Indoor temperature control method and device

Abstract

The invention provides an indoor temperature control method and device, and the method comprises the steps: obtaining a regression model of the operation power data and indoor temperature data of temperature adjustment equipment, time-of-use electricity price data, an indoor temperature limiting interval, and obtaining an indoor temperature limiting interval based on a plurality of segment power parameters, a power segment duration parameter and the time-of-use electricity price data; establishing a sparse model taking the minimum future total electric charge as a target function, determining constraint conditions of the sparse model based on the regression model and the indoor temperature limit interval, optimizing the sparse model, and obtaining an indoor temperature data target set value in each time period corresponding to the minimum future total electric charge based on the regression model; and based on the indoor temperature data target set value in each time period, a temperature adjusting equipment operation strategy is generated, the technical problems of how to adjust the indoor temperature and save electric energy expenditure in related technologies can be solved, and the technical effects of balancing indoor comfort and saving electric energy expenditure are achieved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of indoor temperature control, and in particular to an indoor temperature control method and device. Background Art

[0002] With the acceleration of the factoryization process in the construction industry, energy conservation and carbon reduction have become the primary concern of society. Among them, HVAC, as a key equipment accounting for nearly 50% of energy consumption, has huge energy-saving potential. Traditional air-conditioning operation and maintenance methods often rely on a lot of expert experience to achieve safety and energy-saving effects. Even with the continuous investment of manpower, material resources and financial resources, it is impossible to achieve truly efficient operation of air-conditioning. Each factory, each type of scene and each type of equipment is also non-replicable. Therefore, traditional operation and maintenance methods are quite constrained in terms of stability and reusability. In addition to continuously optimizing traditional methods, applying cold (heat) storage technology to HVAC systems has also become one of the main ways to save energy. With the help of thermal inertia and cold (heat) storage equipment of factory buildings, customers can effectively reduce energy consumption by more than 27%. However, the addition of new equipment is bound to bring additional economic expenses, and more rigorous line design is also required to ensure the safe operation of equipment. Therefore, it is particularly important to design a method with high economy and strong reusability. The electricity energy cost generated by the operation of HVAC systems accounts for a large proportion of the overall energy procurement cost of customers in commercial buildings and discrete manufacturing industries. It is a huge challenge to achieve cost saving and efficiency improvement while taking people-oriented into consideration.

[0003] How to adjust the indoor temperature and save electricity expenditure is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The purpose of the present disclosure is to provide an indoor temperature control method to at least solve the technical problem of how to adjust the indoor temperature and save electricity expenditure in the related art.

[0005] According to one aspect of an embodiment of the present disclosure, there is provided a method for controlling indoor temperature, comprising:

[0006] Obtain the regression model of the operating power data of the temperature control equipment and the indoor temperature data, the time-of-use electricity price data, and the indoor temperature limit range;

[0007] Based on a number of segment power parameters, power segment duration parameters and the time-of-use electricity price data, a sparse model with the minimum future total electricity cost as the objective function is established;

[0008] Determining the constraint conditions of the sparse model based on the regression model and the indoor temperature limit interval;

[0009] Optimizing the sparse model, and obtaining the target setting value of indoor temperature data in each time period corresponding to the minimum future total electricity fee based on the regression model;

[0010] Based on the target set values ​​of indoor temperature data in each time period, a temperature control equipment operation strategy is generated.

[0011] In an exemplary embodiment, based on the segment power parameter, the power segment duration parameter and the time-of-use electricity price data, a sparse model with the minimum future total electricity cost as the objective function is established, including:

[0012] Determine the segment power consumption parameter item based on the segment power parameter and the power segment duration parameter;

[0013] Based on the segment power consumption parameter items and the power segment duration parameters, determine the electricity fee parameter items for each segment;

[0014] Based on the parameters of each segment electricity fee, a sparse expression of the future total electricity fee is constructed;

[0015] Based on the sparse expression, a sparse model with the minimum future total electricity cost as the objective function is established.

[0016] In an exemplary embodiment, before establishing a sparse model with the minimum future total electricity cost as the objective function based on a number of segment power parameters, power segment duration parameters and the time-of-use electricity price data, the method further includes:

[0017] Obtain the segment switch status data of the temperature control device;

[0018] Based on the segmented switch state data of the temperature adjustment device, a weight coefficient of each segmented power consumption parameter item is set.

[0019] In an exemplary embodiment, obtaining a regression model of temperature adjustment device operating power data and indoor temperature data includes:

[0020] Obtain historical indoor temperature data and historical operating power data of temperature control equipment;

[0021] The regression model is constructed based on the historical indoor temperature data and the historical operating power data of the temperature regulating device.

[0022] In an exemplary embodiment, optimizing the sparse model and obtaining the target setting value of indoor temperature data in each time period corresponding to the minimum future total electricity fee based on the regression model includes:

[0023] Predetermining a temperature setting scheme for a temperature regulating device, wherein the temperature setting scheme for the temperature regulating device includes a set value for indoor temperature data in each time period and a set value for the duration of each time period;

[0024] Determining the power data setting value of the temperature adjustment device in each time period based on the indoor temperature data setting value in each time period and the regression model;

[0025] Determine the future total electricity cost corresponding to the temperature setting scheme of the temperature adjustment device based on the sparse model, the power data setting value of the temperature adjustment device in each time period and the setting value of the duration of each time period;

[0026] Optimize the temperature setting plan of the temperature regulating equipment and determine the target setting value of the indoor temperature data in each time period.

[0027] In an exemplary embodiment, determining the constraint conditions of the sparse model based on the regression model and the indoor temperature limit interval includes:

[0028] Based on the regression model, using corresponding segmented indoor temperature parameters to characterize each segmented power parameter in the objective function;

[0029] Based on the indoor temperature limit interval, a data setting interval of the segmented indoor temperature parameter is determined.

[0030] In an exemplary embodiment, before constructing the regression model based on the historical indoor temperature data and the historical operating power data of the temperature regulating device, the method further includes:

[0031] Obtain medium temperature response rate parameters, outdoor temperature segmentation parameters, and indoor temperature segmentation parameters;

[0032] Establishing a conduction factor model based on the medium temperature response rate parameter, the outdoor temperature segmentation parameter and the indoor temperature segmentation parameter;

[0033] Based on the conduction factor model, a conduction factor of the indoor temperature parameter in the regression model is determined.

[0034] In an exemplary embodiment, before constructing the regression model based on the historical indoor temperature data and the historical operating power data of the temperature regulating device, the method further includes:

[0035] Obtain irradiance segmentation parameters, irradiation area parameters and medium thermal resistance parameters;

[0036] Establishing an irradiation factor model based on the irradiance parameter, the irradiation area parameter and the medium thermal resistance parameter;

[0037] Based on the radiation factor model, the radiation factor of the indoor temperature parameter in the regression model is determined.

[0038] In an exemplary embodiment, before constructing the regression model based on the historical indoor temperature data and the historical operating power data of the temperature regulating device, the method further includes:

[0039] Get the thermal resistance parameters of the ambient medium;

[0040] Establishing a seasonal factor model based on the power segmentation parameter and the thermal resistance parameter of the ambient medium;

[0041] Based on the seasonal factor model, a seasonal factor of the indoor temperature parameter in the regression model is determined.

[0042] In an exemplary embodiment, constructing the regression model based on the historical indoor temperature data and the historical operating power data of the temperature regulating device includes:

[0043] Based on the segmented indoor temperature parameters, determining the segmented temperature variation parameters;

[0044] Based on the segment power parameter, determining the segment power variation parameter;

[0045] The regression model characterizing the regression relationship between the segmented temperature variation parameter and the segmented power parameter is constructed.

[0046] In an exemplary embodiment, determining the constraint conditions of the sparse model based on the regression model and the indoor temperature limit interval further includes:

[0047] Get the critical value of indoor temperature change;

[0048] Based on the indoor temperature change critical value, a data setting interval of the segmented temperature change amount parameter is determined.

[0049] According to another aspect of the embodiment of the present disclosure, there is also provided an indoor temperature control device, comprising:

[0050] An acquisition module is used to obtain a regression model of operating power data of a temperature control device and indoor temperature data, time-of-use electricity price data, and a limited indoor temperature range;

[0051] A sparse model building module, used to build a sparse model with the minimum future total electricity cost as the objective function based on a number of segment power parameters, power segment duration parameters and the time-of-use electricity price data;

[0052] A constraint condition determination module, used to determine the constraint conditions of the sparse model based on the regression model and the indoor temperature limit interval;

[0053] A sparse model optimization module, used to optimize the sparse model, and obtain the target setting value of indoor temperature data in each time period corresponding to the minimum future total electricity fee based on the regression model;

[0054] The strategy generation module is used to generate a temperature control device operation strategy based on the target setting value of the indoor temperature data in each time period.

[0055] In an exemplary embodiment, the sparse model building module includes:

[0056] A segment power consumption parameter determination unit, used to determine the segment power consumption parameter item based on the segment power parameter and the power segment duration parameter;

[0057] A segmented electricity fee parameter item determining unit, used to determine each segmented electricity fee parameter item based on the segmented power consumption parameter item and the power segment duration parameter;

[0058] A coefficient expression building unit, used to build a sparse expression of the future total electricity charge based on each segmented electricity charge parameter item;

[0059] The sparse model building unit is used to build the sparse model with the minimum future total electricity cost as the objective function based on the sparse expression.

[0060] In an exemplary embodiment, the indoor temperature control device further includes:

[0061] A status acquisition module is used to obtain the segment switch status data of the temperature adjustment device;

[0062] The weight setting module is used to set the weight coefficient of each segment power consumption parameter item based on the segment switch state data of the temperature adjustment device.

[0063] In an exemplary embodiment, the acquisition module includes:

[0064] A historical data acquisition unit, used to acquire historical indoor temperature data and historical operating power data of a temperature control device;

[0065] The regression model building unit is used to build the regression model based on the historical indoor temperature data and the historical operating power data of the temperature regulating device.

[0066] In an exemplary embodiment, the sparse model optimization module includes:

[0067] A temperature pre-determination unit, used to pre-determine a temperature setting scheme for a temperature regulating device, wherein the temperature setting scheme for the temperature regulating device includes a set value for indoor temperature data in each time period and a set value for the duration of each time period;

[0068] A power pre-determination unit, used to determine the power data setting value of the temperature adjustment device in each time period based on the indoor temperature data setting value in each time period and the regression model;

[0069] An electricity fee pre-determination unit, configured to determine a future total electricity fee corresponding to the temperature setting scheme of the temperature adjustment device based on the sparse model, the power data setting value of the temperature adjustment device in each time period, and the setting value of the duration of each time period;

[0070] The optimization and determination unit is used to optimize the temperature setting scheme of the temperature regulating device and determine the target setting value of the indoor temperature data in each time period.

[0071] In an exemplary embodiment, the constraint determination module includes:

[0072] A constraint regression unit, used to characterize each segmented power parameter in the objective function using the corresponding segmented indoor temperature parameter based on the regression model;

[0073] The constraint determination unit is used to determine the data setting interval of the segmented indoor temperature parameter based on the indoor temperature limit interval.

[0074] In an exemplary embodiment, the acquisition module further includes:

[0075] An environmental parameter acquisition unit, used to acquire medium temperature response rate parameters, outdoor temperature segmentation parameters, and indoor temperature segmentation parameters;

[0076] A conduction factor model unit, used to establish a conduction factor model based on the medium temperature response rate parameter, the outdoor temperature segmentation parameter and the indoor temperature segmentation parameter;

[0077] The conduction factor determination unit is used to determine the conduction factor of the indoor temperature parameter in the regression model based on the conduction factor model.

[0078] In an exemplary embodiment, the acquisition module further includes:

[0079] An irradiation parameter acquisition unit, used to acquire irradiance segmentation parameters, irradiation area parameters and medium thermal resistance parameters;

[0080] An irradiation factor model unit, used to establish an irradiation factor model based on the irradiance parameter, the irradiation area parameter and the medium thermal resistance parameter;

[0081] The radiation factor determination unit is used to determine the radiation factor of the indoor temperature parameter in the regression model based on the radiation factor model.

[0082] In an exemplary embodiment, the acquisition module further includes:

[0083] A medium parameter acquisition unit, used to acquire the thermal resistance parameters of the ambient medium;

[0084] A seasonal factor model unit, used to establish a seasonal factor model based on a power segmentation parameter and a thermal resistance parameter of the ambient medium;

[0085] A seasonal factor determination unit is used to determine the seasonal factor of the indoor temperature parameter in the regression model based on the seasonal factor model.

[0086] In an exemplary embodiment, the regression model building unit includes:

[0087] A segmented temperature variation parameter determination subunit, used to determine a segmented temperature variation parameter based on a segmented indoor temperature parameter;

[0088] A segment power variation parameter determination subunit is used for determining a segment power variation parameter based on the segment power parameter;

[0089] The regression model building subunit is used to build the regression model that characterizes the regression relationship between the segmented temperature variation parameter and the segmented power parameter.

[0090] In an exemplary embodiment, the constraint determination module further includes:

[0091] A critical value acquisition unit, used to acquire a critical value of indoor temperature change;

[0092] The temperature variation parameter constraint unit is used to determine the data setting interval of the segmented temperature variation parameter based on the indoor temperature variation critical value.

[0093] According to another aspect of an embodiment of the present disclosure, a computer device is also provided, comprising: a processor suitable for implementing various instructions and a storage device, wherein the storage device stores a plurality of instructions suitable for being loaded by the processor and executing any one of the above-mentioned indoor temperature control methods.

[0094] According to another aspect of the embodiments of the present disclosure, there is also a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is used to execute any one of the indoor temperature control methods described above.

[0095] According to another aspect of the embodiments of the present disclosure, there is also a computer program product, which includes a computer program, and when the computer program is executed by a processor, any one of the indoor temperature control methods described above is implemented.

[0096] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] The following drawings are intended only to illustrate and explain the present disclosure, and do not limit the scope of the present disclosure.

[0098] Figure 1 is a flow chart of an indoor temperature control method according to an embodiment of the present disclosure; and

[0099] Figure 2 is a schematic diagram of an algorithm flow of an indoor temperature control method according to an optional embodiment of the present disclosure; and

[0100] Figure 3 , is a schematic diagram of an indoor temperature control device according to an embodiment of the present disclosure; and,

[0101] Figure 4 is one of the schematic diagrams of an indoor temperature control device according to an optional embodiment of the present disclosure; and,

[0102] Figure 5 It is a structural schematic diagram of a computer device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0103] The present application is further described in detail below through the accompanying drawings and embodiments. Through these descriptions, the characteristics and advantages of the present application will become clearer and more specific.

[0104] The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise noted.

[0105] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0106] In this embodiment, a method for controlling indoor temperature is provided. Figure 1 is a flow chart of an indoor temperature control method according to an embodiment of the present disclosure, such as Figure 1 As shown, including:

[0107] Step 102, obtaining a regression model of the operating power data of the temperature control device and the indoor temperature data, time-of-use electricity price data, and a limited indoor temperature range.

[0108] The temperature regulating device may be an air conditioning device for indoor cooling or heating of a building. The operating power data and the indoor temperature data may be absolute values ​​or increase or decrease values. The operating power data and the indoor temperature data may be a number of historical data. The regression model may be a model that characterizes the regression relationship between the operating power and the indoor temperature. The time-of-use electricity price data may be charging rule data for the time period of the electricity market where the air conditioning device is located. The indoor temperature limit range may be an artificially set indoor comfortable temperature range.

[0109] Step 104: Based on a number of segment power parameters, power segment duration parameters and the above-mentioned time-of-use electricity price data, a sparse model with the minimum future total electricity cost as the objective function is established.

[0110] The above-mentioned segmented power parameters and the above-mentioned power segment duration parameters may be several parameters for corresponding segmentation of the above-mentioned time-of-use electricity price data. The above-mentioned objective function of the minimum total electricity bill in the future may be a comprehensive representation based on the above-mentioned several segmented power parameters, power segment duration parameters and the above-mentioned time-of-use electricity price data. The above-mentioned sparse model may be constructed based on the sparse representation of the above-mentioned segmented parameters.

[0111] Step 106: Based on the regression model and the indoor temperature limit range, determine the constraint conditions of the sparse model.

[0112] The constraint condition may be a value limit interval of the segmented power parameter determined based on the regression model and the indoor temperature limit interval, or may be an indoor temperature limit interval in which the temperature parameter is substituted for the power parameter based on the regression model.

[0113] Step 108, optimizing the sparse model, and obtaining the target setting value of the indoor temperature data in each time period corresponding to the minimum future total electricity bill based on the regression model.

[0114] The above optimization process may be a scheme for optimizing the values ​​of the various parameters in the above sparse model. The above minimum future total electricity bill may be the minimum prepaid electricity bill for the next 24 hours. The above minimum future total electricity bill may be the minimum evaluation value obtained in the above optimization process. The target setting values ​​of the indoor temperature data in each time period may be obtained by replacing the power parameter with the temperature parameter based on the above regression model.

[0115] Step 110, generating a temperature control device operation strategy based on the target setting value of the indoor temperature data in each time period.

[0116] The temperature control device operation strategy may be a target temperature setting strategy for the temperature control device in each time period within the next 24 hours. The power parameters for each time period and segment may be obtained by segmenting based on the time-of-use electricity price data.

[0117] In the embodiment of the present disclosure, through the above steps 102 to 110, a regression model of the operating power data of the temperature control device and the indoor temperature data, time-of-use electricity price data, and an indoor temperature limit interval are obtained, and based on several segmented power parameters, power segment duration parameters and the above time-of-use electricity price data, a sparse model with the minimum future total electricity bill as the objective function is established, based on the above regression model and the above indoor temperature limit interval, the constraints of the above sparse model are determined, the above sparse model is optimized, and based on the above regression model, the target setting value of the indoor temperature data in each time period corresponding to the minimum future total electricity bill is obtained, and based on the target setting value of the indoor temperature data in each time period, an operating strategy for the temperature control device is generated. It can solve the technical problem of how to adjust the indoor temperature and save electricity expenditure in related technologies. Based on time-of-use electricity price data, the power is set in segments, and a sparse model with the minimum future total electricity bill as the objective function is established. The coefficient model is optimized to obtain the temperature data target setting value corresponding to the minimum future electricity bill, and the temperature control equipment operation strategy is generated. The thermal inertia of the building and the periodicity of electricity bills are used to achieve peak shaving and valley filling of electricity while regulating the indoor temperature, so that the indoor temperature demand can be met with a smaller total electricity bill, thereby achieving the technical effect of balancing indoor comfort and saving electricity expenditure. While ensuring the suitability of the indoor temperature, the peak, flat and valley trends of electricity prices are used to achieve precise control of energy consumption.

[0118] In an exemplary embodiment, the above step 104 includes:

[0119] Based on the segment power parameter and the power segment duration parameter, the segment power consumption parameter item is determined.

[0120] Based on the segment power consumption parameter items and the power segment duration parameters, the electricity fee parameter items for each segment are determined.

[0121] Based on the parameters of each segmented electricity charge, a sparse expression of the future total electricity charge is constructed.

[0122] Based on the above sparse expression, the above sparse model with the minimum future total electricity cost as the objective function is established.

[0123] The above-mentioned segmented power parameter item may be the product of the above-mentioned segmented power parameter and the power segment duration parameter. The above-mentioned individual segmented electricity cost parameter items may be the product of the above-mentioned several segmented power consumption parameter items and the corresponding power segment duration parameters. The above-mentioned sparse expression may be the sum of the above-mentioned individual segmented electricity cost parameter items. The above-mentioned sparse model may be based on the above-mentioned sparse expression, optimizing the set value of the segmented power parameter to obtain the minimum future total electricity cost.

[0124] Through the above embodiments, the future electricity bill is calculated segmented based on the segmented power parameters and the power segment duration parameters, and the future total electricity bill is sparsely expressed based on the segmented electricity bill parameter items, which facilitates determining the power setting corresponding to the minimum value of the future total electricity bill during the model optimization process, and then determining the temperature setting.

[0125] In an exemplary embodiment, before the above step 104, the method further includes:

[0126] Get the temperature control device segment switch status data.

[0127] Based on the above-mentioned segmented switch state data of the temperature adjustment device, the weight coefficient of each segmented power consumption parameter item is set.

[0128] The above-mentioned temperature control device segmented switch state data can be the working state of the room at each moment. For example, the weight coefficient of the time segment in which the temperature control device is in the off state is set to 0; and the weight coefficient of the time segment in which the temperature control device is in the on state is set to 1.

[0129] Through the above embodiment, based on the switch state data of the above temperature control device, the weight coefficient of each segmented power consumption parameter item is set, and the variable space constructed by the segmented power variables is converted into a 0-1 space, which ensures that the adjacent variables are in a reasonable range while reducing the calculation amount of the algorithm and increasing the efficiency of the algorithm.

[0130] In an exemplary embodiment, the above step 102 includes:

[0131] Obtain historical indoor temperature data and historical operating power data of temperature control equipment.

[0132] Based on the historical indoor temperature data and the historical operating power data of the temperature control device, the regression model is constructed.

[0133] The historical indoor temperature data may be the real-time indoor temperature data in the past month. The historical operating power data of the temperature regulating device may be the operating power data of the temperature regulating device in the past month.

[0134] Through the above-mentioned embodiment, a model for converting power parameters and temperature parameters is provided based on the power-temperature regression relationship determined by historical data.

[0135] Optionally, the construction process of the above regression model may mainly include data cleaning, feature engineering, model construction and optimization adjustment. For data cleaning, firstly, according to expert experience and industry standards, the obviously abnormal business data in the historical data is deleted or evenly distributed, and then the special abnormal points are identified by algorithm methods based on clustering, distribution, statistics and other ideas, and the identified abnormal data are filled in according to the distribution law of historical data. For feature engineering, from the perspectives of statistical features, time domain features, frequency domain features, etc., correlation analysis and other methods are used to find effective optimal features. For model construction, a tree model with low computational complexity and low historical data demand is used as the benchmark model to ensure accuracy while improving the calculation rate. For optimization adjustment, the root mean square error is used as an evaluation indicator to find the optimal parameter combination among many algorithm parameters.

[0136] In an exemplary embodiment, the above step 108 includes:

[0137] A temperature setting scheme for the temperature regulating device is predetermined, wherein the temperature setting scheme for the temperature regulating device includes a set value for the indoor temperature data in each time period and a set value for the duration of each time period.

[0138] Based on the indoor temperature data set value in each time period and the above regression model, the power data set value of the temperature adjustment device in each time period is determined.

[0139] Based on the above sparse model, the power data setting value of the temperature control device in each time period and the setting value of the duration of each time period, the future total electricity cost corresponding to the temperature setting scheme of the temperature control device is determined.

[0140] Optimize the temperature setting plan of the above temperature control equipment and determine the target setting value of indoor temperature data in each time period.

[0141] The predetermined temperature setting scheme of the temperature regulating device can be set manually or generated based on an algorithm. The data types of the indoor temperature data setting values ​​of each stage should be unified when they are substituted into the temperature parameters in the regression model. The optimization process of the temperature setting scheme of the temperature regulating device can be optimized by using a branch and bound method and a mixed integer linear programming algorithm.

[0142] Through the above embodiment, the temperature setting scheme of the temperature regulating device is optimized, and the indoor temperature setting values ​​for each future time period corresponding to the minimum future total electricity bill are determined, so as to facilitate the subsequent determination of the temperature setting scheme corresponding to the low electricity bill expenditure.

[0143] In an exemplary embodiment, the above step 106 includes:

[0144] Based on the above regression model, the corresponding segmented indoor temperature parameters are used to characterize each segmented power parameter in the above objective function.

[0145] Based on the above-mentioned indoor temperature limit interval, the data setting interval of the segmented indoor temperature parameter is determined.

[0146] The above-mentioned temperature limit range can be a temperature range within which indoor people feel comfortable.

[0147] Through the above embodiment, the power parameter in the objective function is converted into a temperature parameter, so that the above indoor temperature limit range is used as a constraint condition of the sparse model.

[0148] In an exemplary embodiment, before constructing the regression model based on the historical indoor temperature data and the historical operating power data of the temperature adjustment device, the method further includes:

[0149] Obtain medium temperature response rate parameters, outdoor temperature segmentation parameters, and indoor temperature segmentation parameters.

[0150] A conduction factor model is established based on the medium temperature response rate parameter, the outdoor temperature segmentation parameter and the indoor temperature segmentation parameter.

[0151] Based on the above conduction factor model, the conduction factor of the indoor temperature parameter in the above regression model is determined.

[0152] The above-mentioned medium temperature response rate parameter may be the response rate of air to temperature, the response rate of the wall to temperature, etc. The above-mentioned air thermal conductivity coefficient may refer to the rate of heat conduction through air of unit thickness when the temperature difference is 1 degree Celsius per unit area per unit time. The above-mentioned wall response rate to temperature may refer to the rate of heat conduction through wall of unit thickness when the temperature difference is 1 degree Celsius per unit area per unit time. The above-mentioned outdoor temperature segmentation parameter may be segmented based on the above-mentioned indoor temperature segmentation parameter to ensure segmentation uniformity. The conduction factor in the above-mentioned conduction factor model may be the ratio between the indoor and outdoor temperature difference in each time period and the sum of the medium temperature response rate parameters, which is used to represent the conduction of cold and heat in the room.

[0153] Through the above embodiment, a conduction factor model is constructed based on the above medium temperature response rate parameters, outdoor temperature segmentation parameters, and indoor temperature segmentation parameters, so that the conduction of cold and heat indoors is used as a reference factor for the indoor temperature parameters, further improving the accuracy of parameter optimization.

[0154] In an exemplary embodiment, before constructing the regression model based on the historical indoor temperature data and the historical operating power data of the temperature adjustment device, the method further includes:

[0155] Obtain irradiance segmentation parameters, irradiation area parameters and medium thermal resistance parameters.

[0156] Based on the above irradiance parameter, the above irradiation area parameter and the above medium thermal resistance parameter, an irradiation factor model is established.

[0157] Based on the above radiation factor model, the radiation factor of the indoor temperature parameter in the above regression model is determined.

[0158] The above-mentioned irradiation area parameter can be a window area parameter for indoor lighting. The above-mentioned medium thermal resistance parameter can be the indoor air specific heat capacity, wall specific heat capacity, etc. The irradiation factor in the above-mentioned irradiation factor model can be the ratio between the product of the irradiance parameter and the irradiation area parameter in each time period and the medium thermal resistance parameter, which is used to indicate the impact of indoor radiation on indoor problems.

[0159] Through the above embodiment, an irradiation factor model is constructed based on the above irradiance segmentation parameter, irradiation area parameter and medium thermal resistance parameter, so that the indoor irradiance parameter is used as a reference factor for the indoor temperature parameter, further improving the accuracy of parameter optimization.

[0160] In an exemplary embodiment, before constructing the regression model based on the historical indoor temperature data and the historical operating power data of the temperature adjustment device, the method further includes:

[0161] Get the thermal resistance parameters of the ambient medium.

[0162] A seasonal factor model is established based on the power segmentation parameters and the above-mentioned ambient medium thermal resistance parameters.

[0163] Based on the above seasonal factor model, the seasonal factor of the indoor temperature parameter in the above regression model is determined.

[0164] The above-mentioned environmental medium thermal resistance parameter may be the indoor air specific heat capacity, wall specific heat capacity, etc. The above-mentioned seasonal factor model may be obtained by performing seasonal judgment on the ratio between the above-mentioned power segmentation parameter and the above-mentioned environmental medium thermal resistance parameter. The seasonal judgment may be that the absolute value of the ratio remains unchanged in winter and is directly used as the seasonal factor, and the opposite value is taken as the seasonal factor in summer.

[0165] Through the above embodiment, a seasonal factor model is established based on the above power segmentation parameters and the above ambient medium thermal resistance parameters, so that the heat transfer conditions in the above sparse model are differentiated and considered, thereby improving the seasonal adaptability of the model.

[0166] In an exemplary embodiment, based on the historical indoor temperature data and the historical operating power data of the temperature control device, the regression model is constructed, including:

[0167] Based on the segmented indoor temperature parameters, segmented temperature variation parameters are determined.

[0168] Based on the segment power parameter, a segment power variation parameter is determined.

[0169] The above regression model is constructed to characterize the regression relationship between the segmented temperature variation parameter and the segmented power parameter.

[0170] The segmented temperature variation parameter may be the difference between two adjacent segmented indoor temperature parameters. The segmented power variation parameter may be the difference between two adjacent segmented power parameters. The regression model may be a model that characterizes the regression relationship between the operating power variation and the indoor temperature variation.

[0171] Through the above embodiment, the basic control parameters of the air conditioner in the above regression model (i.e., the above segmented indoor temperature parameters) are converted into variable parameters, thereby reducing the difficulty of quantifying the data parameters in the model, reducing the amount of calculation and reducing the model mapping dimension.

[0172] Optionally, the temperature setting scheme of the temperature regulating device can be a setting scheme of the indoor drift temperature (i.e., the temperature difference between two adjacent moments) for the next 24 hours obtained by using the branch and bound method and the mixed integer linear programming algorithm and optimized based on the branch and bound method and the mixed integer linear programming algorithm. The drift temperature can be the expected indoor temperature difference between two adjacent moments outside the set interval. Each drift temperature setting value is substituted into the corresponding segmented temperature variation parameter.

[0173] In an exemplary embodiment, determining the constraint conditions of the sparse model based on the regression model and the indoor temperature limit interval further includes:

[0174] Get the critical value of indoor temperature change.

[0175] Based on the above-mentioned critical value of indoor temperature change, the data setting interval of the segmented temperature change parameter is determined.

[0176] The indoor temperature change critical value may be the indoor temperature change critical value, that is, the maximum value of the segmented temperature change parameter.

[0177] Through the above embodiment, the data setting range of the above segmented temperature variation parameter is determined based on the indoor temperature variation critical value, thereby reducing the model optimization cycle and improving the strategy generation speed.

[0178] Optionally, the above medium temperature response rate parameters, outdoor temperature segmentation parameters, indoor temperature segmentation parameters, environmental medium thermal resistance parameters, irradiance segmentation parameters, irradiation area parameters, medium thermal resistance parameters and indoor temperature change critical values ​​can be manually set, or can be obtained by constructing a parameter fitting model based on historical data and an optimization algorithm. The above parameter fitting model can be a case where in the historical data, the electricity price, power, indoor temperature, outdoor temperature, irradiance, and irradiation area are known, while the environmental thermal resistance parameters, medium thermal resistance parameters, and medium temperature response rate are unknown, and the branch and bound method and mixed integer linear programming algorithm are used to solve the unknown quantities based on the objective function and historical data.

[0179] Optionally, the construction process of the above-mentioned sparse model may include variable space modeling, basic physical parameter fitting (for example, environmental thermal resistance parameters, medium thermal resistance parameters, air response rate to temperature, wall response rate to temperature), solution space sparseness, optimization calculation and the like. For variable space modeling, it is necessary to convert the basic control parameters of the air conditioner into temperature change parameters, and finally replace them with temperature change parameters to improve the interpretability of the data in the model; for basic physical parameter fitting, the branch and bound method and mixed integer linear programming algorithm are used, and the earliest and latest start-up time, commuting time, area parameters, historical power and other data provided by the factory are combined with the following formula to finally fit the optimal basic physical parameters, which provides convenience for patent users while ensuring the dynamic adaptability of the parameters; for solution space sparseness, it is necessary to convert the variable space constructed by temperature change into 0-1 space to ensure that adjacent temperature changes are in a reasonable range while reducing the amount of calculation of the algorithm and increasing the efficiency of the algorithm.

[0180] Optionally, the objective function and constraints of the sparse model are as follows:

[0181] min Cost

[0182] st Cost=PowerForecast1*Timestep*price1*WS1+…+PowerForecast i *Timestep*price i *WS i

[0183] PowerForecast(i)=Forecasting(ΔTemp i )+PowerForecast i-1

[0184] ΔTemp(i)=IndoorTemp i+1 -IndoorTemp i

[0185]

[0186]

[0187] CTMAX>ImdoorTmep i >CTMIN

[0188] ΔTemp(i) <CTV

[0189] Where: Cair represents the specific heat of air, τAir represents the response rate of air to temperature, Cenv represents the specific heat of wall, τEnv represents the response rate of air to wall, PowerForecast i represents the operating power at the i-th moment, price i represents the electricity price at the i-th moment, WS i represents the switch state weight coefficient at the i-th moment, Forecasting(*) represents the power and temperature variable regression model, ΔTemp i IndoorTemp represents the temperature change at the i-th moment. i IndTemp represents the indoor temperature at the i-th moment. i-1 Indicates the indoor temperature at the i-1th moment, OutdTemp i-1 represents the outdoor temperature at time i-1, irradiance i represents the irradiance at the i-th moment, areaWindow represents the window area, CTMAX represents the maximum comfort temperature, CTMIN represents the minimum comfort temperature, CTV represents the temperature change critical value, min Cost represents the objective function of minimizing the total future electricity cost, and the value range of i represents that it is segmented every 15 minutes in 24 hours, so 24*4 segments can be obtained. The above-mentioned temperature control device operation strategy can also be based on the segmentation to perform strategy correction with a cycle of 15 minutes. For example, a temperature control instruction is issued to the temperature control device operation strategy every 15 minutes, such as reducing 1.2 degrees Celsius.

[0190] The present invention takes into account the thermal inertia of factory buildings and the cyclical nature of electricity charges, and introduces time-of-day electricity price characteristics and commuting status characteristics into the optimization objectives. When solving the above objective function, the algorithm will combine environmental data such as outdoor temperature information to control the air conditioner to accumulate cooling or heat in advance when the electricity price is low, and reduce power to reduce energy consumption when the electricity price is high, thereby achieving dynamic peak shaving and valley filling. At the same time, the air conditioner can be turned on in advance before work to ensure indoor comfort, and the air conditioner can be turned off in advance before get off work to reduce energy consumption and ensure economic optimization.

[0191] Figure 2is a schematic diagram of an algorithm flow of an indoor temperature control method according to an optional embodiment of the present disclosure, such as Figure 2 As shown, including:

[0192] The earliest and latest start-up time, commuting time, window and wall area, indoor temperature, irradiance, outdoor temperature, and air conditioning operating power data for one month in history were input into the parameter fitting model and air conditioning control model for model construction.

[0193] The weather data for the next 24 hours, the electricity price for the next 24 hours, and the wall thermal resistance, temperature response rate, air thermal resistance, and temperature response shorthand obtained by the parameter fitting model are input into the air conditioning control model for model construction.

[0194] The indoor temperature at the working time end is in the comfortable temperature range and the air conditioner cannot be started during the non-start-up time period as the constraint conditions of the above air conditioning control model.

[0195] The air conditioning control model is used to generate a 24-hour indoor drift temperature setting plan. The drift temperature setting plan is input into the power temperature regression model to obtain the air conditioning operation power information for the next 24 hours. The total electricity cost for the next 24 hours is evaluated based on the air conditioning operation power information for the next 24 hours.

[0196] Determine whether the optimization target is reached (whether the minimum total electricity bill for the next 24 hours is obtained). If the optimization target is not reached, the indoor drift temperature setting plan for the next 24 hours is changed, and the total electricity bill for the next 24 hours corresponding to the new plan is evaluated again. If the optimization target is reached, the corresponding indoor drift temperature setting plan for the next 24 hours is converted into a remote control instruction. The remote control instruction is used as the optimal remote control instruction. Furthermore, the optimal remote control instruction can also be sent to the air conditioner for real-time control.

[0197] According to another aspect of the embodiment of the present disclosure, there is also provided an indoor temperature control device. Figure 3 is a schematic diagram of an indoor temperature control device according to an embodiment of the present disclosure, such as Figure 3 As shown, including:

[0198] The acquisition module is used to obtain the regression model of the operating power data of the temperature control equipment and the indoor temperature data, the time-of-use electricity price data, and the indoor temperature limit range.

[0199] The temperature regulating device may be an air conditioning device for indoor cooling or heating of a building. The operating power data and the indoor temperature data may be absolute values ​​or increase or decrease values. The operating power data and the indoor temperature data may be a number of historical data. The regression model may be a model that characterizes the regression relationship between the operating power and the indoor temperature. The time-of-use electricity price data may be charging rule data for the time period of the electricity market where the air conditioning device is located. The indoor temperature limit range may be an artificially set indoor comfortable temperature range.

[0200] The sparse model building module is used to build a sparse model with the minimum future total electricity cost as the objective function based on a number of segment power parameters, power segment duration parameters and the above-mentioned time-of-use electricity price data.

[0201] The above-mentioned segmented power parameters and the above-mentioned power segment duration parameters may be several parameters for corresponding segmentation of the above-mentioned time-of-use electricity price data. The above-mentioned objective function of the minimum total electricity bill in the future may be a comprehensive representation based on the above-mentioned several segmented power parameters, power segment duration parameters and the above-mentioned time-of-use electricity price data. The above-mentioned sparse model may be constructed based on the sparse representation of the above-mentioned segmented parameters.

[0202] The constraint condition determination module is used to determine the constraint conditions of the sparse model based on the regression model and the indoor temperature limit interval.

[0203] The constraint condition may be a value limit interval of the segmented power parameter determined based on the regression model and the indoor temperature limit interval, or may be an indoor temperature limit interval in which the temperature parameter is substituted for the power parameter based on the regression model.

[0204] The sparse model optimization module is used to optimize the above sparse model and obtain the target setting value of indoor temperature data in each time period corresponding to the minimum future total electricity bill based on the above regression model.

[0205] The above optimization process may be a scheme for optimizing the values ​​of the various parameters in the above sparse model. The above minimum future total electricity bill may be the minimum prepaid electricity bill for the next 24 hours. The above minimum future total electricity bill may be the minimum evaluation value obtained in the above optimization process. The target setting values ​​of the indoor temperature data in each time period may be obtained by replacing the power parameter with the temperature parameter based on the above regression model.

[0206] The strategy generation module is used to generate a temperature control device operation strategy based on the target setting value of the indoor temperature data in each time period.

[0207] The temperature control device operation strategy may be a target temperature setting strategy for the temperature control device in each time period within the next 24 hours. The power parameters for each time period and segment may be obtained by segmenting based on the time-of-use electricity price data.

[0208] In the disclosed embodiment, by obtaining a regression model of the operating power data of the temperature control device and the indoor temperature data, time-of-use electricity price data, and an indoor temperature limit interval, a sparse model with the minimum future total electricity bill as the objective function is established based on several segmented power parameters, power segment duration parameters, and the above-mentioned time-of-use electricity price data. Based on the above-mentioned regression model and the above-mentioned indoor temperature limit interval, the constraints of the above-mentioned sparse model are determined, the above-mentioned sparse model is optimized, and based on the above-mentioned regression model, the target setting value of the indoor temperature data in each time period corresponding to the minimum future total electricity bill is obtained. Based on the target setting value of the indoor temperature data in each time period, an operating strategy for the temperature control device is generated. It can solve the technical problem of how to adjust the indoor temperature and save electricity expenditure in related technologies. Based on time-of-use electricity price data, the power is set in segments, and a sparse model with the minimum future total electricity bill as the objective function is established. The coefficient model is optimized to obtain the temperature data target setting value corresponding to the minimum future electricity bill, and the temperature control equipment operation strategy is generated. The thermal inertia of the building and the periodicity of electricity bills are used to achieve peak shaving and valley filling of electricity while regulating the indoor temperature, so that the indoor temperature demand can be met with a smaller total electricity bill, thereby achieving the technical effect of balancing indoor comfort and saving electricity expenditure. While ensuring the suitability of the indoor temperature, the peak, flat and valley trends of electricity prices are used to achieve precise control of energy consumption.

[0209] In an exemplary embodiment, Figure 4 is one of the schematic diagrams of an indoor temperature control device according to an optional embodiment of the present disclosure, such as Figure 4 As shown, the above sparse model building module includes:

[0210] The segment power consumption parameter determination unit is used to determine the segment power consumption parameter item based on the segment power parameter and the power segment duration parameter.

[0211] The segmented electricity fee parameter item determining unit is used to determine each segmented electricity fee parameter item based on the segmented power consumption parameter item and the power segment duration parameter.

[0212] The coefficient expression building unit is used to build a sparse expression of the future total electricity cost based on each segmented electricity cost parameter item.

[0213] The sparse model building unit is used to build the sparse model with the minimum future total electricity cost as the objective function based on the sparse expression.

[0214] The above-mentioned segmented power parameter item may be the product of the above-mentioned segmented power parameter and the power segment duration parameter. The above-mentioned individual segmented electricity cost parameter items may be the product of the above-mentioned several segmented power consumption parameter items and the corresponding power segment duration parameters. The above-mentioned sparse expression may be the sum of the above-mentioned individual segmented electricity cost parameter items. The above-mentioned sparse model may be based on the above-mentioned sparse expression, optimizing the set value of the segmented power parameter to obtain the minimum future total electricity cost.

[0215] Through the above embodiments, the future electricity bill is calculated segmented based on the segmented power parameters and the power segment duration parameters, and the future total electricity bill is sparsely expressed based on the segmented electricity bill parameter items, which facilitates determining the power setting corresponding to the minimum value of the future total electricity bill during the model optimization process, and then determining the temperature setting.

[0216] In an exemplary embodiment, the indoor temperature control device further includes:

[0217] The status acquisition module is used to obtain the segment switch status data of the temperature control device.

[0218] The weight setting module is used to set the weight coefficient of each segment power consumption parameter item based on the segment switch state data of the temperature adjustment device.

[0219] The above-mentioned temperature control device segmented switch state data can be the working state of the room at each moment. For example, the weight coefficient of the time segment in which the temperature control device is in the off state is set to 0; and the weight coefficient of the time segment in which the temperature control device is in the on state is set to 1.

[0220] Through the above embodiment, based on the switch state data of the above temperature control device, the weight coefficient of each segmented power consumption parameter item is set, and the variable space constructed by the segmented power variables is converted into a 0-1 space, which ensures that the adjacent variables are in a reasonable range while reducing the calculation amount of the algorithm and increasing the efficiency of the algorithm.

[0221] In an exemplary embodiment, the acquisition module includes:

[0222] The historical data acquisition unit is used to acquire historical indoor temperature data and historical operating power data of the temperature control device.

[0223] The regression model building unit is used to build the regression model based on the historical indoor temperature data and the historical operating power data of the temperature adjustment device.

[0224] The historical indoor temperature data may be the real-time indoor temperature data in the past month. The historical operating power data of the temperature regulating device may be the operating power data of the temperature regulating device in the past month.

[0225] Through the above-mentioned embodiment, a model for converting power parameters and temperature parameters is provided based on the power-temperature regression relationship determined by historical data.

[0226] Optionally, the construction process of the above regression model may mainly include data cleaning, feature engineering, model construction and optimization adjustment. For data cleaning, firstly, according to expert experience and industry standards, the obviously abnormal business data in the historical data is deleted or evenly distributed, and then the special abnormal points are identified by algorithm methods based on clustering, distribution, statistics and other ideas, and the identified abnormal data are filled in according to the distribution law of historical data. For feature engineering, from the perspectives of statistical features, time domain features, frequency domain features, etc., correlation analysis and other methods are used to find effective optimal features. For model construction, a tree model with low computational complexity and low historical data demand is used as the benchmark model to ensure accuracy while improving the calculation rate. For optimization adjustment, the root mean square error is used as an evaluation indicator to find the optimal parameter combination among many algorithm parameters.

[0227] In an exemplary embodiment, the sparse model optimization module includes:

[0228] The temperature pre-determination unit is used to pre-determine the temperature setting scheme of the temperature regulating device, wherein the temperature setting scheme of the temperature regulating device includes the indoor temperature data setting value in each time period and the duration setting value of each time period.

[0229] The power pre-determination unit is used to determine the power data setting value of the temperature adjustment device in each time period based on the indoor temperature data setting value in each time period and the above regression model.

[0230] The electricity fee pre-determination unit is used to determine the future total electricity fee corresponding to the temperature setting scheme of the temperature adjustment device based on the sparse model, the power data setting value of the temperature adjustment device in each time period and the setting value of the duration of each time period.

[0231] The optimization and determination unit is used to optimize the temperature setting scheme of the temperature adjustment device and determine the target setting value of the indoor temperature data in each time period.

[0232] The predetermined temperature setting scheme of the temperature regulating device can be set manually or generated based on an algorithm. The data types of the indoor temperature data setting values ​​of each stage should be unified when they are substituted into the temperature parameters in the regression model. The optimization process of the temperature setting scheme of the temperature regulating device can be optimized by using a branch and bound method and a mixed integer linear programming algorithm.

[0233] Through the above embodiment, the temperature setting scheme of the temperature regulating device is optimized, and the indoor temperature setting values ​​for each future time period corresponding to the minimum future total electricity bill are determined, so as to facilitate the subsequent determination of the temperature setting scheme corresponding to the low electricity bill expenditure.

[0234] In an exemplary embodiment, the constraint condition determination module includes:

[0235] The constrained regression unit is used to characterize each segmented power parameter in the objective function using the corresponding segmented indoor temperature parameter based on the regression model.

[0236] The constraint determination unit is used to determine the data setting interval of the segmented indoor temperature parameter based on the above-mentioned indoor temperature limit interval.

[0237] The above-mentioned temperature limit range can be a temperature range within which indoor people feel comfortable.

[0238] Through the above embodiment, the power parameter in the objective function is converted into a temperature parameter, so that the above indoor temperature limit range is used as a constraint condition of the sparse model.

[0239] In an exemplary embodiment, the acquisition module further includes:

[0240] The environmental parameter acquisition unit is used to obtain medium temperature response rate parameters, outdoor temperature segmentation parameters, and indoor temperature segmentation parameters.

[0241] The conduction factor model unit is used to establish a conduction factor model based on the medium temperature response rate parameter, the outdoor temperature segmentation parameter and the indoor temperature segmentation parameter.

[0242] The conduction factor determination unit is used to determine the conduction factor of the indoor temperature parameter in the above regression model based on the above conduction factor model.

[0243] The above-mentioned medium temperature response rate parameter may be the response rate of air to temperature, the response rate of the wall to temperature, etc. The above-mentioned air thermal conductivity coefficient may refer to the rate of heat conduction through air of unit thickness when the temperature difference is 1 degree Celsius per unit area per unit time. The above-mentioned wall response rate to temperature may refer to the rate of heat conduction through wall of unit thickness when the temperature difference is 1 degree Celsius per unit area per unit time. The above-mentioned outdoor temperature segmentation parameter may be segmented based on the above-mentioned indoor temperature segmentation parameter to ensure segmentation uniformity. The conduction factor in the above-mentioned conduction factor model may be the ratio between the indoor and outdoor temperature difference in each time period and the sum of the medium temperature response rate parameters, which is used to represent the conduction of cold and heat in the room.

[0244] Through the above embodiment, a conduction factor model is constructed based on the above medium temperature response rate parameters, outdoor temperature segmentation parameters, and indoor temperature segmentation parameters, so that the conduction of cold and heat indoors is used as a reference factor for the indoor temperature parameters, further improving the accuracy of parameter optimization.

[0245] In an exemplary embodiment, the acquisition module further includes:

[0246] The irradiation parameter acquisition unit is used to acquire irradiance segmentation parameters, irradiation area parameters and medium thermal resistance parameters.

[0247] The radiation factor model unit is used to establish a radiation factor model based on the above irradiance parameter, the above irradiation area parameter and the above medium thermal resistance parameter.

[0248] The radiation factor determination unit is used to determine the radiation factor of the indoor temperature parameter in the above regression model based on the above radiation factor model.

[0249] The above-mentioned irradiation area parameter can be a window area parameter for indoor lighting. The above-mentioned medium thermal resistance parameter can be the indoor air specific heat capacity, wall specific heat capacity, etc. The irradiation factor in the above-mentioned irradiation factor model can be the ratio between the product of the irradiance parameter and the irradiation area parameter in each time period and the medium thermal resistance parameter, which is used to indicate the impact of indoor radiation on indoor problems.

[0250] Through the above embodiment, an irradiation factor model is constructed based on the above irradiance segmentation parameter, irradiation area parameter and medium thermal resistance parameter, so that the indoor irradiance parameter is used as a reference factor for the indoor temperature parameter, further improving the accuracy of parameter optimization.

[0251] In an exemplary embodiment, the acquisition module further includes:

[0252] The medium parameter acquisition unit is used to acquire the thermal resistance parameters of the ambient medium.

[0253] The seasonal factor model unit is used to establish a seasonal factor model based on the power segmentation parameter and the above-mentioned environmental medium thermal resistance parameter.

[0254] The seasonal factor determination unit is used to determine the seasonal factor of the indoor temperature parameter in the above regression model based on the above seasonal factor model.

[0255] The above-mentioned environmental medium thermal resistance parameter may be the indoor air specific heat capacity, wall specific heat capacity, etc. The above-mentioned seasonal factor model may be obtained by performing seasonal judgment on the ratio between the above-mentioned power segmentation parameter and the above-mentioned environmental medium thermal resistance parameter. The seasonal judgment may be that the absolute value of the ratio remains unchanged in winter and is directly used as the seasonal factor, and the opposite value is taken as the seasonal factor in summer.

[0256] Through the above embodiment, a seasonal factor model is established based on the above power segmentation parameters and the above ambient medium thermal resistance parameters, so that the heat transfer conditions in the above sparse model are differentiated and considered, thereby improving the seasonal adaptability of the model.

[0257] In an exemplary embodiment, the above-mentioned regression model building unit includes:

[0258] The segmented temperature variation parameter determination subunit is used to determine the segmented temperature variation parameter based on the segmented indoor temperature parameter.

[0259] The segment power variation parameter determination subunit is used for determining the segment power variation parameter based on the segment power parameter.

[0260] The regression model building subunit is used to build the above-mentioned regression model that characterizes the regression relationship between the segmented temperature variation parameter and the segmented power parameter.

[0261] The segmented temperature variation parameter may be the difference between two adjacent segmented indoor temperature parameters. The segmented power variation parameter may be the difference between two adjacent segmented power parameters. The regression model may be a model that characterizes the regression relationship between the operating power variation and the indoor temperature variation.

[0262] Through the above embodiment, the basic control parameters of the air conditioner in the above regression model (i.e., the above segmented indoor temperature parameters) are converted into variable parameters, thereby reducing the difficulty of quantifying the data parameters in the model, reducing the amount of calculation and reducing the model mapping dimension.

[0263] Optionally, the temperature setting scheme of the temperature regulating device can be a future 24-hour indoor drift temperature setting scheme obtained by using a branch and bound method and a mixed integer linear programming algorithm and optimized based on the branch and bound method and the mixed integer linear programming algorithm. The drift temperature can be the expected indoor temperature difference between two adjacent moments outside the set interval. Each drift temperature setting value is substituted into the corresponding segmented temperature variation parameter.

[0264] In an exemplary embodiment, the constraint condition determination module further includes:

[0265] The critical value acquisition unit is used to obtain the critical value of indoor temperature change.

[0266] The temperature variation parameter constraint unit is used to determine the data setting interval of the segmented temperature variation parameter based on the above-mentioned indoor temperature variation critical value.

[0267] The indoor temperature change critical value may be the indoor temperature change critical value, that is, the maximum value of the segmented temperature change parameter.

[0268] Through the above embodiment, the data setting range of the above segmented temperature variation parameter is determined based on the indoor temperature variation critical value, thereby reducing the model optimization cycle and improving the strategy generation speed.

[0269] Optionally, the above medium temperature response rate parameters, outdoor temperature segmentation parameters, indoor temperature segmentation parameters, environmental medium thermal resistance parameters, irradiance segmentation parameters, irradiation area parameters, medium thermal resistance parameters and indoor temperature change critical values ​​can be manually set, or can be obtained by constructing a parameter fitting model based on historical data and an optimization algorithm. The above parameter fitting model can be a case where in the historical data, the electricity price, power, indoor temperature, outdoor temperature, irradiance, and irradiation area are known, while the environmental thermal resistance parameters, medium thermal resistance parameters, and medium temperature response rate are unknown, and the branch and bound method and mixed integer linear programming algorithm are used to solve the unknown quantities based on the objective function and historical data.

[0270] The present disclosure also provides a computer device, Figure 4 Schematic diagram of a computer device in an embodiment of the present disclosure. The computer device can implement all steps in the indoor temperature control method in the above embodiment. The computer device specifically includes the following contents:

[0271] Processor (processor) 401, memory (memory) 402, communication interface (CommunicationsInterface) 403 and communication bus 404;

[0272] The processor 401, the memory 402, and the communication interface 403 communicate with each other through the communication bus 404; the communication interface 403 is used to realize information transmission between related devices;

[0273] The processor 401 is used to call the computer program in the memory 402, and the indoor temperature control method in the above embodiment is implemented when the processor executes the computer program.

[0274] Optionally, in an embodiment, when the above computer program instructions are executed by a processor, the following steps are implemented:

[0275] Step S1, obtaining a regression model of operating power data of a temperature control device and indoor temperature data, time-of-use electricity price data, and a limited indoor temperature range.

[0276] Step S2, based on a number of segment power parameters, power segment duration parameters and the above-mentioned time-of-use electricity price data, a sparse model with the minimum future total electricity cost as the objective function is established.

[0277] Step S3, based on the regression model and the indoor temperature limit range, determine the constraint conditions of the sparse model.

[0278] Step S4, optimizing the above sparse model, and obtaining the target setting value of indoor temperature data in each time period corresponding to the minimum future total electricity bill based on the above regression model.

[0279] Step S5, generating a temperature control device operation strategy based on the target setting value of the indoor temperature data in each time period.

[0280] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and in response to the computer program being executed by a processor, the operations of the indoor temperature control method described above are implemented.

[0281] The embodiment of the present disclosure further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements: the above-mentioned indoor temperature control method.

[0282] Although the present disclosure provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in the order of the method shown in the embodiments or the drawings or in parallel (for example, in a parallel processor or multi-threaded processing room).

[0283] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, devices (systems) or computer program products. Therefore, the embodiments of this specification may take the form of complete hardware embodiments, complete software embodiments or embodiments combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0284] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0285] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0286] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0287] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0288] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure is not limited to any single aspect, nor to any single embodiment, nor to any combination and / or permutation of these aspects and / or embodiments. Moreover, each aspect and / or embodiment of the present disclosure may be used alone or in combination with one or more other aspects and / or embodiments thereof.

[0289] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present disclosure, and they should all be included in the scope of the claims and specification of the present disclosure.

Claims

1. A method for controlling indoor temperature, characterized in that: include: Obtain the regression model of the operating power data of the temperature control equipment and the indoor temperature data, the time-of-use electricity price data, and the indoor temperature limit range; Based on a number of segment power parameters, power segment duration parameters and the time-of-use electricity price data, a sparse model with the minimum future total electricity cost as the objective function is established; Determining the constraint conditions of the sparse model based on the regression model and the indoor temperature limit interval; Optimizing the sparse model, and obtaining the target setting value of indoor temperature data in each time period corresponding to the minimum future total electricity fee based on the regression model; Based on the target set values ​​of indoor temperature data in each time period, a temperature control equipment operation strategy is generated.

2. The indoor temperature control method according to claim 1, characterized in that: Based on the segment power parameters, the power segment duration parameters and the time-of-use electricity price data, a sparse model with the minimum future total electricity cost as the objective function is established, including: Determine the segment power consumption parameter item based on the segment power parameter and the power segment duration parameter; Based on the segment power consumption parameter items and the power segment duration parameters, determine the electricity fee parameter items for each segment; Based on the parameters of each segment electricity fee, a sparse expression of the future total electricity fee is constructed; Based on the sparse expression, a sparse model with the minimum future total electricity cost as the objective function is established.

3. The indoor temperature control method according to claim 2, characterized in that: Before establishing a sparse model with the minimum future total electricity cost as the objective function based on a number of segment power parameters, power segment duration parameters and the time-of-use electricity price data, the method further includes: Obtain the segment switch status data of the temperature control device; Based on the segmented switch state data of the temperature adjustment device, a weight coefficient of each segmented power consumption parameter item is set.

4. The indoor temperature control method according to any one of claims 1 to 3, characterized in that: Obtain a regression model of the temperature control equipment operating power data and indoor temperature data, including: Obtain historical indoor temperature data and historical operating power data of temperature control equipment; The regression model is constructed based on the historical indoor temperature data and the historical operating power data of the temperature regulating device.

5. The indoor temperature control method according to any one of claims 1 to 3, characterized in that: Optimizing the sparse model, based on the regression model, obtaining the target setting value of indoor temperature data in each time period corresponding to the minimum future total electricity fee, including: Predetermining a temperature setting scheme for a temperature regulating device, wherein the temperature setting scheme for the temperature regulating device includes a set value for indoor temperature data in each time period and a set value for the duration of each time period; Determining the power data setting value of the temperature adjustment device in each time period based on the indoor temperature data setting value in each time period and the regression model; Determine the future total electricity cost corresponding to the temperature setting scheme of the temperature adjustment device based on the sparse model, the power data setting value of the temperature adjustment device in each time period and the setting value of the duration of each time period; Optimize the temperature setting plan of the temperature regulating equipment and determine the target setting value of the indoor temperature data in each time period.

6. The indoor temperature control method according to any one of claims 1 to 3, characterized in that: Based on the regression model and the indoor temperature limit interval, determining the constraint conditions of the sparse model includes: Based on the regression model, using corresponding segmented indoor temperature parameters to characterize each segmented power parameter in the objective function; Based on the indoor temperature limit interval, a data setting interval of the segmented indoor temperature parameter is determined.

7. The indoor temperature control method according to claim 4, characterized in that: Before constructing the regression model based on the historical indoor temperature data and the historical operating power data of the temperature regulating device, the method further includes: Obtain medium temperature response rate parameters, outdoor temperature segmentation parameters, and indoor temperature segmentation parameters; Establishing a conduction factor model based on the medium temperature response rate parameter, the outdoor temperature segmentation parameter and the indoor temperature segmentation parameter; Based on the conduction factor model, a conduction factor of the indoor temperature parameter in the regression model is determined.

8. The indoor temperature control method according to claim 4, characterized in that: Before constructing the regression model based on the historical indoor temperature data and the historical operating power data of the temperature regulating device, the method further includes: Obtain irradiance segmentation parameters, irradiation area parameters and medium thermal resistance parameters; Establishing an irradiation factor model based on the irradiance parameter, the irradiation area parameter and the medium thermal resistance parameter; Based on the radiation factor model, the radiation factor of the indoor temperature parameter in the regression model is determined.

9. The indoor temperature control method according to claim 4, characterized in that: Before constructing the regression model based on the historical indoor temperature data and the historical operating power data of the temperature regulating device, the method further includes: Get the thermal resistance parameters of the ambient medium; Establishing a seasonal factor model based on the power segmentation parameter and the thermal resistance parameter of the ambient medium; Based on the seasonal factor model, a seasonal factor of the indoor temperature parameter in the regression model is determined.

10. The indoor temperature control method according to claim 5, characterized in that: The regression model is constructed based on the historical indoor temperature data and the historical operating power data of the temperature regulating device, including: Based on the segmented indoor temperature parameters, determining the segmented temperature variation parameters; Based on the segment power parameter, determining the segment power variation parameter; The regression model characterizing the regression relationship between the segmented temperature variation parameter and the segmented power parameter is constructed.

11. The indoor temperature control method according to claim 10, characterized in that: Determining the constraint conditions of the sparse model based on the regression model and the indoor temperature limit interval also includes: Get the critical value of indoor temperature change; Based on the indoor temperature change critical value, a data setting interval of the segmented temperature change amount parameter is determined.

12. An indoor temperature control device, characterized in that: include: An acquisition module is used to obtain a regression model of operating power data of a temperature control device and indoor temperature data, time-of-use electricity price data, and a limited indoor temperature range; A sparse model building module, used to build a sparse model with the minimum future total electricity cost as the objective function based on a number of segment power parameters, power segment duration parameters and the time-of-use electricity price data; A constraint condition determination module, used to determine the constraint conditions of the sparse model based on the regression model and the indoor temperature limit interval; A sparse model optimization module, used to optimize the sparse model, and obtain the target setting value of indoor temperature data in each time period corresponding to the minimum future total electricity fee based on the regression model; The strategy generation module is used to generate a temperature control device operation strategy based on the target setting value of the indoor temperature data in each time period.

13. The indoor temperature control device according to claim 12, characterized in that: The sparse model building module includes: A segment power consumption parameter determination unit, used to determine the segment power consumption parameter item based on the segment power parameter and the power segment duration parameter; A segmented electricity fee parameter item determining unit, used to determine each segmented electricity fee parameter item based on the segmented power consumption parameter item and the power segment duration parameter; A coefficient expression building unit, used to build a sparse expression of the future total electricity charge based on each segmented electricity charge parameter item; The sparse model building unit is used to build the sparse model with the minimum future total electricity cost as the objective function based on the sparse expression.

14. The indoor temperature control device according to claim 13, characterized in that: The indoor temperature control device further comprises: A status acquisition module is used to obtain the segment switch status data of the temperature adjustment device; The weight setting module is used to set the weight coefficient of each segment power consumption parameter item based on the segment switch state data of the temperature adjustment device.

15. The indoor temperature control device according to any one of claims 12 to 14, characterized in that: The acquisition module comprises: A historical data acquisition unit, used to acquire historical indoor temperature data and historical operating power data of a temperature control device; The regression model building unit is used to build the regression model based on the historical indoor temperature data and the historical operating power data of the temperature regulating device.

16. The indoor temperature control device according to any one of claims 12 to 14, characterized in that: The sparse model optimization module comprises: A temperature pre-determination unit, used to pre-determine a temperature setting scheme for a temperature regulating device, wherein the temperature setting scheme for the temperature regulating device includes a set value for indoor temperature data in each time period and a set value for the duration of each time period; A power pre-determination unit, used to determine the power data setting value of the temperature adjustment device in each time period based on the indoor temperature data setting value in each time period and the regression model; An electricity fee pre-determination unit, configured to determine a future total electricity fee corresponding to the temperature setting scheme of the temperature adjustment device based on the sparse model, the power data setting value of the temperature adjustment device in each time period, and the setting value of the duration of each time period; The optimization and determination unit is used to optimize the temperature setting scheme of the temperature regulating device and determine the target setting value of the indoor temperature data in each time period.

17. The indoor temperature control device according to any one of claims 12 to 14, characterized in that: The constraint condition determination module comprises: A constraint regression unit, used to characterize each segmented power parameter in the objective function using the corresponding segmented indoor temperature parameter based on the regression model; The constraint determination unit is used to determine the data setting interval of the segmented indoor temperature parameter based on the indoor temperature limit interval.

18. The indoor temperature control device according to claim 15, characterized in that: The acquisition module further includes: An environmental parameter acquisition unit, used to acquire medium temperature response rate parameters, outdoor temperature segmentation parameters, and indoor temperature segmentation parameters; A conduction factor model unit, used to establish a conduction factor model based on the medium temperature response rate parameter, the outdoor temperature segmentation parameter and the indoor temperature segmentation parameter; The conduction factor determination unit is used to determine the conduction factor of the indoor temperature parameter in the regression model based on the conduction factor model.

19. The indoor temperature control device according to claim 15, characterized in that: The acquisition module further includes: An irradiation parameter acquisition unit, used to acquire irradiance segmentation parameters, irradiation area parameters and medium thermal resistance parameters; An irradiation factor model unit, used to establish an irradiation factor model based on the irradiance parameter, the irradiation area parameter and the medium thermal resistance parameter; The radiation factor determination unit is used to determine the radiation factor of the indoor temperature parameter in the regression model based on the radiation factor model.

20. The indoor temperature control device according to claim 15, characterized in that: The acquisition module further includes: A medium parameter acquisition unit, used to acquire the thermal resistance parameters of the ambient medium; A seasonal factor model unit, used to establish a seasonal factor model based on a power segmentation parameter and a thermal resistance parameter of the ambient medium; A seasonal factor determination unit is used to determine the seasonal factor of the indoor temperature parameter in the regression model based on the seasonal factor model.

21. The indoor temperature control device according to claim 16, characterized in that: The regression model building unit comprises: A segmented temperature variation parameter determination subunit, used to determine a segmented temperature variation parameter based on a segmented indoor temperature parameter; A segment power variation parameter determination subunit is used for determining a segment power variation parameter based on the segment power parameter; The regression model building subunit is used to build the regression model that characterizes the regression relationship between the segmented temperature variation parameter and the segmented power parameter.

22. The indoor temperature control device according to claim 21, characterized in that: The constraint condition determination module further includes: A critical value acquisition unit, used to acquire a critical value of indoor temperature change; The temperature variation parameter constraint unit is used to determine the data setting interval of the segmented temperature variation parameter based on the indoor temperature variation critical value.

23. A computer device, characterized in that: The computer device comprises: a processor suitable for implementing various instructions and a storage device, wherein the storage device stores a plurality of instructions, and the instructions are suitable for being loaded by the processor and executing the indoor temperature control method according to any one of claims 1 to 11.

24. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to execute the indoor temperature control method according to any one of claims 1 to 11.

25. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the indoor temperature control method according to any one of claims 1 to 11 is implemented.

Images