Equipment regulation and control method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses an equipment regulation and control method and device, electronic equipment and a storage medium. The method comprises the steps that a first environment disturbance behavior and first temperature data of a first control period are acquired; the first environment disturbance behavior is a behavior enabling the first indoor temperature to change; according to the first environment disturbance behavior and the first temperature data, the temperature of each first moment in n first moments after a target moment is predicted, n predicted temperatures are obtained, and the target moment is the end moment of the control period; determining a target control period and target regulation and control power according to the n predicted temperatures and a preset target temperature; and according to the target regulation and control power, the target equipment is regulated and controlled in the target control period, so that the indoor temperature of the room at each first moment is smaller than or equal to the target temperature. By adopting the embodiment of the invention, when the cold and heat source equipment is used for refrigerating or heating, the indoor temperature fluctuation can be reduced, and the living experience of a user is improved.

Description

Technical Field

[0001] The present invention relates to the field of equipment control technology, and in particular to an equipment control method, device, electronic equipment and storage medium. Background Art

[0002] In smart home scenarios, cold and heat source devices such as air conditioning systems are usually used for cooling or heating.

[0003] However, due to the wide variety of living habits and behavior patterns of users, for example, some users are accustomed to opening and closing windows frequently in a short period of time, which will cause changes in parameters such as indoor temperature, resulting in a poor living experience for users. Summary of the Invention

[0004] To solve the above problems, embodiments of the present invention provide a device control method, apparatus, electronic device, and storage medium, which can reduce indoor temperature fluctuations and improve the user's living experience when cooling or heating is performed through cold or hot source equipment.

[0005] In a first aspect, an embodiment of the present invention provides a device control method, including:

[0006] Acquiring a first environmental disturbance behavior and first temperature data during a first control period, wherein the first temperature data includes a first indoor temperature and a first outdoor temperature of the room during the first control period, and the first environmental disturbance behavior is a behavior that causes the first indoor temperature to change;

[0007] Predicting the temperature at each of n first moments after a target moment according to the first environmental disturbance behavior and the first temperature data, to obtain n predicted temperatures, wherein the target moment is an end moment of the control cycle;

[0008] Determining a target control period and a target regulation power according to the n predicted temperatures and a preset target temperature;

[0009] According to the target regulation power, the target device is regulated in the target control period so that the indoor temperature of the room at each first moment is less than or equal to the target temperature.

[0010] In a second aspect, an embodiment of the present invention provides a device control apparatus, the apparatus comprising an acquisition unit and a processing unit;

[0011] The acquisition unit is configured to acquire a first environmental disturbance behavior and first temperature data during a first control period; the first temperature data includes a first indoor temperature and a first outdoor temperature of the room during the first control period; the first environmental disturbance behavior is a behavior that causes the first indoor temperature to change;

[0012] The processing unit is configured to predict the temperature at each of n first moments after a target moment based on the first environmental disturbance behavior and the first temperature data, to obtain n predicted temperatures, where the target moment is an end moment of the control cycle;

[0013] Determining a target control period and a target regulation power according to the n predicted temperatures and a preset target temperature;

[0014] According to the target regulation power, the target device is regulated in the target control period so that the indoor temperature of the room at each first moment is less than or equal to the target temperature.

[0015] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the electronic device performs the method described in the first aspect.

[0016] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in the first aspect.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer is operable to enable the computer to execute the method described in the first aspect.

[0018] The implementation of the embodiments of the present application has the following beneficial effects:

[0019] In an embodiment of the present application, the first environmental disturbance behavior and the first temperature data of the first control cycle are first obtained, wherein the first temperature data include the first indoor temperature and the first outdoor temperature of the room in the first control cycle, and the first environmental disturbance behavior is a behavior that causes the first indoor temperature to change. Then, based on the first environmental disturbance behavior and the first temperature data, the temperature at each of the n first moments after the target moment is predicted to obtain n predicted temperatures, where the target moment is the end moment of the control cycle. Next, based on the n predicted temperatures and the preset target temperature, the target control cycle and the target regulation power are determined. Finally, based on the target regulation power, the target device is regulated in the target control cycle so that the indoor temperature of the room at each first moment is less than or equal to the target temperature. Therefore, by predicting in advance the temperature changes at n first moments caused by the first environmental disturbance behavior when there is a first environmental disturbance behavior in the first control period, n predicted temperatures are obtained, and the target control period and target control power that need to be adjusted in advance are determined according to the n predicted temperatures. Finally, according to the target control power, the target device is adjusted in the target control period. Through prediction, advance adjustment is performed before the indoor temperature exceeds the target temperature. When cooling or heating is performed through the cold and heat source equipment, the indoor temperature fluctuations can be reduced, thereby improving the user's living experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a schematic diagram of the architecture of a device control system provided in an embodiment of the present application;

[0022] Figure 2 This is a flow chart of a device control method provided in an embodiment of the present application;

[0023] Figure 3 This is a schematic diagram of an indoor scene before the first control cycle provided by an embodiment of the present application;

[0024] Figure 4 This is a schematic diagram of user behavior within a first control period provided by an embodiment of the present application;

[0025] Figure 5 is a schematic diagram of a first environmental disturbance behavior within a first control period provided by an embodiment of the present application;

[0026] Figure 6This is a module diagram of a device control method based on parameter verification provided in an embodiment of the present application;

[0027] Figure 7 This is a schematic structural diagram of a device control apparatus provided in an embodiment of the present application;

[0028] Figure 8 This is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0030] The terms "first," "second," "third," and "fourth," etc., in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, rather than to describe a particular order. In addition, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or modules is not limited to the listed steps or modules, but may optionally include steps or modules not listed, or may optionally include other steps or modules inherent to the process, method, product, or apparatus.

[0031] References herein to "embodiments" mean that a particular feature, result, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] The following describes the relevant contents, concepts, technical issues, technical solutions, beneficial effects, etc. involved in the embodiments of this application.

[0033] First, some professional terms involved in this application are explained:

[0034] Model Predictive Control (MPC): It is an advanced control strategy based on models, rolling optimization and feedback correction. It realizes dynamic control of multivariable systems by solving optimization problems in a limited time domain in real time.

[0035] See Figure 1 , Figure 1 This is a schematic diagram of the architecture of a device control system provided by an embodiment of the present application. Figure 1 As shown, the device control system includes an acquisition device, a server and a target device, wherein the acquisition device is used for data acquisition and transmits the collected data to the server. The data collected by the acquisition device can be ambient temperature, ambient humidity, operating time of the target device, etc. The server can interact with the target device based on the data collected by the acquisition device to control the power and other operating parameters of the target device.

[0036] Specifically, the target device may be a device capable of outputting heat or cooling, such as an air conditioner.

[0037] See Figure 2 , Figure 2 This is a flow chart of a device control method provided in an embodiment of the present application. The device control method provided in an embodiment of the present application includes but is not limited to the following steps:

[0038] Step S101: Acquire a first environmental disturbance behavior and first temperature data of a first control period;

[0039] The first temperature data includes a first indoor temperature and a first outdoor temperature of the room in a first control period, and the first environmental disturbance behavior is a behavior that causes the first indoor temperature to change;

[0040] Step S102: predicting the temperature at each of n first moments after the target moment based on the first environmental disturbance behavior and the first temperature data, to obtain n predicted temperatures;

[0041] Among them, the target time is the end time of the control cycle;

[0042] Step S103: determining a target control period and a target regulation power according to the n predicted temperatures and a preset target temperature;

[0043] Step S104: According to the target control power, the target device is controlled in the target control period so that the indoor temperature of the room at each first moment is less than or equal to the target temperature.

[0044] In a possible embodiment, the target device includes multiple control cycles after startup. Taking the target device as an air conditioner as an example, the control cycle of the air conditioner generally refers to the frequency of starting and stopping the air conditioner per unit time. For different types of air conditioners, the control cycle is different. Taking a household air conditioner as an example, the control cycle of a household air conditioner is generally between 10 and 20 seconds, and each operation time is approximately 15 to 20 seconds.

[0045] In a possible embodiment, the first environmental disturbance behavior may be detected behaviors such as doors and windows being opened or closed. The presence of the first environmental disturbance behavior may be determined by detecting the switch status of the doors and windows, and the presence of the first environmental disturbance behavior may also be determined based on the detected trend of indoor temperature changes. Exemplarily, by real-time monitoring of key operating parameters and data analysis, a machine learning algorithm is combined to quickly identify parameter anomalies. Once a sudden change or deviation exceeding a set threshold is found, it is determined that the first environmental disturbance behavior exists. The key operating parameters may include power consumption, temperature, flow, etc. The set threshold is less than the absolute value of the difference between the first indoor temperature and the target temperature. For example, when the first indoor temperature is 26°C and the target temperature is 28°C, the set threshold may be 0.5°C or 1°C, or a value less than 2°C, to ensure that the target device can be pre-regulated before the indoor temperature exceeds the target temperature.

[0046] In one possible embodiment, the first temperature data includes a first indoor temperature and a first outdoor temperature. The first environmental disturbance action causes the first indoor temperature to increase or decrease based on the first outdoor temperature. For example, if the first indoor temperature is 26°C and the first outdoor temperature is 35°C, and the first environmental disturbance action is opening doors and windows, then because the first outdoor temperature is higher than the first indoor temperature, the first environmental disturbance action causes the first indoor temperature to increase. It should be noted that, since the time length of the first control cycle is relatively short, the first indoor temperature and the first outdoor temperature of the first control cycle generally fluctuate less. For example, the first indoor temperature is always 26°C during the first control cycle, and the first outdoor temperature is always 30°C during the first control cycle. If the first indoor temperature and the first outdoor temperature need to be accurate to one decimal place, then the first indoor temperature and the first outdoor temperature can be the indoor temperature and the outdoor temperature at the end of the first control cycle, respectively. For example, if the indoor temperatures collected during the first control cycle are 26.1°C, 26.3°C, 26.0°C, and 26.2°C, the first indoor temperature can be 26.2°C, or the first indoor temperature and the first outdoor temperature can be the average indoor temperature and the average outdoor temperature during the first control cycle, respectively. Taking the numerical values of the above embodiment as an example, the corresponding first indoor temperature can be 26.15°C.

[0047] In a possible embodiment, the target control period may be the first control period, or may be a period after the first control period.

[0048] In one possible embodiment, based on the first environmental disturbance behavior and the first temperature data, the temperature at each of the n first moments after the target moment is predicted to obtain n predicted temperatures. Here, n is a positive integer, and the value of n is determined based on the prediction capability. The stronger the prediction capability, the larger the value of n. In a specific embodiment, after the first environmental disturbance behavior occurs, the n predicted temperatures will transition from the first indoor temperature to the first outdoor temperature. The speed of the transition will vary depending on the difference in indoor and outdoor temperature and the type and duration of the first environmental disturbance behavior.

[0049] In a possible embodiment, a target control period and a target control power are determined based on n predicted temperatures and a preset target temperature. The target temperature can be preset to 22°C, 26°C, 28°C, and so on. The target control period is the target control period corresponding to the first moment before the n predicted temperatures exceed the target temperature. For example, if the period of the control period is 1 minute, the interval between the n adjacent first moments is 30 seconds. If the first moment before the n predicted temperatures exceed the target temperature is the second first moment, then the target control period may be the next control period of the first control period. If the first moment before the n predicted temperatures exceed the target temperature is the fifth first moment, then the target control period may be the third control period after the first control period. In this way, an appropriate control period is determined to avoid premature or late control.

[0050] In one possible embodiment, based on the target regulated power, the target device is regulated during a target control period so that the indoor temperature of the room at each first moment is less than or equal to the target temperature. During regulation, the power of the target device can be regulated to the target regulated power all at once during the target control period, or it can be regulated to the target regulated power gradually within the target control period. This prevents excessive device wear and excessive temperature fluctuations.

[0051] In a specific embodiment, the first environmental disturbance behavior and the first temperature data of the first control period are obtained. The first environmental disturbance behavior is to open the window. The first indoor temperature and the first outdoor temperature are 26°C and 33°C respectively. It can be seen that the target device is in a cooling scene. Then, based on the first environmental disturbance behavior and the first temperature data, the temperature of each of the n first moments after the target moment is predicted to obtain n predicted temperatures. If the value of n is 5, the 5 first moments are the 1st minute, 2nd minute, 3rd minute, 4th minute, and 5th minute after the target moment, and the 5 predicted temperatures are 26°C, 33°C, and 33°C respectively. 27℃, 28℃, 30℃, 32℃. If the target temperature is 28℃, the target control period and target regulation power are determined according to the n predicted temperatures and the preset target temperature. The target regulation period can be determined as the regulation period before the third first moment. For example, the regulation period corresponding to the 1st minute or 2nd minute after the target moment can be determined as the target regulation period. The target regulation power is determined according to the temperature increase value of the n predicted temperatures. Finally, according to the target regulation power, the target device is regulated in the target control period so that the indoor temperature of the room at each first moment is less than or equal to the target temperature.

[0052] In an embodiment of the present application, by predicting in advance the temperature changes at n first moments caused by the first environmental disturbance behavior when there is a first environmental disturbance behavior in the first control period, n predicted temperatures are obtained, and the target control period and target control power that need to be adjusted in advance are determined based on the n predicted temperatures. Finally, according to the target control power, the target device is regulated in the target control period. Through prediction, advance regulation is performed before the indoor temperature exceeds the target temperature. This can reduce indoor temperature fluctuations when cooling or heating is performed through cold and heat source equipment, thereby improving the user's living experience.

[0053] Optionally, step S102, predicting the temperature at each of n first moments after the target moment based on the first environmental disturbance behavior and the first temperature data to obtain n predicted temperatures, may include the following steps:

[0054] Step S201: determining a first behavior type and a first duration of a first environmental disturbance behavior;

[0055] Step S202: predicting a temperature disturbance index of the first environmental disturbance behavior on the first indoor temperature based on the first behavior type, the first duration, and the first outdoor temperature; the temperature disturbance index is used to indicate the temperature disturbance change amount and the temperature disturbance change rate;

[0056] Step S203: predicting the temperature at each of n first moments after the target moment according to the first indoor temperature and the temperature disturbance index, and obtaining n predicted temperatures.

[0057] In a possible embodiment, the first behavior type and the first duration of the first environmental disturbance behavior are determined, wherein the first behavior type may be opening a window, opening a door, closing a window, closing a door, etc. The first behavior type may also include the angle of opening a window, the angle of opening a door, etc. The first duration is the duration of the behavior of the first environmental disturbance behavior in the first control cycle. For example, the first duration may be 10 seconds, 20 seconds, 30 seconds, and so on.

[0058] In one possible embodiment, a temperature disturbance index of the first environmental disturbance behavior on the first indoor temperature is predicted based on the first behavior type, the first duration, and the first outdoor temperature, wherein the temperature disturbance index is used to indicate the amount of change in the temperature disturbance and the rate of change of the temperature disturbance. Specifically, a higher type level of the first behavior type, a longer first duration, and a greater temperature difference between the first outdoor temperature and the first indoor temperature, a greater temperature disturbance index is generated. The type level is used to reflect the degree of impact of the first disturbance behavior on the temperature. The greater the angle at which the window or door is opened, the higher the type level is.

[0059] In one possible embodiment, based on the first indoor temperature and the temperature disturbance index, the temperature at each of n first moments after the target moment is predicted, resulting in n predicted temperatures. Specifically, if the first temperature change at the n first moments according to the temperature disturbance change rate is greater than the temperature disturbance change, then the highest value of the n predicted temperatures is no higher than the sum of the first indoor temperature and the temperature disturbance change. For example, if the temperature disturbance index indicates a temperature disturbance change of 5°C and a temperature disturbance change rate of 1°C per minute, respectively, and the first indoor temperature is 26°C, when n is 6, then for the six first moments after the target moment, the first temperature change is 6°C, which is greater than the temperature disturbance change. The predicted temperatures are: 27°C, 28°C, 29°C, 30°C, 31°C, and 31°C, respectively. Specifically, if the first temperature change at the n first moments according to the temperature disturbance change rate is less than the temperature disturbance change, then the highest value of the n predicted temperatures is the sum of the first temperature change and the first indoor temperature. For example, if the temperature disturbance index indicates that the temperature disturbance change and the temperature disturbance change rate are 5°C and 1°C per minute respectively, and the first indoor temperature is 26°C, when the value of n is 4, for the 4 first moments after the target moment, the first temperature change is 4°C, and the first temperature change is less than the temperature disturbance change, and the predicted temperatures are: 27°C, 28°C, 29°C and 30°C respectively.

[0060] In a specific embodiment, the window switch status and time, personnel activity area and activity time data are obtained, and the user's daily behavior patterns and habits are analyzed using data mining and machine learning algorithms. A user behavior prediction model is constructed based on the user's historical behavior patterns. Then, the user behavior prediction model outputs the influence coefficient of the switch status and time, personnel activity area and activity time data on the heat load, and evaluates the potential impact of user behavior on real-time operating parameters, so as to adjust the feedback control strategy in advance for pre-compensation.

[0061] Optionally, in step S103, determining a target control period according to the n predicted temperatures and a preset target temperature may include the following steps:

[0062] Step S301: determining a target first moment among n first moments according to n predicted temperatures and target temperature;

[0063] Step S302: Obtaining the system response time of the target device;

[0064] Step S303: Determine a target control period according to the system response time and the target first moment.

[0065] In a possible embodiment, a target first moment among the n first moments is determined based on the n predicted temperatures and the target temperature. The target first moment is a moment among the n first moments when the predicted temperature is higher than or equal to the target temperature.

[0066] In a possible embodiment, a system response duration of the target device is acquired, where the system response duration is the length of time from when the target device receives the target regulated power to when the regulation is completed.

[0067] In a possible embodiment, the target control period is determined based on the system response time and the target first moment. The target control period is the control period of the moment corresponding to the system response time before the target first moment. For example, if the target first moment is 3:00 and the system response time is 5 minutes, then the target control period is the control period corresponding to the moment 2:55.

[0068] Optionally, in step S103, determining the target control power according to the n predicted temperatures and the preset target temperature may include the following steps:

[0069] Step S401: determining a predicted temperature change according to n predicted temperatures;

[0070] Step S402: determining the target cooling and heating amount according to the control response time, the temperature disturbance index, and the predicted temperature change;

[0071] Step S403: obtaining the first power of the target device in the first control period;

[0072] Step S404: determining the target regulated power according to the target regulated cooling and heating amount and the first power.

[0073] In a possible embodiment, a predicted temperature change is determined based on n predicted temperatures, where the predicted temperature change is a difference between a maximum predicted temperature and a minimum predicted temperature among the n predicted temperatures.

[0074] In a possible embodiment, the target controlled cooling and heating amount is determined according to the control response time, the temperature disturbance index and the predicted temperature change. Specifically, according to the formula Determine the target cooling and heating quantity, where ΔT is the predicted temperature change, C p is the specific heat capacity of air, V room is the room volume, t delay is the pre-compensation time, which is determined by the system response time, f(S win ,t win ,A act ,t act ) is the temperature disturbance index.

[0075] In a possible embodiment, the first power of the target device in the first control period is obtained, and the target control power is determined according to the target control heat and the first power. Specifically, the target control power is the sum of the first power and the target control heat.

[0076] Optionally, step S404, determining the target regulated power according to the target regulated cooling and heating amount and the first power, may include the following steps:

[0077] Step S501: determining m second moments that are later than the target control period among n first moments;

[0078] Step S502: Determine the predicted time domain length according to the m second moments;

[0079] Step S503: predicting the cooling / heating reference value at each second moment according to the first power, and obtaining m cooling / heating reference values;

[0080] Step S504: determining a target optimization function based on the prediction time domain length and the m cooling and heating reference values; the target optimization function is used to indicate an optimization target between the target control power within the prediction time domain length, the m cooling and heating reference values, and the cooling and heating predicted values at each second moment obtained based on the target control power prediction;

[0081] Step S505: Determine the target control power according to the target optimization function and the preset target relationship expression; the target relationship expression is used to predict the cooling and heating prediction value at each second moment according to the target control power.

[0082] In a possible embodiment, m is a positive integer, and the predicted time domain length is determined according to the m second moments. Specifically, the predicted time domain length is the time length of the m second moments.

[0083] In a possible embodiment, based on the first power, the heat and cold reference value at each second moment is predicted to obtain m heat and cold reference values. Specifically, the heat and cold reference value is the heat and cold output value at the m second moments when the target device is not regulated.

[0084] For example, the first power P, the inlet and outlet refrigerant / heat medium temperature T are obtained. in 、T out , flow rate Q, running time t run , outdoor temperature T outdoor 、Humidity H outdoor and the target temperature T set by the user set Based on the acquired data, the initial equipment performance model is constructed by combining the physical characteristics of the equipment, thermodynamic principles and machine learning algorithms. The mathematical expression of the equipment performance model is: Y = f'(X), where Y is the equipment's cooling and heating output, X is the acquired power consumption P, and the inlet and outlet cooling / heating medium temperature T in 、T out , flow rate Q, running time t run , outdoor temperature T outdoor 、Humidity H outdoor and the target temperature T set by the user set The data set, f′(·), is a functional relationship based on physics and machine learning, which is used to predict the cooling and heating output under different working conditions, thereby obtaining m cooling and heating reference values.

[0085] In one possible embodiment, a target optimization function is determined based on the prediction time domain length and m cold and heat reference values, where the target optimization function is used to indicate the optimization target between the target control power within the prediction time domain length, the m cold and heat reference values, and the cold and heat predicted values at each second moment obtained based on the target control power prediction. Specifically, the target optimization function is set as: Among them, N p is the predicted time domain length; Y pred (k+i) is the predicted value of cold and heat at the second moment of the i-th control cycle according to the target control power prediction, Y ref (k+i) is the reference value of the amount of heat and cold at the i-th second moment of the k-th control cycle, λ is the weight coefficient, which can be dynamically adjusted through the user behavior prediction model, U(k+i-1) is the target control power at the i-1-th second moment of the k-th control cycle, and when i is 1, U(k+i-1) is the target control power of the k-th control cycle.

[0086] In a possible embodiment, the target control power is determined according to the target optimization function and a preset target relationship; the target relationship is used to predict the cooling and heating value at each second moment according to the target control power. Specifically, the target relationship is: pred (k+i)=f(X(k),U(k),i), where, when k is the target control period, X(k) is the current state variable of the target control period {T room ,H room}, U(k) is the current control input variable {P} of the target control period, that is, the target control power, f(·) is the prediction model function, Y pred (k+i) is the predicted value of cold and heat at the second moment of the i-th control cycle according to the target control power prediction.

[0087] In a possible embodiment, among multiple possible target control power values, it is necessary to satisfy both the target relationship and the target optimization function.

[0088] Optionally, the target control period includes a control moments, the target control power includes a sub-control powers, and the a control moments correspond to the a sub-control powers in a one-to-one manner; step S104, regulating the target device in the target control period according to the target control power, may include the following steps:

[0089] Step S601: obtaining a control scenario index of a target control cycle;

[0090] Step S602: determining a control rate according to the control scenario indicator;

[0091] Step S603: Determine the sub-control power at each of the a control moments according to the control rate and the target control power, and obtain a sub-control powers;

[0092] Step S604: According to a control time and a sub-regulation power, the target device is regulated in the target control period.

[0093] In a possible embodiment, a control moments can be a moments among n first moments, and the control scenario indicators of the target control cycle are obtained. The control scenario indicators can be the operating time of the target device, the model prediction accuracy, etc.

[0094] In a possible embodiment, the control rate is determined according to the control scenario index. Specifically, the longer the target device runs, the higher the model prediction accuracy, and the larger the control scenario index, the greater the control rate.

[0095] In a possible embodiment, according to the control rate and the target control power, the sub-control power of each control moment in a control moments is determined to obtain a sub-control powers, where a is a positive integer. Specifically, according to different control rates, if the control rate is large, the value of a is 5, and the target control power is 50, and the first power is 30, then the a sub-control powers can be 35, 40, 44, 48, or 50.

[0096] Optionally, step S102, predicting the temperature at each of n first moments after the target moment based on the first environmental disturbance behavior and the first temperature data to obtain n predicted temperatures, may include the following steps:

[0097] Step S701: Acquire historical environmental disturbance behavior data;

[0098] Step S702: predicting the occurrence probability of the second environmental disturbance behavior at each first moment based on the historical environmental disturbance behavior data, and obtaining n behavior occurrence probabilities;

[0099] Step S703: predicting the temperature at each of the n first moments after the target moment according to the n behavior occurrence probabilities, the first environmental disturbance behavior and the first temperature data, and obtaining n predicted temperatures.

[0100] In one possible embodiment, the second environmental disturbance behavior can be the same environmental disturbance behavior as the first environmental disturbance behavior, or it can be different, and there is no limitation here. In addition to predicting n predicted temperatures based on the first environmental disturbance behavior, the probability of the second environmental disturbance behavior at each first moment is predicted based on the historical environmental disturbance behavior data, and n behavior occurrence probabilities are obtained. For example, based on the historical environmental disturbance behavior data, the user's long-term window opening and closing time, personnel activity areas such as bedrooms or living rooms, activity duration and other data are collected, and it can be obtained that: the user opens the window for ventilation for 15 minutes at 8:00 every day, and is active in the living room from 12:00 to 13:00 at noon, etc., thereby predicting the probability of the second environmental disturbance behavior. If there is a behavior with a probability of occurrence greater than a preset probability threshold, the start time of the second disturbance behavior is determined according to the probability of occurrence of the behavior, and the second behavior duration of the second environmental disturbance behavior is predicted. According to the second behavior type and the second behavior duration of the second environmental disturbance behavior, as well as the start time of the second disturbance behavior, b second predicted fluctuation values are determined, where b is a positive integer less than or equal to n. According to the first behavior type and the first behavior duration of the first environmental disturbance behavior, n first predicted fluctuation values are determined. According to the first indoor temperature in the first temperature data, the sum of the b second predicted fluctuation values and the n first predicted fluctuation values, n predicted temperatures are determined.

[0101] In the specific embodiment, see Figure 3 , Figure 3 This is a schematic diagram of an indoor scene before the first control cycle provided by an embodiment of the present application, such as Figure 3 As shown, the indoor space where the target device acts includes a first area and a second area, the first area is provided with a first window, and the second area is provided with a second window. The user has been in the illustrated position before the first control cycle, and before the first control cycle, the first window and the second window are both in a closed state.

[0102] Furthermore, if it is detected in the first control period that the user is still in Figure 3 As shown in the user's position, there is no first environmental disturbance behavior in the first control cycle, and the temperatures in the first area and the second area at n first moments after the first control cycle basically do not fluctuate, and there is no need to take regulatory measures on the target device, and the target device is controlled to continue working according to the first power of the first control cycle.

[0103] Further, see Figure 4 , Figure 4 This is a user behavior diagram within a first control period provided by an embodiment of the present application. Figure 4 As shown, if the user is detected along the first control cycle Figure 4 If the user moves in the direction of the dotted arrow in the figure, it is uncertain whether there is a first environmental disturbance behavior in the first control period. After the first control period, there is a possibility that the user implements the first environmental disturbance behavior. At this time, the first behavior occurrence probability of the first environmental disturbance behavior at n first moments after the first control period can be predicted based on the historical environmental disturbance behavior data to obtain n first behavior occurrence probabilities. If there is a first behavior occurrence probability higher than the first preset probability, then the temperature at each first moment in the n first moments after the first control period is predicted based on the n first behavior occurrence probabilities to obtain n predicted temperatures.

[0104] Further, see Figure 5 , Figure 5 This is a schematic diagram of a first environmental disturbance behavior in a first control period provided by an embodiment of the present application. If a user is detected along Figure 5 Move in the direction of the dotted arrow c in the figure, and the second window moves ... Figure 5 If the window is opened in the direction of the dotted arrow d in the figure, then there is a first environmental disturbance in the first control cycle. In this case, the temperature change can be predicted based on the first environmental disturbance to obtain n predicted temperatures. For example, the prediction can be made based on the opening angle of the second window and the indoor and outdoor temperature difference.

[0105] In a specific embodiment, the embodiment of the present application also adopts real-time operation parameter mutation impact verification and correction technology. By real-time monitoring of key operating parameters, using equipment performance models and user behavior prediction models for data analysis, combined with machine learning algorithms to quickly identify parameter anomalies, once a mutation or deviation is found to exceed the set threshold, the verification program is immediately started to evaluate the degree of impact, and corrective measures are automatically implemented through predictive control strategies to ensure stable and efficient operation of the system, which helps to save energy and reduce consumption, extend equipment life and improve overall operating efficiency. Due to changes in the characteristics of the cold and heat sources, the performance curves of cold and heat source equipment such as air-conditioning systems will change in different seasons and different usage frequencies. For example, when heating in winter, low outdoor temperatures will affect the heating efficiency of the air conditioner, and the traditional feedback control model may be based on fixed performance parameters under standard operating conditions of the equipment. In this case, the cold and heat output predicted by the model deviates from the actual output, resulting in a decrease in control accuracy. In addition, the performance characteristics of equipment of different brands and models are also different, and a universal model is difficult to accurately adapt. Therefore, the embodiment of the present application further provides an equipment control method based on correction verification and model update. See Figure 6 , Figure 6 This is a module diagram of a device control method based on parameter verification provided by an embodiment of the present application. Figure 6 As shown, the device control method includes a device performance prediction module, a user behavior prediction module, a verification module, a control prediction module and a smoothing control module. The functions of each module and the method of performing device control through each module are shown below.

[0106] In a specific embodiment, the operating parameters of the cold and heat source equipment are monitored and optimized in real time. By building an equipment performance model and combining it with real-time data for comparison and online learning and updating, deviations in equipment operation can be promptly discovered and corrected. At the same time, comprehensive consideration is given to user behavior, window switch status, and indoor environmental factors, etc., to predict and compensate in advance for the potential impact of user behavior on operating parameters, thereby ensuring the stability of indoor environmental parameters. In addition, by building an MPC controller prediction model, it is possible to solve optimization problems based on real-time data within each control cycle and achieve precise control strategy adjustments, thereby effectively improving the overall operating efficiency of the system and the comfort of the indoor environment.

[0107] Specifically, for the equipment performance prediction module, the operating power consumption P of the cold and heat source equipment, the inlet and outlet cold / heat medium temperature T in 、T out , flow rate Q, running time t run , outdoor temperature T outdoor 、Humidity H outdoor and the target temperature T set by the user setBased on the acquired data, the initial equipment performance model is constructed by combining the physical characteristics of the equipment, thermodynamic principles and machine learning algorithms. The mathematical expression of the equipment performance model is: Y = f'(X), where Y is the equipment's cooling and heating output, X is the acquired power consumption P, and the inlet and outlet cooling / heating medium temperature T in 、T out , flow rate Q, running time t run , outdoor temperature T outdoor 、Humidity H outdoor and the target temperature T set by the user set The data set, f′(·) is a functional relationship based on physics and machine learning, which is used to predict the cooling and heating output under different working conditions. In addition, the operating data and environmental factors of the cooling and heating source equipment are monitored in real time, and compared with the predicted value of the equipment performance model. If the deviation exceeds the set threshold θ th When the device performance model is updated, the online learning algorithm is used to update the device performance model in real time.

[0108] In one possible embodiment, the online learning algorithm updates the equipment performance model in real time, enabling rapid adaptation to changes in equipment performance and operating conditions, ensuring the accuracy and reliability of the equipment performance model. By updating model parameters in real time, the actual operating status of the equipment can be promptly reflected, providing an accurate basis for subsequent optimization control. Specifically, the mathematical expression for the online learning algorithm to update the equipment performance model in real time is: Where θ new is the updated model parameter, θ old is the model parameter before updating, η is the learning rate, is the loss function J(·) with respect to θ old The gradient is used to adapt to changes in equipment performance. Real-time updating of the equipment performance model can ensure that the system accurately grasps the operating status of the equipment, improve the pertinence and effectiveness of the control strategy, thereby improving the overall performance of the system and the operating efficiency of the equipment. At the same time, it can respond to changes in equipment performance and adjustments to working conditions in a timely manner, enhance the adaptability and stability of the system, and reduce equipment maintenance costs.

[0109] Furthermore, for the user behavior prediction module, the window switch state S is obtained win and time t win , Personnel activity area A act and activity time t act Data, using data mining and machine learning algorithms to analyze users' daily behavior patterns and habits, build a user behavior prediction model based on users' historical behavior patterns, and output the switch state S through the prediction model win and time t win , Personnel activity area A act and activity time t actThe influence coefficient of data on heat load f(S win ,t win ,A act ,t act ), and combined with the user behavior prediction model and equipment performance model, evaluate the potential impact of user behavior on real-time operating parameters, and adjust the feedback control strategy in advance for pre-compensation.

[0110] The model construction steps are as follows: first, data collection and annotation are performed, and the input data is the window switch state S win and time t win , Personnel activity area A act and activity time t act Data is output, and the output label is the behavior pattern of the future time period, such as the window opening period, the bedroom activity period, etc., and then time series feature statistics are performed, including: sliding window statistics, spatial feature statistics and environmental coupling feature statistics. Among them, sliding window statistics can be the window opening frequency in the past 1 hour, and spatial feature statistics can include regional heat maps, which are used to reflect the proportion of people's stay time in different areas. Environmental coupling features include the correlation coefficient between outdoor temperature and window opening behavior. Next, model selection and training are performed. Among them, the model algorithm uses long short-term memory network (LSTM) to process time series and combines random forest to process spatial features. The training goal is to maximize the F1 score of behavior pattern prediction. In addition, an online learning mechanism is used to trigger incremental model updates when a sudden change in user behavior pattern is detected, such as the difference between weekends and weekdays.

[0111] In one possible embodiment, by acquiring data such as the window switch status and analyzing user behavior patterns, a user behavior prediction model is constructed. This allows the impact of user behavior on parameters such as indoor temperature to be estimated in advance. Based on this prediction model and the equipment performance model, the pre-compensated cooling and heating amounts are calculated and the feedback control strategy is adjusted in advance. This can effectively reduce indoor environmental fluctuations caused by user behavior and ensure the stability of indoor environmental parameters.

[0112] Specifically, the window switch status S win , 1 means open, 0 means closed, pre-compensation of cooling and heating ΔY pre The calculation formula is: Where ΔT is the estimated temperature change, C p is the specific heat capacity of air, V room is the room volume, t delayIt is the pre-compensation time, which is determined by the system response time. It effectively reduces the indoor environment fluctuations caused by user behavior, improves the stability and comfort of indoor temperature, humidity and air quality. At the same time, adjusting the control strategy in advance can reduce the system's adjustment frequency and amplitude, reduce energy consumption, and improve the system's economy and environmental protection.

[0113] Furthermore, for the verification module, the indoor temperature T room , humidity T room and air quality Q air The system measures the operating parameters of the system and receives sensor data in real time and compares it with the predicted values of the feedback control model. It uses statistical process control and data-driven anomaly detection algorithms to verify the operating parameters and determine whether an anomaly occurs. According to the severity and impact of the anomaly of the operating parameters, the warning is divided into different levels and corresponding graded response measures are taken. The level of the anomaly is graded by adjusting σ.

[0114] In one possible embodiment, an operating parameter verification method based on statistical process control and data-driven algorithms is provided, which can promptly detect abnormalities in operating parameters. By setting reasonable judgment principles and a graded early warning mechanism, it can quickly respond to abnormal situations of different levels and take corresponding measures to deal with them, thereby ensuring the stable operation of the system.

[0115] Specifically, if It is judged as abnormal, where X i is the real-time running parameter value collected for the i-th time, is the parameter mean, σ is the parameter standard deviation. The abnormality judgment principle maps the graded response measures as follows: If |ΔT room |>ΔT th , then the warning level is moderate, where ΔT room is the indoor temperature variation, ΔT th Setting the temperature mutation threshold and timely detecting and handling the mutation and anomaly of operating parameters can avoid system operation risks, reduce the possibility of equipment failure and damage, and improve the reliability and stability of the system. The hierarchical early warning mechanism can ensure that appropriate measures are taken under different levels of abnormal situations, improve the system's response capability and flexibility, and reduce losses.

[0116] Furthermore, for the control prediction module, an MPC controller prediction model is constructed based on the updated device performance model and user behavior prediction model to predict the key operating parameter value Y at the i-th future moment in the k-th control cycle. pred(k+i), and set the target optimization function. In each control cycle, the optimization problem is solved according to the real-time monitoring data and the prediction model, the optimal control strategy is obtained, the control signal is generated and sent to the actuator, the equipment operation status is adjusted, and the cold and heat source equipment is effectively ensured to operate in the optimal state, reducing energy consumption, improving the economy and environmental protection of the system, predicting and compensating the impact of user behavior in advance, reducing the indoor environment fluctuations caused by user behavior, and improving the stability and comfort of indoor temperature, humidity and air quality. At the same time, based on the precise prediction and optimization control strategy, the reliability and stability of the system are further enhanced, and the service life of the equipment is extended.

[0117] In one possible embodiment, by constructing an MPC controller prediction model, key operating parameters can be accurately predicted and a reasonable target optimization function can be set. In each control cycle, the optimization problem is solved based on real-time monitoring data and the prediction model, and the optimal control strategy is obtained and a control signal is generated, thereby achieving precise adjustment of the equipment operating status, ensuring the stability of indoor environmental parameters and the efficient operation of the equipment.

[0118] Specifically, predict the key operating parameter value Y at the i-th future moment in the k-th control cycle pred The mathematical expression of (k+i) is: pred (k+i)=f(X(k),U(k),i), where X(k) is the current state variable {T room ,H room}, U(k) is the current control input variable {P}, and f(·) is the prediction model function.

[0119] Specifically, the target optimization function is set as: Among them, N p is the predicted time domain length; Y ref (k+i) is the reference value of the key operating parameter at the i-th future moment, and λ is the weight coefficient. Through dynamic adjustment of the user behavior prediction model, the application of the MPC control strategy can achieve precise control of the system, improve the stability and comfort of indoor environmental parameters, while reducing energy consumption and equipment wear, and extending the service life of equipment. Optimization and adjustment based on real-time data can ensure that the system always operates in the best state, enhance the system's economy and environmental protection, and improve the user experience.

[0120] In one possible embodiment, a smoothing control algorithm is introduced to process the control signal to effectively reduce the fluctuation and mutation of the control signal, making the operation of the equipment more stable. Multiple sets of feedback control strategies are designed, and the control strategy is automatically switched according to different scenarios and real-time operating status to ensure that the system can adopt the most suitable control strategy under various working conditions, thereby improving the adaptability and flexibility of the system.

[0121] Specifically, for the smoothing control module, a smoothing control algorithm is introduced in the feedback control process to smooth the control signal, and multiple feedback control strategies are designed to automatically switch the control strategy according to different scenarios and real-time operating conditions: when the system is initially started or the model prediction accuracy is low, a rule-based control strategy is adopted; when the system operation is stable and the model prediction accuracy is high, it is switched to the MPC control strategy to reduce equipment wear and energy consumption, extend the service life of the equipment, and improve the stability and comfort of indoor environmental parameters. The automatic switching of multiple control strategies can ensure that the system can maintain efficient and stable operation under different working conditions, enhance the reliability and stability of the system, and improve the user experience.

[0122] In the present invention, for highly random behaviors such as users frequently opening and closing windows in smart home scenarios, by real-time monitoring of changes in indoor temperature, humidity and other parameters, and combining feedback control models with user behavior prediction models, the impact of such sudden behaviors can be quickly identified, and machine learning is used to continuously optimize the prediction model, so that the system can make predictions and adjust the control strategy in advance, reducing the frequent adjustments of control strategies caused by random user behaviors, thereby effectively stabilizing indoor environmental parameters, maintaining the system in an ideal operating state, and improving the stability of the smart home system and the user's comfort experience.

[0123] In the present invention, multiple feedback control strategies and online learning algorithms are introduced to solve the control problems caused by random behaviors such as users frequently opening and closing windows. In the initial stage of the system, a rule-based control strategy is adopted to ensure stable operation. After the operation is stable, it switches to the MPC control strategy to achieve precise control. The online learning algorithm updates the equipment performance model in real time to adapt to changes in equipment and user behavior, reduce frequent adjustments to the control strategy, improve system stability, ensure that the indoor environment is stable in an ideal state for a long time, and provide users with a more comfortable living environment.

[0124] In the present invention, the user behavior prediction model and the equipment performance model are integrated to accurately evaluate and pre-compensate the impact of user behavior on real-time operating parameters. In response to changes in indoor parameters caused by users frequently opening and closing windows, the system adjusts the control strategy in advance and implements pre-compensation measures. By analyzing user behavior patterns, the window opening and closing status and its impact are predicted, and the pre-compensated cooling and heating amount is calculated in combination with the equipment performance model, and the indoor environment is adjusted in advance. This reduces frequent system adjustments, reduces equipment wear and energy consumption, and improves the stability and comfort of the indoor environment. The multi-level early warning mechanism can timely detect and handle sudden changes or anomalies in operating parameters, thereby enhancing system reliability.

[0125] To summarize, in an embodiment of the present application, the first environmental disturbance behavior and the first temperature data of the first control cycle are first obtained, wherein the first temperature data include the first indoor temperature and the first outdoor temperature of the room in the first control cycle, and the first environmental disturbance behavior is a behavior that causes the first indoor temperature to change. Then, based on the first environmental disturbance behavior and the first temperature data, the temperature of each of the n first moments after the target moment is predicted to obtain n predicted temperatures, where the target moment is the end moment of the control cycle. Next, based on the n predicted temperatures and the preset target temperature, the target control cycle and the target control power are determined. Finally, based on the target control power, the target device is controlled in the target control cycle so that the indoor temperature of the room at each first moment is less than or equal to the target temperature. Therefore, by predicting in advance the temperature changes at n first moments caused by the first environmental disturbance behavior when there is a first environmental disturbance behavior in the first control period, n predicted temperatures are obtained, and the target control period and target control power that need to be adjusted in advance are determined according to the n predicted temperatures. Finally, according to the target control power, the target device is adjusted in the target control period. Through prediction, advance adjustment is performed before the indoor temperature exceeds the target temperature. When cooling or heating is performed through the cold and heat source equipment, the indoor temperature fluctuations can be reduced, thereby improving the user's living experience.

[0126] The above describes in detail the method according to the embodiment of the present invention. The following provides an apparatus according to the embodiment of the present invention.

[0127] See Figure 7 , Figure 7 This is a schematic diagram of the structure of a device control device provided in an embodiment of the present application. Figure 7 As shown, the equipment control device 800 includes an acquisition unit 801 and a processing unit 802; the acquisition unit 801 is used to acquire the first environmental disturbance behavior and the first temperature data of the first control cycle; the first temperature data includes the first indoor temperature and the first outdoor temperature of the room in the first control cycle, and the first environmental disturbance behavior is a behavior that causes the first indoor temperature to change; the processing unit 802 is used to predict the temperature at each of the n first moments after the target moment based on the first environmental disturbance behavior and the first temperature data, and obtain n predicted temperatures, where the target moment is the end moment of the control cycle; based on the n predicted temperatures and the preset target temperature, determine the target control cycle and the target control power; based on the target control power, control the target device in the target control cycle so that the indoor temperature of the room at each first moment is less than or equal to the target temperature.

[0128] In a specific implementation, the acquisition unit 801 and the processing unit 802 in the embodiment of the present application may also execute other implementations described in the device control method in the above embodiment of the present application, which will not be repeated here.

[0129] See Figure 8 , Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 8 As shown, the electronic device 900 includes a transceiver 901, a processor 902, and a memory 903, which are connected via a bus 904. The memory 903 is used to store computer programs and data, and can transmit the data stored in the memory 903 to the processor 902. The electronic device 900 can be the above-mentioned device control device 800, and the processor 902 can be the above-mentioned acquisition unit 801 and processing unit 802. In this embodiment of the present application, the processor 902 is used to read the computer program in the memory 903 to execute some or all steps of the above-mentioned device control method.

[0130] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement part or all of the steps of any device control method described in the above method embodiments.

[0131] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute part or all of the steps of any device control method recorded in the above method embodiments.

[0132] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0133] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical or other forms.

[0135] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of the present embodiment according to actual needs.

[0136] In addition, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The above-mentioned integrated modules may be implemented in the form of hardware or software program modules.

[0137] If the integrated module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0138] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for those skilled in the art, according to the idea of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A device control method, characterized in that: include: Acquire a first environmental disturbance behavior and first temperature data in a first control period; The first temperature data includes a first indoor temperature and a first outdoor temperature of the room within the first control period, and the first environmental disturbance behavior is a behavior that causes the first indoor temperature to change; Predicting the temperature at each of n first moments after a target moment according to the first environmental disturbance behavior and the first temperature data, to obtain n predicted temperatures, wherein the target moment is an end moment of the control cycle; Determining a target control period and a target regulation power according to the n predicted temperatures and a preset target temperature; According to the target regulation power, the target device is regulated in the target control period so that the indoor temperature of the room at each first moment is less than or equal to the target temperature.

2. The method according to claim 1, wherein The step of predicting the temperature at each of n first moments after the target moment based on the first environmental disturbance behavior and the first temperature data to obtain n predicted temperatures includes: determining a first behavior type and a first duration of the first environmental disturbance behavior; Predicting a temperature disturbance index of the first environmental disturbance behavior on the first indoor temperature based on the first behavior type, the first duration, and the first outdoor temperature; the temperature disturbance index is used to indicate a temperature disturbance change amount and a temperature disturbance change rate; The temperature of each of n first moments after the target moment is predicted according to the first indoor temperature and the temperature disturbance index to obtain the n predicted temperatures.

3. The method according to claim 2, wherein Determining a target control period according to the n predicted temperatures and a preset target temperature includes: determining a target first moment among the n first moments according to the n predicted temperatures and the target temperature; Obtaining the system response time of the target device; The target control period is determined according to the system response time and the target first moment.

4. The method according to claim 3, wherein Determining a target control power according to the n predicted temperatures and a preset target temperature includes: Determining a predicted temperature change according to the n predicted temperatures; Determining a target controlled cooling and heating amount according to the control response time, the temperature disturbance index, and the predicted temperature change; Acquire a first power of the target device in the first control period; The target regulated power is determined according to the target regulated cooling and heating amount and the first power.

5. The method according to claim 4, wherein The determining the target regulated power according to the target regulated cooling and heating amount and the first power includes: determining m second moments that are later than the target control period among the n first moments; Determining a predicted time domain length according to the m second moments; Predicting a cold / heat reference value at each second moment according to the first power to obtain m cold / heat reference values; Determining a target optimization function based on the predicted time domain length and the m cold and heat reference values; the target optimization function is used to indicate an optimization target between the target control power within the predicted time domain length, the m cold and heat reference values, and the cold and heat predicted values at each second moment obtained based on the target control power prediction; The target control power is determined according to the target optimization function and a preset target relationship expression; the target relationship expression is used to predict the cold and heat prediction value at each second moment according to the target control power.

6. The method according to claim 5, wherein The target control period includes a control moments, the target regulation power includes a sub-regulation powers, and the a control moments correspond to the a sub-regulation powers in a one-to-one manner; and regulating the target device in the target control period according to the target regulation power includes: Obtain control scenario indicators for the target control cycle; Determining a control rate according to the control scenario indicator; Determining a sub-control power at each of the a control moments according to the control rate and the target control power, to obtain the a sub-control powers; The target device is regulated in the target control period according to the a control moments and the a sub-regulation powers.

7. The method according to any one of claims 1 to 6, wherein: The step of predicting the temperature at each of n first moments after the target moment based on the first environmental disturbance behavior and the first temperature data to obtain n predicted temperatures includes: Obtain historical environmental disturbance behavior data; Predicting the occurrence probability of the second environmental disturbance behavior at each first moment based on the historical environmental disturbance behavior data to obtain n behavior occurrence probabilities; The temperature at each of the n first moments after the target moment is predicted based on the n behavior occurrence probabilities, the first environmental disturbance behavior, and the first temperature data to obtain the n predicted temperatures.

8. A device control device, characterized in that: The device includes an acquisition unit and a processing unit; The acquisition unit is configured to acquire a first environmental disturbance behavior and first temperature data during a first control period; the first temperature data includes a first indoor temperature and a first outdoor temperature of the room during the first control period; the first environmental disturbance behavior is a behavior that causes the first indoor temperature to change; The processing unit is configured to predict the temperature at each of n first moments after a target moment based on the first environmental disturbance behavior and the first temperature data, to obtain n predicted temperatures, where the target moment is an end moment of the control cycle; Determining a target control period and a target regulation power according to the n predicted temperatures and a preset target temperature; According to the target regulation power, the target device is regulated in the target control period so that the indoor temperature of the room at each first moment is less than or equal to the target temperature.

9. An electronic device, characterized in that: include: A processor and a memory, the processor being connected to the memory, the memory being used to store a computer program, and the processor being used to execute the computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images