Indoor temperature control method and device, electronic equipment and readable storage medium

Abstract

The invention relates to the technical field of temperature control, and provides an indoor temperature control method and device, electronic equipment and a readable storage medium. The method comprises the steps that operation state data, corresponding to current time, of temperature control equipment is obtained according to the current time, indoor and outdoor environment characteristic data corresponding to the current time are obtained, and the temperature control equipment is cold station equipment or hot station equipment; predicting an indoor load demand in the next time period according to the indoor and outdoor environment characteristic data to obtain an indoor target load in the next time period; wherein the load demand is a cooling capacity demand or a heat demand; predicting operation parameters of the temperature control equipment according to the target load, the operation state data and the indoor and outdoor environment characteristic data, and generating target operation state data of the temperature control equipment; and the temperature control equipment is controlled according to the target operation state data, so that the performance of the temperature control equipment is remarkably improved, and more refined and personalized temperature control is realized.

Description

Technical Field

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

[0002] With the development of science and technology, public places such as shopping malls and office buildings have installed smart temperature control equipment in factories to improve energy utilization efficiency and management efficiency, save energy input costs and reduce carbon emissions. Temperature control equipment usually consumes a lot of cold or hot energy when maintaining indoor temperature. Existing temperature control equipment collects indoor and outdoor temperature, humidity and other data through sensors, and automatically adjusts the operating status of the temperature control equipment according to the preset control logic. However, it relies on fixed control strategies and cannot accurately predict the demand for cold and heat. It lacks the ability to deeply analyze and predict real-time data, and cannot achieve refined and personalized temperature control of indoor temperature. Summary of the invention

[0003] In view of this, the embodiments of the present disclosure provide an indoor temperature control method, device, electronic device and readable storage medium to solve the problem in the prior art that the temperature control device cannot accurately predict the demand for cooling and heating and thus the indoor temperature control is inaccurate.

[0004] According to a first aspect of an embodiment of the present disclosure, there is provided a method for controlling indoor temperature, comprising:

[0005] According to the current time, the operating status data of the temperature control device corresponding to the current time is obtained, and the indoor and outdoor environment characteristic data corresponding to the current time is obtained, and the temperature control device is a cold station device or a hot station device;

[0006] Predicting the indoor load demand for the next time period based on the indoor and outdoor environmental characteristic data to obtain the indoor target load for the next time period; wherein the load demand is cooling demand or heating demand;

[0007] Predicting the operating parameters of the temperature control device according to the target load, operating status data and indoor and outdoor environmental characteristic data, and generating target operating status data of the temperature control device;

[0008] Control the temperature control equipment according to the target operating status data.

[0009] According to a second aspect of the embodiments of the present disclosure, there is provided an indoor temperature control device, comprising:

[0010] An acquisition module is configured to acquire, according to the current time, the operating status data of the temperature control device corresponding to the current time, and acquire the indoor and outdoor environment characteristic data corresponding to the current time, wherein the temperature control device is a cold station device or a hot station device;

[0011] A prediction module is configured to predict the indoor load demand for the next time period according to the indoor and outdoor environmental characteristic data to obtain the indoor target load for the next time period; wherein the load demand is a cooling demand or a heating demand;

[0012] a strategy generation module configured to predict the operating parameters of the temperature control device according to the target load, the operating status data and the indoor and outdoor environment characteristic data, and generate target operating status data of the temperature control device;

[0013] The control module is configured to control the temperature control device according to the target operating state data.

[0014] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0015] According to a fourth aspect of an embodiment of the present disclosure, a readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0016] Compared with the prior art, the disclosed embodiment has the following beneficial effects: by obtaining the operating status data of the temperature control device (such as a cold station or a hot station device) at the current time, as well as the indoor and outdoor environmental characteristic data, an accurate data basis is provided for subsequent prediction and control, so that the temperature control device can make predictions and decisions based on the environment and device status, thereby improving the real-time and accuracy of the prediction. By establishing a prediction model that can capture the complex relationship between environmental parameters and load demand, the indoor load demand for the next time period is predicted based on the indoor and outdoor environmental characteristic data, and the indoor target load for the next time period is obtained, and the future cold or hot load demand is accurately predicted through the prediction model. Based on the target load, the current device status and environmental characteristics, a variety of factors are combined to predict the optimal operating state of the temperature control device for the next time period, and the target operating state data of the temperature control device is generated to achieve more refined and personalized temperature control. The temperature control device is controlled according to the predicted target operating state data to achieve a predetermined operating state, thereby meeting the indoor temperature demand. The temperature control method provided by the present invention utilizes indoor and outdoor environmental characteristic data to perform load prediction, rather than relying solely on a single model or parameter, thereby improving the accuracy and robustness of the prediction, and by acquiring the operating status data of the temperature control device in real time, dynamically adjusting the control strategy using the operating status data, target load, and indoor and outdoor environmental characteristic data, thereby overcoming the problem in the prior art that the temperature control device cannot accurately predict the demand for cooling and heating and thus the indoor temperature control is inaccurate, and comprehensively considers the target load, device status, and environmental characteristics, optimizes the device operating parameters, achieves minimization of energy consumption, and ensures indoor comfort, significantly improves the performance of the temperature control device, and achieves more refined and personalized temperature control. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 is a flow chart of an indoor temperature control method provided by an embodiment of the present disclosure;

[0019] Figure 2 is a flow chart of another indoor temperature control method provided by an embodiment of the present disclosure;

[0020] Figure 3 is a flow chart of another indoor temperature control method provided by an embodiment of the present disclosure;

[0021] Figure 4is a flowchart of a sequential feature selection algorithm provided by an embodiment of the present disclosure;

[0022] Figure 5 is a flow chart of another indoor temperature control method provided by an embodiment of the present disclosure;

[0023] Figure 6 is a structural schematic diagram of an indoor temperature control device provided by an embodiment of the present disclosure;

[0024] Figure 7 It is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0026] A method and device for controlling indoor temperature according to an embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0027] Figure 1 FIG. 1 is a flow chart of an indoor temperature control method provided by an embodiment of the present disclosure. Figure 1 As shown, the indoor temperature control method includes:

[0028] Step 101, according to the current time, obtain the operating status data of the temperature control device corresponding to the current time, and obtain the indoor and outdoor environment characteristic data corresponding to the current time, the temperature control device is a cold station device or a hot station device.

[0029] In some embodiments, different times correspond to different operating temperature control devices. For example, in June, the operating temperature control device is a cold station device; in December, the operating temperature control device is a hot station device. Specifically, the operating status data of the cold station device is the data after preprocessing the collected original data (i.e., the current initial operating state data). By preprocessing the original data (i.e., the current initial operating state data), the original data is effectively cleaned and converted to obtain the operating status data of the cold station device, which can provide reliable input data for subsequent machine learning models and improve the accuracy and generalization ability of the model. The operating status data of the cold station device may include the chilled water supply and return water temperature difference, chilled water supply temperature, chilled water return temperature, chilled water supply pressure, chilled water return pressure, flow rate, freezing pump frequency, number of cooling towers, number of chillers, set temperature, operating status of chillers, etc. The running state data of the heat station equipment is the data after preprocessing the collected original data (i.e., the current initial running state data). The running state data of the heat station equipment may include the hot water pipe supply and return water temperature difference, hot water pipe supply water temperature, hot water pipe return water temperature, hot water pipe supply water pressure, hot water pipe return water pressure, flow, hot water pump frequency, number of boilers, number of hot water pumps, set temperature, boiler running state, etc. The running state data corresponding to the current time is the running state data of the current time period. For example, the current time period may be the time period from 9:00 to 10:00. The indoor and outdoor environment characteristic data is the data after preprocessing the collected original data (i.e., the indoor and outdoor environment initial characteristic data). The indoor and outdoor environment characteristic data may include the current time characteristics, indoor wet bulb temperature, indoor average temperature, indoor humidity, indoor and outdoor temperature difference, indoor and outdoor wet bulb temperature difference, indoor temperature median, indoor temperature variance, outdoor temperature in the next time period, characteristic vector of outdoor weather in the current time period, and characteristic vector of outdoor weather in the next time period. The current time period may be the time period from 9:00 to 10:00, and the next time period may be the time period from 10:00 to 11:00.

[0030] Obtaining the operating status data of the temperature control equipment (such as cold station equipment or hot station equipment) corresponding to the current time and the indoor and outdoor environmental characteristic data according to the current time is an important prerequisite for achieving accurate and efficient temperature control. Through real-time data collection, the temperature control equipment can timely understand the operating status of the equipment and the current environmental parameters, providing a basis for subsequent control decisions. The operating status data of the temperature control equipment and the indoor and outdoor environmental characteristic data corresponding to the current time can provide the necessary input information for subsequent load forecasting. By using more information sources and making predictions based on the latest actual situation, the temperature control equipment can respond quickly to changes in the current environment and adjust the operating status of the equipment to adapt to changing needs.

[0031] Step 102, predicting the indoor load demand for the next time period based on the indoor and outdoor environmental characteristic data, and obtaining the indoor target load for the next time period; wherein the load demand is cooling demand or heating demand.

[0032] In some embodiments, the indoor load demand for the next time period is predicted based on the indoor and outdoor environmental characteristic data, and advanced prediction algorithms (such as machine learning, deep learning, etc.) are used to accurately predict the indoor cooling or heating demand in the next time period, that is, the target load. Existing temperature control often uses a single prediction model, which is difficult to accurately capture the complex relationship between indoor and outdoor environmental parameters and cooling and heating load requirements, resulting in errors in the prediction of cooling and heating demand, and thus unable to achieve more refined and personalized temperature control. The target load obtained by the above prediction can be reflected as the amount of heat or cooling required to meet the indoor target temperature. By accurately predicting the load demand for the next time period, it is helpful to reasonably generate the optimal operating status data for the next time period. On the one hand, it can avoid excessive consumption and waste of energy, thereby improving energy utilization efficiency. On the other hand, it makes the indoor temperature more stable, achieves more refined and personalized temperature control, and meets the user's usage needs to achieve personalized control.

[0033] Step 103 , predicting the operating parameters of the temperature control device according to the target load, the operating status data and the indoor and outdoor environment characteristic data, and generating target operating status data of the temperature control device.

[0034] In some embodiments, the target load, indoor and outdoor environmental characteristic data, and operating status characteristic data are comprehensively considered, and a data analysis algorithm or a machine learning model can be used. At the same time, the stability and efficiency of temperature control can be considered to avoid frequent power on and off and excessive adjustment that lead to increased energy consumption or equipment damage. The target operating status data to which the temperature control should be adjusted is predicted. The target operating status data is the optimized recommended value. In order to meet the demand and achieve the optimal energy-saving control strategy, the temperature control can respond quickly and maintain optimal working efficiency when facing future load changes, while ensuring indoor temperature stability.

[0035] Specifically, when the temperature control is for a cold station equipment, the target operating status data may include: cold source system name: identifying the name or identifier of the cold station system; project name: identifying the name of the current project or shopping mall; indoor target temperature: the set target indoor temperature; target number of cooling towers: setting the number of cooling towers that need to be run; number of refrigeration pumps: setting the number of refrigeration pumps that need to be run; target frequency: setting the operating frequency of the refrigeration pump; target number of chillers: setting the number of chillers that need to be run; target set temperature: setting the set temperature of the chiller, etc.

[0036] Specifically, when the temperature control is for a thermal station device, the target operating status data may include: heat source system name: identifying the name or identifier of the thermal station system; project name: identifying the name of the current project or shopping mall; indoor target temperature: the set target indoor temperature; target number of hot water pumps: the set number of hot water pumps that need to be run; target frequency: the set operating frequency of the hot water pump; target number of boilers: the set number of boilers that need to be run; target set temperature: the set temperature of the boiler, etc.

[0037] Step 104: Control the temperature control device according to the target operating state data.

[0038] In some embodiments, the predicted target operating status data is applied to the actual temperature control device, and by adjusting the working parameters of the device, the temperature control device operates according to the target operating status data, realizing automatic control and reducing dependence on manual operation. The temperature control device can be a cold station device or a hot station device. The specific operation may include adjusting the start and stop status of the chiller, the frequency of the freezing pump, the valve opening and other parameters to meet the predicted cold target load demand. By converting the prediction results (i.e., the target operating status data) into actual control instructions, the prediction results are converted into actual actions, so that the temperature control device operates as expected. By accurately controlling the operating status of the temperature control device, better coping with complex real-life situations, and achieving more accurate and personalized temperature control, the indoor temperature can be better maintained within the set comfort range, thereby improving the user experience.

[0039] In addition, the temperature control device continuously collects actual indoor and outdoor environmental characteristic data and operating status data during operation, and feeds these data back to the temperature control device for subsequent updating and optimization of parameters in the temperature control device. Specifically, the feedback adjustment mechanism includes: continuously collecting actual indoor and outdoor environmental characteristic data and operating status data of the temperature control device; feeding back the collected indoor and outdoor environmental characteristic data and operating status data of the temperature control device to the temperature control device for parameter updating and optimization of the temperature control system of the temperature control device. According to the feedback data, the parameters of the temperature control device are updated and adjusted to improve the accuracy and prediction ability of the temperature control device. According to the updated temperature control device, the generated control strategy (i.e., the target operating status data obtained by screening) is adjusted to adapt to the current environmental changes and energy consumption requirements. By continuously collecting actual indoor and outdoor environmental characteristic data and operating status data of the temperature control device and feeding back to the temperature control device, the temperature control device is adjusted and optimized in a timely manner, thereby improving the accuracy and stability of prediction and control. The above feedback adjustment mechanism enables the temperature control device to continuously adapt to changes in the indoor and outdoor environment and realize intelligent management and optimization of the temperature control device.

[0040] The indoor temperature control method provided by the present disclosure obtains the operating status data of the temperature control device (such as a cold station or a hot station device) at the current time, as well as the indoor and outdoor environmental characteristic data, to provide an accurate data basis for subsequent prediction and control, so that the temperature control device can make predictions and decisions based on the environment and device status, thereby improving the real-time and accuracy of the prediction. By establishing a prediction model that can capture the complex relationship between environmental parameters and load demand, the indoor load demand for the next time period is predicted based on the indoor and outdoor environmental characteristic data, and the indoor target load for the next time period is obtained, and the future cold or hot load demand is accurately predicted through the prediction model. Based on the target load, the current device status and environmental characteristics, a variety of factors are combined to predict the optimal operating state of the temperature control device for the next time period, and the target operating state data of the temperature control device is generated to achieve more refined and personalized temperature control. The temperature control device is controlled according to the predicted target operating state data to achieve a predetermined operating state, thereby meeting the indoor temperature demand. The temperature control method provided by the present invention utilizes indoor and outdoor environmental characteristic data to perform load prediction, rather than relying solely on a single model or parameter, thereby improving the accuracy and robustness of the prediction, and by acquiring the operating status data of the temperature control device in real time, dynamically adjusting the control strategy using the operating status data, target load, and indoor and outdoor environmental characteristic data, thereby overcoming the problem in the prior art that the temperature control device cannot accurately predict the demand for cooling and heating and thus the indoor temperature control is inaccurate, and comprehensively considers the target load, device status, and environmental characteristics, optimizes the device operating parameters, achieves minimization of energy consumption, and ensures indoor comfort, significantly improves the performance of the temperature control device, and achieves more refined and personalized temperature control.

[0041] In some embodiments, when the temperature control device is a cold station device, the load demand indoors for the next time period is predicted based on indoor and outdoor environmental characteristic data to obtain the target indoor load for the next time period, including: inputting the indoor and outdoor environmental characteristic data into a cooling capacity prediction model to obtain the target indoor cooling capacity for the next time period output by the cooling capacity prediction model; and determining the target cooling capacity as the target load.

[0042] Specifically, the above-mentioned cooling capacity prediction model can fit the indoor and outdoor parameters of the current time period and the required cooling capacity of the next time period. The cooling capacity prediction model is obtained by training based on the historical indoor and outdoor environmental characteristic data and the corresponding historical generated cooling capacity of the next period. The historical generated cooling capacity can be calculated based on the historical operating status data of the cooling station equipment. For example, the historical operating status data of the cooling station equipment includes flow, chilled water supply temperature and chilled water return temperature. The corresponding generated cooling capacity can be calculated based on the flow, chilled water supply temperature and chilled water return temperature. Input the indoor and outdoor environmental characteristic data into the cooling capacity prediction model, and predict the indoor cooling capacity demand in the future period based on the indoor and outdoor environmental characteristic data. The target cooling capacity of the indoor room in the next time period output by the cooling capacity prediction model provides a data basis for subsequent steps. And the target cooling capacity output by the cooling capacity prediction model is determined as the target load of the next time period. The predicted target cooling capacity is used as the target load to provide a basis for the subsequent control of the cooling station equipment, so that the target operating state of the temperature control equipment can be generated with reference to the target cooling capacity to meet the predicted cooling capacity demand.

[0043] In some embodiments, when constructing a cooling capacity prediction model, indoor and outdoor environmental feature data are used as original data sets, and the indoor and outdoor environmental feature data may include current time features, indoor wet bulb temperature, indoor average temperature, indoor humidity, indoor and outdoor temperature difference, indoor and outdoor wet bulb temperature difference, indoor temperature median, indoor temperature variance, outdoor temperature in the next time period, feature vector of outdoor weather in the current time period, and feature vector of outdoor weather in the next time period, etc., and multiple sub-features can be obtained by screening the sequential feature selection algorithm (Sequential Backward Floating Selection, SBFS), and the features in the optimal feature subset are the most informative for the cooling capacity prediction model. The cooling capacity prediction model to be trained can be a lightweight gradient boosting machine (Light Gradient Boosting Machine, LightGBM), and a hyperparameter search space is specified, and then a random search or grid search is used to determine the optimal hyperparameters to improve the performance of the model. The optimal feature subset and historically generated cooling capacity are used for model training. By fitting the relationship between environmental parameters and the actual cooling demand in the next time period, the cooling prediction model can accurately predict the cooling demand in the next time period. The cooling prediction model is evaluated using indicators such as Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) to verify the accuracy and stability of the model, and a trained cooling prediction model is obtained.

[0044] In some embodiments, when the temperature control device is a thermal station device, the load demand indoors for the next time period is predicted based on indoor and outdoor environmental characteristic data to obtain the target load indoors for the next time period, including: inputting the indoor and outdoor environmental characteristic data into a heat prediction model to obtain the target heat indoors for the next time period output by the heat prediction model; and determining the target heat as the target load.

[0045] Specifically, the heat prediction model can fit the indoor and outdoor parameters of the current time period and the required heat in the next time period. The heat prediction model is trained based on the historical indoor and outdoor environmental characteristic data and the historical generated heat of the next period of the heat station equipment. The historical generated heat is calculated based on the historical operating status data of the heat station equipment. For example, the historical operating status data of the heat station equipment includes flow, hot water pipe supply temperature and hot water pipe return temperature. The corresponding generated heat can be calculated based on the flow, hot water pipe supply temperature and hot water pipe return temperature. Input the indoor and outdoor environmental characteristic data into the heat prediction model, predict the indoor heat demand in the future period based on the indoor and outdoor environmental characteristic data, and obtain the predicted indoor heat in the next time period output by the heat prediction model, providing a data basis for subsequent steps. The target cooling capacity output by the heat prediction model is determined as the target load of the next time period. The predicted target heat is used as the target load to provide a basis for the subsequent control of the heat station equipment, so that the target operating state of the temperature control device can be controlled with reference to the target heat generation to meet the predicted heat demand.

[0046] In some embodiments, when constructing a heat prediction model, the indoor and outdoor environmental feature data are used as the original data set. The indoor and outdoor environmental feature data may include current time features, indoor wet bulb temperature, indoor average temperature, indoor humidity, indoor and outdoor temperature difference, indoor and outdoor wet bulb temperature difference, indoor temperature median, indoor temperature variance, outdoor temperature in the next time period, feature vector of outdoor weather in the current time period, and feature vector of outdoor weather in the next time period, etc., and the optimal feature subset can be obtained by SBFS screening. The features in the optimal feature subset are the most informative for the heat prediction model. The heat prediction model to be trained can be a LightGBM model, and a hyperparameter search space is specified, and then a random search or grid search is used to determine the optimal hyperparameters to improve the performance of the model. The model is trained using the optimal feature subset and historically generated heat. By fitting the relationship between environmental parameters and the operating status of the equipment and the actual heat demand, the heat prediction model can accurately predict the heat demand in the next time period, and the heat prediction model is evaluated using indicators such as RMSE or MAE to verify the accuracy and stability of the model, and a trained heat prediction model is obtained.

[0047] In some embodiments, reference Figure 2, when the temperature control device is a cold station device, step 103 includes steps 201 to 206, the indoor and outdoor environmental characteristic data include the indoor and outdoor wet-bulb temperature difference and the indoor average temperature, and the operating status data include the chilled water supply temperature and the chilled water return temperature;

[0048] The operating parameters of the temperature control equipment are predicted based on the target load, operating status data and indoor and outdoor environmental characteristic data, and the target operating status data of the temperature control equipment is generated, including:

[0049] Step 201, input the indoor and outdoor wet bulb temperature difference and the target cooling capacity as a set of data into a cooling tower quantity prediction model, and obtain the target number of cooling towers in the next time period output by the cooling tower quantity prediction model.

[0050] Specifically, the indoor and outdoor wet-bulb temperature difference can reflect the humidity conditions of the indoor and outdoor air, and can be used as an important reference factor for the efficiency of the cooling tower. A higher wet-bulb temperature means a higher moisture content in the air, and the cooling effect of the cooling tower may be affected. The target cooling capacity is the cooling capacity demand that needs to be provided in the next time period. The cooling tower needs to adjust its working state according to the target cooling capacity to meet the cooling capacity demand. The above cooling tower quantity prediction model can fit the indoor and outdoor wet-bulb temperature difference, the target cooling capacity and the target number of cooling towers in the next time period. The indoor and outdoor wet-bulb temperature difference and the target cooling capacity are input into the cooling tower quantity prediction model as a set of data to predict the required number of cooling towers and obtain the target number of cooling towers in the next time period of the cold station equipment, which helps to determine whether there is enough cooling capacity to support the target cooling capacity demand while avoiding excessive or insufficient use of cooling towers. The cooling tower is an important heat dissipation component in the cold station equipment. The number of cooling towers directly affects the heat dissipation efficiency. Through a comprehensive analysis of the indoor and outdoor wet-bulb temperature difference and the target cooling capacity, the most economical and effective cooling tower configuration is determined, and the target number of cooling towers is obtained to meet the expected target cooling capacity demand. The cooling tower quantity prediction model comprehensively considers the impact of environmental conditions on the cooling effect to ensure that the system can effectively dissipate heat under different environments.

[0051] In addition, the cooling tower quantity prediction model is trained based on historical indoor and outdoor environmental characteristic data, historical operating status data of cold station equipment, target cooling capacity and corresponding historical number of cooling towers, and the historical number of cooling towers is the number of cooling towers in the operating status data of the next time period in the above historical operating status data. Specifically, the historical operating status data of the cold station equipment may include the temperature difference between the supply and return water of chilled water, the supply water temperature of chilled water, the return water temperature of chilled water, the supply water pressure of chilled water, the return water pressure of chilled water, the flow rate, the frequency of the freezing pump, the number of cooling towers, the number of chillers, the set temperature, the operating status of the chiller, etc. The historical indoor and outdoor environmental characteristic data may include current time characteristics, indoor wet-bulb temperature, indoor average temperature, indoor humidity, indoor and outdoor temperature difference, indoor and outdoor wet-bulb temperature difference, indoor temperature median, indoor temperature variance, outdoor temperature in the next time period, characteristic vector of outdoor weather in the current time period, and characteristic vector of outdoor weather in the next time period, etc. When constructing a cooling tower quantity prediction model, the historical indoor and outdoor environmental characteristic data, the historical operating status data of the cold station equipment, and the target cooling capacity are used as the original data set. The original data set includes multiple sub-features, and the optimal feature subset can be obtained by SBFS screening. The features in the optimal feature subset are the most informative for the cooling tower quantity prediction model. Specifically, the optimal feature subset can include the indoor and outdoor wet-bulb temperature difference and the target cooling capacity. The cooling tower quantity prediction model to be trained can be a Ridge model, and the hyperparameter search space is specified, and then the optimal hyperparameters are determined using random search or grid search to improve the performance of the model. The model is trained using the optimal feature subset and the historical number of cooling towers. By fitting the relationship between the input parameters and the actual number of cooling towers, the cooling tower quantity prediction model can accurately predict the number of cooling towers in the next time period, and the cooling tower quantity prediction model is evaluated using indicators such as RMSE or MAE to verify the accuracy and stability of the model, and a trained cooling tower quantity prediction model is obtained.

[0052] Step 202: input the target cooling capacity into the refrigeration machine quantity prediction model to obtain the target quantity of refrigeration machines in the next time period output by the refrigeration machine quantity prediction model.

[0053] Specifically, the chiller is the main equipment for generating cooling capacity. By predicting the number of chillers, the load can be reasonably distributed to avoid overloading of a single chiller or too many chillers being idle. The target cooling capacity is directly input into the chiller quantity prediction model. The chiller quantity prediction model predicts the number of chillers that need to be started in the next time period based on the target cooling capacity, which helps the cold station equipment to provide enough cooling capacity to meet the target cooling capacity demand. Through the chiller quantity prediction model, the number of chillers can be dynamically adjusted according to the target cooling capacity to avoid resource waste or insufficient cooling capacity caused by too many or too few chillers.

[0054] In addition, the chiller quantity prediction model is trained based on the historical generated cooling capacity and the corresponding historical number of chillers. The trained chiller quantity prediction model can fit the relationship between the generated cooling capacity and the number of chillers turned on. The chiller quantity prediction model to be trained can be a Ridge model, and the hyperparameter search space is specified, and then the optimal hyperparameters are determined using random search or grid search to improve the performance of the model. The model is trained using the historical generated cooling capacity and the corresponding historical number of chillers. By fitting the relationship between the input parameters and the actual number of chillers, the chiller quantity prediction model can accurately predict the number of chillers in the next time period, and the chiller quantity prediction model is evaluated using indicators such as the root mean square error or the mean absolute error to verify the accuracy and stability of the model, and a trained chiller quantity prediction model is obtained.

[0055] Step 203, the indoor average temperature and the chilled water supply temperature are input as a set of data into the chiller set temperature prediction model to obtain the target set temperature for the next time period output by the chiller set temperature prediction model.

[0056] Specifically, the indoor average temperature is the indoor average temperature in the current time period. The indoor average temperature in the current time period is the indoor average temperature obtained by multiple indoor temperature sensors in the current time period. The time period can be 1 hour, and each temperature sensor can send back temperature data every five minutes. The indoor average temperature is an important reference for the set temperature of the chiller. A higher indoor temperature may require a lower set temperature of the chiller to quickly cool down. The chilled water supply temperature can reflect the temperature state of the chilled water in the current cold station equipment. If the water supply temperature is high, the set temperature of the chiller needs to be adjusted to lower the temperature of the chilled water. The above-mentioned chiller set temperature prediction model can predict the target temperature that the chiller should be set to in the next time period based on the input indoor average temperature and chilled water supply temperature, which helps to optimize the operating efficiency of the chiller and ensure that the chilled water can reach the required temperature to meet the requirements of indoor temperature control.

[0057] In addition, the cold machine set temperature prediction model is trained based on historical indoor and outdoor environmental characteristic data, historical operating status data of cold station equipment, target cooling capacity and corresponding historical set temperature. The historical set temperature is the set temperature in the operating status data of the next time period in the above historical operating status data. When constructing the cold machine set temperature prediction model, the historical indoor and outdoor environmental characteristic data, the historical operating status data of the cold station equipment, and the target cooling capacity are used as the original data set. The original data set includes multiple sub-features, and the optimal feature subset can be obtained by SBFS screening. The features in the optimal feature subset are the most informative for the cold machine set temperature prediction model. Specifically, the optimal feature subset can include the average indoor temperature and the chilled water supply temperature. The cold machine set temperature prediction model to be trained can be a Ridge model, and a hyperparameter search space is specified, and then a random search or grid search is used to determine the optimal hyperparameters to improve the performance of the model. The model is trained using the optimal feature subset and historical set temperatures. By fitting the relationship between the input parameters and the actual set temperatures, the refrigerator set temperature prediction model can accurately predict the refrigerator set temperature of the next time period. The refrigerator set temperature prediction model is evaluated using indicators such as root mean square error or mean absolute error to verify the accuracy and stability of the model, thereby obtaining a trained refrigerator set temperature prediction model.

[0058] Step 204, obtaining multiple candidate frequencies of the refrigeration pump and candidate flow rates corresponding to each candidate frequency, and generating candidate heat corresponding to each candidate frequency based on the candidate flow rates corresponding to each candidate frequency, the target set temperature and the chilled water return temperature;

[0059] Step 205, calculating the absolute value of the difference between the candidate heat and the target cooling capacity corresponding to each candidate frequency, and determining the candidate frequency that meets the preset requirements among the candidate frequencies as the target frequency for the next time period, wherein the preset requirements are that the candidate frequency is less than or equal to the first preset value and the absolute value of the difference with the target cooling capacity is the smallest;

[0060] Step 206 : generating target operating state data of the temperature control device based on the target frequency, the target set temperature, the target number of chillers, and the target number of cooling towers.

[0061] In some embodiments, multiple candidate frequencies of the freezing pump and candidate flow rates corresponding to each candidate frequency are obtained, and the candidate frequencies are different frequency values ​​at which the freezing pump may operate. For each candidate frequency, there is a flow rate value corresponding to it. The candidate frequency is input into the freezing pump frequency model, and the freezing pump frequency model can be calculated using internal algorithms and parameters to output the candidate flow rate corresponding to the candidate frequency. By obtaining multiple candidate frequencies of the freezing pump and candidate flow rates corresponding to each candidate frequency, multiple possible options can be provided for subsequent heat calculation and frequency optimization.

[0062] Specifically, the above-mentioned freezing pump frequency model can fit the flow rate according to the freezing pump frequency. When training the freezing pump frequency model, the freezing pump frequency in each historical operating status data is used as a training sample, and the flow rate corresponding to each historical operating status data is used as the label corresponding to the sample to construct a training set. The freezing pump frequency model to be trained can be a Ridge model, and the model hyperparameters are determined using Bayesian search. MAPE is used to evaluate the model performance and obtain a trained flow heat model. Through the freezing pump frequency model, the flow output under different freezing pump frequency models can be quantified, providing a basis for the subsequent screening of the target frequency from multiple candidate frequencies.

[0063] Specifically, the target set temperature is the target temperature of the chilled water output by the chiller predicted by the above-mentioned chiller set temperature prediction model. The chilled water return temperature is the chilled water return temperature in the current time period. The chilled water return temperature can reflect the actual cooling effect. The difference between the chilled water return temperature and the target set temperature affects the actual cooling capacity. For each candidate frequency, the candidate heat corresponding to each candidate frequency is calculated using its corresponding flow, target set temperature and chilled water return temperature, and the frequency of the chilled pump is converted into a specific cooling capacity, which is convenient for subsequent comparison and selection. The absolute value of the difference between the candidate heat corresponding to each candidate frequency and the target cooling capacity is calculated, and a frequency that meets the preset requirements is selected from all candidate frequencies as the target frequency for the next time period. The preset requirement is that the absolute value of the difference between the candidate cooling capacity corresponding to the target frequency and the target cooling capacity is less than or equal to the first preset value, and the absolute value of the difference between the candidate cooling capacity corresponding to the target frequency and the target cooling capacity is the smallest. By calculating the difference, the gap between the cooling capacity generated by the chilled pump at different frequencies and the actual required cooling capacity can be quantified. The first preset value is the tolerance range of the difference, which ensures that the operating frequency of the chilled pump does not deviate too far from the target cooling capacity. The candidate frequency with the smallest difference is selected as the target frequency, so that the refrigeration pump can run as efficiently as possible while meeting the target cooling capacity. The determined target frequency, target set temperature, target number of chillers and target number of cooling towers are integrated to form the target operating status data of the complete temperature control equipment, which is used to control the operation of the refrigeration station equipment in the next time period.

[0064] In some embodiments, reference Figure 3 , step 103 may include steps 301 to 304, that is, when the temperature control device is a heat station device, the indoor and outdoor environmental characteristic data include the indoor temperature median and the indoor temperature variance, and the operating status data include the hot water pipe supply and return water temperature difference and the hot water pipe supply water temperature;

[0065] The operating parameters of the temperature control equipment are predicted based on the target load, operating status data and indoor and outdoor environmental characteristic data, and the target operating status data of the temperature control equipment is generated, including:

[0066] Step 301, obtaining the indoor target temperature, the first temperature difference between the indoor target temperature and the median indoor temperature, and inputting the median indoor temperature, the indoor target temperature, the hot water pipe supply and return water temperature difference and the first temperature difference as a set of data into a hot water pump quantity prediction model to obtain the hot water pump quantity prediction model outputs the target number of hot water pumps for the next time period;

[0067] Specifically, the indoor temperature data within a set time period (such as 1 hour) can be collected by a temperature sensor installed indoors. The temperature sensor can collect data every 5 minutes to obtain multiple initial indoor temperatures. The initial indoor temperature in the previous time period can reflect the change of the indoor temperature in the current time period. The multiple initial indoor temperature data collected are sorted, and the median indoor temperature can be determined according to the number of data. The median indoor temperature can reflect the overall level of the indoor temperature in the current time period. The indoor temperature variance is calculated by multiple initial indoor temperatures, which can reflect the degree of fluctuation of the indoor temperature and help evaluate the stability of the indoor temperature. The hot water pipe supply and return water temperature difference can be calculated by the hot water pipe supply water temperature and the hot water pipe return water temperature. The hot water pipe supply and return water temperature difference can reflect the heat loss or transfer efficiency of hot water during the circulation process. It is a key parameter for evaluating the efficiency of the heat station equipment. The larger the hot water pipe supply and return water temperature difference, the more heat the heat station equipment provides. The hot water pipe supply water temperature can reflect the current operating temperature of the heat station equipment and is an important reference for adjusting the operating status of the heat station equipment. The indoor target temperature is the indoor temperature that the user wants to achieve or maintain, which can be set by the user. The first temperature difference between the indoor target temperature and the indoor temperature median is calculated, and the first temperature difference reflects the gap between the current indoor temperature and the target temperature.

[0068] Specifically, the above-mentioned hot water pump quantity prediction model can fit the median indoor temperature, the indoor target temperature, the hot water pipe supply and return water temperature difference, the first temperature difference and the target number of hot water pumps in the next time period. The median indoor temperature, the indoor target temperature, the hot water pipe supply and return water temperature difference and the first temperature difference are input into the hot water pump quantity prediction model as a set of data to predict the required number of hot water pumps and obtain the target number of hot water pumps in the next time period of the thermal station equipment, which helps to determine whether there is enough heating capacity to support the target heat demand while avoiding excessive or insufficient use of hot water pumps. The hot water pump is an important component in the thermal station equipment. The number of hot water pumps directly affects the heat production efficiency. Through a comprehensive analysis of the median indoor temperature, the indoor target temperature, the hot water pipe supply and return water temperature difference, and the first temperature difference, the most economical and effective hot water pump configuration is determined, and the target number of hot water pumps is obtained to meet the expected target heat demand.

[0069] In addition, the hot water pump quantity prediction model is trained based on historical indoor and outdoor environmental characteristic data, historical operating status data of heat station equipment, target heat and corresponding historical hot water pump quantity, and the historical hot water pump quantity is the number of hot water pumps in the operating status data of the next time period in the above historical operating status data. Specifically, the historical operating status data of the heat station equipment may include the hot water pipe supply and return water temperature difference, hot water pipe supply water temperature, hot water pipe return water temperature, hot water pipe supply water pressure, hot water pipe return water pressure, flow rate, hot water pump frequency, number of boilers, number of hot water pumps, set temperature, boiler operating status, etc. The historical indoor and outdoor environmental characteristic data may include current time characteristics, indoor wet bulb temperature, indoor average temperature, indoor humidity, indoor and outdoor temperature difference, indoor and outdoor wet bulb temperature difference, indoor temperature median, indoor temperature variance, outdoor temperature in the next time period, feature vector of outdoor weather in the current time period, and feature vector of outdoor weather in the next time period. When constructing a hot water pump quantity prediction model, the historical indoor and outdoor environmental feature data, the historical operating status data of the heat station equipment, and the target heat are used as the original data set. The original data set includes multiple sub-features, and the optimal feature subset can be obtained by SBFS screening. The features in the optimal feature subset are the most informative for the hot water pump quantity prediction model. Specifically, the optimal feature subset can include the median indoor temperature, the indoor target temperature, the hot water pipe supply and return water temperature difference, and the first temperature difference. The hot water pump quantity prediction model to be trained can be a LightGBM model, and the hyperparameter search space is specified, and then the optimal hyperparameters are determined using random search or grid search to improve the performance of the model. The model is trained using the optimal feature subset and the historical number of hot water pumps. By fitting the relationship between the input parameters and the actual number of hot water pumps, the hot water pump quantity prediction model can accurately predict the number of hot water pumps in the next time period, and the root mean square error (RMSE), mean absolute error (MAE) and other indicators are used to evaluate the hot water pump quantity prediction model to verify the accuracy and stability of the model, and obtain the trained hot water pump quantity prediction model.

[0070] Step 302, input the indoor temperature median, indoor temperature variance, indoor target temperature, hot water pipe supply and return water temperature difference, first temperature difference and hot water pipe supply water temperature as a set of data into the boiler quantity prediction model to obtain the boiler target quantity for the next time period output by the boiler quantity prediction model.

[0071] Specifically, the above boiler quantity prediction model can fit the median indoor temperature, indoor temperature variance, indoor target temperature, hot water pipe supply and return water temperature difference, first temperature difference, hot water pipe supply water temperature and the target number of boilers in the next time period. The median indoor temperature, indoor temperature variance, indoor target temperature, hot water pipe supply and return water temperature difference, first temperature difference and hot water pipe supply water temperature are input into the boiler quantity prediction model as a set of data to predict the required number of boilers and obtain the target number of boilers in the next time period of the heat station equipment, which helps to determine whether there is enough heating capacity to support the target heat demand while avoiding excessive or insufficient use of boilers. Boilers are important components in heat station equipment. The number of boilers directly affects the heat production efficiency. Through a comprehensive analysis of the median indoor temperature, indoor temperature variance, indoor target temperature, hot water pipe supply and return water temperature difference, first temperature difference and hot water pipe supply water temperature, the most economical and effective boiler configuration is determined and the target number of boilers is obtained to meet the expected target heat demand.

[0072] In addition, the boiler quantity prediction model is trained based on historical indoor and outdoor environmental characteristic data, historical operating status data of heat station equipment, target heat and corresponding historical boiler quantity, and the historical boiler quantity is the number of boilers in the operating status data of the next time period in the above historical operating status data. Specifically, the historical operating status data of the heat station equipment may include the hot water pipe supply and return water temperature difference, hot water pipe supply water temperature, hot water pipe return water temperature, hot water pipe supply water pressure, hot water pipe return water pressure, flow rate, boiler frequency, number of boilers, number of boilers, set temperature, boiler operating status, etc. The historical indoor and outdoor environmental characteristic data may include current time characteristics, indoor wet bulb temperature, indoor average temperature, indoor humidity, indoor and outdoor temperature difference, indoor and outdoor wet bulb temperature difference, indoor temperature median, indoor temperature variance, outdoor temperature in the next time period, characteristic vector of outdoor weather in the current time period, and characteristic vector of outdoor weather in the next time period. When constructing the boiler quantity prediction model, the historical indoor and outdoor environmental feature data, the historical operating status data of the heat station equipment, and the target heat are used as the original data set. The original data set includes multiple sub-features, and the optimal feature subset can be obtained by SBFS screening. The features in the optimal feature subset are the most informative for the boiler quantity prediction model. Specifically, the optimal feature subset can include the median of indoor temperature, the variance of indoor temperature, the indoor target temperature, the supply and return water temperature difference of the hot water pipe, the first temperature difference, and the supply water temperature of the hot water pipe. The boiler quantity prediction model to be trained can be a LightGBM model, and the hyperparameter search space is specified, and then the optimal hyperparameters are determined using random search or grid search to improve the performance of the model. The model is trained using the optimal feature subset and the historical number of boilers. By fitting the relationship between the input parameters and the actual number of boilers, the boiler quantity prediction model can accurately predict the number of boilers in the next time period, and the root mean square error (RMSE) and mean absolute error (MAE) and other indicators are used to evaluate the boiler quantity prediction model to verify the accuracy and stability of the model, and obtain the trained boiler quantity prediction model.

[0073] Step 303: input the median indoor temperature and the hot water pipe supply temperature as a set of data into the boiler set temperature prediction model to obtain the target set temperature for the next time period output by the boiler set temperature prediction model.

[0074] Specifically, the boiler set temperature prediction model can fit the median indoor temperature, the hot water pipe water supply temperature and the boiler set temperature for the next time period. The median indoor temperature and the hot water pipe water supply temperature are input into the boiler set temperature prediction model as a set of data to predict the required target set temperature, and obtain the boiler target set temperature for the next time period of the thermal station equipment, which helps to optimize the operating efficiency of the boiler and meet the requirements of indoor temperature control. Through a comprehensive analysis of the median indoor temperature and the hot water pipe water supply temperature, the most economical and effective boiler temperature configuration is determined, and the target set temperature of the boiler is obtained to meet the expected target heat demand.

[0075] In addition, the boiler set temperature prediction model is trained based on historical indoor and outdoor environmental characteristic data, historical operating status data of thermal station equipment, target heat and corresponding historical boiler set temperature. The historical boiler set temperature is the historical boiler set temperature in the operating status data of the next time period in the above historical operating status data. When constructing the boiler set temperature prediction model, the historical indoor and outdoor environmental characteristic data, the historical operating status data of the thermal station equipment, and the target heat are used as the original data set. The original data set includes multiple sub-features, and the optimal feature subset can be screened by SBFS. The features in the optimal feature subset are the most informative for the boiler set temperature prediction model. Specifically, the optimal feature subset may include the median indoor temperature and the water supply temperature of the hot water pipe. The boiler set temperature prediction model to be trained can be a LightGBM model, and a hyperparameter search space is specified, and then random search or grid search is used to determine the optimal hyperparameters to improve the performance of the model. The optimal feature subset and historical boiler set temperatures are used for model training. By fitting the relationship between the input parameters and the actual boiler set temperatures, the boiler set temperature prediction model can accurately predict the target set temperature of the next time period. The root mean square error (RMSE) and mean absolute error (MAE) are used to evaluate the boiler set temperature prediction model to verify the accuracy and stability of the model, and a trained boiler set temperature prediction model is obtained.

[0076] Step 304 : generating target operating state data of the temperature control device based on the target set temperature, the target number of boilers, and the target number of hot water pumps.

[0077] Specifically, the target set temperature is the target temperature that the boiler should be set to in the next time period obtained by the boiler set temperature prediction model, the target number of boilers is the number of boilers that need to be started in the next time period obtained by the boiler number prediction model, and the target number of hot water pumps is the number of hot water pumps that need to be started in the next time period obtained by the hot water pump number prediction model. The target set temperature, the target number of boilers and the target number of hot water pumps are integrated to generate the target operating status data of the temperature control device in the next time period. The target operating status data will be used to control the actual operation of the thermal station equipment, so that all relevant equipment of the thermal station equipment can work together in the same time period to generate target heat. Through refined prediction and control, the operating efficiency of the thermal station system is improved, ensuring that the heating demand is accurately met.

[0078] In some embodiments, before inputting the indoor and outdoor environmental characteristic data into the cooling capacity prediction model, the method further includes:

[0079] Acquire a historical indoor and outdoor environment characteristic data set and historical operation status data of the cooling station equipment, and determine the corresponding historical cooling capacity according to the historical operation status data, wherein the historical indoor and outdoor environment characteristic data set includes multiple sub-characteristics;

[0080] The historical indoor and outdoor environmental feature data sets are used as training samples, and the historical cooling capacity is used as the label corresponding to the training samples. The sequential feature selection algorithm is used to obtain the optimal feature subset of the cooling capacity prediction model.

[0081] The cooling capacity prediction model to be trained is trained based on the optimal feature subset and the historical cooling capacity to obtain a trained cooling capacity prediction model.

[0082] In some embodiments, the historical indoor and outdoor environment feature data set is a set of historical data sets containing multiple sub-features, such as current time features, indoor wet bulb temperature, indoor average temperature, indoor humidity, indoor and outdoor temperature difference, indoor and outdoor wet bulb temperature difference, indoor temperature median, indoor temperature variance, outdoor temperature in the next time period, feature vector of outdoor weather in the current time period, and feature vector of outdoor weather in the next time period. The historical operation status data of the cold station equipment is a set of operation status data recording the cold station equipment at different time points in the past, such as the chilled water supply and return water temperature difference, chilled water supply water temperature, chilled water return water temperature, chilled water supply water pressure, chilled water return water pressure, flow rate, freezing pump frequency, number of cooling towers, number of chillers, set temperature, operation status of chillers, etc. According to the historical operation status data, the actual cooling capacity provided in different time periods is calculated. The historical indoor and outdoor environment feature data set is used as a training sample and the historical cooling capacity is used as a label corresponding to the training sample.

[0083] The sequential feature selection algorithm is used to obtain the optimal feature subset of the cold volume prediction model. The sequential feature selection algorithm includes forward selection and backward elimination. The sequential feature selection algorithm (such as sequential forward selection, sequential backward selection or bidirectional selection) evaluates the contribution of each feature to the model performance by gradually adding or removing features. In this process, the optimal feature subset can be selected based on a certain evaluation criterion (such as accuracy, recall rate, F1 score or cross-validation score). Through the sequential feature selection algorithm, it can be determined which sub-features are most important for predicting cold volume. These features constitute the optimal feature subset for subsequent model training. Using the optimal feature subset after feature selection as input and the historical cold volume as the corresponding label, the cold volume prediction model to be trained is trained to obtain the trained cold volume prediction model. The cold volume prediction model to be trained can be a linear regression model, a decision tree, a random forest, a gradient boosting tree or a neural network. The model can also be evaluated using indicators such as root mean square error and mean absolute error to verify the accuracy and stability of the model.

[0084] Specifically, the sequential feature selection algorithm is a feature selection algorithm that optimizes model performance by gradually removing features. The algorithm starts with all features and removes the features that contribute the least to model performance at each step until the best feature subset is found. Specifically, the steps of the sequential feature selection algorithm refer to Figure 4, initialize the feature set F. At the beginning, the feature set F contains all available features to ensure that all potentially useful features are taken into account; calculate the full feature model performance M, use all features to train the model, and calculate the performance of the model to provide a benchmark performance for subsequent steps, which can be used for comparison; set the error threshold E to define the error range allowed for model performance. By setting an allowable performance degradation limit, it is ensured that the model performance will not drop significantly while reducing features; initialize the best feature subset B. Initially, the best feature subset is equal to all features, which can provide an initial "best" feature subset for subsequent steps. The subsequent steps will try to reduce the number of features without sacrificing too much performance; initialize the current feature set C. The current feature set is equal to all features, which can be used as a temporary set to gradually remove features in subsequent iterations; initialize the current model performance P. The current model performance is equal to the full feature model Model performance can provide an initial model performance for subsequent steps for comparison; check whether the current feature set is empty, if not, continue to the next step, in this process to ensure that the iteration process will not go on indefinitely, when the feature set is empty, end the iteration; for each feature f, remove it and calculate the model performance of the new set, evaluate the impact of each feature on the model performance; if the new model performance after removing the feature is within the error threshold and the new feature set is smaller than the current best set, update the best feature subset, ensure that the set with fewer features is selected as the current best feature subset when the performance does not drop significantly; remove the features that have the least impact on model performance from the current feature set, gradually reduce the number of features, while trying to maintain model performance; return the best feature subset B, when the current feature set is empty, return the best feature subset, return the subset with the least number of features while maintaining model performance. The above sequential feature selection algorithm ensures that the number of features is minimized while maintaining model performance, making the model more concise and efficient.

[0085] In some embodiments, reference Figure 5 , after step 101, it also includes steps 501 to 506, after obtaining the indoor and outdoor environment characteristic data corresponding to the current time, it also includes:

[0086] Step 501, obtaining a plurality of historical indoor and outdoor environmental characteristic data and a historical load generated by an indoor temperature control device in the next time period corresponding to each historical indoor and outdoor environmental characteristic data, where the historical load is historical cooling capacity or historical heating capacity;

[0087] Step 502, calculating the similarity between each historical indoor and outdoor environment characteristic data and the indoor and outdoor environment characteristic data, and obtaining corresponding multiple similarity values;

[0088] Step 503, based on each similarity value, screening a preset number of candidate indoor and outdoor environment feature data from each historical indoor and outdoor environment feature data;

[0089] Step 504, calculating the average load between the historical loads corresponding to the preset candidate indoor and outdoor environmental characteristic data, and determining the average load as the second target load;

[0090] Step 505, predicting the operating parameters of the temperature control device according to the second target load, the operating status data and the indoor and outdoor environment characteristic data, and generating second target operating status data of the temperature control device;

[0091] Step 506: Control the temperature control device according to the second target operating status data.

[0092] In some embodiments, the operating status data and indoor and outdoor environmental characteristic data of the temperature control device corresponding to the current time are obtained to understand the current status of the device and the external environmental conditions, and provide a data basis for subsequent predictions. The operating status data can reflect the working status of the current device and provide basic information for subsequent predictions. The indoor and outdoor environmental characteristic data can reflect the current environmental conditions and are important input information for predicting load demand. The historical indoor and outdoor environmental characteristic data and the historical load (cooling or heating) in the next time period corresponding to the historical data are obtained. The historical load can reflect the actual load demand under the past environmental characteristics. Through a large amount of historical data, the potential relationship between the environmental characteristics and the load of the next time period can be excavated. Calculate the similarity between each historical indoor and outdoor environmental characteristic data and the indoor and outdoor environmental characteristic data, and obtain corresponding multiple similarity values. By calculating the similarity between historical environmental data and current environmental data, the time period with the most similar historical environmental conditions to the current environmental conditions is found. Based on the calculated similarity value, the preset historical indoor and outdoor environmental characteristic data with the highest similarity are selected as candidate indoor and outdoor environmental characteristic data. The average value of the historical load corresponding to the preset candidate indoor and outdoor environmental characteristic data is calculated to obtain the second target load. Through mean calculation, a more stable load prediction value is obtained to reduce the impact of individual abnormal values. According to the second target load, the operating status data of the current equipment and the indoor and outdoor environmental characteristic data, the operating parameters of the temperature control equipment, i.e., the second target operating status data, are predicted. With reference to multi-source information, the generated operating parameters can meet the predicted load demand (i.e., the second target load). According to the predicted second target operating status data, the actual operation of the temperature control device is controlled, so that the temperature control device operates according to the predicted results, meets the load demand, and improves the response speed and control accuracy of the temperature control device. This solves the problem that the existing temperature control usually adopts a single prediction model, which is difficult to accurately capture the complex relationship between indoor and outdoor environmental parameters and cold and hot load demands, resulting in errors in the prediction of cold and heat demand. This allows the temperature control device to better adapt to complex and changeable environmental conditions and achieve more refined and personalized temperature control, thereby improving the overall performance of the temperature control device.

[0093] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present disclosure, and will not be described in detail here.

[0094] The following are embodiments of the device disclosed herein, which can be used to execute the method embodiments disclosed herein. For details not disclosed in the device embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0095] Figure 6 Schematic diagram of an indoor temperature control device provided by an embodiment of the present disclosure. Figure 6 As shown, the indoor temperature control device comprises:

[0096] The acquisition module 601 is configured to acquire the operating status data of the temperature control device corresponding to the current time and acquire the indoor and outdoor environment characteristic data corresponding to the current time according to the current time, wherein the temperature control device is a cold station device or a hot station device;

[0097] The prediction module 602 is configured to predict the indoor load demand for the next time period according to the indoor and outdoor environmental characteristic data, and obtain the indoor target load for the next time period; wherein the load demand is the cooling demand or the heating demand;

[0098] A strategy generation module 603 is configured to predict the operating parameters of the temperature control device according to the target load, the operating status data and the indoor and outdoor environment characteristic data, and generate target operating status data of the temperature control device;

[0099] The control module 604 is configured to control the temperature control device according to the target operating state data.

[0100] According to the technical solution provided by the embodiment of the present disclosure, by obtaining the operating status data of the temperature control device (such as a cold station or a hot station device) at the current time, as well as the indoor and outdoor environmental characteristic data, an accurate data basis is provided for subsequent prediction and control, so that the temperature control device can make predictions and decisions based on the environment and device status, thereby improving the real-time and accuracy of the prediction. By establishing a prediction model that can capture the complex relationship between environmental parameters and load demand, the indoor load demand for the next time period is predicted based on the indoor and outdoor environmental characteristic data, and the indoor target load for the next time period is obtained, and the future cold or hot load demand is accurately predicted through the prediction model. Based on the target load, the current device status and environmental characteristics, a variety of factors are combined to predict the optimal operating state of the temperature control device for the next time period, and the target operating state data of the temperature control device is generated to achieve more refined and personalized temperature control. The temperature control device is controlled according to the predicted target operating state data to achieve a predetermined operating state, thereby meeting the indoor temperature demand. The temperature control method provided by the present invention utilizes indoor and outdoor environmental characteristic data to perform load prediction, rather than relying solely on a single model or parameter, thereby improving the accuracy and robustness of the prediction, and by acquiring the operating status data of the temperature control device in real time, dynamically adjusting the control strategy using the operating status data, target load, and indoor and outdoor environmental characteristic data, thereby overcoming the problem in the prior art that the temperature control device cannot accurately predict the demand for cooling and heating and thus the indoor temperature control is inaccurate, and comprehensively considers the target load, device status, and environmental characteristics, optimizes the device operating parameters, achieves minimization of energy consumption, and ensures indoor comfort, significantly improves the performance of the temperature control device, and achieves more refined and personalized temperature control.

[0101] In some embodiments, when the temperature control device is a cold station device, the prediction module 602 is configured to input indoor and outdoor environmental characteristic data into a cooling capacity prediction model to obtain the target indoor cooling capacity in the next time period output by the cooling capacity prediction model; and determine the target cooling capacity as the target load.

[0102] In some embodiments, when the temperature control device is a heat station device, the prediction module 602 is configured to input the indoor and outdoor environmental characteristic data into the heat prediction model to obtain the indoor target heat of the next time period output by the heat prediction model; determine the target heat as the target load,

[0103] In some embodiments, when the temperature control device is a cold station device, the indoor and outdoor environmental characteristic data include the indoor and outdoor wet-bulb temperature difference and the indoor average temperature, and the operating status data include the chilled water supply temperature and the chilled water return temperature. The strategy generation module 603 is configured to input the indoor and outdoor wet-bulb temperature difference and the target cooling capacity as a set of data into the cooling tower quantity prediction model to obtain the target number of cooling towers for the next time period output by the cooling tower quantity prediction model; input the target cooling capacity into the chiller quantity prediction model to obtain the target number of chillers for the next time period output by the chiller quantity prediction model; input the indoor average temperature and the chilled water supply temperature as a set of data into the chiller set temperature prediction model to obtain the chiller set temperature The target set temperature for the next time period is output by the prediction model; multiple candidate frequencies of the refrigeration pump and the candidate flow rates corresponding to each candidate frequency are obtained, and the candidate heat corresponding to each candidate frequency is generated based on the candidate flow rates, target set temperatures and chilled water return temperature corresponding to each candidate frequency; the absolute value of the difference between the candidate heat corresponding to each candidate frequency and the target cooling capacity is calculated, and the candidate frequency that meets the preset requirements among the candidate frequencies is determined as the target frequency for the next time period, and the preset requirement is that the frequency is less than or equal to the first preset value and the absolute value of the difference with the target cooling capacity is the smallest; the target operating status data of the temperature control device is generated based on the target frequency, the target set temperature, the target number of chillers and the target number of cooling towers.

[0104] In some embodiments, when the temperature control device is a thermal station device, the indoor and outdoor environmental characteristic data include the indoor temperature median and the indoor temperature variance, and the operating status data include the hot water pipe supply and return water temperature difference and the hot water pipe supply temperature. The strategy generation module 603 is configured to obtain the indoor target temperature, the first temperature difference between the indoor target temperature and the indoor temperature median, and input the indoor temperature median, the indoor target temperature, the hot water pipe supply and return water temperature difference and the first temperature difference as a group of data into the hot water pump quantity prediction model to obtain the target number of hot water pumps for the next time period output by the hot water pump quantity prediction model; input the indoor temperature median, the indoor temperature variance, the indoor target temperature, the hot water pipe supply and return water temperature difference, the first temperature difference and the hot water pipe supply temperature as a group of data into the boiler quantity prediction model to obtain the target number of boilers for the next time period output by the boiler quantity prediction model; input the indoor temperature median and the hot water pipe supply temperature as a group of data into the boiler set temperature prediction model to obtain the target set temperature for the next time period output by the boiler set temperature prediction model; generate the target operating status data of the temperature control device based on the target set temperature, the target number of boilers and the target number of hot water pumps.

[0105] In some embodiments, before inputting the indoor and outdoor environmental characteristic data into the cooling capacity prediction model, the indoor temperature control device is configured to obtain a set of historical indoor and outdoor environmental characteristic data and historical operating status data of the cooling station equipment, and determine the corresponding historical cooling capacity based on the historical operating status data, wherein the set of historical indoor and outdoor environmental characteristic data includes multiple sub-features; the historical indoor and outdoor environmental characteristic data are combined as training samples and the historical cooling capacity is used as the label corresponding to the training sample, and a sequential feature selection algorithm is used to obtain the optimal feature subset of the cooling capacity prediction model; the cooling capacity prediction model to be trained is trained based on the optimal feature subset and the historical cooling capacity to obtain a trained cooling capacity prediction model.

[0106] In some embodiments, after obtaining the indoor and outdoor environmental characteristic data corresponding to the current time, the indoor temperature control device is configured to obtain multiple historical indoor and outdoor environmental characteristic data and the historical load generated by the indoor temperature control device in the next time period corresponding to each historical indoor and outdoor environmental characteristic data, where the historical load is the historical cooling capacity or the historical heating capacity; calculate the similarity between each historical indoor and outdoor environmental characteristic data and the indoor and outdoor environmental characteristic data, and obtain multiple corresponding similarity values; based on each similarity value, screen a preset number of candidate indoor and outdoor environmental characteristic data from each historical indoor and outdoor environmental characteristic data; calculate the average load between the historical loads corresponding to the preset number of candidate indoor and outdoor environmental characteristic data, and determine the average load as the second target load; predict the operating parameters of the temperature control device according to the second target load, the operating status data and the indoor and outdoor environmental characteristic data, and generate the second target operating status data of the temperature control device; and control the temperature control device according to the second target operating status data.

[0107] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

[0108] Figure 7 Schematic diagram of an electronic device 7 provided by an embodiment of the present disclosure. Figure 7 As shown, the electronic device 7 of this embodiment includes: a processor 701, a memory 702, and a computer program 703 stored in the memory 702 and executable on the processor 701. When the processor 701 executes the computer program 703, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 701 executes the computer program 703, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0109] The electronic device 7 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 7 may include, but is not limited to, a processor 701 and a memory 702. Those skilled in the art will appreciate that Figure 7 The electronic device 7 is merely an example and does not limit the electronic device 7 , and may include more or less components than those shown in the figure, or different components.

[0110] The processor 701 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0111] The memory 702 may be an internal storage unit of the electronic device 7, for example, a hard disk or memory of the electronic device 7. The memory 702 may also be an external storage device of the electronic device 7, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 7. The memory 702 may also include both an internal storage unit of the electronic device 7 and an external storage device. The memory 702 is used to store computer programs and other programs and data required by the electronic device.

[0112] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0113] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium (e.g., a computer-readable storage medium). Based on this understanding, the present disclosure implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0114] 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 make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should all be included in the protection scope of the present disclosure.

Claims

1. A method for controlling indoor temperature, characterized in that: include: According to the current time, the operating status data of the temperature control device corresponding to the current time is obtained, and the indoor and outdoor environment characteristic data corresponding to the current time are obtained, wherein the temperature control device is a cold station device or a hot station device; Predicting the indoor load demand for the next time period according to the indoor and outdoor environmental characteristic data to obtain the indoor target load for the next time period, wherein the load demand is a cooling demand or a heating demand; Predicting the operating parameters of the temperature control device according to the target load, the operating status data and the indoor and outdoor environment characteristic data, and generating target operating status data of the temperature control device; The temperature control device is controlled according to the target operating state data.

2. The method according to claim 1, characterized in that: When the temperature control device is the cold station device, predicting the indoor load demand for the next time period according to the indoor and outdoor environmental characteristic data to obtain the indoor target load for the next time period includes: Inputting the indoor and outdoor environmental characteristic data into a cooling capacity prediction model to obtain a target indoor cooling capacity for the next time period output by the cooling capacity prediction model; The target cooling capacity is determined as the target load.

3. The method according to claim 1, characterized in that When the temperature control device is the heat station device, predicting the indoor load demand for the next time period according to the indoor and outdoor environmental characteristic data to obtain the indoor target load for the next time period includes: Inputting the indoor and outdoor environmental characteristic data into a heat prediction model to obtain a target indoor heat for the next time period output by the heat prediction model; The target heat amount is determined as the target load.

4. The method according to claim 2, characterized in that: The indoor and outdoor environmental characteristic data include the indoor and outdoor wet-bulb temperature difference and the indoor average temperature, and the operating status data include the chilled water supply temperature and the chilled water return temperature; The predicting the operating parameters of the temperature control device according to the target load, the operating status data and the indoor and outdoor environment characteristic data to generate the target operating status data of the temperature control device includes: Input the indoor and outdoor wet-bulb temperature difference and the target cooling capacity as a set of data into a cooling tower quantity prediction model to obtain a target number of cooling towers for the next time period output by the cooling tower quantity prediction model; Inputting the target cooling capacity into a refrigeration machine quantity prediction model to obtain a target quantity of refrigeration machines for the next time period output by the refrigeration machine quantity prediction model; Input the indoor average temperature and the chilled water supply temperature as a set of data into a chiller set temperature prediction model to obtain a target set temperature for the next time period output by the chiller set temperature prediction model; Acquire multiple candidate frequencies of the refrigeration pump and candidate flow rates corresponding to each candidate frequency, and generate candidate heat corresponding to each candidate frequency based on the candidate flow rates corresponding to each candidate frequency, the target set temperature and the chilled water return temperature; Calculate the absolute value of the difference between the candidate heat corresponding to each of the candidate frequencies and the target cooling capacity, and determine the candidate frequency that meets the preset requirements among the candidate frequencies as the target frequency for the next time period, wherein the preset requirements are that the candidate heat is less than or equal to the first preset value and the absolute value of the difference with the target cooling capacity is the smallest; The target operating state data of the temperature control device is generated based on the target frequency, the target set temperature, the target number of chillers, and the target number of cooling towers.

5. The method according to claim 3, characterized in that: The indoor and outdoor environmental characteristic data include the indoor temperature median and the indoor temperature variance, and the operating status data include the hot water pipe supply and return water temperature difference and the hot water pipe supply water temperature; The predicting the operating parameters of the temperature control device according to the target load, the operating status data and the indoor and outdoor environment characteristic data to generate the target operating status data of the temperature control device includes: Obtaining an indoor target temperature and a first temperature difference between the indoor target temperature and the median indoor temperature, and inputting the median indoor temperature, the indoor target temperature, the hot water pipe supply and return water temperature difference and the first temperature difference as a set of data into a hot water pump quantity prediction model to obtain a target number of hot water pumps for the next time period output by the hot water pump quantity prediction model; The indoor temperature median, the indoor temperature variance, the indoor target temperature, the hot water pipe supply and return water temperature difference, the first temperature difference and the hot water pipe supply water temperature are input as a set of data into a boiler quantity prediction model to obtain the boiler target quantity for the next time period output by the boiler quantity prediction model; Input the indoor temperature median and the hot water pipe water supply temperature as a set of data into a boiler set temperature prediction model to obtain a target set temperature for the next time period output by the boiler set temperature prediction model; Target operating state data of the temperature control device is generated based on the target set temperature, the target number of boilers, and the target number of hot water pumps.

6. The method according to claim 2, characterized in that Before inputting the indoor and outdoor environment characteristic data into the cooling capacity prediction model, the method further includes: Acquire a historical indoor and outdoor environment characteristic data set and historical operation status data of a cooling station device, and determine a corresponding historical cooling capacity according to the historical operation status data, wherein the historical indoor and outdoor environment characteristic data set includes a plurality of sub-characteristics; The historical indoor and outdoor environmental feature data sets are used as training samples, and the historical cooling capacity is used as the label corresponding to the training samples. The sequential feature selection algorithm is used to obtain the optimal feature subset of the cooling capacity prediction model. The cooling capacity prediction model to be trained is trained based on the optimal feature subset and the historical cooling capacity to obtain a trained cooling capacity prediction model.

7. The method according to claim 1, characterized in that After obtaining the indoor and outdoor environment characteristic data corresponding to the current time, the method further includes: Acquire a plurality of historical indoor and outdoor environmental characteristic data and a historical load generated by the indoor temperature control device in the next time period corresponding to each historical indoor and outdoor environmental characteristic data, wherein the historical load is historical cooling capacity or historical heating capacity; Calculating the similarity between each of the historical indoor and outdoor environment characteristic data and the indoor and outdoor environment characteristic data, and obtaining a corresponding plurality of similarity values; Based on each of the similarity values, a preset number of candidate indoor and outdoor environment feature data are selected from each of the historical indoor and outdoor environment feature data; Calculating the average load between the historical loads corresponding to the preset candidate indoor and outdoor environment characteristic data, and determining the average load as the second target load; Predicting the operating parameters of the temperature control device according to the second target load, the operating status data and the indoor and outdoor environment characteristic data, and generating second target operating status data of the temperature control device; The temperature control device is controlled according to the second target operating state data.

8. An indoor temperature control device, characterized in that: include: an acquisition module, configured to acquire, according to the current time, operation status data of a temperature control device corresponding to the current time, and acquire indoor and outdoor environment characteristic data corresponding to the current time, wherein the temperature control device is a cold station device or a hot station device; A prediction module is configured to predict the indoor load demand for the next time period according to the indoor and outdoor environmental characteristic data to obtain the indoor target load for the next time period; The load demand is cooling demand or heating demand; a strategy generation module, configured to predict the operating parameters of the temperature control device according to the target load, the operating status data and the indoor and outdoor environment characteristic data, and generate target operating status data of the temperature control device; The control module is configured to control the temperature control device according to the target operating state data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images