Air conditioner control method and device, electronic equipment and readable storage medium

Abstract

The invention provides an air conditioner control method and device, electronic equipment and a readable storage medium, and is applied to the technical field of air conditioner control. The method comprises the steps of obtaining historical time sequence data; the historical time sequence data comprises historical operation parameters of the air conditioner at a plurality of historical moments; according to the historical time series data and a preset time series prediction model, predicted time series data are obtained, and the predicted time series data comprise predicted operation parameters of the air conditioner at multiple future moments; taking the condition that the operation parameters of the air conditioner are within a preset parameter range as a constraint condition, taking the evaluation score of the operation parameters of the air conditioner as a fitness function value, optimizing the predicted operation parameters based on a genetic algorithm to obtain target operation parameters, and controlling the air conditioner to operate according to the target operation parameters; wherein the evaluation score is positively correlated with the accuracy of the operation parameters and is negatively correlated with the energy consumption. According to the air conditioner control method, the requirements for comfort and energy consumption can be met, and the air conditioner can be accurately controlled.

Description

Technical Field

[0001] The present application belongs to the technical field of air conditioning control, and specifically relates to an air conditioning control method, device, electronic device and readable storage medium. Background Art

[0002] With the development of technology, air conditioning has become a necessity in daily life.

[0003] In the related art, the air conditioner obtains the operating parameters such as temperature and humidity set by the user most recently, and in the subsequent operation process, operates according to the operating parameters set by the user.

[0004] However, with this method, the air conditioner can only operate based on fixed set parameters, and cannot perform adaptive automatic control according to the actual operating conditions of the air conditioner, which will make it difficult for the air conditioner to meet user needs, the air conditioner control is inaccurate, and there will be problems with high air conditioner energy consumption. Summary of the invention

[0005] The present application aims to provide an air conditioning control method, device, electronic device and readable storage medium, which at least solve the problem that the air conditioning control method in the prior art is difficult to meet the control accuracy and energy consumption requirements.

[0006] In a first aspect, an embodiment of the present application discloses an air conditioning control method, comprising:

[0007] Acquire historical time series data; the historical time series data includes historical operating parameters of the air conditioner at multiple historical moments;

[0008] According to the historical time series data and the preset time series prediction model, the predicted time series data is obtained; the predicted time series data includes the predicted operating parameters of the air conditioner at multiple future moments;

[0009] Taking the operating parameters of the air conditioner being within the preset parameter range as a constraint condition and the evaluation score of the operating parameters of the air conditioner as the fitness function value, the predicted operating parameters are optimized based on the genetic algorithm to obtain the target operating parameters, so as to control the operation of the air conditioner according to the target operating parameters;

[0010] Among them, the evaluation score is positively correlated with the accuracy of operating parameters and negatively correlated with energy consumption.

[0011] In a second aspect, an embodiment of the present application discloses an air conditioning control device, comprising:

[0012] A first acquisition module is used to acquire historical time series data; the historical time series data includes historical operating parameters of the air conditioner at multiple historical moments;

[0013] A second acquisition module is used to acquire predicted time series data according to the historical time series data and a preset time series prediction model; the predicted time series data includes predicted operating parameters of the air conditioner at multiple future moments;

[0014] The third acquisition module is used to optimize the predicted operating parameters based on a genetic algorithm, with the operating parameters of the air conditioner being within a preset parameter range as a constraint condition and the evaluation score as the fitness function value, to obtain target operating parameters, so as to control the operation of the air conditioner according to the target operating parameters; the evaluation score is positively correlated with the accuracy of the operating parameters and negatively correlated with the energy consumption of the air conditioner.

[0015] In a third aspect, an embodiment of the present application further discloses an electronic device, comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0016] In a fourth aspect, an embodiment of the present application further discloses a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0017] In a fifth aspect, an embodiment of the present application further discloses an air conditioner, which includes the air conditioner control device as described in the second aspect, or the electronic device as described in the third aspect.

[0018] In summary, in this implementation, based on historical time series data and a time series prediction model, predicted time series data is obtained. The predicted time series data is obtained based on the actual data of the air conditioner in the historical time period. The data can meet the user's dynamic needs for the air conditioner operating parameters. With the operating parameters of the air conditioner being within the preset parameter range as a constraint condition and the evaluation score as the fitness function value, the predicted operating parameters in the predicted time series data are optimized through a genetic algorithm. The obtained target operating parameters are operating parameters that are within the preset parameter range and meet the user's needs, and the target operating parameters are operating parameters that meet the control result accuracy and energy consumption requirements. The air conditioner is operated based on the target operating parameters obtained in this embodiment, which can meet the control result accuracy requirements and energy consumption requirements, and realizes automatic control of the air conditioner, solving the problem that the air conditioner control method in the related art is difficult to meet the control result accuracy and energy consumption requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In the attached picture:

[0020] Figure 1 is a flowchart of the steps of an air conditioning control method provided by an embodiment of the present application;

[0021] Figure 2It is a schematic diagram of the topological structure of a RNN model provided in an embodiment of the present application;

[0022] Figure 3 It is a schematic diagram of the topological structure of an LSTM model provided in an embodiment of the present application;

[0023] Figure 4 It is a schematic diagram of controlling a gate through an LSTM model provided in an embodiment of the present application;

[0024] Figure 5 is a flowchart of another air conditioning control method provided by an embodiment of the present application;

[0025] Figure 6 is a flowchart of another air conditioning control method provided by an embodiment of the present application;

[0026] Figure 7 is a flowchart of another method for obtaining historical operating parameters provided by an embodiment of the present application;

[0027] Figure 8 It is a flowchart of the steps of a method for obtaining a time series prediction model provided by an embodiment of the present application;

[0028] Fig. 9 is a flowchart of another air conditioning control method provided by an embodiment of the present application;

[0029] Fig.10 is a structural schematic diagram of an air conditioning control system provided by an embodiment of the present application;

[0030] Fig.11 is a block diagram of an air conditioning control device provided in an embodiment of the present application;

[0031] Fig.12 is a block diagram of an electronic device according to an embodiment of the present application;

[0032] Fig.13 It is a block diagram of an electronic device of another embodiment provided by the embodiments of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0035] Figure 1 This is an air conditioning control method provided by this embodiment, referring to Figure 1 , the method may include the following steps:

[0036] Step 101, obtaining historical time series parameters.

[0037] Specifically, the historical time series data includes historical operating parameters of the air conditioner at multiple historical moments.

[0038] The historical operating parameters of the air conditioner at multiple historical moments are obtained, and the multiple historical operating parameters are arranged in chronological order to form historical time series data. The historical operating data may be temperature, humidity, energy consumption, or other operating parameters.

[0039] Step 102, obtaining predicted time series data according to historical time series data and a preset time series prediction model.

[0040] The predicted time series data includes predicted operating parameters of the air conditioner at multiple future moments.

[0041] For example, a time series data sample is obtained, and a machine learning model for time series prediction is trained using the time series data sample to obtain a time series prediction model.

[0042] For example, a time series data sample includes data samples at multiple time points, and the samples at each time point include temperature, humidity, and energy consumption.

[0043] The machine learning model is a long short-term memory network (LSTM) neural network model. Among them, the LSTM neural network model adds memory units to the phrenic nerve units in the hidden layer of the ordinary recurrent neural network (RNN) model, so that the RNN model has a long-term memory function. Furthermore, the RNN model is based on the artificial neural network, adding a hidden layer to imply the horizontal connection between units, and then transferring the value of the previous time step of the neural network to the current time step, so that the neural network has a memory function.

[0044] The RNN model can be used to process natural language recognition (NLP) and time series machine learning problems with contextual connections. Specifically, the RNN model structure can be as follows: Figure 2 As shown, O represents the output layer, O t-1 , O t and O t+1 represents the output data of the output layer at time t-1, time t, and time t+1 respectively; V represents the weight matrix from the hidden layer to the output layer; s represents the hidden layer, S t-1 , S t and S t+1 Respectively represent the output data of the hidden layer at time t-1, time t, and time t+1; U represents the weight matrix from the input layer to the hidden layer; T represents the input layer, T t-1 , T t and T t+1 Respectively represent the data of the input layer at time t-1, time t, and time t+1; W represents the weight matrix that uses the previous value of the hidden layer as the input this time.

[0045] Reference Figure 2 The hidden layer of the RNN model is mainly used to capture time series information for iterative calculations. The original RNN hidden layer has only one state s, which is sensitive to short-term data input. The LSTM model adds a cell state (cellstate) on the basis of the RNN model to save the state of long-term data.

[0046] For example, the structure of the LSTM neural network is as follows Figure 3 As shown, refer to Figure 3 , C represents a cell state (cellstate) added by the LSTM model based on the RNN model ， The cell state is used to save the state of long-term data; C t-2 , C t-1 , C t , and C t+1Respectively represent the data saved at time t-2, time t-1, time t, and time t+1; s represents the hidden layer, S t-2 , S t-1 , S t and S t+1 represents the output data of the hidden layer at time t-2, time t-1, time t and time t+1 respectively; T represents the input layer, T t-1 、T t and T t+1 Represent the data of the input layer at time t-1, time t, and time t+1 respectively.

[0047] Reference Figure 3 , LSTM can adjust the weights of historical data and current data through three controllable gates, and then optimize the model to obtain the optimal model.

[0048] Figure 4 The control gate diagram of LSTM is shown. Figure 4 , through three controllable gates, the weight of historical information and current information can be adjusted to optimize and obtain the optimal LSTM model. t-1 is the long-term state at time t-1, C t is the updated state at time t, C tt is the instantaneous state at the current time t, S t is the output at the current moment.

[0049] Based on the RNN model, LSTM calculates the state of the current unit according to the previous temperature output value and the current temperature input value:

[0050] c tt =tanh(Wc×(s t-1 , T t )+bc)

[0051] Among them, c tt is the memory unit state at the current moment; (s t-1 , Tt) represents connecting two vectors; Wc and bc are the weight and bias parameters of the forget gate respectively; s t-1 is the neuron output value at the previous moment. t-1 is the neuron output value at time t-1, T t Represents the input at time t.

[0052] Through the control of the forget gate in the LSTM model, the new cell state c tInformation from a long time ago can be saved. By controlling the input gate in the LSTM model, non-important features of the current time step can be prevented from entering the memory unit. The final output value (for example, temperature) of the LSTM model is determined by the output gate and the unit state. If the output value is temperature, then the temperature O t for:

[0053] O t =σ(Wo×(s t-1 , T t )+bo)

[0054] Among them, O t is the final output value of LSTM; Wo and bo are the weight and bias parameters of the output gate respectively. When using the LSTM model for time series prediction, the output value of the LSTM model is the predicted value of the LSTM model. σ is the activation function, and the linear rectification function (ReLU) can be used to enhance the nonlinear processing ability of the function. t is the neuron input value at the tth moment.

[0055] Based on the same processing method as above, the humidity value H and energy consumption E predicted by the LSTM model can be obtained.

[0056] Step 103, taking the operating parameters of the air conditioner being within the preset parameter range as a constraint condition and the evaluation score of the operating parameters of the air conditioner as the fitness function value, based on the genetic algorithm, the predicted operating parameters are optimized to obtain the target operating parameters, so as to control the operation of the air conditioner according to the target operating parameters.

[0057] Among them, the evaluation score is positively correlated with the accuracy of operating parameters and negatively correlated with energy consumption.

[0058] For example, the operating parameters may include temperature, humidity and energy consumption. In each iteration of parameter optimization through the genetic algorithm, the temperature, humidity and energy consumption are taken as an individual. When adjusting the operating parameters in the individual, the temperature needs to fall within the preset temperature range, the humidity needs to fall within the preset humidity range, and the energy consumption needs to fall within the preset energy consumption range.

[0059] During each iteration, for each individual, the operating parameters in the individual are substituted into the preset total evaluation score calculation model to obtain the evaluation score corresponding to the individual. If the maximum evaluation score is greater than or equal to the preset score threshold, or the number of iterations of the current iteration is greater than the preset number threshold, the iteration is stopped, and the operating parameters in the individual corresponding to the maximum total evaluation score are determined as the target operating parameters.

[0060] With the rapid development of science and technology and the improvement of living standards, air conditioners play an increasingly important role in daily life. In related technologies, air conditioners are controlled by users setting fixed operating parameters. Based on this control method, air conditioners cannot be accurately adjusted according to changes in indoor and outdoor environments and user needs. Because they cannot be adjusted automatically, the air conditioner control method in related technologies also has problems such as high energy consumption and poor control result accuracy.

[0061] In this embodiment, the predicted time series data is obtained based on the historical time series data and the time series prediction model. The predicted time series data is obtained based on the actual data of the air conditioner in the historical time period. The data can meet the user's dynamic needs for the air conditioner operating parameters. With the operating parameters of the air conditioner being within the preset parameter range as a constraint condition and the evaluation score as the fitness function value, the predicted operating parameters in the predicted time series data are optimized through a genetic algorithm. The obtained target operating parameters are operating parameters that are within the preset parameter range and meet the user's needs, and the target operating parameters are operating parameters that meet the control result accuracy and energy consumption requirements. The air conditioner is operated based on the target operating parameters obtained in this embodiment, which can meet the control result accuracy requirements and energy consumption requirements, and realizes automatic control of the air conditioner, solving the problem that the air conditioner control method in the related art is difficult to meet the control result accuracy and energy consumption requirements.

[0062] Figure 5 A flowchart of another air conditioning control method provided in an embodiment of the present application is shown. Figure 5 , the method may include the following steps:

[0063] Step 201, obtaining historical time series data.

[0064] The historical time series data includes the historical operating parameters of the air conditioner at multiple historical moments.

[0065] The method of this step has been described in the aforementioned step 101 and will not be repeated here.

[0066] Step 202, obtaining predicted time series data according to historical time series data and a preset time series prediction model.

[0067] The forecast time series data includes the forecast operating parameters of the air conditioner at multiple future moments.

[0068] The method of this step has been described in the aforementioned step 102 and will not be repeated here.

[0069] Step 203: In each iteration process, a plurality of first operating parameters satisfying the constraint conditions are obtained according to the predicted operating parameters.

[0070] The process of optimizing the predicted operating parameters based on genetic algorithms includes multiple iterations.

[0071] In the first iteration, the predicted operating parameters are obtained, and the predicted operating parameters are adjusted within the preset parameter range to obtain multiple sets of operating parameters. The adjustment method may include: encoding the predicted operating parameters, changing the data of the encoded data bits, or using a preset step size to adjust the predicted operating parameters, or other adjustment methods.

[0072] The multiple groups of operating parameters obtained after adjusting the predicted operating parameters are determined as the initial population of the genetic algorithm, and each group of operating parameters constitutes an individual in the initial population.

[0073] For example, the population size is set to N, and each individual includes a set of air conditioning operation parameters, such as temperature, humidity and energy consumption. For example, the preset parameter range corresponding to the temperature can be 16°C to 30°C, and the humidity can be 40% to 70%.

[0074] In the second iteration, multiple second operating parameters are selected from the multiple initial individuals of the first iteration, and the second operating parameters are adjusted to obtain the first operating parameters.

[0075] For example, step 203 may include the following sub-steps:

[0076] Sub-step A1, selecting a plurality of third operating parameters from a plurality of second operating parameters obtained in the previous iteration.

[0077] For example, a plurality of third operating parameters can be selected from a plurality of second operating parameters by a roulette wheel selection method. Specifically, the fitness value of each second operating parameter is obtained, and the probability of the individual being selected is determined according to the size of the fitness value, wherein the probability of being selected is proportional to the size of the fitness value. In other words, selection is made based on the fitness ratio, and the best individual is retained according to the elitism strategy, and then the retained best individual is used as the individual to be optimized in the next iteration and enters the next iteration.

[0078] For example, a plurality of third operating parameters can be selected from a plurality of second operating parameters by a tournament selection method. Specifically, a plurality of individuals are randomly selected from a plurality of individuals in a population, the fitness values ​​of the plurality of individuals are compared, and the individual with the largest fitness value is selected as the individual to be optimized in the next iteration and enters the next iteration.

[0079] Sub-step A2: performing an encoding operation on the third operating parameter to obtain a string structure of the third operating parameter.

[0080] For example, the third operating parameter may be encoded to obtain a string structure representation in a binary format.

[0081] Sub-step A3: obtaining a third operating parameter combination from a plurality of third operating parameters.

[0082] For example, the third operating parameters are randomly combined in pairs to obtain multiple third operating parameter combinations.

[0083] Sub-step A4: exchanging data of first preset data bits of different third operating parameter string structures in the third operating parameter combination to obtain first operating parameters that meet multiple constraint conditions.

[0084] For example, the third operating parameter combination includes two third operating parameters, each of which is a string structure obtained through encoding processing, and the number of data bits of each third operating parameter is the same. For example, the string structure of one third operating parameter is 10001, and the string structure of the other is 10010. The first data bits (the second data bit from the right) of the two third operating parameters are exchanged, and the first operating parameters obtained are 10011 and 10000.

[0085] Through step A2 to step A4, the crossover operation on the third operating parameter can be completed. Further, the third operating parameter of the current iteration is the parent parameter selected from the previous iteration. The selected parent parameter is crossover-operated to exchange at least part of the parameters, such as temperature, humidity, and / or energy consumption, to obtain a new offspring individual, which is the first operating parameter.

[0086] For example, when performing a crossover operation on the parent generation parameters, the crossover probability can be set according to user requirements, and for example, the crossover probability can be set to 0.1. Performing a crossover operation based on the set crossover probability can improve the diversity of samples in the population.

[0087] For example, step 203 may include the following sub-steps:

[0088] Sub-step B1 selects a plurality of third operating parameters from a plurality of second operating parameters obtained in the previous iteration.

[0089] The method of this step has been described in A1 above and will not be repeated here.

[0090] Sub-step B2: performing an encoding operation on the third operating parameter to obtain a string structure of the third operating parameter.

[0091] The method of this step has been described in A2 above and will not be repeated here.

[0092] Sub-step B3, exchanging the data of the second preset data bit and the third preset data bit in the string structure of the third operating parameter to obtain the first operating parameter that meets the constraint condition.

[0093] For example, the string structure of a third operating parameter is 10001, and the second preset data bit (the first data bit from the right) and the third preset data bit (the second data bit from the right) are exchanged to obtain the first operating parameter 10010.

[0094] Through sub-step B3, the variation operation of the third operating parameter can be completed. Furthermore, the third operating parameter of the current iteration is the parent parameter selected from the previous iteration. Randomly changing some selected parent parameters (such as temperature and humidity) with a small probability (such as 0.01) can increase the diversity of the population and avoid falling into the local optimum.

[0095] For example, the first operating parameter can be obtained by the method of sub-steps A1 to A4, or by the method of sub-steps B1 to B3. The third operating parameter can also be cross-processed according to the method of sub-steps A1 to A4 to obtain the fourth operating parameter, and then the method shown in sub-step B2 can be performed according to the fourth operating parameter as the offspring individual to perform a random change with a small probability on the offspring individual to obtain the first operating parameter.

[0096] For example, the first operating parameters after crossover and mutation can be combined with a preset number of second operating parameters with higher fitness values ​​in the second operating parameters to form the final first operating parameters. The first operating parameters thus obtained are the new generation population formed according to the parameter optimization results of the previous iteration.

[0097] Furthermore, the fitness value corresponding to each first operating parameter is calculated, the first operating parameters whose fitness values ​​are less than the fitness threshold are deleted, and the remaining first operating parameters are determined as the final first operating parameters.

[0098] For example, an iteration number threshold (for example, 10,000 times) may be set, and when the iteration number of the current iteration reaches the iteration number threshold, the iteration is stopped; a fitness threshold may be set, and when the fitness value reaches the fitness threshold, the iteration is stopped.

[0099] After the iteration is stopped, the individual with the highest fitness in the current population is output as the optimal target operating parameter, so that the air conditioner can operate according to the target operating parameter.

[0100] Furthermore, when the genetic algorithm outputs the optimal combination of air conditioning operating parameters, these parameters will be sent to the air conditioning control system as control instructions. The control system adjusts the operating state of the air conditioner in real time according to these parameters to get as close as possible to the predicted future environmental parameters and keep the indoor environment within the comfort range expected by the user.

[0101] Step 204: Obtain a first evaluation score corresponding to the first operating parameter.

[0102] For example, the first operating parameter is substituted into a preset evaluation score model to obtain a first evaluation score corresponding to the first operating parameter.

[0103] Step 205: Obtain the maximum first evaluation score from the multiple first evaluation scores.

[0104] A set of first operating parameters corresponds to a first evaluation score. The first evaluation scores are compared to obtain a maximum first evaluation score.

[0105] Step 206: If the maximum first evaluation score is greater than or equal to the preset score threshold, the iteration is stopped, and the first operating parameter corresponding to the maximum first evaluation score is determined as the target operating parameter.

[0106] Furthermore, if the maximum first evaluation score is less than the preset score threshold, the iteration continues until a maximum first evaluation score greater than or equal to the preset score threshold is obtained.

[0107] In this embodiment, the predicted time series data is obtained based on the historical time series data, and the prediction of the air conditioner operating parameters is realized. In each iteration process, multiple first operating parameters that meet the constraint conditions are obtained based on the predicted operating parameters, and then the target operating parameters are obtained based on the first evaluation scores of the first operating parameters. The target operating parameters thus obtained not only meet the preset operating parameter range, but also meet the control result accuracy and energy consumption requirements. The air conditioner operation is controlled based on the target operating parameters, and the air conditioner operating parameters are automatically controlled, and the control method can meet the control result accuracy and energy consumption requirements.

[0108] For example, the evaluation score of the air conditioner operating parameters can be obtained by the following method:

[0109] Step 207, obtaining the evaluation score of the air conditioner operating parameters according to the air conditioner operating parameters and a preset evaluation score model;

[0110] The default evaluation score model is:

[0111] F(T,H,E)=ω1×f1(T,H)-ω2×f2(E)

[0112] Among them, F(T, H, E) is the evaluation score, f1(T, H) is the evaluation score for the air conditioner operating parameters, f2(E) is the evaluation score for the energy consumption of the operating parameters, ω1 and ω2 are the weight values ​​of the evaluation score for the air conditioner operating parameters and the weight value of the evaluation score for energy consumption respectively; T, H, E are temperature, humidity and energy consumption respectively. For example, ω1+ω2=1.

[0113] Obtain historical time series data, input it into the time series prediction model, obtain the predicted time series data output by the time series prediction model, and predict the operating parameters at each time point in the predicted time series data. According to the preset operating parameter range and target energy consumption set by the user, build an evaluation score model and an energy consumption evaluation score model, and then obtain an evaluation score calculation model. The evaluation score output by the evaluation score calculation model is related to environmental parameters, user-expected humidity, temperature, and energy consumption.

[0114] For example, the user sets the temperature range to [T1, T2], the humidity range to [H1, H2], and the energy consumption target to E0. T1 and T2 are the lower and upper limits of the temperature, respectively; H1 and H2 are the lower and upper limits of the humidity, respectively.

[0115] For example, the evaluation score f1(T, H) for the operating parameters of the air conditioner is obtained according to the following method:

[0116]

[0117] T and H are the temperature and humidity in the air conditioning operation parameters, T0 is the preset temperature, H0 is the preset humidity, T r H is the difference between the upper temperature limit and the lower temperature limit in the preset temperature range. r It is the difference between the upper humidity limit and the lower humidity limit in the preset humidity range.

[0118] Among them, |T-T0| and |H-H0| represent the deviations of temperature and humidity from the optimal values, respectively; the exponential function is used to smoothly penalize the deviation so that the fitness decreases as the deviation increases.

[0119] The higher the accuracy of the air conditioner operating parameters, the higher the user comfort level. Conversely, the lower the user comfort level, ω1 and ω2 can be adjusted according to the specific needs of the user. For example, if the user is more concerned about the accuracy of the air conditioner operating parameters, the value of ω1 can be increased; if the user is more concerned about energy saving, the value of ω2 can be increased.

[0120] For each possible combination of environmental parameters, its fitness value F is calculated. The higher the fitness value, the better the set of parameters.

[0121] The evaluation score f2(E) of the energy consumption for the operating parameters is obtained according to the following method:

[0122]

[0123] E is the energy consumption in the air conditioner operation parameters, E0 is the preset energy consumption, and E1 is the difference between the upper limit and the lower limit of energy consumption in the preset energy consumption range. The exponential function is also used to smoothly punish the deviation of energy consumption from the target.

[0124] Figure 6 is a flowchart of another air conditioning control method provided in an embodiment of the present application, referring to Figure 6 , the method may include the following steps:

[0125] Step S1, collect historical operating parameters at multiple historical moments and construct historical time series data.

[0126] After collecting the initial historical operating parameters of multiple historical moments, the historical operating parameters are first cleaned and preprocessed. After the processed historical operating parameters are obtained, historical time series data are constructed based on the processed historical operating parameters.

[0127] For example, refer to Figure 7 , the method for obtaining historical operating parameters may include the following sub-steps:

[0128] Sub-step S11, starting the air conditioning sensor module.

[0129] For example, the air conditioning sensor module includes a temperature sensor, a humidity sensor, and a power sensor for calculating energy consumption.

[0130] Sub-step S12, collecting historical operating parameters through the air conditioning sensor module.

[0131] For example, the temperature of the air conditioner operating environment is collected through a temperature sensor, the humidity of the air conditioner operating environment is collected through a humidity sensor, the power information of the air conditioner is obtained through a power sensor, and the energy consumption of the air conditioner is calculated based on the power.

[0132] Sub-step S13, performing data preprocessing on historical operating parameters.

[0133] For example, the collected historical operating parameters are processed to remove outliers, missing values ​​and noise data.

[0134] Sub-step S14, storing the pre-processed historical operating parameters.

[0135] For example, a storage medium may be used to store processed historical operating parameters, and historical event sequence data may be constructed based on the processed historical operating parameters.

[0136] In this embodiment, a rule-based data cleaning method can be used, combined with statistical analysis and machine learning algorithms, to automatically identify and process outliers and noise data. Specifically, in the data preprocessing stage, a minimum-maximum (Min-Max) standardization or a standard score (Z-score) standardization method can be used to convert different types of operating parameters (such as temperature, humidity, and energy consumption) into a unified format and dimension.

[0137] Furthermore, various sensors deployed indoors and outdoors collect environmental parameter data in real time. Sensors include temperature sensors, humidity sensors, air quality sensors, etc. After collecting the operating parameters, the collected raw data is transmitted to the data processing center.

[0138] The data processing center cleans the data, including removing outliers, missing values, and noise data, to ensure data quality. The data is standardized, and data of different dimensions and ranges are converted into a unified format for subsequent analysis.

[0139] Step S2, inputting the historical time series data into a preset time series prediction model to obtain predicted time series data.

[0140] The time series prediction model is constructed according to the following method: During the model construction process, first select the appropriate neural network architecture according to the characteristics of the problem. The neural network architecture can be an LSTM model or a gated recurrent unit (GRU). Then, design a network structure including the following layers: input layer, hidden layer (multi-layer) and output layer, as well as the connection method between layers (such as full connection, sequence connection, etc.). During the training process, optimization algorithms such as batch gradient descent or Adam optimizer are used, combined with cross entropy loss function or mean square error loss function, to iteratively update the model parameters.

[0141] After obtaining the forecast time series data, the forecast results are optimized. Specifically, in order to improve the accuracy and reliability of the forecast results, an ensemble learning method is used to weighted average or vote the forecast results of multiple time series forecast models to reduce the uncertainty of a single model. At the same time, a time window mechanism is introduced to dynamically adjust the size of the forecast time window according to the historical forecast error, thereby adapting to environmental changes in different time periods.

[0142] For example, historical data is extracted from the data storage system as a training set, and a deep learning prediction model (such as LSTM or GRU) is trained through the training set. The model is trained using the training set data, and the model parameters are continuously optimized through the back propagation algorithm to improve the prediction accuracy, and finally a trained time series prediction model is obtained.

[0143] When new real-time data is received, the historical time series data is updated according to the real-time data and passed as input to the trained prediction model. The time series prediction model outputs the prediction results of environmental parameters in the future based on real-time data and historical rules. The prediction results include data such as temperature and humidity.

[0144] For example, the method to obtain the time series prediction model is as follows Figure 8 As shown, refer to Figure 8, the method may include the following steps:

[0145] Sub-step S21, obtaining an LSTM model based on the RNN model.

[0146] For example, based on the RNN model, memory units are added to each neural unit in the hidden layer to enable the RNN network to have long-term memory function and obtain the LSTM model.

[0147] Sub-step S22, using the time series data samples to train the LSTM model.

[0148] You can obtain multiple sets of time series data samples and use the time series samples to train the LSTM model.

[0149] Sub-step S23, during the model training process, using the prediction results of each iteration to optimize the LSTM model.

[0150] The expected time series data can be used as labels, and the time series data samples and labels can be used to train the LSTM model. In each iteration, the loss function value is obtained, and the model parameters of the LSTM model are optimized according to the loss function value. When the loss function value tends to be stable, or when the number of iterations reaches the preset iteration threshold, the iteration is stopped to complete the optimization of the LSTM model.

[0151] Sub-step S24, when the iteration condition is met, the LSTM model obtained in the last iteration is determined as the time series prediction model.

[0152] Further, see Fig. 9 After obtaining the time series prediction model, the predicted time series data can be obtained by the following method:

[0153] Sub-step S25, obtaining historical time series data.

[0154] Use sensors to collect operating parameters at multiple times and then construct historical time series data.

[0155] Sub-step S26, obtaining predicted time series data including environmental parameters based on historical time series data.

[0156] The historical time series data are input into the time series prediction model to obtain the predicted time series data including environmental parameters.

[0157] Sub-step S27, adjusting the predicted time series data to obtain adjusted operating parameters.

[0158] For example, the forecast time series data is processed by removing abnormal data, removing noise data, etc. to obtain adjusted operating parameters.

[0159] Sub-step S28, performing feedback optimization on the adjusted operating parameters to obtain target operating parameters.

[0160] The adjusted operating parameters are used as the operating parameters to be optimized and are optimized through a genetic algorithm to obtain the target operating parameters.

[0161] Step S3, optimizing the predicted operating parameters through a genetic algorithm to obtain target operating parameters.

[0162] For example, the control strategy optimization adopted includes: using a multi-objective optimization algorithm (Nondominated Sorting Genetic Algorithm II, NSGA-II), comprehensively considering multiple objectives such as user comfort, energy consumption and system stability, and finding the optimal control parameter combination through iterative calculation. At the same time, a feedback mechanism is introduced to adjust and optimize the control strategy in real time according to the actual operation effect.

[0163] Furthermore, a preliminary control strategy can be formulated based on the comfort range set by the user and the prediction results. A multi-objective optimization algorithm is used to comprehensively consider multiple objectives such as user comfort, energy consumption, and system stability to optimize and adjust the preliminary control strategy.

[0164] According to the method of this embodiment, target operating parameters can be obtained, and the target operating parameters are the optimal control parameter combination. The operating parameters in the optimal control parameter combination may include set temperature, wind speed, operating mode, etc.

[0165] Step S4, controlling the air conditioner operation according to the target operation parameters.

[0166] The optimal control parameter combination is sent to the air conditioning control system for the air conditioning to execute the corresponding control instructions. The air conditioning system adjusts the operating parameters according to the received control instructions to achieve precise control of the indoor environment.

[0167] For example, the indoor environmental parameters and the operating status of the air conditioning system can be continuously monitored, and the actual operating effect data can be collected. The actual operating effect data can be compared and analyzed with the predicted results to evaluate the control effect.

[0168] For example, the prediction model and control strategy are iteratively optimized according to the feedback results to improve the overall performance of the system and user satisfaction. The current indoor environment parameters, prediction results, control status and other information can be displayed through the user interaction interface. In this embodiment, the user is allowed to adjust the control strategy or set a new comfort range according to the user's preference.

[0169] For example, the method of this embodiment supports the user remote control function, and the user can monitor and control the air-conditioning system anytime and anywhere through a mobile phone application (Application, APP).

[0170] For example, air conditioning control can be performed through big data analysis and model predictive control (MPC) technology. Specifically, based on historical environmental parameter data and real-time environmental parameter data, a trained large model is used to predict environmental parameters in the future, such as temperature, humidity, air quality, etc. The operating parameters of the air conditioner are adjusted in advance according to the predicted environmental parameters, thereby achieving precise control of the indoor environment.

[0171] The air conditioning control system in the related art cannot be accurately adjusted according to the changes in the indoor and outdoor environment and the needs of users, resulting in high energy consumption and poor comfort; the air conditioning control system in the related art lacks the ability to predict future environmental parameters and cannot adjust the air conditioning operating parameters in advance to adapt to future environmental changes. The air conditioning control method of this embodiment can ensure that the indoor environment always remains within the comfort range expected by the user through accurate prediction and dynamic adjustment, thereby improving the user's comfort. The air conditioning operating parameters can be adjusted according to actual needs to avoid unnecessary energy waste and reduce energy consumption. The operating efficiency and service life of the air conditioning system can be improved by optimizing the control strategy. The use of large models for prediction and control improves the intelligence level and adaptive ability of the system.

[0172] For example, the air conditioning can be controlled through the intelligent predictive control model, which combines big data analysis and model predictive control technology. It can accurately predict the environmental parameters in the future and adjust the operating parameters of the air conditioner in advance according to the predicted environmental parameters to achieve accurate control of the indoor environment. Furthermore, the big model is used to train historical data and real-time data, learn the inherent laws and associations between the data, and thus build a model that can accurately predict future environmental parameters.

[0173] For example, the present application also provides an air conditioning control system, referring to Fig.10 ,The system may include a data acquisition module, a data processing module, a model prediction module, a control execution module and a user interaction module.

[0174] The data acquisition module is used to deploy various sensors, including but not limited to temperature sensors, humidity sensors, air quality sensors, human infrared sensors, and smart meters, to comprehensively collect indoor and outdoor environmental parameters, user behavior information, and energy consumption data. Furthermore, each sensor network is connected to the data processing layer via wired or wireless means to ensure the real-time and accuracy of the data.

[0175] The data processing layer is used to clean the data after receiving it from the data collection layer, remove outliers and noise data, and then perform data standardization to unify the data format and dimension for subsequent analysis. The data processing layer also has data storage functions and uses a distributed database system to ensure efficient storage and fast retrieval of massive data.

[0176] The model prediction layer is the core of the air conditioning control system. The model prediction layer uses deep learning technology to build a prediction model. Specifically, a neural network model suitable for processing time series data such as LSTM or GRU is selected. Furthermore, during the model training process, historical environmental parameters and user behavior data are used as input, and environmental parameters in the future are used as output. The model parameters are continuously optimized through the back propagation algorithm to improve the prediction accuracy. At the same time, regularization and dropout layers in the model are introduced to prevent overfitting and ensure the generalization ability of the model.

[0177] The control execution layer is used to calculate and adjust the operating parameters of the air conditioner based on the prediction results of future environmental parameters output by the model prediction layer. Specifically, first, based on the comfort range set by the user, such as temperature range, humidity range, etc., combined with the prediction results, the optimal air conditioner operating parameters, such as set temperature, wind speed, operating mode, etc., are calculated through optimization algorithms such as genetic algorithms and particle swarm optimization algorithms. Then, the control instructions are sent to the air conditioner control system to realize automatic adjustment of the air conditioner parameters.

[0178] The user interaction layer is used to provide a user-friendly interactive interface, allowing users to view the current indoor environmental parameters, prediction results and control status, and allow users to adjust the control strategy according to user preferences. At the same time, this layer also has a remote control function, and users can remotely monitor and control the air conditioning system through a mobile phone APP or a web page.

[0179] The data collection layer is used to deploy various sensors, including temperature sensors, humidity sensors, air quality sensors,

[0180] refer to Fig.11 , which shows an air conditioning control device 30 provided in an embodiment of the present application, the air conditioning control device 30 includes:

[0181] The first acquisition module 301 is used to acquire historical time series data; the historical time series data includes historical operating parameters of the air conditioner at multiple historical moments;

[0182] The second acquisition module 302 is used to acquire predicted time series data according to the historical time series data and the preset time series prediction model; the predicted time series data includes predicted operating parameters of the air conditioner at multiple future moments;

[0183] The third acquisition module 303 is used to optimize the predicted operating parameters based on a genetic algorithm, with the operating parameters of the air conditioner being within a preset parameter range as a constraint condition and the evaluation score of the operating parameters of the air conditioner as the fitness function value, to obtain target operating parameters so as to control the operation of the air conditioner according to the target operating parameters; the evaluation score is positively correlated with the accuracy of the operating parameters and negatively correlated with energy consumption.

[0184] Optionally, the third acquisition module 303 includes:

[0185] A first acquisition submodule is used to acquire a plurality of first operating parameters satisfying the constraint conditions according to the predicted operating parameters during each iteration;

[0186] A second acquisition submodule, used to acquire a first evaluation score corresponding to the first operating parameter;

[0187] A third acquisition submodule is used to acquire the maximum first evaluation score from multiple first evaluation scores;

[0188] The first determination submodule is used to stop iteration if the maximum first evaluation score is greater than or equal to a preset score threshold, and determine the first operating parameter corresponding to the maximum first evaluation score as the target operating parameter.

[0189] Optionally, the first acquisition submodule includes:

[0190] A first selection unit, configured to select a plurality of third operating parameters from a plurality of second operating parameters obtained in a previous iteration;

[0191] A first acquisition unit, configured to perform an encoding operation on the third operating parameter to obtain a string structure of the third operating parameter;

[0192] A second acquisition unit, used for acquiring a third operating parameter combination from a plurality of third operating parameters;

[0193] The third acquisition unit is used to exchange the data of the first preset data bits of different third operating parameter string structures in the third operating parameter combination to obtain the first operating parameter that meets the constraint condition.

[0194] Optionally, the first acquisition submodule includes:

[0195] a fourth acquisition unit, configured to select a plurality of third operating parameters from the plurality of second operating parameters obtained in the previous iteration;

[0196] a fifth acquiring unit, configured to perform an encoding operation on the third operating parameter to obtain a string structure of the third operating parameter;

[0197] The sixth acquisition unit is used to exchange the data of the second preset data bit and the third preset data bit in the string structure of the third operating parameter to obtain the first operating parameter that meets the constraint condition.

[0198] Optionally, the device 30 further includes:

[0199] A fourth acquisition module, used to acquire the evaluation score of the air conditioner operating parameters according to the air conditioner operating parameters and a preset evaluation score calculation model;

[0200] The preset evaluation score calculation model is:

[0201] F(T,H,E)=ω1×f1(T,H)-ω2×f2(E)

[0202] Among them, F(T, H, E) is the evaluation score, f1(T, H) is the evaluation score for air-conditioning operating parameters, f2(E) is the evaluation score for energy consumption, ω1 and ω2 are the weight values ​​of the evaluation score for air-conditioning operating parameters and the weight value of the evaluation score for energy consumption, respectively; T, H, and E are temperature, humidity, and energy consumption, respectively.

[0203] Optionally, the device 30 further includes:

[0204] The fifth acquisition module is used to acquire the evaluation score f1(T, H) for the air conditioner operation parameters according to the following method:

[0205]

[0206] T and H are the temperature and humidity in the air conditioning operation parameters, T0 is the preset temperature, H0 is the preset humidity, T r H is the difference between the upper temperature limit and the lower temperature limit in the preset temperature range. r The difference between the upper humidity limit and the lower humidity limit in the preset humidity range;

[0207] The sixth acquisition module is used to acquire the evaluation score f2(E) for energy consumption according to the following method:

[0208]

[0209] E is the energy consumption in the air conditioner operation parameters, E0 is the preset energy consumption, and E1 is the difference between the upper limit value and the lower limit value of the energy consumption in the preset energy consumption range.

[0210] In this embodiment, the predicted time series data is obtained based on the historical time series data and the time series prediction model. The predicted time series data is obtained based on the actual data of the air conditioner in the historical time period. The data can meet the user's dynamic needs for the air conditioner operating parameters. With the operating parameters of the air conditioner being within the preset parameter range as a constraint condition and the evaluation score as the fitness function value, the predicted operating parameters in the predicted time series data are optimized through a genetic algorithm. The obtained target operating parameters are operating parameters that are within the preset parameter range and meet the user's needs, and the target operating parameters are operating parameters that meet the accuracy and energy consumption requirements of the operating parameters. The air conditioner is operated based on the target operating parameters obtained in this embodiment, which can meet the accuracy requirements and energy consumption requirements of the operating parameters, and realizes automatic control of the air conditioner, solving the problem that the air conditioner control method in the related art is difficult to meet the accuracy and energy consumption requirements of the operating parameters.

[0211] Reference Fig.12 , the electronic device 500 may include one or more of the following components: a processing component 502 , a memory 504 , a power component 506 , a multimedia component 508 , an audio component 510 , an input / output (I / O) interface 512 , a sensor component 514 , and a communication component 516 .

[0212] The processing component 502 generally controls the overall operation of the electronic device 500, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 502 may include one or more processors 520 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 502 may include one or more modules to facilitate the interaction between the processing component 502 and other components. For example, the processing component 502 may include a multimedia module to facilitate the interaction between the multimedia component 508 and the processing component 502.

[0213] The memory 504 is used to store various types of data to support the operation of the electronic device 500. Examples of such data include instructions for any application or method operating on the electronic device 500, contact data, phone book data, messages, pictures, multimedia, etc. The memory 504 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0214] The power supply component 506 provides power to the various components of the electronic device 500. The power supply component 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 500.

[0215] The multimedia component 508 includes an interface that provides an output interface between the electronic device 500 and the user. In some embodiments, the interface may include a liquid crystal display (LCD) and a touch panel (TP). If the interface includes a touch panel, the interface may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front camera and / or a rear camera. When the electronic device 500 is in an operating mode, such as a shooting mode or a multimedia mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0216] The audio component 510 is used to output and / or input audio signals. For example, the audio component 510 includes a microphone (MIC), and when the electronic device 500 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is used to receive an external audio signal. The received audio signal can be further stored in the memory 504 or sent via the communication component 516. In some embodiments, the audio component 510 also includes a speaker for outputting audio signals.

[0217] The input / output I / O interface 512 provides an interface between the processing component 502 and the peripheral interface module, which may be a keyboard, a click wheel, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0218] The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the electronic device 500. For example, the sensor assembly 514 can detect the open / closed state of the electronic device 500, the relative positioning of components, such as the display and keypad of the electronic device 500, and the sensor assembly 514 can also detect the position change of the electronic device 500 or a component of the electronic device 500, the presence or absence of user contact with the electronic device 500, the orientation or acceleration / deceleration of the electronic device 500, and the temperature change of the electronic device 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 514 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0219] The communication component 516 is used to facilitate wired or wireless communication between the electronic device 500 and other devices. The electronic device 500 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 5G), or a combination thereof. In an exemplary embodiment, the communication component 516 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 516 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0220] In an exemplary embodiment, the electronic device 500 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to implement an air conditioning control method provided in an embodiment of the present application.

[0221] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 504 including instructions, and the instructions can be executed by a processor 520 of an electronic device 500 to perform the above method. For example, the non-transitory storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0222] In one embodiment, the present application further provides an air conditioner, which includes the air conditioner control device in the above embodiment, or the electronic device in the above embodiment.

[0223] Fig.13 600 is a block diagram of an electronic device 600 according to another embodiment of the present invention. For example, the electronic device 600 may be provided as a server. Fig.13 The electronic device 600 includes a processing component 622, which further includes one or more processors, and a memory resource represented by a memory 632 for storing instructions executable by the processing component 622, such as an application. The application stored in the memory 632 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 622 is configured to execute instructions to perform an air conditioning control method provided in an embodiment of the present application.

[0224] The electronic device 600 may also include a power supply component 626 configured to perform power management of the electronic device 600, a wired or wireless network interface 650 configured to connect the electronic device 600 to a network, and an input / output (I / O) interface 658. The electronic device 600 may operate based on an operating system stored in the memory 632, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0225] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the application disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0226] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. An air conditioning control method, characterized in that: include: Acquire historical time series data; the historical time series data includes historical operating parameters of the air conditioner at multiple historical moments; According to the historical time series data and the preset time series prediction model, the predicted time series data is obtained; the predicted time series data includes the predicted operating parameters of the air conditioner at multiple future moments; Taking the operating parameters of the air conditioner being within the preset parameter range as a constraint condition and the evaluation score of the operating parameters of the air conditioner as the fitness function value, the predicted operating parameters are optimized based on the genetic algorithm to obtain the target operating parameters, so as to control the operation of the air conditioner according to the target operating parameters; Among them, the evaluation score is positively correlated with the accuracy of operating parameters and negatively correlated with air conditioning energy consumption.

2. The method according to claim 1, characterized in that Taking the operating parameters of the air conditioner within the preset parameter range as the constraint condition and the evaluation score of the operating parameters of the air conditioner as the fitness function value, the predicted operating parameters are optimized based on the genetic algorithm to obtain the target operating parameters, including: In each iteration process, a plurality of first operating parameters satisfying the constraint condition are obtained according to the predicted operating parameters; Obtaining a first evaluation score corresponding to the first operating parameter; From the plurality of first evaluation scores, obtaining the largest first evaluation score; If the maximum first evaluation score is greater than or equal to the preset score threshold, the iteration is stopped, and the first operating parameter corresponding to the maximum first evaluation score is determined as the target operating parameter.

3. The method according to claim 2, characterized in that The obtaining of a plurality of first operating parameters satisfying the constraint condition comprises: Selecting a plurality of third operating parameters from the plurality of second operating parameters obtained in the previous iteration; Performing an encoding operation on the third operating parameter to obtain a string structure of the third operating parameter; Acquire a third operating parameter combination from the plurality of third operating parameters; The data of the first preset data bits of different third operating parameter string structures in the third operating parameter combination are exchanged to obtain the first operating parameter that meets the constraint condition.

4. The method according to claim 2, characterized in that: Acquiring a plurality of first operating parameters that satisfy the constraint condition includes: Selecting a plurality of third operating parameters from the plurality of second operating parameters obtained in the previous iteration; Performing an encoding operation on the third operating parameter to obtain a string structure of the third operating parameter; The data of the second preset data bit and the third preset data bit in the string structure of the third operating parameter are exchanged to obtain the first operating parameter that meets the constraint condition.

5. The method according to claim 1, characterized in that The method further comprises: Obtaining the evaluation score of the air conditioner operating parameter according to the air conditioner operating parameter and a preset evaluation score calculation model; The preset evaluation score calculation model is: F(T,H,E)=ω1×f1(T,H)-ω2×f2(E) Among them, F(T, H, E) is the evaluation score, f1(T, H) is the evaluation score for the accuracy of operating parameters, f2(E) is the evaluation score for the energy consumption of operating parameters, ω1 and ω2 are the weight values ​​of the evaluation score for the accuracy of operating parameters and the weight value of the evaluation score for energy consumption, respectively; T, H, and E are temperature, humidity, and energy consumption, respectively.

6. The method according to claim 5, characterized in that The method further comprises: The evaluation score f1(T, H) for the accuracy of the operating parameters is obtained according to the following method: Among them, T0 is the preset temperature, H0 is the preset humidity, T r H is the difference between the upper temperature limit and the lower temperature limit in the preset temperature range. r The difference between the upper humidity limit and the lower humidity limit in the preset humidity range; The evaluation score f2(E) of the energy consumption of the operating parameters is obtained according to the following method: Among them, E0 is the preset energy consumption, and E1 is the difference between the upper limit value and the lower limit value of energy consumption in the preset energy consumption range.

7. An air conditioning control device, characterized in that: include: A first acquisition module is used to acquire historical time series data; the historical time series data includes historical operating parameters of the air conditioner at multiple historical moments; A second acquisition module is used to acquire predicted time series data according to the historical time series data and a preset time series prediction model; the predicted time series data includes predicted operating parameters of the air conditioner at multiple future moments; The third acquisition module is used to optimize the predicted operating parameters based on a genetic algorithm, with the operating parameters of the air conditioner being within a preset parameter range as a constraint condition and the evaluation score of the operating parameters of the air conditioner as the fitness function value, to obtain target operating parameters so as to control the operation of the air conditioner according to the target operating parameters; the evaluation score is positively correlated with the accuracy of the operating parameters and negatively correlated with the energy consumption of the air conditioner.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. An air conditioner, characterized in that: The air conditioner includes the air conditioner control device according to claim 7, or the electronic device according to claim 8.

Images