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

Abstract

The present disclosure 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: predicting heat demand of an indoor environment in a next time period based on outdoor and indoor environment characteristic data and a target temperature to obtain target demand heat; selecting initial operation state data from a plurality of operation state data based on a correspondence relationship between the target demand heat and a preset operation state data and heat generated by a heat station device; generating target operation state data of the heat station device based on the initial operation state data, the target demand heat, current operation characteristic data and the outdoor and indoor environment characteristic data; and controlling the heat station device according to the target operation state data. The present disclosure solves the problem of inaccurate indoor temperature control in the prior art, maintains the indoor temperature within a set comfortable range at all times, and improves the accuracy and efficiency of temperature control by fine control of the heat station device.

Description

Technical Field

[0001] This disclosure relates to the field of temperature control technology, and in particular to an indoor temperature control method, apparatus, electronic device, and readable storage medium. Background Technology

[0002] In order to ensure a comfortable and safe shopping and working environment, heating stations are installed in large shopping malls to control the indoor temperature. Existing heating station equipment collects data such as indoor and outdoor temperature and humidity through sensors and automatically adjusts the operating status of the heating station according to preset control logic. However, it relies on fixed control strategies, cannot accurately predict heat demand, lacks the ability to deeply analyze and predict real-time data, and cannot achieve fine and personalized temperature control of indoor temperature. Summary of the Invention

[0003] In view of this, the present disclosure provides an indoor temperature control method, apparatus, electronic device, and readable storage medium to solve the problem of inaccurate indoor temperature control in the prior art.

[0004] A first aspect of this disclosure provides an indoor temperature control method, comprising:

[0005] Acquire indoor and outdoor environmental characteristic data and target indoor temperature;

[0006] Based on indoor and outdoor environmental characteristic data and target temperature, the indoor heat demand for the next time period is predicted to obtain the target indoor heat demand for the next time period.

[0007] Based on the target heat demand and the correspondence between each operating status data and the heat generated by the heat station equipment in the multiple operating status data of the pre-set heat station equipment, the initial operating status data is obtained by filtering from the multiple operating status data;

[0008] Acquire the current operating characteristic data of the heating station equipment, and generate the target operating status data of the heating station equipment based on the initial operating status data, target demand heat, current operating characteristic data and indoor and outdoor environmental characteristic data;

[0009] Control the heating station equipment based on the target operating status data.

[0010] A second aspect of this disclosure provides an indoor temperature control device, comprising:

[0011] The acquisition module is configured to acquire indoor and outdoor environmental characteristic data and the target indoor temperature;

[0012] The prediction module is configured to predict the indoor heat demand for the next time period based on indoor and outdoor environmental characteristic data and target temperature, and obtain the target indoor heat demand for the next time period.

[0013] The filtering module is configured to filter initial operating status data from multiple operating status data based on the target heat demand and the correspondence between each operating status data and the heat generated by the heat station equipment in multiple pre-set operating status data.

[0014] The generation module is configured to acquire the current operating characteristic data of the heating station equipment, and generate the target operating status data of the heating station equipment based on the initial operating status data, target demand heat, current operating characteristic data and indoor and outdoor environmental characteristic data;

[0015] The control module is configured to control the heating station equipment based on the target operating status data.

[0016] A third aspect of this disclosure provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0017] A fourth aspect of this disclosure provides a readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0018] The beneficial effects of this disclosed embodiment compared to the prior art are as follows: By acquiring indoor and outdoor environmental characteristic data and the target indoor temperature, a foundation is provided for subsequent data processing and analysis, enabling the indoor temperature control method to be based on real-time environmental data and the actual needs of users. Based on indoor and outdoor environmental characteristic data and the target temperature, the target indoor heat demand for the next time period is predicted, improving the predictability and accuracy of temperature control. Based on the predicted target heat demand, and combined with the correspondence between the operating status of the heating station equipment and heat generation, the initial operating status data of the heating station equipment that can meet the target heat demand is initially determined. The initial operating status data is supplemented by combining the current operating characteristic data of the heating station equipment, the predicted target heat demand, and indoor and outdoor environmental characteristic data to generate more accurate and efficient target operating status data for the heating station equipment. The heating station equipment is then controlled based on this target operating status data, achieving dynamic control of the heating station equipment and facilitating timely response to changing environmental conditions and demands. The indoor temperature control method proposed in this disclosure introduces a heat demand prediction mechanism and a dynamic adjustment mechanism, no longer relying on a fixed control strategy. It performs in-depth analysis and prediction of real-time data, and generates target operating status data of heating station equipment based on real-time data. This enables more refined and personalized temperature control based on current environmental conditions and user needs, and dynamically adjusts the operating status of heating station equipment. This solves the limitations of traditional fixed strategy control methods and improves the precision of indoor temperature control. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic flowchart of an internal temperature control method provided in an embodiment of this disclosure;

[0021] Figure 2 This is a schematic flowchart of another internal temperature control method provided in this embodiment of the present disclosure;

[0022] Figure 3 This is a schematic diagram of the structure of an internal temperature control device provided in an embodiment of this disclosure;

[0023] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0024] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of the embodiments of this disclosure. However, those skilled in the art will understand that this disclosure may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this disclosure with unnecessary detail.

[0025] An indoor temperature control method and apparatus according to an embodiment of the present disclosure will now be described in detail with reference to the accompanying drawings.

[0026] Figure 1 This is a schematic flowchart of an indoor temperature control method provided in an embodiment of this disclosure. Figure 1 As shown, the indoor temperature control method includes:

[0027] Step 101: Obtain indoor and outdoor environmental characteristic data and the target indoor temperature.

[0028] In some embodiments, indoor and outdoor environmental characteristic data refers to data obtained after preprocessing the collected raw data (i.e., initial indoor and outdoor environmental characteristic data). This data may include current time characteristics, indoor wet-bulb temperature within the current time period, average indoor temperature within the current time period, indoor humidity within the current time period, indoor-outdoor temperature difference within the current time period, outdoor temperature for the next time period, feature vectors of outdoor weather within the current time period, and feature vectors of outdoor weather for the next time period. This data reflects the state of the indoor and outdoor environment within the current time period and the outdoor weather for the next time period. It directly affects indoor comfort and the direction of boiler regulation in the heating station, and is a crucial factor in predicting the target heat demand for the next time period. Acquiring this data provides reliable data support for the intelligent control of the heating station equipment. The target indoor temperature can be the desired indoor temperature set by the user; it is the target value for temperature control. The target temperature indicates the direction for the heating station equipment, i.e., the indoor temperature setpoint that the equipment attempts to reach or maintain. The target temperature can serve as a reference point for heating station equipment, guiding the equipment to adjust its operating parameters to achieve the target temperature. By adjusting the indoor temperature to the target temperature, the comfort of the indoor environment can be improved to meet the needs of indoor occupants.

[0029] Step 102: Based on indoor and outdoor environmental characteristic data and target temperature, predict the indoor heat demand for the next time period to obtain the target indoor heat demand for the next time period.

[0030] In some embodiments, indoor and outdoor environmental characteristic data include current time characteristics, indoor wet-bulb temperature within the current time period, indoor average temperature within the current time period, indoor humidity within the current time period, indoor-outdoor temperature difference within the current time period, outdoor temperature for the next time period, feature vectors of outdoor weather within the current time period, and feature vectors of outdoor weather for the next time period. The target temperature is the indoor temperature that the user sets to achieve. Based on the current indoor and outdoor environmental characteristic data and the target temperature, the heat that needs to be provided indoors in the future is predicted, i.e., the target heat demand for the indoors in the next time period, which can be the next hour. Specifically, the current time can be 10:00 AM, the indoor and outdoor environmental characteristic data includes the indoor and outdoor environmental characteristics from 9:00 AM to 10:00 AM and the outdoor weather from 10:00 AM to 11:00 AM obtained from the weather forecast, and the next time period is the period from 10:00 AM to 11:00 AM. A machine learning model can be used to process the indoor and outdoor environmental characteristic data and the target temperature, and, referring to various factors such as the indoor and outdoor environmental characteristic data and the target temperature, predict the indoor heat demand for the next time period (e.g., the next hour). The machine learning model outputs the target heat demand for the indoors in the next time period, which reflects the heat required to meet the target indoor temperature. Predicted target heat demand helps heating station equipment allocate resources more effectively, such as adjusting boiler operation and heat pump frequency conversion to meet the predicted demand. This also reduces unnecessary energy consumption, improves the overall efficiency of the heating station equipment, and allows for better fulfillment of individual user needs by referencing the target temperature. In-depth analysis of real-time environmental data enables more accurate adjustments to the operating status of heating station equipment to meet current environmental conditions and individual user requirements.

[0031] Step 103: Based on the target heat demand and the correspondence between each operating status data and the heat generated by the heat station equipment in the multiple operating status data of the pre-set heat station equipment, the initial operating status data is obtained by filtering from the multiple operating status data.

[0032] Specifically, the target heat demand is the heat output target that the heating station equipment needs to achieve, determined based on indoor and outdoor environmental characteristics and the target temperature. The operating status data of the heating station equipment includes operating parameters such as the number of boilers, hot water pumps, set temperature, and hot water pump frequency. The current operating status data of the heating station equipment directly reflects its operating condition and heat generation capacity, thus directly affecting the current indoor temperature. The correspondence between the operating status data and the heat generated by the heating station equipment is the relationship between each operating status data point and the heat that the heating station equipment can generate. Each operating status data point is related to the heat generated by the heating station equipment; for example, increasing the operating power of the heating station equipment can increase the heat generation; adjusting the flow rate and set temperature can also affect the heat transfer and distribution. The above correspondence is constructed based on multiple historical operating status data points of the heating station equipment. From these multiple operating status data points, the operating status data point whose heat generation is closest to the target heat demand is selected as the initial operating status data. For example, the correspondence between operating status data and the heat generated by the heating station equipment can be as follows: when there are 2 boilers, 2 hot water pumps, and a hot water pump frequency of 40Hz, the corresponding heat generated is 95kW; when there are 2 boilers, 2 hot water pumps, and a hot water pump frequency of 50Hz, the corresponding heat generated is 105kW; and when there are 3 boilers, 3 hot water pumps, and a hot water pump frequency of 40Hz, the corresponding heat generated is 120kW. When the target heat demand is determined to be 104kW, the operating status data of the heating station equipment closest to this demand is selected. Among the above operating status data, the heat output when there are 2 boilers, 2 hot water pumps, and a hot water pump frequency of 50Hz is closest to 104kW is selected as the initial operating status data. Based on the initial operating status data obtained from the predicted target heat demand selection, the control strategy of the heating station equipment is adjusted according to real-time data to achieve more precise control of indoor temperature.

[0033] Step 104: Obtain the current operating characteristic data of the heating station equipment. Based on the initial operating status data, target heat demand, current operating characteristic data, and indoor and outdoor environmental characteristic data, generate the target operating status data of the heating station equipment.

[0034] Specifically, the current operating characteristic data of the heating station equipment is the data after preprocessing the collected raw data (i.e., the initial operating characteristic data). This data may include the supply and return water temperature difference, the hot water supply temperature of the main hot water pipe, the hot water return temperature of the main hot water pipe, flow rate, hot water pump frequency, number of boilers, hot water pumps, and set temperature. The current operating characteristic data is for the current time period, for example, from 9:00 to 10:00. This data not only reflects the current operating status of the heating station equipment but also implies trends in equipment performance and potential problems. Continuous monitoring and recording of the operating characteristic data allows for a more accurate understanding of the operating status of the heating station equipment within the shopping mall, providing reliable data support for intelligent control. Based on the target heat demand, the current operating characteristic data, and indoor and outdoor environmental characteristic data, the target set temperature for the next time period is generated. This target set temperature is then combined with the initial operating status data to generate the target operating status data for the heating station equipment.

[0035] In some embodiments, by combining current operating characteristic data, predicted target heat demand, indoor and outdoor environmental characteristic data, and target temperature, more refined target operating status data for the heating station equipment is generated. This allows the target operating status data of the heating station equipment to not only meet the predicted heat demand but also be optimized according to current environmental conditions to improve efficiency and reduce energy consumption. By comprehensively considering the current operating status of the heating station equipment and indoor and outdoor environmental conditions, the operating status of the heating station equipment is dynamically adjusted to cope with changing demands, enhancing the in-depth analysis and predictive capabilities of real-time data, and achieving more refined and personalized temperature control.

[0036] Step 105: Control the heating station equipment based on the target operating status data.

[0037] In some embodiments, the target operating status data includes specific operating parameters for each device to be set in order to achieve the target temperature. The target operating status data may include: Project Name: the name that identifies the current project or shopping mall; Target Temperature: the set target indoor temperature; Number of Boilers: the number of boilers that need to be operated; Hot Water Pump Frequency: the operating frequency of the hot water pumps; Number of Hot Water Pumps: the number of hot water pumps that need to be operated; Set Temperature: the set hot water supply set temperature of the boilers.

[0038] The heating station equipment sends instructions to each device based on target operating status data to precisely control the equipment, ensuring optimal operation to meet expected heat demand. Controlling the heating station equipment based on target operating status data enables intelligent temperature regulation of the indoor environment. Controlling the cooling station equipment based on the same data automatically adjusts the operating status of the heating station equipment, achieving automated control, reducing reliance on manual operation, and improving the response speed and operational efficiency of the heating station's temperature control system.

[0039] In some embodiments, the heating station equipment continuously collects actual indoor and outdoor environmental characteristic data and operational status data during operation, and feeds this data back to the heating station equipment for subsequent parameter updates and optimization. Specifically, the feedback adjustment mechanism includes: continuously collecting actual indoor and outdoor environmental characteristic data and operational status data of the heating station equipment; feeding the collected indoor and outdoor environmental characteristic data and operational status data of the heating station equipment back to the temperature control system of the heating station equipment for parameter updates and optimization of the temperature control system. Based on the feedback data, the temperature control system of the heating station equipment is updated and adjusted to improve its accuracy and predictive capability. Based on the updated temperature control system, the generated control strategy (i.e., the selected target operational status data) is adjusted to adapt to current environmental changes and energy consumption demands. By continuously collecting actual indoor and outdoor environmental characteristic data and operational status data of the heating station equipment and feeding it back to the temperature control system, the temperature control system of the heating station equipment 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 system of the heating station equipment to continuously adapt to changes in the indoor and outdoor environment and achieve intelligent management and optimization of the heating station equipment.

[0040] The indoor temperature control method provided in this disclosure acquires indoor and outdoor environmental characteristic data and the target indoor temperature, laying the foundation for subsequent data processing and analysis. This allows the indoor temperature control method to be based on real-time environmental data and the actual needs of users. Based on the indoor and outdoor environmental characteristic data and the target temperature, the target heat demand for the next time period is predicted, improving the predictability and accuracy of temperature control. Based on the predicted target heat demand and the correspondence between the operating status of the heating station equipment and heat generation, the initial operating status data of the heating station equipment that can meet the target heat demand is initially determined. The initial operating status data is supplemented by combining the current operating characteristic data of the heating station equipment, the predicted target heat demand, and the indoor and outdoor environmental characteristic data to generate more accurate and efficient target operating status data for the heating station equipment. The heating station equipment is then controlled based on this target operating status data, achieving dynamic control of the heating station equipment and facilitating timely response to changing environmental conditions and demands. The indoor temperature control method proposed in this disclosure introduces a heat demand prediction mechanism and a dynamic adjustment mechanism, no longer relying on a fixed control strategy. It performs in-depth analysis and prediction of real-time data, and generates target operating status data of heating station equipment based on real-time data. This enables more refined and personalized temperature control based on current environmental conditions and user needs, and dynamically adjusts the operating status of heating station equipment. This solves the limitations of traditional fixed strategy control methods and improves the precision of indoor temperature control.

[0041] In some embodiments, based on indoor and outdoor environmental characteristic data and a target temperature, the indoor heat demand for the next time period is predicted to obtain the target indoor heat demand for the next time period. This includes: inputting indoor and outdoor environmental characteristic data into a heat prediction model to obtain the predicted indoor heat for the next time period output by the heat prediction model; inputting the predicted heat and indoor and outdoor environmental characteristic data as a set of data into a temperature regulation heat model to obtain the initial predicted temperature corresponding to the predicted heat output by the temperature regulation heat model; correcting the initial predicted temperature based on the target temperature to obtain the target predicted temperature, until the absolute value of the difference between the target predicted temperature and the target temperature is less than or equal to a first preset value, and determining the heat corresponding to the target predicted temperature as the target heat demand.

[0042] Specifically, the aforementioned heat prediction model can fit the indoor and outdoor environmental parameters of the current time period with the heat demand of the next time period. The heat prediction model is trained based on historical indoor and outdoor environmental characteristic data and corresponding historical heat generation data. The historical heat generation data is calculated based on the historical operating characteristic data of the heating station equipment. For example, the historical operating characteristic data of the heating station equipment includes flow rate, hot water supply temperature, and hot water return temperature. The corresponding heat generation data can be calculated based on these parameters. Indoor and outdoor environmental characteristic data are input into the heat prediction model, and the indoor heat demand for a future period is predicted based on this data. This yields the predicted indoor heat demand for the next time period, providing a data foundation for subsequent steps.

[0043] Specifically, the aforementioned temperature regulation heat model can be used to fit the average indoor temperature for the next time period based on indoor and outdoor environmental characteristic data and the predicted indoor heat for the next time period. The predicted heat and indoor and outdoor environmental characteristic data are input into the temperature regulation heat model as a set of data. Based on the predicted heat and environmental characteristics, the indoor temperature is simulated under the current environment and when the predicted heat is generated, resulting in the initial predicted temperature corresponding to the predicted heat output by the temperature regulation heat model. The initial predicted temperature is the average indoor temperature. By evaluating whether the predicted indoor temperature under the current environmental conditions and the generated predicted heat can meet the target temperature requirements, a basis for subsequent corrections is provided.

[0044] In some embodiments, when constructing a heat prediction model, indoor and outdoor environmental feature data are used as the original dataset. This data includes multiple sub-features such as time features, indoor wet-bulb temperature in the current time period, indoor average temperature in the current time period, indoor humidity in the current time period, indoor-outdoor temperature difference in the current time period, outdoor temperature in the next time period, feature vectors of outdoor weather in the current time period, and feature vectors of outdoor weather in the next time period. The optimal feature subset is obtained through Sequential Floating Forward Selection (SFFS), and the features in the optimal feature subset are the most informative for the heat prediction model. During training, a multi-fold cross-validation dataset splitting method, CustomTimeSeriesSplit, is constructed. This can be built using the base class BaseCrossValidator of all cross-validators in sklearn, allowing for custom intervals between training and test sets, thus constructing a multi-fold time series dataset. For example, a 3-day prediction set (February 1, 2023 to February 3, 2023) is reserved for the test set. A 5-fold cross-validation dataset is constructed with a 7-day interval between the training set and a 1-day interval between the validation set, as shown in the table below.

[0045] discount Training set period (7-day interval) Validation set period 1 2023-01-24～2023-01-30 2023-01-31 2 2023-01-23～2023-01-29 2023-01-30 3 2023-01-22～2023-01-28 2023-01-29 4 2023-01-21～2023-01-27 2023-01-28 5 2023-01-20～2023-01-26 2023-01-29

[0046] The heat prediction model to be trained can be either a Lightweight Gradient Boosting Machine (LightGBM) algorithm or a Ridge regression model. Bayesian search is used to determine the model's hyperparameters, and the Mean Absolute Percentage Error (MAPE) is used to evaluate the model. The optimal model is selected and saved, resulting in the trained heat prediction model. When constructing the temperature regulation heat model, the predicted heat and indoor / outdoor environmental feature data are used as the original dataset. Both the indoor / outdoor environmental feature data and the predicted heat include multiple sub-features. SFFS (Simplified Functional Optimization Search) can be used to select the optimal feature subset, which contains the most information for the temperature regulation heat model. The temperature regulation heat model to be trained can be either a LightGBM or a Ridge model, and Bayesian search is used to determine the model's hyperparameters. MAPE is then used to evaluate the model, and the optimal model is selected and saved, resulting in the trained temperature regulation heat model.

[0047] Furthermore, the initial predicted temperature is corrected based on the target temperature to obtain the target predicted temperature, until the absolute value of the difference between the target predicted temperature and the target temperature is less than or equal to a first preset value. Through iterative adjustments, the predicted indoor temperature is made sufficiently close to the target temperature, helping the indoor temperature to accurately reach the user's desired target temperature. The heat corresponding to the target predicted temperature is determined as the target demand heat, defining the final heat value that the heating station equipment needs to provide to achieve the target indoor temperature, providing a clear heat demand value as the basis for generating subsequent control strategies. By introducing a heat prediction model and a temperature regulation heat model, accurate prediction of future heat demand is achieved, avoiding the blindness and lag in traditional temperature control methods. By comprehensively referencing indoor and outdoor environmental characteristic data and the target temperature, and dynamically adjusting based on real-time data, temperature control becomes more refined and personalized, meeting the needs of different users and scenarios. By accurately predicting and adjusting heat demand, unnecessary energy consumption and waste can be avoided, improving energy utilization efficiency. By acquiring data in real time, rapid response and adjustments can be made in the face of complex and changing environmental conditions, ensuring the stability and comfort of indoor temperature, and enhancing the adaptability and stability of the heating station equipment in temperature control.

[0048] In some embodiments, the initial predicted temperature is corrected based on the target temperature to obtain the target predicted temperature, including: when the absolute value of the difference between the initial predicted temperature and the target temperature is greater than a first preset value, adjusting the predicted heat according to a preset heat adjustment step size to obtain multiple candidate heats; inputting each candidate heat and indoor and outdoor environmental feature data as a set of data into the temperature regulation heat model to obtain the initial predicted temperature corresponding to each candidate heat output by the temperature regulation heat model; calculating the absolute value of the difference between the initial predicted temperature corresponding to each candidate heat and the target temperature, and determining the initial predicted temperature that meets the preset requirement among the initial predicted temperatures corresponding to each candidate heat as the target predicted temperature, wherein the preset requirement is less than or equal to the first preset value and the absolute value of the difference with the target temperature is the smallest.

[0049] Specifically, the target temperature is the ideal indoor temperature to be achieved, and the initial predicted temperature is the predicted indoor temperature derived from predicted heat and indoor and outdoor environmental characteristic data. The absolute value of the difference between the initial predicted temperature and the target temperature is calculated to clarify the gap between the current predicted temperature and the target temperature. It is then determined whether the absolute value of the difference is greater than a first preset value. If the absolute value of the difference is less than or equal to the first preset value, it indicates that the current prediction is close enough to the target and no significant adjustment is needed; if the absolute value of the difference is greater than the first preset value, adjustment is required to narrow the gap. The predicted heat is adjusted using a preset heat adjustment step size, generating multiple candidate heat values. These candidate heat values ​​represent possible adjustment directions and magnitudes, providing a basis for subsequent screening. By generating multiple candidate heat values, different generated heat values ​​can be explored to find the solution closest to the target temperature. Each candidate heat value and indoor and outdoor environmental characteristic data are input into the temperature regulation heat model to obtain the initial predicted temperature corresponding to each candidate heat value output by the temperature regulation heat model. The indoor temperature change under different heat values ​​is simulated to evaluate whether the target temperature requirement can be met under different candidate heat values. By calculating the difference between the initial predicted temperature and the target temperature corresponding to each candidate heat, the gap between the predicted temperature and the target temperature corresponding to each candidate heat is evaluated. The initial predicted temperature that meets the preset requirements among the initial predicted temperatures corresponding to each candidate heat is determined as the target predicted temperature. The preset requirements are that the initial predicted temperature is less than or equal to the first preset value and the absolute value of the difference with the target temperature is the smallest, so that the adjusted target predicted temperature is close to the target temperature without being over-adjusted.

[0050] For example, with an initial predicted temperature of 25℃, a target temperature of 26℃, a first preset value of 0.5, and a predicted heat of 103kW, the absolute value of the difference between the initial predicted temperature and the target temperature is 1. Since this absolute value is greater than the first preset value, the predicted heat needs adjustment. Multiple candidate heat values ​​are generated in 1kW increments: 104kW, 105kW, and 106kW. These candidate heat values, along with indoor and outdoor environmental characteristic data, are input into a temperature regulation heat model. The model is then used to simulate indoor temperature changes under different heat values, yielding the result for 104kW. The initial predicted temperature is 25.4℃, the initial predicted temperature for 105kW is 25.9℃, and the initial predicted temperature for 106kW is 26.4℃. The difference between the initial predicted temperature and the target temperature for the candidate heat is calculated. The difference for 104kW is 0.6, for 105kW it is 0.1, and for 106kW it is 0.4. The difference for 105kW (0.1) is less than the first preset value of 0.5, and the absolute value of the difference from the target temperature of 26℃ is the smallest. Therefore, the initial predicted temperature of 25.9℃ for 105kW can be determined as the target predicted temperature.

[0051] In some embodiments, reference Figure 2 Step 103, which involves filtering the initial operating status data from multiple operating status data based on the target heat demand and the correspondence between each operating status data and the heat generated by the pre-set heating station equipment, further includes:

[0052] Step 201: Obtain multiple historical operating status data of the heating station equipment and the flow rate corresponding to each historical operating status data. The historical operating status data includes the historical number of boilers, the historical number of hot water pumps, and the historical frequency of hot water pumps.

[0053] Step 202: Based on the traffic corresponding to each historical operating status data, cluster each historical operating status data to obtain the processed operating status data and the traffic corresponding to the processed operating status data corresponding to multiple cluster centers after clustering.

[0054] Step 203: Determine the adjustment step size corresponding to the hot water pump frequency based on the hot water pump frequency and hot water pump frequency range in the processed operating status data;

[0055] Step 204: Adjust the hot water pump frequency in each processed operating status data according to the adjustment step size corresponding to the hot water pump frequency to obtain multiple operating status data of the heating station equipment.

[0056] Step 205: Based on each running status data and each processed running status data, determine the traffic corresponding to each running status data.

[0057] Step 206: Input the flow rate corresponding to each operating status data into the flow rate heat prediction model to obtain the heat corresponding to each operating status data output by the flow rate heat prediction model.

[0058] Step 207: Establish a correspondence based on the data of each operating status and the heat corresponding to each operating status.

[0059] Specifically, this involves acquiring multiple historical operating status data points for the heating station equipment and the corresponding flow rates for each historical operating status. This allows for understanding the behavioral characteristics of the heating station equipment under different operating conditions and obtaining its performance under past operating conditions, providing a basis for further analysis and optimization. Historical operating status data includes the historical number of boilers, the historical number of hot water pumps, and the historical hot water pump frequency. Historical flow rates are the flow rate data corresponding to the historical operating status data. The historical number of boilers refers to the number of boilers operating in the heating station equipment during the corresponding historical time period; the number of boilers directly affects the heat generation capacity of the heating station equipment. The historical number of hot water pumps refers to the number of hot water pumps operating in the heating station equipment during the corresponding historical time period. Hot water pumps deliver hot water to where it is needed; the number of hot water pumps affects the hot water delivery efficiency. The historical hot water pump frequency refers to the operating frequency during the corresponding historical time period. The frequency of the hot water pumps determines the pump speed, which in turn affects the water flow rate and heat transfer. For each historical operating status data point, there is a corresponding flow rate. The flow rate is the carrier of heat transfer, and its magnitude is closely related to the amount of heat transferred. K-means clustering can be used to cluster historical operational status data, identifying groups of operational statuses with similar behavioral patterns. This yields processed operational status data and corresponding traffic volumes for multiple cluster centers. Each cluster center represents a group of operational status data for heat station equipment with similar traffic characteristics. Furthermore, the processed operational status data for multiple cluster centers can be sorted from smallest to largest based on their corresponding traffic volumes. These sorted cluster centers can then represent different traffic patterns or demand levels, providing a reference for subsequent optimization and scheduling.

[0060] In some embodiments, within the hot water pump frequency range, an adjustment step size for the hot water pump frequency is determined. This adjustment step size can be 1 Hz, and the frequency range can be 35 Hz to 50 Hz. This adjustment step size is used to adjust the hot water pump frequency in the processed operating status data. By adjusting the step size, different hot water pump frequency configurations can be explored. Based on the adjustment step size corresponding to the hot water pump frequency, the hot water pump frequency in each processed operating status data is adjusted. Based on each processed operating status data, the hot water pump frequency is gradually adjusted according to the determined adjustment step size. Each adjustment generates a new operating status data set. Through multiple adjustments, a series of operating status data for the heating station equipment under different hot water pump frequencies are obtained. Flow rate is a key parameter for heat transfer. When the number of boilers and hot water pumps is the same in the operating status data, the ratio of the flow rates corresponding to the operating status is equal to the ratio of the hot water pump frequencies in the operating status. Based on the processed operating status data and the hot water pump frequencies in the operating status data, and given the known flow rates corresponding to the processed operating status data, the flow rate corresponding to each operating status data set can be calculated. By determining the flow rate, necessary data support can be provided for subsequent heat prediction.

[0061] The flow rate corresponding to each operating state data is input into the flow rate heat prediction model to predict the heat output under different flow rates. Based on the input flow rate, the flow rate heat prediction model uses its internal algorithm and parameters to calculate the heat output corresponding to each operating state data. This flow rate heat prediction model can fit the heat output based on the flow rate. When training the flow rate heat prediction model, the flow rate corresponding to each historical operating state data is used as the training sample, and the heat output corresponding to each historical operating state data is used as the label for the sample, constructing a flow rate heat prediction training set. The flow rate heat prediction model to be trained can be either a LightGBM or Ridge model, and Bayesian search is used to determine the model hyperparameters. MAPE is used to evaluate the model performance, and the optimal model is selected and saved, resulting in the trained flow rate heat prediction model. Through the flow rate heat prediction model, the heat output under different operating states can be quantified, providing a basis for subsequently selecting initial operating state data from multiple operating state data sets.

[0062] Furthermore, based on the different operating status data of the heating station equipment and the corresponding heat volume of each operating status data, a mapping table or database can be established to record the relationship between each operating status data and its corresponding heat volume. By establishing the correspondence between operating status and heat volume, given a target heat demand, the operating status data closest to that target heat demand can be quickly found, i.e., the initial operating status data can be selected to meet the predicted target heat demand, thereby achieving precise control of the heating station equipment.

[0063] In some embodiments, the target operating status data of the heating station equipment is generated based on initial operating status data, target heat demand, current operating characteristic data, and indoor and outdoor environmental characteristic data. This includes: inputting the target heat demand, current operating characteristic data, and indoor and outdoor environmental characteristic data as a set of data into a set temperature prediction model to obtain the target set temperature for the next time period output by the set temperature prediction model; and generating the target operating status data of the heating station equipment based on the target set temperature and the initial operating status data.

[0064] Specifically, the set temperature prediction model can fit the target set temperature for the next time period based on the target heat demand, current operating characteristic data, and indoor and outdoor environmental characteristic data. The target set temperature is the boiler supply water temperature setpoint. The aforementioned indoor and outdoor environmental characteristic data can be the outdoor temperature for the next time period, the indoor and outdoor temperature difference within the current time period, and the feature vector of the outdoor weather for the next time period. The current operating characteristic data can be the supply and return water temperature difference. The outdoor temperature for the next time period, the indoor and outdoor temperature difference within the current time period, the feature vector of the outdoor weather for the next time period, the supply and return water temperature difference, and the target heat demand are input into the set temperature prediction model. Through the set temperature prediction model, the target set temperature for the next time period is predicted based on the current environmental conditions, operating status, and heat demand, providing a basis for subsequent operating status adjustments. Based on the target set temperature and initial operating status data, target operating status data for the heating station equipment is generated. For example, the initial operating status data could be: 2 boilers, 2 hot water pumps, hot water pump frequency of 50Hz, and target set temperature of 60℃. The generated target operating status data would then be: 2 boilers, 2 hot water pumps, hot water pump frequency of 50Hz, and target set temperature of 60℃. By generating target operating status data for heating station equipment from initial operating status data, target heat demand, current operating characteristic data, and indoor and outdoor environmental characteristic data, more refined control can be achieved based on current environmental conditions and user needs, thereby meeting heat demand and improving user experience and satisfaction.

[0065] Furthermore, when constructing the setpoint temperature prediction model, the target heat demand, current operational characteristic data, and indoor and outdoor environmental characteristic data are used as the original dataset. The indoor and outdoor environmental characteristic data includes multiple sub-features such as time features, indoor wet-bulb temperature within the current time period, indoor average temperature within the current time period, indoor humidity within the current time period, indoor-outdoor temperature difference within the current time period, outdoor temperature for the next time period, feature vectors of outdoor weather within the current time period, and feature vectors of outdoor weather for the next time period. The current operational characteristic data includes multiple sub-features such as supply and return water temperature difference, hot water main supply temperature, hot water main return temperature, flow rate, hot water pump frequency, number of boilers, hot water pumps, and setpoint temperature. The optimal feature subset can be obtained through SFFS (Survey-Free Feature Filtering), as the features in the optimal feature subset are the most informative for the setpoint temperature prediction model. Specifically, the optimal feature subset may include the outdoor temperature for the next time period, the indoor-outdoor temperature difference within the current time period, the feature vectors of outdoor weather for the next time period, the supply and return water temperature difference, and the target heat demand. The set temperature prediction model to be trained can be either LightGBM or Ridge. Bayesian search is used to determine the model hyperparameters, and MAPE is used to evaluate the model. The optimal model is selected and saved to obtain the trained set temperature prediction model.

[0066] In some embodiments, acquiring indoor and outdoor environmental feature data includes: acquiring initial indoor and outdoor environmental feature data, which includes the average indoor temperature, outdoor temperature, indoor humidity, outdoor weather, outdoor temperature, outdoor weather, and current time within the current time period; constructing time features based on the current time period; determining the corresponding indoor wet-bulb temperature within the current time period based on the average indoor temperature and indoor humidity within the current time period; determining the corresponding indoor-outdoor temperature difference within the current time period based on the average indoor temperature and outdoor temperature within the current time period; encoding the outdoor weather within the current time period and the outdoor weather in the next time period to obtain the feature vectors of the outdoor weather within the current time period and the outdoor weather in the next time period; and determining the time features, the indoor wet-bulb temperature, the average indoor temperature, the indoor humidity, the indoor-outdoor temperature difference, the outdoor temperature, the outdoor weather feature vectors, and the outdoor weather feature vectors as indoor and outdoor environmental feature data.

[0067] Specifically, the initial characteristic data of the indoor and outdoor environments are basic data directly obtained from environmental monitoring equipment or data sources. The average indoor temperature within the current time period is the average indoor temperature obtained by multiple indoor temperature sensors within the current time period, which can be 1 hour, with each temperature sensor transmitting temperature data every five minutes. The average outdoor temperature within the current time period is the average outdoor temperature obtained by multiple outdoor temperature sensors within the current time period, which can also be 1 hour, with each outdoor temperature sensor transmitting temperature data every five minutes. The average indoor humidity within the current time period is the average humidity level of the indoor environment, which can be measured by a humidity sensor. The outdoor weather within the current time period can be sunny, rainy, cloudy, etc. The outdoor temperature and weather for the next time period can be obtained based on weather forecasts. The current time is the specific point in time when the data is recorded, which is helpful for time-series data analysis. In addition, the initial characteristic data of the indoor and outdoor environments may also include CO2. 2 Content, wind force, wind speed, etc. Based on the current time period, construct time features, including whether it's a holiday, whether there are adjusted workdays, number of days until the holiday, number of days until the solstice, business hours, opening and closing times, etc. These features help the model better capture time-related influences. After filtering out abnormal sensors, exploratory data analysis (EDA) can be performed on indoor temperature and humidity data. Based on the average indoor temperature and humidity within the current time period, the corresponding indoor wet-bulb temperature for the current time period is determined. Indoor wet-bulb temperature is crucial for assessing indoor comfort. The aforementioned indoor-outdoor temperature difference is the difference between the average indoor temperature and outdoor temperature within the current time period. This is important for understanding building heat exchange efficiency and capturing the impact of environmental temperature changes on heat consumption. Encode the outdoor weather for the current and next time periods. OneHot encoding can be used to map weather types to numerical values ​​and convert textual weather descriptions (such as sunny or rainy) into vector form, enabling the model to identify and learn the impact of weather on the indoor and outdoor environments. The above preprocessing steps effectively clean and transform the raw data, providing reliable input data for subsequent models and improving their accuracy and generalization ability. Integrating the processed feature data forms complete indoor and outdoor environmental feature data, resulting in a dataset that comprehensively reflects environmental conditions, which can be used to predict target heat demand and target set temperature for the next time period.

[0068] In some embodiments, obtaining current operating characteristic data of the heating station equipment includes: obtaining current initial operating characteristic data of the heating station equipment, the current initial operating characteristic data including the hot water main supply temperature and the hot water main return temperature; determining the corresponding supply and return water temperature difference based on the hot water main supply temperature and the hot water main return temperature; and determining the supply and return water temperature difference as current operating characteristic data.

[0069] In some embodiments, the current initial operating characteristic data refers to basic data that directly reflects the operating status of the heating station equipment at a certain moment or time period. This current initial operating characteristic data may include the hot water main supply temperature, hot water main return temperature, boiler operating status, hot water pump operating status, and hot water pump frequency. The hot water main supply temperature is the temperature of the hot water supplied to the system by the heating station equipment, reflecting its heating capacity and efficiency. The hot water main return temperature is the temperature at which the hot water returns to the heating station equipment after use, reflecting heat consumption and system heat loss. The supply and return water temperature difference = hot water main supply temperature - hot water main return temperature. This temperature difference is an important indicator for evaluating the heating station equipment's thermal efficiency, heat loss, and the degree to which user heat demand is met. A larger supply and return water temperature difference indicates that more heat is absorbed by the indoor air or that heat loss is smaller. The supply and return water temperature difference comprehensively reflects the operating status, thermal efficiency, and heat demand of the heating station equipment and can be considered one of the current operating characteristic data of the heating station equipment. By incorporating the supply and return water temperature difference into the operational feature dataset, a more comprehensive understanding of the operating status of the heating station equipment can be obtained, enabling performance evaluation, fault diagnosis, or optimized scheduling.

[0070] All of the above-mentioned optional technical solutions can be combined in any way to form optional embodiments of this disclosure, and will not be described in detail here.

[0071] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0072] Figure 3 This is a schematic diagram of an indoor temperature control device provided in an embodiment of this disclosure. Figure 3 As shown, the indoor temperature control device includes:

[0073] The acquisition module 301 is configured to acquire indoor and outdoor environmental characteristic data and the target indoor temperature;

[0074] The prediction module 302 is configured to predict the indoor heat demand for the next time period based on indoor and outdoor environmental characteristic data and target temperature, so as to obtain the target indoor heat demand for the next time period.

[0075] The filtering module 303 is configured to filter initial operating status data from multiple operating status data based on the target heat demand and the correspondence between each operating status data and the heat generated by the heat station equipment in multiple pre-set operating status data of the heat station equipment.

[0076] The generation module 304 is configured to acquire the current operating characteristic data of the heating station equipment, and generate the target operating status data of the heating station equipment based on the initial operating status data, the target demand heat, the current operating characteristic data and the indoor and outdoor environmental characteristic data;

[0077] The control module 305 is configured to control the heating station equipment based on the target operating status data.

[0078] According to the technical solution provided in this disclosure, by acquiring indoor and outdoor environmental characteristic data and the target indoor temperature, a foundation is laid for subsequent data processing and analysis, enabling the indoor temperature control method to be based on real-time environmental data and the actual needs of users. Based on the indoor and outdoor environmental characteristic data and the target temperature, the target heat demand for the indoor environment in the next time period is predicted, improving the predictability and accuracy of temperature control. Based on the predicted target heat demand, and combined with the correspondence between the operating status of the heating station equipment and heat generation, the initial operating status data of the heating station equipment that can meet the target heat demand is initially determined. The initial operating status data is supplemented by combining the current operating characteristic data of the heating station equipment, the predicted target heat demand, and the indoor and outdoor environmental characteristic data to generate more accurate and efficient target operating status data for the heating station equipment. The heating station equipment is then controlled based on the target operating status data, achieving dynamic control of the heating station equipment and facilitating timely response to changing environmental conditions and demands. The indoor temperature control method proposed in this disclosure introduces a heat demand prediction mechanism and a dynamic adjustment mechanism, no longer relying on a fixed control strategy. It performs in-depth analysis and prediction of real-time data, and generates target operating status data of heating station equipment based on real-time data. This enables more refined and personalized temperature control based on current environmental conditions and user needs, and dynamically adjusts the operating status of heating station equipment. This solves the limitations of traditional fixed strategy control methods and improves the precision of indoor temperature control.

[0079] In some embodiments, the prediction module 302 is configured to input indoor and outdoor environmental feature data into a heat prediction model to obtain the predicted indoor heat for the next time period output by the heat prediction model; input the predicted heat and indoor and outdoor environmental feature data as a set of data into a temperature regulation heat model to obtain the initial predicted temperature corresponding to the predicted heat output by the temperature regulation heat model; correct the initial predicted temperature based on the target temperature to obtain the target predicted temperature, until the absolute value of the difference between the target predicted temperature and the target temperature is less than or equal to a first preset value, and determine the heat corresponding to the target predicted temperature as the target demand heat.

[0080] In some embodiments, the prediction module 302 is configured to adjust the predicted heat according to a preset heat adjustment step size when the absolute value of the difference between the initial predicted temperature and the target temperature is greater than a first preset value, thereby obtaining multiple candidate heats; input each candidate heat and indoor and outdoor environmental feature data as a set of data into the temperature regulation heat model to obtain the initial predicted temperature corresponding to each candidate heat output by the temperature regulation heat model; calculate the absolute value of the difference between the initial predicted temperature corresponding to each candidate heat and the target temperature, and determine the initial predicted temperature that meets the preset requirement among the initial predicted temperatures corresponding to each candidate heat as the target predicted temperature, wherein the preset requirement is less than or equal to the first preset value and the absolute value of the difference with the target temperature is the smallest.

[0081] In some embodiments, before filtering initial operating status data from multiple operating status data based on the target heat demand and the pre-set correspondence between each operating status data and the heat generated by the heating station equipment, the filtering module 303 is configured to acquire multiple historical operating status data of the heating station equipment and the flow rate corresponding to each historical operating status data, wherein the historical operating status data includes the historical number of boilers, the historical number of hot water pumps, and the historical frequency of hot water pumps; based on the flow rate corresponding to each historical operating status data, the historical operating status data is clustered to obtain the processed operating status data and processed operating status data corresponding to multiple cluster centers. The process involves: determining the flow rate corresponding to the operational status data; determining the adjustment step size for the hot water pump frequency based on the frequency and range of the hot water pump in the processed operational status data; adjusting the hot water pump frequency in each processed operational status data based on the adjustment step size to obtain multiple operational status data for the heating station equipment; determining the flow rate corresponding to each operational status data based on each operational status data and each processed operational status data; inputting the flow rate corresponding to each operational status data into the flow rate heat prediction model to obtain the heat corresponding to each operational status data output by the flow rate heat prediction model; and establishing a correspondence between each operational status data and the heat corresponding to each operational status data.

[0082] In some embodiments, the generation module 304 is configured to input the target heat demand, current operating characteristic data, and indoor and outdoor environmental characteristic data as a set of data into the set temperature prediction model to obtain the target set temperature for the next time period output by the set temperature prediction model; and generate target operating status data of the heating station equipment based on the target set temperature and the initial operating status data.

[0083] In some embodiments, the acquisition module 301 is configured to acquire initial feature data of the indoor and outdoor environment, which includes the average indoor temperature, outdoor temperature, indoor humidity, outdoor weather, outdoor temperature, outdoor weather, and current time within the current time period; construct time features based on the current time period; determine the corresponding indoor wet-bulb temperature within the current time period based on the average indoor temperature and indoor humidity within the current time period; determine the corresponding indoor-outdoor temperature difference within the current time period based on the average indoor temperature and outdoor temperature within the current time period; encode the outdoor weather within the current time period and the outdoor weather in the next time period to obtain the feature vectors of the outdoor weather within the current time period and the outdoor weather in the next time period; and determine the time features, the indoor wet-bulb temperature, the average indoor temperature, the indoor humidity, the indoor-outdoor temperature difference, the outdoor temperature, the outdoor weather feature vectors, and the outdoor weather feature vectors as the indoor and outdoor environment feature data.

[0084] In some embodiments, the generation module 304 is configured to acquire the current initial operating characteristic data of the heating station equipment, the current initial operating characteristic data including the hot water supply temperature and the hot water return temperature of the hot water main pipe; determine the corresponding supply and return water temperature difference based on the hot water supply temperature and the hot water return temperature of the hot water main pipe; and determine the supply and return water temperature difference as the current operating characteristic data.

[0085] It should be understood that the sequence number of each step in the above embodiments does not imply 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 this disclosure.

[0086] Figure 4 This is a schematic diagram of the electronic device 4 provided in an embodiment of this disclosure. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, it implements the steps in the various method embodiments described above. Alternatively, when the processor 401 executes the computer program 403, it implements the functions of each module / unit in the various device embodiments described above.

[0087] Electronic device 4 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 4 may include, but is not limited to, processor 401 and memory 402. Those skilled in the art will understand that... Figure 4This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or different components.

[0088] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0089] The memory 402 can be an internal storage unit of the electronic device 4, such as a hard disk or RAM of the electronic device 4. The memory 402 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the electronic device 4. The memory 402 can also include both internal and external storage units of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device.

[0090] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above 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 integrated unit can be implemented in hardware or as a software functional unit.

[0091] If integrated modules / units are implemented as software functional units and sold or used as independent products, they can be stored in a readable storage medium (e.g., a computer-readable storage medium). Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0092] The above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit it. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be included within the protection scope of this disclosure.

Claims

1. An indoor temperature control method, characterized in that, include: Acquire indoor and outdoor environmental characteristic data and target indoor temperature; Based on the indoor and outdoor environmental characteristic data and the target temperature, the indoor heat demand for the next time period is predicted to obtain the target indoor heat demand for the next time period. Based on the target heat demand and the correspondence between each operating status data and the heat generated by the heat station equipment in the multiple pre-set operating status data, initial operating status data is obtained by filtering from the multiple operating status data; Obtain the current operating characteristic data of the heating station equipment, and generate the target operating status data of the heating station equipment based on the initial operating status data, the target demand heat, the current operating characteristic data, and the indoor and outdoor environmental characteristic data; The heating station equipment is controlled based on the target operating status data; The process of predicting indoor heat demand for the next time period based on the indoor and outdoor environmental characteristic data and the target temperature, to obtain the target indoor heat demand for the next time period, includes: The indoor and outdoor environmental characteristic data are input into the heat prediction model to obtain the predicted indoor heat for the next time period output by the heat prediction model. The predicted heat and the indoor and outdoor environmental characteristic data are input as a set of data into the temperature regulation heat model to obtain the initial predicted temperature corresponding to the predicted heat output by the temperature regulation heat model. The initial predicted temperature is corrected based on the target temperature to obtain the target predicted temperature, until the absolute value of the difference between the target predicted temperature and the target temperature is less than or equal to a first preset value, and the heat corresponding to the target predicted temperature is determined as the target required heat. The process of generating target operating status data for the heating station equipment based on the initial operating status data, the target heat demand, the current operating characteristic data, and the indoor and outdoor environmental characteristic data includes: The target heat demand, the current operating characteristic data, and the indoor and outdoor environmental characteristic data are input as a set of data into the set temperature prediction model to obtain the target set temperature for the next time period output by the set temperature prediction model. The target operating status data of the heating station equipment is generated based on the target set temperature and the initial operating status data.

2. The method according to claim 1, characterized in that, The step of correcting the initial predicted temperature based on the target temperature to obtain the target predicted temperature includes: If the absolute value of the difference between the initial predicted temperature and the target temperature is greater than the first preset value, the predicted heat is adjusted according to the preset heat adjustment step size to obtain multiple candidate heats; Each candidate heat source is input into the temperature regulation heat model along with the indoor and outdoor environmental feature data as a set of data to obtain the initial predicted temperature corresponding to each candidate heat source output by the temperature regulation heat model. Calculate the absolute value of the difference between the initial predicted temperature corresponding to each of the candidate heat sources and the target temperature. Determine the initial predicted temperature that meets the preset requirement among the initial predicted temperatures corresponding to each of the candidate heat sources as the target predicted temperature. The preset requirement is that the initial predicted temperature is less than or equal to the first preset value and has the smallest absolute value of the difference between the initial predicted temperature and the target temperature.

3. The method according to claim 1, characterized in that, Before obtaining the initial operating status data by filtering from the multiple operating status data based on the target heat demand and the correspondence between each operating status data and the heat generated by the heat station equipment in a pre-set set of multiple operating status data, the method further includes: Acquire multiple historical operating status data of the heating station equipment and the flow rate corresponding to each historical operating status data, wherein the historical operating status data includes the historical number of boilers, the historical number of hot water pumps, and the historical frequency of hot water pumps; Based on the traffic corresponding to each historical operational status data, the historical operational status data is clustered to obtain the processed operational status data and the traffic corresponding to the processed operational status data for multiple cluster centers. Based on the hot water pump frequency and hot water pump frequency range in the processed operating status data, determine the adjustment step size corresponding to the hot water pump frequency; Based on the adjustment step size corresponding to the hot water pump frequency, the hot water pump frequency in each of the processed operating status data is adjusted to obtain multiple operating status data of the heating station equipment. Based on each of the aforementioned operational status data and each of the processed operational status data, the traffic corresponding to each operational status data is determined. Input the flow rate corresponding to each of the aforementioned operating status data into the flow rate heat prediction model to obtain the heat corresponding to each of the operating status data output by the flow rate heat prediction model. The corresponding relationship is established based on each of the aforementioned operating status data and the heat corresponding to each of the aforementioned operating status data.

4. The method according to claim 1, characterized in that, The acquisition of indoor and outdoor environmental feature data includes: Acquire initial characteristic data of indoor and outdoor environment, which includes the average indoor temperature in the current time period, the outdoor temperature in the current time period, the indoor humidity in the current time period, the outdoor weather in the current time period, the outdoor temperature in the next time period, the outdoor weather in the next time period, and the current time. Based on the current time period, construct time features; Based on the average indoor temperature and indoor humidity within the current time period, determine the corresponding indoor wet-bulb temperature within the current time period. Based on the average indoor temperature and the outdoor temperature within the current time period, determine the corresponding indoor-outdoor temperature difference within the current time period; Encode the outdoor weather in the current time period and the outdoor weather in the next time period to obtain the feature vector of the outdoor weather in the current time period and the feature vector of the outdoor weather in the next time period. The time features, indoor wet-bulb temperature in the current time period, indoor average temperature in the current time period, indoor humidity in the current time period, indoor-outdoor temperature difference in the current time period, 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 are determined as the indoor and outdoor environmental feature data.

5. The method according to claim 1, characterized in that, The acquisition of the current operating characteristic data of the heating station equipment includes: Acquire the current initial operating characteristic data of the heating station equipment, which includes the hot water supply temperature and the hot water return temperature of the hot water main pipe; Based on the supply water temperature and return water temperature of the hot water main pipe, determine the corresponding supply and return water temperature difference; The supply and return water temperature difference is determined as the current operating characteristic data.

6. An indoor temperature control device, characterized in that, include: The acquisition module is configured to acquire indoor and outdoor environmental characteristic data and the target indoor temperature; The prediction module is configured to predict the indoor heat demand for the next time period based on the indoor and outdoor environmental characteristic data and the target temperature, so as to obtain the target indoor heat demand for the next time period. The filtering module is configured to filter initial operating status data from multiple operating status data based on the target heat demand and the correspondence between each operating status data and the heat generated by the heat station equipment in multiple pre-set operating status data of the heat station equipment. The generation module is configured to acquire the current operating characteristic data of the heating station equipment, and generate the target operating status data of the heating station equipment based on the initial operating status data, the target demand heat, the current operating characteristic data and the indoor and outdoor environmental characteristic data; The control module is configured to control the heating station equipment based on the target operating status data; The prediction module is specifically configured to: input the indoor and outdoor environmental feature data into a heat prediction model to obtain the predicted indoor heat for the next time period output by the heat prediction model; input the predicted heat and the indoor and outdoor environmental feature data as a set of data into a temperature regulation heat model to obtain the initial predicted temperature corresponding to the predicted heat output by the temperature regulation heat model; correct the initial predicted temperature based on the target temperature to obtain the target predicted temperature, until the absolute value of the difference between the target predicted temperature and the target temperature is less than or equal to a first preset value, and determine the heat corresponding to the target predicted temperature as the target demand heat; The generation module is specifically configured to: input the target heat demand, the current operating characteristic data, and the indoor and outdoor environmental characteristic data as a set of data into the set temperature prediction model to obtain the target set temperature for the next time period output by the set temperature prediction model; and generate the target operating status data of the heating station equipment based on the target set temperature and the initial operating status data.

7. 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, it implements the steps of the method as described in any one of claims 1 to 5.

8. A readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images