-time prediction, the shutdown time of the air conditioner is determined. If the indoor temperature is less than or equal to the sum of the indoor set temperature and the indoor set temperature threshold value, a fourth current time is obtained; and a difference value between the fourth current time and the shutdown time is used as the temperature-reaching time.
According to the temperature-reaching time as shown in FIG. 4 , the controller may collect the indoor temperature in real time, determine that the indoor temperature is less than or equal to the sum of the indoor set temperature and the indoor set temperature threshold value. The indoor temperature T_in=indoor set temperature T_set+the indoor set temperature threshold value T_comp. If the indoor temperature is less than or equal to the sum of the indoor set temperature and the indoor set temperature threshold value, the third current time t₂is recorded, the temperature-reaching time Δt_r=the third current time t₂-close-of-business time t₁. Otherwise, the controller continues to wait.
In a step of S210, the parameters of the prediction model are adjusted based on the temperature-reaching time.
If a time deviation between the temperature-reaching time and the predicted startup time or the predicted shutdown time is great, the parameters of the prediction model may be adjusted. For example, a first absolute value of a difference value between the temperature-reaching time and the predicted startup time is determined if the prediction type of the air conditioner is the startup-time prediction; the parameters of the prediction model are adjusted if the first absolute value is greater than a preset first error threshold value. As an alternative, a second absolute value of a difference between the temperature-reaching time and the predicted shutdown time is determined in response to the prediction type of the air conditioner is the shutdown-time prediction; the parameters of the prediction model is adjusted in response to the second absolute value is greater than a preset second error threshold value.
The first error threshold value and the second error threshold value may be the same or be different. The first error threshold value and the second error threshold value are not limited in this embodiment.
The coefficient of the prediction equation is self-learned and updated as shown in FIG. 3 . An error between the temperature-reaching time Δt_rand the predicted startup time Δt_openis compared. If |Δt_r−Δt_open|≤the first error threshold value, the coefficient of the prediction equation is not updated. If |Δt_r−Δt_open|>the first error threshold value, the coefficient of the prediction equation is updated according to the historical indoor temperature and humidity, in combination with the outdoor temperature and humidity and the actual temperature-reaching time.
The coefficient of the prediction equation is self-learned and updated as shown in FIG. 4 . An error between the temperature-reaching time Δt_rand the predicted shutdown time Δt_closeis compared. If |Δt_r−Δt_close|<the second error threshold value, the coefficient of the prediction equation is not updated. If |Δt_r−Δt_close|>the second error threshold value, the coefficient of the prediction equation is updated according to the historical indoor temperature and humidity, in combination with the outdoor temperature and humidity and the actual temperature-reaching time.
When performing the step of adjusting the parameters of the prediction model, parameter adjustment may be performed according to the historical temperature data and the historical humidity data of the air conditioner. For example, the historical temperature data and the historical humidity data of the air conditioner within a preset time range are obtained; and the parameters of the prediction model are obtained based on the historical temperature data and the historical humidity data.
The parameters of the prediction model in the controller are not fixed because that the building load changes with the change of the outdoor meteorological parameter. Thus, the parameters of the prediction model should also be self-learned and adjusted over time, thereby adapting to the change of the load and ensuring the accuracy of the predicted time. Taking the early startup of the air conditioner as an example, the parameters of the prediction model need to be updated, and four simultaneous equations can be established for solution. Thus, the controller needs to record at least the indoor temperature and humidity values and the outdoor temperature and humidity values in four consecutive days, and perform adaptive updating on the four coefficients every day, updating of the coefficient of the equation of the startup-time prediction is expressed as follows:
${\begin{matrix} Δ t_{r, k} = d_{1} \cdot (T_{in, k} - T_{set} - T_{comp}) + d_{2} \cdot (T_{out, k} - T_{set} - T_{comp}) + d_{3} \cdot ({RH}_{in, k} - {RH}_{set} - {RH}_{comp}) + d_{4} \cdot ({RH}_{out, k} - {RH}_{set} - {RH}_{comp}) \\ Δ t_{r, k - 1} = d_{1} \cdot (T_{in, k - 1} - T_{set} - T_{comp}) + d_{2} \cdot (T_{out, k - 1} - T_{set} - T_{comp}) + d_{3} \cdot ({RH}_{in, k - 1} - {RH}_{set} - {RH}_{comp}) + d_{4} \cdot ({RH}_{out, k - 1} - {RH}_{set} - {RH}_{comp}) \\ Δ t_{r, k - 2} = d_{1} \cdot (T_{in, k - 2} - T_{set} - T_{comp}) + d_{2} \cdot (T_{out, k - 2} - T_{set} - T_{comp}) + d_{3} \cdot ({RH}_{in, k - 2} - {RH}_{set} - {RH}_{comp}) + d_{4} \cdot ({RH}_{out, k - 2} - {RH}_{set} - {RH}_{comp}) \\ Δ t_{r, k - 3} = d_{1} \cdot (T_{in, k - 3} - T_{set} - T_{comp}) + d_{2} \cdot (T_{out, k - 3} - T_{set} - T_{comp}) + d_{3} \cdot ({RH}_{in, k - 3} - {RH}_{set} - {RH}_{comp}) + d_{4} \cdot ({RH}_{out, k - 3} - {RH}_{set} - {RH}_{comp}) \end{matrix}} .$
In the above equation, Δt_rrepresents the actual temperature-reaching time of the air conditioner (i.e., the time when the indoor temperature reaches T_set+T_comp), the subscript k represents today, k−1 represents yesterday, k−2 represents a day before yesterday, and k−3 represents three days ago. The controller implements the self-learning and updating of the coefficient of the prediction equation by collecting the indoor temperature and humidity values, the outdoor temperature and humidity values, and the temperature-reaching time of the air conditioner in four consecutive days.
In addition, it should be noted that the controller of the air conditioner may be disposed in the air conditioner. As an alternative, the controller of the air conditioner may be disposed in a server being in communication connection with the air conditioner. The controller of the air conditioner may be composed of a time module, a signal collection module, a memory module, and a prediction module. Where, the time module may be configured to collect the current time. In order to ensure the accuracy of time, time may be automatically synchronized each time when the time module performs network connection with a principle computer. The signal collection module may be configured to collect indoor temperature and humidity and indoor temperature and humidity parameters. The memory module may be configured to record indoor temperature and humidity, indoor temperature and humidity parameters in consecutive few days at a preset determination moment, and some preset parameters of the controller, such as a cooling target temperature, a heating target temperature, a preset temperature threshold value, an business-open time, a close-of-business time, a preset determination time, an earliest startup time, a latest startup time, a time error threshold value, etc. The prediction module may be configured to calculate a predicted startup time or a predicted shutdown time according to a pre-programmed startup and shutdown-time prediction equation based on temperature and humidity parameters transmitted from the collection module.
In addition, regarding the result of the method for controlling the air conditioner provided in this embodiment, reference can be made to the schematic diagram of the curve of the startup time shown in FIG. 5 . FIG. 5 illustrates a startup time of the method for controlling the air conditioner provided in this embodiment used by a combined air conditioner in one building, a curve 1 is the actual pre-cooling time, and a curve 2 is a predicted pre-cooling time. It can be seen from FIG. 5 that the coefficient of the prediction equation is optimized by self-learning, and there is little error between the predicted cooling time and the actual pre-cooling time, which indicates that the energy consumption of the combined air conditioner can be reduced in maximum while the indoor temperature is effectively ensured.
In conclusion, a method for predicting optimized startup and shutdown times of the air conditioner in different modes according to indoor and outdoor temperatures, humidity, and preset temperature in the room in the consecutive few days are provided in the embodiments of the present application. Thus, the indoor temperature at the business-open time or the close-of-business time does not exceed a preset threshold range, and energy consumption of the air conditioner may be furthest saved. In this method, the prediction model of the air conditioner can self-learn adjustment parameters with the change of the building load, thereby ensuring the accuracy of the predicted time. One embodiment of the present application further provides a controller having an air conditioner startup- and shutdown-time prediction function. The controller is composed of the time module, the signal acquisition module, the memory module and the prediction module, not only a personnel operation is unnecessary, it does not need to access a BMS group control system, either. Thus, a local optimization startup and shutdown control of the air conditioner can be realized. Certainly, it is also possible that the controller is not disposed in the air conditioner, this function may be implemented by writing an optimization control algorithm into the principle computer or a cloud platform.
According to the method provided in the embodiments of the present application, the early startup or shutdown time of the air conditioner in the cooling/heating scenario may be predicted according to the indoor and outdoor air temperature and humidity parameters, in order that the indoor temperature at business-open time is just within the preset temperature range, and the air conditioner is shut down before the close-of-business time, large fluctuation of the temperature is not caused, so that the energy consumption during the operation of the air conditioner is furthest reduced. Moreover, the prediction model may self-learn adjustment parameters with the change of the building load, thereby ensuring the accuracy of the predicted time. The calculation of prediction is absolutely completed by a local controller, without the assistance of the principle computer or the cloud platform. It is convenient to operate and use this method, and investment cost is saved.
Corresponding to the aforesaid method embodiments, another embodiment of the present application provides an apparatus for controlling air conditioner, which is applied to a controller of the air conditioner. Referring to a schematic structural diagram of the apparatus for controlling the air conditioner shown in FIG. 6 , the apparatus for controlling the air conditioner may include:

- a data acquisition module 61 configured to obtain temperature data and humidity data of the air conditioner, where the temperature data includes an indoor temperature and an outdoor temperature, the humidity data includes indoor humidity and outdoor humidity;
- a time prediction module 62 configured to input a mode of the air conditioner, a prediction type of the air conditioner, the temperature data and the humidity data into a pre-trained prediction model of the air conditioner, and output a predicted time of the air conditioner; where the mode of the air conditioner includes a cooling mode and/or a heating mode; the prediction type of the air conditioner includes a startup-time prediction and/or a shutdown-time prediction; parameters of the prediction model include an indoor set temperature, an indoor set temperature threshold value, indoor set humidity and an indoor set humidity threshold value; the predicted time includes a predicted startup time and/or a predicted shutdown time;
- an air conditioner control module 63 configured to control a startup or a shutdown of the air conditioner based on the predicted time.

According to the apparatus for controlling the air conditioner provided by the embodiment of the present application, the mode, the prediction type, the temperature data and the humidity data of the air conditioner may be input into the pre-trained prediction model of the air conditioner, the predicted time of the air conditioner is output, and the startup or the shutdown of the air conditioner is controlled based on the predicted time. In this way, the predicted startup time and the predicted shutdown time of the air conditioner are predicted through the prediction model, so that the energy consumption of the air conditioner may be saved, occurrence of waste of energy would not be caused, and the air conditioner has a good thermal adaptability.
The data acquisition module may be configured to obtain a first current time, and obtain temperature data and humidity data of the air conditioner in response to the first current time reaches a preset determination time.
The time prediction module may be configured to determine, if the prediction type of the air conditioner is the startup-time prediction, the predicted startup time of the air conditioner by using a following computational formula which is expressed as:
$Δ t_{open} = c_{1} \cdot (T_{in} - T_{set} - T_{comp}) + c_{2} \cdot (T_{out} - T_{set} - T_{comp}) + c_{3} \cdot ({RH}_{in} - {RH}_{set} - {RH}_{comp}) + c_{4} ({RH}_{out} - {RH}_{set} - {RH}_{comp});$
where, Δt_openrepresents the predicted startup time, c₁-c₄represent a preset coefficient for the startup-time prediction, T_inrepresents the indoor temperature, RH_inrepresents the indoor humidity, T_outrepresents the outdoor temperature, RH_outrepresents the outdoor humidity, T_setrepresents the indoor set temperature, RH_setrepresents the indoor set humidity, T_comprepresents the indoor set temperature threshold value, RH_comprepresents the indoor set humidity threshold value.
The time prediction module is further configured to determine, in response to the prediction type of the air conditioner is the shutdown-time prediction, the predicted shutdown time of the air conditioner by using the following computational formula which is expressed as:
$Δ t_{close} = d_{1} \cdot (T_{in} - T_{set} - T_{comp}) + d_{2} \cdot (T_{out} - T_{set} - T_{comp}) + d_{3} \cdot ({RH}_{in} - {RH}_{set} - {RH}_{comp}) + d_{4} \cdot ({RH}_{out} - {RH}_{set} - {RH}_{comp});$
where, Δt_closerepresents the predicted shutdown time, and d₁-d₄represent predetermined coefficients for the shutdown-time prediction.
The time prediction module may further be configured to use an upper limit value as the predicted time if the predicted time is greater than the preset upper limit value of the startup time or the shutdown time, and use a lower limit value as the predicted time if the predicted time is less than the lower limit value of the startup time or the shutdown time.
The air conditioner control module may be configured to obtain a second current time; and calculate a time difference between the second current time and a preset business-open time or a close-of-business time, and control the air conditioner to be started up or shut down if the time difference is less than or equal to the predicted startup time or the predicted shutdown time.
Referring to another structural schematic diagram of another apparatus for controlling an air conditioner shown in FIG. 7 , the apparatus for controlling the air conditioner may further include: a model updating module 64 which may be connected to the air conditioner control module 63. The model updating module 64 may be configured to determine a temperature-reaching time of the air conditioner, and adjust parameters of the prediction model based on the temperature-reaching time.
The model updating module may be configured to: determine a startup time of the air conditioner in response to the prediction type of the air conditioner is the startup-time prediction; obtain a third current time if the indoor temperature is greater than or equal to a sum of the indoor set temperature and the indoor set temperature threshold value; and use a difference value between the third current time and the startup time as the temperature-reaching time; or determine the shutdown time of the air conditioner in response to the prediction type of the air conditioner is the shutdown-time prediction, obtain a fourth current time if the indoor temperature is less than or equal to a sum of the indoor set temperature and the indoor set temperature threshold value, and use a difference value between the fourth current time and the shutdown time as the temperature-reaching time.
The model updating module may be configured to: determine a first absolute value of a difference value between the temperature-reaching time and the predicted startup time if the prediction type of the air conditioner is the startup-time prediction, and adjust the parameters of the prediction model if the first absolute value is greater than a preset first error threshold value; or determine a second absolute value of a difference between the temperature-reaching time and the predicted shutdown time in response to the prediction type of the air conditioner is the shutdown-time prediction, and adjust the parameters of the prediction model in response to the second absolute value is greater than a preset second error threshold value.
The model updating module may be configured to obtain historical temperature data and historical humidity data of the air conditioner within a preset time range; and adjust the parameters of the prediction model based on the historical temperature data and the historical humidity data.
The controller of the air conditioner may be arranged in the air conditioner. As an alternative, the controller of the air conditioner may be arranged in a server being in communication connection with the air conditioner.
A person skilled in the art may clearly understand that, for the convenience and brevity of illustration, regarding the specific operating process of the apparatus for controlling the air conditioner described above, reference can be made to the corresponding process in the above-described embodiments of the method for controlling the air conditioner, details of the specific operating process are not repeatedly described herein.
An electronic device for operating the aforesaid method for controlling the air conditioner is provided in another embodiment of the present application. With reference to the schematic structural diagram of an electronic device shown in FIG. 8 , the electronic device may include a memory 100 and a processor 101, where the memory 100 may be configured to store one or a plurality of computer instruction(s), and the one or plurality of computer instruction(s) is/are configured to be executed by the processor 101 so as to implement the method for controlling the air conditioner.
Optionally, the electronic device shown in FIG. 8 may further include a bus 102 and a communication interface 103. The processor 101, the communication interface 103, and the memory 100 may be connected through the bus 102.
The memory 100 may include a high-speed random access memory (RAM), or alternatively, the memory 100 may further include a non-volatile memory, for example, at least one disk memory. Communication connection between a system network element and at least one other network element may be implemented through the at least one communication interface 103 (which may be wired or wireless). Internet, a wide area network, a local area network, a metropolitan area network (MAN), etc. may be used. The bus 102 may be an ISA bus, a PCI bus, an EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one bidirectional arrow is used to represent the bus in FIG. 8 , however, this bidirectional arrow does not mean that there is only one bus or one type of bus.
The processor 101 may be an integrated circuit chip having signal processing capabilities. During an implementation process, the various steps of the aforesaid method may be completed through the integrated logic circuit in hardware form or the software instructions in software form in the processor 101. The aforesaid processor 101 may be a general-purpose processor which includes a central processing unit (CPU), a network processor (NP), etc. The processor 101 may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components. The methods, steps, and logical block diagrams disclosed in the embodiments of the present application may be implemented or executed. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiment of the present application may be directly executed and completed by a processor for hardware decoding, or by the combination of hardware and software modules in the processor for hardware decoding. Software modules may be located in a conventional storage medium in this field, such as random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), or electrically erasable programmable read-only memory (EEPROM), registers, etc. The storage medium may be located in the memory 100. The processor 101 may read information in the memory 100, and complete the steps of the method in the embodiments described above in combination with hardware thereof.
A computer-readable storage medium is further provided in the embodiments of the present application. The computer-readable storage medium may store a computer executable instruction. When the computer-executable instruction is invoked and executed by the processor, the computer executable instructions may cause the processor to implement the aforesaid method for controlling the air conditioner. Regarding the specific implementation of the method for controlling the air conditioner, reference can be made to the method embodiments, the implementation of the method for controlling the air conditioner is not be repeatedly described herein.
A computer program product of the method and the apparatus for controlling the air conditioner, and the electronic device provided in the embodiments of the present application may include a computer-readable storage medium that stores program codes. The program codes include instructions that may be used for executing the method in the aforesaid method embodiment. Regarding the specific implementation of the method in the method embodiment, reference can be made to the method embodiment, the method is not repeatedly described herein.
The person of ordinary skill in the art may understand clearly that, for the convenience of illustration and conciseness, regarding the detailed operating process of the system and/or the apparatus, reference may be made to the corresponding process in the previously described method embodiment, the detailed operating process of the system and/or the apparatus is not repeatedly described herein.
In the present application, terms such as “mount,” “connect with each other,” “connect” should be generally interpreted, unless there is additional explicit stipulation and limitation. For example, “connect” may be interpreted as being fixedly connected, detachably connected, or connected integrally; “connect” may also be interpreted as being mechanically connected or electrically connected; “connect” may be further interpreted as being directly connected or indirectly connected through intermediary, or being internal communication between two components or an interaction relationship between the two components. For the person of ordinary skill in the art, the specific meanings of the aforementioned terms in the present application may be interpreted according to specific conditions.
When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, the integrated unit may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially, or the part contributing to the prior art, or all or a part of the technical solutions may be implemented in the form of a software product. The software product is stored in a storage medium and includes a plurality of instructions for instructing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or some of the steps of the methods described in the embodiments of the present application. The aforesaid storage medium includes: any medium that can store program code, such as a USB flash drive, a removable hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc.
In the description of the present application, it needs to be noted that, directions or location relationships indicated by terms including “center,” “up,” “down,” “left,” “right,” “vertical,” “horizontal,” “inside,” “outside” are the directions or location relationships shown in the accompanying figures, which are only intended to describe the present application conveniently and simplify the description, but not to indicate or imply that an indicated device or component must have specific locations or be constructed and manipulated according to specific locations. Thus, these terms shouldn't be considered as any limitation to the present application. In addition, terms of “the first,” “the second” and “the third” are only used for description purposes, and thus should not be considered as indicating or implying any relative importance.
In conclusion, it should be noted that the aforesaid embodiments are only specific embodiments of the present application, and are used to illustrate the technical solutions of the present application, rather than limiting the technical solutions of the present application. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the aforesaid embodiments, the person of ordinary skill in the art should understand that any person familiar with this technical field can still modify the technical solutions recited in the aforesaid embodiments or is conceivable of changes within the technical scope disclosed in the present application, or equivalently replace some of the technical features. However, these modifications, changes or substitutions do not make the essence of the corresponding technical solution to be deviated from the spirits and the scopes of the technical solutions in the embodiments of the present application, and should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be determined by the protection scope of the claims.

INDUSTRIAL APPLICABILITY

A method and an apparatus for controlling an air conditioner, and electronic device are provided in the present application. This method is applied to a controller of the air conditioner and includes: obtaining temperature data and humidity data of the air conditioner; inputting a mode, a prediction type, temperature data and humidity data of the air conditioner into a pre-trained prediction model of the air conditioner, and outputting a predicted time of the air conditioner; and controlling a startup or a shutdown of the air conditioner based on the predicted time. In this method, the mode, the prediction type, the temperature data and the humidity data of the air conditioner are input into the pre-trained prediction model of the air conditioner, the predicted time of the air conditioner is output, and the startup or the shutdown of the air conditioner is controlled based on the predicted time. According to this method, the predicted startup time and the predicted shutdown time of the air conditioner are predicted through the prediction model, an energy consumption of the air conditioner may be saved, an occurrence of waste of energy would not be caused. The air conditioner has a good thermal adaptability.
In addition, it should be understood that the method and the apparatus for controlling the air conditioner and electronic device in the present application may be reproducible, and may be applied in various industrial applications. For example, the method for controlling the air conditioner in the present application may be applied to the field of air conditioners.

Claims

1.-15. (canceled)

16. A method for controlling an air conditioner and implemented by a controller, comprising:

obtaining temperature data and humidity data of the air conditioner, the temperature data including an indoor temperature and an outdoor temperature, and the humidity data including an indoor humidity and an outdoor humidity;

inputting a mode of the air conditioner, a prediction type of the air conditioner, the temperature data, and the humidity data into a pre-trained prediction model of the air conditioner, the mode of the air conditioner including at least one of a cooling mode or a heating mode, the prediction type of the air conditioner including at least one of a startup-time prediction or a shutdown-time prediction, and parameters of the prediction model including an indoor set temperature, an indoor set temperature threshold value, an indoor set humidity, and an indoor set humidity threshold value; and

controlling a startup or a shutdown of the air conditioner based on a predicted time output by the prediction model, the predicted time including at least one of a predicted startup time or a predicted shutdown time.

17. The method according to claim 16, wherein obtaining the temperature data and the humidity data of the air conditioner includes:

obtaining a current time; and

obtaining the temperature data and the humidity data in response to the current time reaching a preset determination time.

18. The method according to claim 16, further comprising:

determining, in response to the prediction type being the startup-time prediction, the predicted startup time using following formula:

Δ t_{open} = c_{1} \cdot (T_{in} - T_{set} - T_{comp}) + c_{2} \cdot (T_{out} - T_{set} - T_{comp}) + c_{3} \cdot ({RH}_{in} - {RH}_{set} - {RH}_{comp}) + c_{4} ({RH}_{out} - {RH}_{set} - {RH}_{comp});

wherein, □t_openrepresents the predicted startup time, c₁-c₄represent preset coefficients for the startup-time prediction, T_inrepresents the indoor temperature, RH_inrepresents the indoor humidity, T_outrepresents the outdoor temperature, RH_outrepresents the outdoor humidity, T_setrepresents the indoor set temperature, RH_setrepresents the indoor set humidity, T_comprepresents the indoor set temperature threshold value, and RH_comprepresents the indoor set humidity threshold value.

19. The method according to claim 16, further comprising:

determining, in response to the prediction type being the shutdown-time prediction, the predicted shutdown time using following formula:

Δ t_{close} = d_{1} \cdot (T_{in} - T_{set} - T_{comp}) + d_{2} \cdot (T_{out} - T_{set} - T_{comp}) + d_{3} \cdot ({RH}_{in} - {RH}_{set} - {RH}_{comp}) + d_{4} \cdot ({RH}_{out} - {RH}_{set} - {RH}_{comp});

wherein, □t_closerepresents the predicted shutdown time, d₁-d₄represent preset coefficients for the shutdown-time prediction, T_inrepresents the indoor temperature, RH_inrepresents the indoor humidity, T_outrepresents the outdoor temperature, RH_outrepresents the outdoor humidity, T_setrepresents the indoor set temperature, RH_setrepresents the indoor set humidity, T_comprepresents the indoor set temperature threshold value, and RH_comprepresents the indoor set humidity threshold value.

20. The method according to claim 16, further comprising, after the predicted time is output:

using, in response to the predicted time being greater than a preset upper limit value of a startup time or a shutdown time, the upper limit value as the predicted time.

21. The method according to claim 16, further comprising, after the predicted time is output:

using, in response to the predicted time is less than a lower limit value of a startup time or a shutdown time, the lower limit value as the predicted time.

22. The method according to claim 16, wherein controlling the startup or the shutdown of the air conditioner based on the predicted time includes:

obtaining a current time;

determining a time difference between the current time and a preset business-open time or a preset close-of-business time; and

controlling the air conditioner to be powered on in response to the time difference being smaller than or equal to the predicted startup time, or to be powered off in response to the time difference being smaller than or equal to the predicted shutdown time.

23. The method according to claim 16, wherein controlling the startup or the shutdown of the air conditioner based on the predicted time includes:

obtaining a current time;

determining, after obtaining the predicted startup time, a time difference between the current time and a business-open time in real time; and

controlling the air conditioner based on the time difference and the predicted time, including:

in response to the time difference being greater than the predicted startup time, continuing to wait; or

in response to the time difference being smaller than or equal to the predicted shutdown time, sending a startup instruction to the air conditioner in order that the air conditioner starts to operate.

24. The method according to claim 16, wherein controlling the startup or the shutdown of the air conditioner based on the predicted time includes:

obtaining a current time;

calculating, after obtaining the predicted shutdown time, a time difference between the current time and the close-of-business time in real time; and

in response to the time difference being greater than the predicted shutdown time, continuing to wait; or

in response to the time difference being smaller than or equal to the predicted shutdown time, sending a shutdown instruction to the air conditioner in order that the air conditioner stops operating.

25. The method according to claim 16, further comprising, after controlling the startup or the shutdown of the air conditioner based on the predicted time:

determining a temperature-reaching time of the air conditioner; and

adjusting the parameters of the prediction model based on the temperature-reaching time.

26. The method according to claim 25, wherein determining the temperature-reaching time of the air conditioner includes:

determining a startup time of the air conditioner in response to the prediction type of the air conditioner being the startup-time prediction;

obtaining a current time in response to the indoor temperature being greater than or equal to a sum of the indoor set temperature and the indoor set temperature threshold value; and

determining a difference value between the current time and the startup time as the temperature-reaching time.

27. The method according to claim 25, wherein determining the temperature-reaching time of the air conditioner includes:

determining a shutdown time of the air conditioner in response to the prediction type of the air conditioner being the shutdown-time prediction;

obtaining a current time in response to the indoor temperature being less than or equal to a sum of the indoor set temperature and the indoor set temperature threshold value; and

determining a difference value between the current time and the shutdown time as the temperature-reaching time.

28. The method according to claim 25, wherein adjusting the parameters of the prediction model based on the temperature-reaching time includes:

determining an absolute value of a difference value between the temperature-reaching time and the predicted startup time in response to the prediction type of the air conditioner being the startup-time prediction; and

adjusting the parameters of the prediction model in response to the absolute value being greater than a preset error threshold value.

29. The method according to claim 25, wherein adjusting the parameters of the prediction model based on the temperature-reaching time includes:

determining an absolute value of a difference between the temperature-reaching time and the predicted shutdown time in response to the prediction type of the air conditioner being the shutdown-time prediction; and

30. The method according to claim 25, wherein adjusting the parameters of the prediction model based on the temperature-reaching time includes:

obtaining historical temperature data and historical humidity data of the air conditioner within a preset time range; and

adjusting the parameters of the prediction model further based on the historical temperature data and the historical humidity data.

31. The method according to claim 16, wherein the controller is arranged in the air conditioner or in a server in communication connection with the air conditioner.

32. An electronic device comprising:

a processor; and

a memory storing a computer-executable instruction that, when executed by the processor, causes the processor to:

obtain temperature data and humidity data of the air conditioner, the temperature data including an indoor temperature and an outdoor temperature, and the humidity data including an indoor humidity and an outdoor humidity;

input a mode of the air conditioner, a prediction type of the air conditioner, the temperature data, and the humidity data into a pre-trained prediction model of the air conditioner, the mode of the air conditioner including at least one of a cooling mode or a heating mode, the prediction type of the air conditioner including at least one of a startup-time prediction or a shutdown-time prediction, and parameters of the prediction model including an indoor set temperature, an indoor set temperature threshold value, an indoor set humidity, and an indoor set humidity threshold value; and

control a startup or a shutdown of the air conditioner based on a predicted time output by the prediction model, the predicted time including at least one of a predicted startup time or a predicted shutdown time.

33. The electronic device according to claim 32, wherein the instruction further causes the processor to:

obtain a current time; and

obtain the temperature data and the humidity data in response to the current time reaching a preset determination time.

34. The electronic device according to claim 32, wherein the instruction further causes the processor to:

determine, in response to the prediction type being the startup-time prediction, the predicted startup time using following formula:

Δ t_{open} = c_{1} \cdot (T_{in} - T_{set} - T_{comp}) + c_{2} \cdot (T_{out} - T_{set} - T_{comp}) + c_{3} \cdot ({RH}_{in} - {RH}_{set} - {RH}_{comp}) + c_{4} ({RH}_{out} - {RH}_{set} - {RH}_{comp});

35. A computer-readable storage medium storing a computer-executable instruction that, when invoked and executed by a processor, causes the processor to: