Geothermal heating temperature control method and system based on environmental perception

Abstract

The invention relates to the field of geothermal heating temperature control, and provides a geothermal heating temperature control method and system based on environmental perception, and the method comprises the steps: obtaining indoor and outdoor environmental perception data through indoor perception equipment and outdoor monitoring channels of each heating room; preprocessing the indoor and outdoor environment sensing data; according to the preprocessed indoor and outdoor environment sensing data, the indoor temperature change trend of each heating room is predicted, and a temperature prediction change curve is obtained; when the fluctuation quantity of the temperature prediction change curve reaches the adjustment requirement, optimizing control parameters of a geothermal heating system adopted by each heating room according to the temperature prediction change curve by taking the preset comfortable room temperature and the minimum geothermal heating energy consumption as targets to obtain optimal geothermal control parameters; and dynamically adjusting the control parameters of the geothermal heating system according to the optimal geothermal control parameters. By means of the method, the comfortable room temperature can be preset, geothermal heating energy consumption can be minimized, the indoor comfort degree is improved, and meanwhile heating energy consumption is reduced.

Description

Technical Field

[0001] This invention relates to the field of geothermal heating temperature control technology, and in particular to a geothermal heating temperature control method and system based on environmental perception. Background Technology

[0002] Currently, temperature control methods for geothermal heating have many shortcomings. Existing technologies mainly rely on simple temperature settings and fixed heating modes for temperature control, failing to accurately adjust the geothermal heating system according to real-time changes in the indoor and outdoor environment. For example, when the outside temperature changes abruptly, the water supply temperature and valve opening cannot be adjusted in time, resulting in indoor temperatures that are either too high, leading to energy waste, or too low, affecting comfort. As people's demands for living environment comfort and energy efficiency continue to increase, the limitations of existing temperature control methods for geothermal heating become increasingly apparent. These limitations are mainly manifested in the difficulty of obtaining comprehensive real-time information on the indoor and outdoor environment, the inability to accurately predict indoor temperature change trends, and consequently, the inability to achieve a preset comfortable room temperature while minimizing geothermal heating energy consumption, thus failing to meet the modern demands for green and intelligent heating. Summary of the Invention

[0003] The present invention aims to solve at least one of the problems existing in the prior art, and to provide a geothermal heating temperature control method and system based on environmental perception.

[0004] One aspect of the present invention provides a geothermal heating temperature control method based on environmental perception, the geothermal heating temperature control method based on environmental perception comprising: By utilizing the indoor sensing devices and outdoor monitoring channels of each heating room, indoor and outdoor environmental sensing data of each heating room are obtained. The indoor and outdoor environmental perception data are preprocessed; Based on the preprocessed indoor and outdoor environmental sensing data, the indoor temperature change trend of each heating room is predicted to obtain a temperature prediction change curve. When the fluctuation of the temperature prediction curve reaches the adjustment requirement, with the goal of minimizing the preset comfortable room temperature and geothermal heating energy consumption, the control parameters of the geothermal heating system used in each of the heating rooms are optimized according to the temperature prediction curve to obtain the optimal geothermal control parameters. The control parameters of the geothermal heating system are dynamically adjusted based on the optimal geothermal control parameters.

[0005] Optionally, the step of acquiring indoor and outdoor environmental sensing data for each heating room using indoor sensing devices and outdoor monitoring channels includes: Temperature sensors and humidity sensors are installed in each of the heating rooms, and indoor environmental perception data of each heating room are obtained using the temperature sensors and humidity sensors. Based on the geographical location of each heating room, the outdoor temperature, wind speed, and light intensity of each heating room are obtained through a weather forecast data interface to obtain outdoor environmental perception data for each heating room.

[0006] Optionally, the step of predicting the indoor temperature change trend of each of the heated rooms based on the preprocessed indoor and outdoor environmental sensing data to obtain a temperature prediction change curve includes: Using the historical data of indoor and outdoor environmental perception of each of the heating rooms, a training dataset and a test dataset are constructed respectively. The training dataset and the test dataset both include the historical data of indoor environmental perception and the corresponding historical data of outdoor environmental perception of each of the heating rooms. The long short-term memory network model is trained and tested using the training dataset and the test dataset until the convergence target of the long short-term memory network model is reached, thereby obtaining the temperature prediction model. The preprocessed indoor and outdoor environmental perception data are used as input data for the temperature prediction model. The temperature prediction model is then used to predict the future temperature change trend of each of the heating rooms, resulting in the temperature prediction change curve.

[0007] Optionally, the step of optimizing the control parameters of the geothermal heating system used in each of the heated rooms based on the temperature prediction curve, with the goal of minimizing the preset comfortable room temperature and geothermal heating energy consumption, to obtain the optimal geothermal control parameters, includes: Collect geothermal heating energy consumption data of the geothermal heating system under different control parameters, and fit the relationship function between the control parameters and energy consumption of the geothermal heating system based on the geothermal heating energy consumption data under different control parameters. Based on the relationship function between the control parameters and energy consumption, an energy consumption objective function is constructed with the goal of minimizing geothermal heating energy consumption. Using the preset comfortable room temperature as the target, a comfort deviation penalty function is constructed. The energy consumption target function and the comfort deviation penalty function are then merged to construct a target evaluation function. Using the maximum power and water temperature safety threshold of the geothermal heating system as constraints, the control parameters of the geothermal heating system are evaluated and optimized according to the target evaluation function until the evaluation target value or the maximum number of searches is reached, so as to obtain the optimal geothermal control parameters. The optimal geothermal control parameters are the optimal combination of values ​​of each control parameter of the geothermal heating system when the target evaluation result is maximized.

[0008] Optionally, fitting the relationship function between the control parameters and energy consumption of the geothermal heating system based on the geothermal heating energy consumption data under different control parameters includes: Based on the geothermal heating energy consumption data under different control parameters, a regression analysis method was used to fit the relationship function between the control parameters and energy consumption.

[0009] Optionally, constructing a comfort deviation penalty function with the preset comfortable room temperature as the target includes: With the preset comfortable room temperature as the target, multiple deviation ranges and corresponding penalty values ​​are set; Based on the multi-level deviation ranges and corresponding penalty values, the comfort deviation penalty function is constructed.

[0010] Optionally, the step of evaluating and optimizing the control parameters of the geothermal heating system based on the target evaluation function, using the maximum power and water temperature safety threshold of the geothermal heating system as constraints, includes: Using the maximum power, minimum safe water temperature threshold, and maximum safe water temperature threshold of the geothermal heating system as constraints, a genetic optimization algorithm is used to optimize the control parameters of the geothermal heating system according to the objective evaluation function.

[0011] Optionally, the preprocessing of the indoor and outdoor environmental perception data includes: Set the window size of the sliding window; Based on the window size of the sliding window, the indoor and outdoor environmental perception data are processed using a moving average filter.

[0012] Optionally, the size of the sliding window ranges from 5 to 10 data points in the indoor and outdoor environment perception data.

[0013] Another aspect of the present invention provides an environment-sensing-based geothermal heating temperature control system for use in the aforementioned environment-sensing-based geothermal heating temperature control method, wherein the environment-sensing-based geothermal heating temperature control system comprises: The sensing data acquisition module is connected to the indoor sensing devices and outdoor monitoring channels of each heating room, and is used to acquire indoor and outdoor environmental sensing data of each heating room using the indoor sensing devices and the outdoor monitoring channels. The sensing data preprocessing module is used to preprocess the indoor and outdoor environmental sensing data; The temperature curve acquisition module is used to predict the indoor temperature change trend of each heating room based on the preprocessed indoor and outdoor environmental sensing data, and obtain the predicted temperature change curve. The geothermal parameter acquisition module is used to optimize the control parameters of the geothermal heating system used in each of the heating rooms based on the temperature prediction curve when the fluctuation of the temperature prediction curve reaches the adjustment requirements, with the goal of minimizing the preset comfortable room temperature and geothermal heating energy consumption. The parameter dynamic adjustment module is used to dynamically adjust the control parameters of the geothermal heating system according to the optimal geothermal control parameters.

[0014] Compared with the prior art, this invention solves the technical problem that traditional geothermal heating systems are unable to accurately balance indoor comfort and heating energy consumption in terms of temperature control. It can accurately predict the indoor temperature change trend of the heated room and dynamically adjust the control parameters of the geothermal heating system according to the indoor temperature change trend, so as to achieve the preset comfortable room temperature and minimize geothermal heating energy consumption, thereby improving indoor comfort while reducing heating energy consumption. Attached Figure Description

[0015] One or more embodiments are illustrated by way of example with the corresponding pictures in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0016] Figure 1 A flowchart of a geothermal heating temperature control method based on environmental perception provided in one embodiment of the present invention; Figure 2 This is a schematic diagram of a geothermal heating temperature control system based on environmental perception, provided as another embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details are presented in the various embodiments of the present invention to facilitate a better understanding of the invention. However, the technical solutions claimed in the present invention can be implemented even without these technical details and with various variations and modifications based on the following embodiments. The division of the various embodiments below is for ease of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with and referenced by each other without contradiction.

[0018] One embodiment of the present invention relates to a geothermal heating temperature control method based on environmental sensing, the process of which is as follows: Figure 1 As shown, it includes steps A100 to A500.

[0019] Step A100: Use the indoor sensing devices and outdoor monitoring channels of each heating room to obtain indoor and outdoor environmental sensing data for each heating room.

[0020] Specifically, the indoor sensing equipment mainly includes temperature and humidity sensors deployed in each heated room to monitor indoor temperature and humidity. The outdoor monitoring pathway includes a data interface connected to weather forecasts, and a channel through which relevant meteorological data is obtained based on the geographical location of each heated room. Indoor and outdoor environmental sensing data includes indoor environmental sensing data obtained using the indoor sensing equipment such as temperature and humidity sensors deployed in each heated room, and outdoor environmental sensing data such as outdoor temperature, wind speed, and light intensity obtained using the outdoor monitoring pathway.

[0021] For example, step A100 includes steps A110 and A120.

[0022] Step A110: Install temperature and humidity sensors in each heated room and use them to acquire indoor environmental sensing data for each heated room.

[0023] Specifically, each heated room typically possesses different characteristics, which influences its temperature and humidity differently. For instance, in a residence with multiple heated rooms, the orientation, area, and window size of each room often vary. For example, suppose heated room A in the same residence has an area of ​​20 square meters, a window size of 5 square meters, and faces the sun. Another heated room in the same residence has an area of ​​15 square meters, a window size of 3 square meters, and faces away from the sun. Because heated room A has a larger window area and faces the sun, its temperature change will be more pronounced than that of heated room B within the same timeframe. By installing temperature sensors in each heated room, temperature changes can be captured in real time. Similarly, by installing humidity sensors in each heated room, humidity changes can be captured in real time. Step A110 can summarize the data collected by the temperature and humidity sensors in each heated room, thereby comprehensively and accurately obtaining indoor environmental perception data, including temperature and humidity data, for each heated room, providing a basis for accurately judging the indoor thermal environment status of each heated room in the future.

[0024] Step A120: Based on the geographical location of each heated room, obtain the outdoor temperature, wind speed, and light intensity of each heated room through the weather forecast data interface to obtain the outdoor environmental perception data of each heated room.

[0025] Specifically, step A120 can use the Global Positioning System (GPS) or the BeiDou Navigation Satellite System to locate the geographical location of each heated room. Since weather forecasts typically target a specific city or region, when acquiring outdoor environmental sensing data, step A120 can obtain the outdoor temperature, wind speed, and light intensity of the city or region indicated by the geographical location of each heated room through a weather forecast data interface, using this as the outdoor environmental sensing data for each heated room. For example, assuming the geographical location of each heated room, obtained through geographical location tracking, is 30 degrees North latitude and 120 degrees East longitude, then step A120 can obtain the outdoor temperature, wind speed, and light intensity at that location through the weather forecast data interface as the outdoor environmental sensing data for each heated room. For example, suppose on a certain winter day, the temperature at 30 degrees north latitude and 120 degrees east longitude is 5°C, the wind speed is 3 m / s, and the light intensity is 1000 lux. Then the outdoor environmental perception data for each heated room would include the temperature of 5°C, the wind speed of 3 m / s, and the light intensity of 1000 lux. These data reflect the real-time status of the outdoor environment for each heated room and can be used to determine the impact of the outdoor environment on the indoor temperature of each heated room.

[0026] By acquiring indoor and outdoor environmental perception data for each heated room, a solid foundation can be laid for subsequent precise geothermal heating temperature control, thereby more effectively balancing indoor comfort and energy consumption.

[0027] Step A200: Preprocess the indoor and outdoor environmental perception data.

[0028] Specifically, preprocessing indoor and outdoor environmental perception data is mainly to reduce noise and fluctuations in the data.

[0029] For example, step A200 includes steps A210 and A220.

[0030] Step A210: Set the window size of the sliding window.

[0031] Specifically, a sliding window is a pre-defined range of sample data used for processing indoor and outdoor environmental perception data during preprocessing. In other words, a sliding window is a fixed-length "window" that slides across a data sequence.

[0032] For example, the window size of the sliding window ranges from 5 to 10 data points in the indoor and outdoor environmental perception data.

[0033] Specifically, data points, also known as sample data, refer to data units used for preprocessing indoor and outdoor environmental sensing data. To obtain the optimal sliding window size, the inventors of this application collected massive amounts of indoor and outdoor environmental sensing data covering different seasons, time periods, and building structures in multiple geothermal heating projects across different climate regions, and conducted simulation experiments on the sliding window size. The experiments showed that when the sliding window is too small, such as setting it to 3 sample data points, the smoothing effect of the indoor and outdoor environmental sensing data is poor, making it difficult to effectively remove noise. This leads to significant noise interference in the subsequent temperature prediction model, resulting in higher prediction errors. Conversely, when the sliding window is too large, such as setting it to 15 sample data points, the indoor and outdoor environmental sensing data is over-smoothed, losing some short-term data fluctuation characteristics. This causes the prediction results of the subsequent temperature prediction model to lag behind the actual temperature changes in the heated rooms, failing to provide timely and accurate data for the control of the geothermal heating system. Based on a large amount of experimental data, it can be seen that when the sliding window size is set to cover 5 to 10 data points in the indoor and outdoor environmental sensing data, that is, when the sliding window size is set to the range of 5 to 10 sample data points, it can effectively filter out noise in the data, making the data more stable and reliable, and can also better retain the key fluctuation information of the data. This can provide a solid data foundation for subsequent prediction of indoor temperature change trends and precise control of geothermal heating systems.

[0034] For example, when monitoring a geothermal heating system in a certain area, assuming that indoor and outdoor environmental sensing data are collected for 100 consecutive moments, if the sliding window size is set to 5 sample data points (covering 5 data points), it means that each time indoor and outdoor environmental sensing data is processed, the data from 5 consecutive moments is used as a group. However, if the sliding window size is set to 10 sample data points (covering 10 data points), it means that each time indoor and outdoor environmental sensing data is processed, the data from 10 consecutive moments is used as a group.

[0035] By setting the sliding window size to cover 5 to 10 data points in the indoor and outdoor environmental sensing data, the local characteristics and overall trends of the indoor and outdoor environmental sensing data can be effectively balanced. This can preserve the short-term fluctuation information of the indoor and outdoor environmental sensing data, while avoiding the problems of information loss or excessive noise interference caused by the sliding window being too large or too small.

[0036] Step A220: Based on the window size of the sliding window, use a moving average filter to process the indoor and outdoor environmental perception data.

[0037] Specifically, moving average filtering is a preprocessing method that smooths data to reduce noise and fluctuations. Moving average filtering uses the average value of the data within a moving window to replace the data at the center of the window. For example, step A220 includes steps A221 to A225.

[0038] Step A221: Determine the sliding window size. Assume the sliding window size is set to 7 sample data points, meaning that during data processing, 7 consecutive data points will be selected as a group for calculation each time.

[0039] Step A222: Select a data window. Starting from the beginning of the indoor and outdoor environmental sensing data sequence, select the first window containing 7 data points. For example, when the indoor temperature data sequence is [20,21,22,23,24,25,26,27,28,29,…], the data in the first window is [20,21,22,23,24,25,26].

[0040] Step A223: Calculate the average of the window data. Sum the 7 data points within the selected window and calculate the average. For example, the average of the data [20,21,22,23,24,25,26] in the first window is (20+21+22+23+24+25+26)÷7=23.

[0041] Step A224: Replace the data at the center of the window with the average value of the window data. For example, for the data in the first window [20,21,22,23,24,25,26], replace the data at the center of the window (i.e., the 4th data point) with the average value of 23, and the processed data for the first window is [20,21,22,23,24,25,26] (where the 4th data point was originally 23, and after processing, the value remains unchanged, but its meaning has changed to the average value of the data in this window).

[0042] Step A225: Slide the window and repeat the process. Move the sliding window one data position forward sequentially. For example, when the indoor temperature data sequence is [20,21,22,23,24,25,26,27,28,29,…], the data in the second window will be [21,22,23,24,25,26,27]. Repeat the steps of calculating the average value of the window data and replacing the data at the center of the window with the average value of the window data until the entire indoor and outdoor environmental sensing data sequence has been processed, thus completing the moving average filtering process for all indoor and outdoor environmental sensing data.

[0043] By using a moving average filter based on the window size of the sliding window to process indoor and outdoor environmental perception data, random noise and fluctuations in the data can be effectively reduced, making the processed data smoother, more stable, and more accurately reflecting the true trend of indoor and outdoor environmental perception data.

[0044] Step A300: Based on the preprocessed indoor and outdoor environmental sensing data, predict the indoor temperature change trend of each heating room to obtain the predicted temperature change curve.

[0045] Specifically, when predicting the indoor temperature change trend of each heating room, step A300 can use a trained temperature prediction model, such as a trained Long Short-Term Memory (LSTM) network model, to predict the indoor temperature change of each heating room in the future based on the preprocessed indoor and outdoor environmental perception data, and obtain the corresponding temperature prediction change curve.

[0046] By predicting the indoor temperature change trend of each heated room based on preprocessed indoor and outdoor environmental sensing data, especially by using a trained temperature prediction model, the indoor temperature change trend of each heated room in the future can be accurately obtained, thus providing a basis for adjusting the control parameters of the geothermal heating system.

[0047] For example, step A300 includes steps A310 to A330.

[0048] Step A310: Using the historical data of indoor and outdoor environmental perception for each heated room, construct training datasets and test datasets respectively. Both training datasets and test datasets include historical data of indoor environmental perception for each heated room and the corresponding historical data of outdoor environmental perception.

[0049] Specifically, the historical data of indoor and outdoor environmental perception for each heated room refers to the data collected by indoor sensing devices deployed in each heated room, including temperature sensors and humidity sensors, over a period of time.

[0050] Step A310 primarily involves constructing training and testing datasets using historical indoor and outdoor environmental perception data for each heated room. Since factors such as the orientation, area, and window size of each heated room affect its response to temperature changes, targeted training is required for each room's specific characteristics. For example, in a residence with multiple heated rooms, room A, which faces the sun and has large windows, experiences direct sunlight during the winter daytime, resulting in a faster temperature rise, while room B, which is shaded and has a smaller area, experiences a relatively slower temperature change. To more accurately predict temperature changes in each heated room, hourly temperature and humidity data for both room A and room B over the past heating season can be collected as historical indoor environmental perception data. Simultaneously, historical outdoor environmental perception data such as temperature, wind speed, and light intensity at corresponding times can be recorded. This allows for the construction of training and testing datasets for room A using both indoor and outdoor environmental perception data, and similarly for room B.

[0051] For example, to reduce computational load, the heated rooms can be clustered. For instance, multiple heated rooms can be grouped into one category based on similar orientation and area, so that a temperature prediction model for that category of heated rooms can be trained using the training and test datasets corresponding to that category. This process can specifically include the following steps A311 to A314.

[0052] Step A311: Collect key characteristic data such as orientation and area for all heated rooms in the same building. For example, in a multi-story residential building, collect the window orientation (such as due south, due north, due east, due west, etc.) and the actual usable area of ​​each heated room.

[0053] Step A312: Use similar orientation and area as the main clustering criteria. For example, heated rooms with an orientation deviation within ±30° and an area deviation within ±10 square meters can be grouped into one category.

[0054] Step A313: Classify the heated rooms according to the determined clustering criteria. For example, suppose there are 10 heated rooms on a certain floor. After analysis, 4 heated rooms facing south with an area of ​​20-30 square meters can be classified as Class A rooms, 3 heated rooms facing north with an area of ​​15-25 square meters can be classified as Class B rooms, and the remaining 3 heated rooms facing east with an area of ​​22-32 square meters can be classified as Class C rooms.

[0055] Step A314: For each type of room, collect its indoor environmental perception historical data and corresponding outdoor environmental perception historical data. For example, for type A rooms, collect indoor and outdoor environmental data at different times of day over the past week to form the training dataset and test dataset for this type of room. Similarly, the training dataset and test dataset for type B and type C rooms can be obtained.

[0056] Step A320: Train and test the long short-term memory network model using the training dataset and the test dataset until the convergence target of the long short-term memory network model is reached, and obtain the temperature prediction model.

[0057] Specifically, LSTM network models are suitable for predicting time-dependent data such as indoor temperature. For example, when building an LSTM network model for a type A room, the first step is to determine the number of LSTM layers and the number of neurons in each LSTM layer. For instance, the LSTM network model can include two or three LSTM layers. Taking a two-LSTM model as an example, the first LSTM layer can be set to include 64 neurons, and the second LSTM layer can be set to include 32 neurons. This configuration allows the LSTM network model to effectively capture complex features in the data. Simultaneously, fully connected layers are added to the LSTM network model. These fully connected layers map the features output by the LSTM layers (information extracted after processing the indoor and outdoor environmental perception data, including trends in indoor and outdoor temperature changes, humidity-temperature correlation patterns, and other information related to indoor temperature changes) to the final prediction result. For example, a fully connected layer with an output dimension of 1 can be set in the LSTM network model to output the predicted indoor temperature value. In addition, to prevent overfitting, a Dropout layer can be added to the LSTM network model. The Dropout layer randomly drops some neurons to enhance the model's generalization ability. The proportion of Dropout can be set to 0.2.

[0058] After constructing the LSTM network model for Class A rooms, train the LSTM network model using the Class A room training dataset. During training, the training data from the training dataset is input into the LSTM network model in batches; for example, each batch of input training data may include 32 samples.

[0059] The error between the predicted value and the true value is calculated by backpropagation algorithm. This process specifically includes the following steps A321 to A322.

[0060] Step A321: Input the historical indoor and outdoor environmental perception data from the training dataset of Class A rooms into the LSTM network model for Class A rooms in a time series order. The data is passed layer by layer in the LSTM network model. After the LSTM layers extract the features of the time series data and the fully connected layers map them, the predicted value of the indoor temperature is finally obtained. For example, given the indoor temperature and humidity of Class A room at a certain moment, as well as the outdoor temperature and wind speed, the LSTM network model outputs the predicted value of the indoor temperature of Class A room at that moment.

[0061] Step A322: Compare the predicted indoor temperature output by the LSTM network model with the actual indoor temperature values ​​at the corresponding times in the training dataset, and calculate the mean squared error (MSE). The formula for calculating the mean squared error is as follows: Where n is the number of samples included in the training dataset. It is the true value of the i-th sample in the training dataset. This is the predicted value of the i-th sample in the training dataset. Assuming a batch of training data contains 32 samples, the mean squared error of this batch of training data can be calculated by substituting the predicted value and the true value of each sample into the formula for calculating the mean squared error.

[0062] Adjusting the parameters of the LSTM network model, including weights and biases, to gradually reduce the mean squared error involves steps A323 to A324.

[0063] Step A323: Using the backpropagation algorithm, starting from the output layer of the LSTM network model, propagate the mean squared error back along the network connections. During this process, calculate the gradient of each parameter (weight and bias) with respect to the mean squared error. Taking the weights in the LSTM layer as an example, according to the chain rule, calculate the derivative of the weights with respect to the mean squared error, which is the gradient. This gradient represents the impact of a small change in the weights on the mean squared error.

[0064] Step A324: Based on the calculated gradient, use the stochastic gradient descent (SGD) optimization algorithm to adjust the parameters of the LSTM network model. The parameter update formula for stochastic gradient descent is as follows: ,in, This is the updated weight. This is the current weight. It's the learning rate. Weight The gradient with respect to the mean squared error. Learning rate. This determines the step size for parameter updates, for example, setting... =0.001. Following the parameter update formula, all weights and biases in the LSTM network model are updated, gradually reducing the error. During training, the steps of forward propagation, error calculation, backpropagation gradient calculation, and parameter update (steps A321, A322, A323, and A324) are repeated until the mean squared error of the LSTM network model on the test dataset reaches the set convergence target, completing the training of the temperature prediction model for room A.

[0065] Similarly, using the same method as described above for constructing and training the LSTM network model corresponding to room type A, we can construct and train LSTM network models corresponding to other room types such as room type B and room type C, thereby obtaining the corresponding temperature prediction models.

[0066] Specifically, during the training of the LSTM network model, it is crucial to closely monitor its performance on the test dataset. When the mean squared error of the LSTM network model on the test dataset is less than a pre-set specific value, such as 0.5℃, the LSTM network model can be considered to have reached the convergence objective, and training can be stopped at this point. Afterward, the trained LSTM network model is used to make predictions on the test dataset, and its performance is comprehensively evaluated using various assessment metrics such as root mean square error and mean absolute error. This ensures that the LSTM network model can accurately learn the relationship between indoor and outdoor environmental data and indoor temperature changes for various room types, such as Class A, Class B, and Class C rooms.

[0067] Step A330: Use the preprocessed indoor and outdoor environmental perception data as input data for the temperature prediction model, and use the temperature prediction model to predict the future trend of indoor temperature change in each heated room to obtain the temperature prediction change curve.

[0068] Specifically, preprocessed indoor and outdoor environmental perception data are used as input data and fed into a trained temperature prediction model. Based on learned patterns, the temperature prediction model predicts future indoor temperature changes corresponding to the input data, thus obtaining a temperature prediction curve as output data. For example, given the current indoor temperature and humidity of each heated room, as well as outdoor temperature and wind speed data, the temperature prediction model can calculate and predict the temperature changes of each heated room over the next few hours, presenting the results as a temperature prediction curve, thus visually demonstrating the trend of indoor temperature changes in each heated room.

[0069] By using temperature prediction models to predict future trends in indoor temperature for each heated room, a strong basis can be provided for adjusting the control parameters of the geothermal heating system, enabling the geothermal heating system to more accurately meet indoor comfort temperature requirements while reducing energy consumption.

[0070] Step A400: When the fluctuation of the temperature prediction curve reaches the adjustment requirement, with the goal of minimizing the preset comfortable room temperature and geothermal heating energy consumption, the control parameters of the geothermal heating system used in each heated room are optimized according to the temperature prediction curve to obtain the optimal geothermal control parameters.

[0071] Specifically, a preset comfortable room temperature is an ideal temperature value for a heated room that is pre-set by the user. A geothermal heating system is a combination of devices that utilizes geothermal energy for indoor heating. By adjusting its control parameters, the indoor temperature of the heated room can be regulated. The optimal geothermal control parameters are determined when the fluctuation of the temperature prediction curve reaches the pre-set adjustment requirements. The goal is to achieve the preset comfortable room temperature and minimize geothermal heating energy consumption. This involves considering the temperature prediction curve, power consumption, and water temperature thresholds of the geothermal heating system, and optimizing the various control parameters, including valve opening and supply water temperature, to obtain the optimal combination of values ​​for these parameters when the target evaluation result is maximized.

[0072] By optimizing the control parameters of the geothermal heating system used in each heated room based on the temperature prediction curve when the fluctuation of the temperature change curve reaches the adjustment requirements, with the goal of minimizing the preset comfortable room temperature and geothermal heating energy consumption, the optimal geothermal control parameters can be obtained. When the geothermal heating system is controlled using the optimal geothermal control parameters, the indoor temperature of the heated room can reach the preset comfortable room temperature, while reducing geothermal heating energy consumption.

[0073] For example, in step A400, with the goal of minimizing the preset comfortable room temperature and the energy consumption of geothermal heating, the control parameters of the geothermal heating system used in each heated room are optimized according to the temperature prediction change curve to obtain the optimal geothermal control parameters, including the following steps A410 to A440.

[0074] Step A410: Collect geothermal heating energy consumption data of the geothermal heating system under different control parameters, and fit the relationship function between the corresponding control parameters and energy consumption of the geothermal heating system based on the geothermal heating energy consumption data under different control parameters.

[0075] Specifically, the control parameters of the geothermal heating system may include valve opening degree and water supply temperature. Geothermal heating energy consumption data can be used as evaluation data to fit the relationship function between the corresponding control parameters and energy consumption of the geothermal heating system through step A410.

[0076] For example, in step A410, the relationship function between the control parameters and energy consumption of the geothermal heating system is fitted based on the geothermal heating energy consumption data under different control parameters, including: fitting the relationship function between the control parameters and energy consumption using regression analysis based on the geothermal heating energy consumption data under different control parameters.

[0077] Specifically, in actual operation, step A410 can monitor and record the energy consumption of the geothermal heating system under different combinations of valve opening and water supply temperature. For example, over a month, different valve opening levels such as 30%, 40%, and 50% can be set, along with different water supply temperatures such as 25℃, 30℃, and 35℃, and the energy consumption data per unit time under each value combination can be recorded. Based on this large amount of data, regression analysis can be used to fit the relationship function between control parameters and energy consumption. This process specifically includes steps A411 to A414.

[0078] Step A411: Determine the variables of the study as valve opening (x), water supply temperature (y), and energy consumption (E). Following the actual operation, continuously monitor and record energy consumption data per unit time (e.g., per hour) using different combinations of valve opening (x) and water supply temperature (y). During this process, a large number of observed energy consumption E values ​​corresponding to different combinations of (x, y) values ​​will be obtained, forming a sample dataset. This sample dataset may include, for example... , Numerous sample points, etc.

[0079] Step A412: Considering the potential nonlinear relationship between energy consumption, valve opening, and water supply temperature, a common polynomial regression model is a suitable choice. Let's start with a simple quadratic polynomial model assumption, that is, assuming the relationship between energy consumption E and valve opening x and water supply temperature y is E=a +by+c, where a, b, and c are coefficients to be determined.

[0080] Step A413: Estimate the regression coefficients a, b, and c using the least squares method. The principle of the least squares method is to minimize the sum of squared errors between the observed values ​​of the sample data and the predicted values ​​of the relational model. For the relational model assumed above, the sum of squared errors... ,in, The number of samples included in the sample dataset. Let the valve opening be the j-th sample in the sample dataset. Let be the water supply temperature of the j-th sample in the sample dataset. Let S be the energy consumption of the j-th sample in the dataset. By taking the partial derivatives of S with respect to a, b, and c, and setting the partial derivatives equal to 0, we obtain a system of three equations, which includes: Take the partial derivative with respect to a: =0; Take the partial derivative with respect to b: =0; Take the partial derivative with respect to c: =0; Solving the above system of equations, we get a = 0.5, b = 0.3, and c = 10.

[0081] Step A414: Substituting the above coefficients into the relationship model between energy consumption E, valve opening degree x, and water supply temperature y from step A412, we obtain E=0.5. +0.3y+10, E=0.5 +0.3y+10 can be used as the relationship function between the control parameters and energy consumption of the geothermal heating system.

[0082] Step A420: Based on the relationship function between control parameters and energy consumption, construct an energy consumption objective function with the goal of minimizing geothermal heating energy consumption.

[0083] Specifically, the energy consumption objective function is a function constructed based on the relationship between control parameters and energy consumption, with the goal of minimizing the energy consumption of geothermal heating.

[0084] Specifically, the relationship function between the control parameters and energy consumption of the local thermal heating system is E=0.5. When +0.3y+10, based on this relationship function, an energy consumption objective function is constructed with the goal of minimizing geothermal heating energy consumption. In this case, the energy consumption objective function can be set as minimizeE=0.5. +0.3y+10.

[0085] Step A430: With the preset comfortable room temperature as the target, construct a comfort deviation penalty function, merge the energy consumption target function and the comfort deviation penalty function to construct a target evaluation function.

[0086] Specifically, the comfort deviation penalty function is constructed by setting a preset comfortable room temperature as the target and defining multiple deviation ranges and corresponding penalty values. The target evaluation function is obtained by merging the energy consumption target function and the comfort deviation penalty function.

[0087] For example, a comfort deviation penalty function is constructed with a preset comfortable room temperature as the target, specifically including the following steps A431 to A432.

[0088] Step A431: Set multiple deviation ranges and corresponding penalty values ​​based on the preset comfortable room temperature.

[0089] Specifically, the multi-level deviation ranges are different temperature deviation ranges set based on a preset comfortable room temperature. The penalty value is used to measure the degree of discomfort or impact on the target when the actual room temperature deviates from the preset comfortable room temperature.

[0090] When setting multiple deviation ranges and corresponding penalty values, it is necessary to comprehensively consider the human body's sensitivity to temperature and actual heating needs. Taking a preset comfortable room temperature of 22℃ as an example, according to human thermal comfort research, most people experience almost no significant discomfort within a temperature deviation of ±1℃. Therefore, the penalty value can be set to 0 when the actual room temperature deviates from 22℃ by ±1℃. When the room temperature is lower than the comfortable room temperature, people's discomfort will be more obvious. Therefore, the penalty value can be set to 1 when the room temperature is in the range of (20℃-21℃) and (23℃-24℃); 3 when the room temperature is in the range of (18℃-20℃) and (24℃-26℃); and 5 when the room temperature deviation is greater than 6℃. These penalty values ​​were derived by the inventors of this application through extensive user experience surveys and experimental data, and can accurately reflect the degree of discomfort people experience under different temperature deviations.

[0091] Step A432: Construct a comfort deviation penalty function based on the multi-level deviation intervals and corresponding penalty values.

[0092] Assuming the actual room temperature is T, the comfort deviation penalty function P can be represented by a piecewise function: when |T When |22≤1, P=0; when 1<|T When |2|≤2, P=1; when 2<|T When |22≤4, P=3; when |T When 22|>4, P=5.

[0093] Thus, in the process of optimizing the control parameters of the geothermal heating system in steps A430 and A440, the comfort deviation penalty function can be used as a quantitative indicator to measure comfort. It can be combined with the energy consumption objective function to construct the objective evaluation function, thereby achieving the optimization of control parameters with the goal of maximizing the preset comfortable room temperature and minimizing the geothermal heating energy consumption.

[0094] The energy consumption objective function and the comfort deviation penalty function are combined to construct the objective evaluation function J=E+λP, where λ is a weighting coefficient used to balance the importance of energy consumption and comfort, and its value ranges from (0,1). The specific value can be selected based on experience and different types of rooms.

[0095] Step A440: Using the maximum power and water temperature safety threshold of the geothermal heating system as constraints, evaluate and optimize the control parameters of the geothermal heating system according to the objective evaluation function until the evaluation target value or the maximum number of searches is reached, and obtain the optimal geothermal control parameters. The optimal geothermal control parameters are the optimal combination of values ​​of each control parameter of the geothermal heating system when the objective evaluation result is maximized.

[0096] For example, in step A440, the control parameters of the geothermal heating system are evaluated and optimized according to the objective evaluation function, using the maximum power and water temperature safety threshold of the geothermal heating system as constraints. This includes: using the maximum power, minimum water temperature safety threshold, and maximum water temperature safety threshold of the geothermal heating system as constraints, and using a genetic optimization algorithm to optimize the control parameters of the geothermal heating system according to the objective evaluation function.

[0097] Specifically, in the process of optimizing the control parameters of the geothermal heating system, the maximum power of the system is used as the benchmark. The minimum safe water temperature threshold is Maximum safe water temperature threshold As constraints, a genetic optimization algorithm can be used to optimize the control parameters of the geothermal heating system based on the objective evaluation function.

[0098] When using a genetic optimization algorithm to optimize the control parameters of a geothermal heating system, a set of valve opening and water supply temperature combinations is first initialized as an initial population, with each combination representing an individual in the genetic optimization algorithm population. For each individual in the population, it is checked whether it meets the constraint condition that the system power corresponding to the valve opening and water supply temperature does not exceed the limit. And the water supply temperature is and Between. For individuals that meet the constraints, their target evaluation function value is calculated using the function J=E+λP.

[0099] Then, through genetic operations such as selection (e.g., roulette wheel selection), crossover (exchanging some genes), and mutation (changing some gene values), a new population is generated. Specifically, roulette wheel selection is used to select individuals from the current population. Roulette wheel selection calculates the selection probability based on the objective evaluation function value of each individual; individuals with higher objective evaluation function values ​​have a higher probability of being selected, much like dividing a roulette wheel into regions, with individuals with higher fitness corresponding to larger regions and being more likely to be selected by the pointer. Selected individuals are then paired up for crossover, randomly selecting gene exchange points to exchange some genes, thus creating new individual combinations. For example, two individuals might exchange gene segments related to valve opening and water temperature, allowing the new individual to incorporate characteristics of the parent individuals. Mutation involves randomly changing some gene values ​​of individuals, such as randomly fine-tuning the valve opening or water temperature values ​​of a particular individual, introducing new genes into the population and preventing the algorithm from getting trapped in local optima. Through this series of selection, crossover, and mutation operations, a new population is ultimately generated.

[0100] The above genetic operation process is repeated continuously and iterated until the target evaluation function J is less than a preset specific value, or the maximum number of searches is reached. At this point, the optimal combination of valve opening and water supply temperature for the best individual is the optimal combination of valve opening and water supply temperature that can minimize geothermal heating energy consumption while ensuring a comfortable indoor temperature. When the combination of valve opening and water supply temperature of the geothermal heating system is this optimal combination, geothermal heating energy consumption can be minimized as much as possible while ensuring a comfortable indoor temperature.

[0101] Step A500: Dynamically adjust the control parameters of the geothermal heating system based on the optimal geothermal control parameters.

[0102] Specifically, the optimal geothermal control parameters aim to achieve a preset comfortable room temperature and minimize geothermal heating energy consumption. They can comprehensively consider factors such as the temperature prediction curve of each heated room, the maximum power of the geothermal heating system, and the water temperature safety threshold. This can be the optimal combination of valve opening and water supply temperature for the geothermal heating system.

[0103] For example, assuming that in a certain region, the optimal geothermal control parameters include a valve opening of 40% and a water supply temperature of 45℃, then step A500 can dynamically adjust the control parameters of the geothermal heating system accordingly, adjusting the valve opening to 40% and the water supply temperature to 45℃.

[0104] The geothermal heating system can precisely control the valve opening degree by adjusting the valve opening value. Changes in valve opening directly affect the hot water flow rate. Increasing the valve opening increases the hot water flow rate, resulting in more heat received in the heated room and a corresponding rise in indoor temperature. Conversely, decreasing the valve opening reduces the hot water flow rate, leading to less heat received and a drop in indoor temperature. With the optimal geothermal control parameters including a valve opening of 40%, adjusting the valve opening of the geothermal heating system to 40% maintains a hot water flow rate that meets indoor temperature requirements without wasting energy.

[0105] The temperature of the water supply determines the amount of heat carried by the hot water. When the optimal geothermal control parameters include a water supply temperature of 45℃, adjusting the water supply temperature of the geothermal heating system to 45℃ can optimize energy consumption while maintaining a comfortable room temperature. The water supply temperature can be adjusted using heating equipment or other control devices (flow regulating valves, temperature controllers, mixing devices, etc.). Flow regulating valves indirectly affect the water supply temperature by adjusting the hot water flow. Temperature controllers monitor and provide feedback on the water supply temperature signal, precisely controlling the operation of the heating equipment. Mixing devices regulate the water supply temperature by mixing water of different temperatures, thus stabilizing it at 45℃. When the indoor temperature of the heated room decreases, it may be necessary to appropriately increase the water supply temperature to maintain a comfortable indoor temperature and increase the heat received by the heated room. Conversely, when the indoor temperature of the heated room increases, the water supply temperature can be decreased to reduce the heat received by the heated room, avoiding excessively high indoor temperatures and energy waste.

[0106] By dynamically and precisely adjusting the valve opening and water supply temperature of the geothermal heating system using optimal geothermal control parameters, the performance of the geothermal heating system can be effectively improved, achieving the dual goals of comfort and energy saving.

[0107] In particular, during actual operation, the temperature prediction model and its parameters can be continuously optimized based on actual operating data to continuously improve the model's prediction effect, more accurately predict indoor temperature change trends, and dynamically optimize the control parameters of the geothermal heating system based on more accurate indoor temperature change trends, thereby improving the subsequent geothermal heating control effect.

[0108] The geothermal heating temperature control method based on environmental perception provided by the embodiments of the present invention can accurately predict the indoor temperature change trend of the heated room compared with the prior art, and dynamically adjust the control parameters of the geothermal heating system according to the indoor temperature change trend, so as to achieve the preset comfortable room temperature and minimize geothermal heating energy consumption, thereby improving indoor comfort while reducing heating energy consumption.

[0109] Another embodiment of the present invention relates to an environment-sensing geothermal heating temperature control system for implementing the environment-sensing geothermal heating temperature control method described in the above embodiments.

[0110] like Figure 2 As shown, the geothermal heating temperature control system based on environmental perception includes a sensing data acquisition module 201, a sensing data preprocessing module 202, a temperature curve acquisition module 203, a geothermal parameter acquisition module 204, and a parameter dynamic adjustment module 205.

[0111] The sensing data acquisition module 201 is connected to the indoor sensing devices and outdoor monitoring channels of each heating room, and is used to acquire indoor and outdoor environmental sensing data of each heating room using the indoor sensing devices and outdoor monitoring channels.

[0112] The sensing data preprocessing module 202 is used to preprocess the sensing data of indoor and outdoor environments.

[0113] The temperature curve acquisition module 203 is used to predict the indoor temperature change trend of each heating room based on the preprocessed indoor and outdoor environmental sensing data, and obtain the predicted temperature change curve.

[0114] The geothermal parameter acquisition module 204 is used to optimize the control parameters of the geothermal heating system used in each heated room based on the temperature prediction curve when the fluctuation of the temperature prediction curve reaches the adjustment requirements, with the goal of minimizing the preset comfortable room temperature and geothermal heating energy consumption.

[0115] The parameter dynamic adjustment module 205 is used to dynamically adjust the control parameters of the geothermal heating system according to the optimal geothermal control parameters.

[0116] The specific implementation method of the geothermal heating temperature control system based on environmental perception provided in the embodiments of the present invention can be found in the geothermal heating temperature control method based on environmental perception provided in the embodiments of the present invention, and will not be repeated here.

[0117] The geothermal heating temperature control method based on environmental perception provided by the embodiments of the present invention can accurately predict the indoor temperature change trend of the heated room compared with the prior art, and dynamically adjust the control parameters of the geothermal heating system according to the indoor temperature change trend, so as to achieve the preset comfortable room temperature and minimize geothermal heating energy consumption, thereby improving indoor comfort while reducing heating energy consumption.

[0118] Those skilled in the art will understand that the above embodiments are specific implementations of the present invention, and in practical applications, various changes can be made in form and detail without departing from the spirit and scope of the present invention.

Claims

1. A geothermal heating temperature control method based on environmental perception, characterized in that, The geothermal heating temperature control method based on environmental perception includes: By utilizing the indoor sensing devices and outdoor monitoring channels of each heating room, indoor and outdoor environmental sensing data of each heating room are obtained. The indoor and outdoor environmental perception data are preprocessed; Based on the preprocessed indoor and outdoor environmental sensing data, the indoor temperature change trend of each heating room is predicted to obtain a temperature prediction change curve. When the fluctuation of the temperature prediction curve reaches the adjustment requirement, with the goal of minimizing the preset comfortable room temperature and geothermal heating energy consumption, the control parameters of the geothermal heating system used in each of the heating rooms are optimized according to the temperature prediction curve to obtain the optimal geothermal control parameters. The control parameters of the geothermal heating system are dynamically adjusted based on the optimal geothermal control parameters.

2. The geothermal heating temperature control method based on environmental perception according to claim 1, characterized in that, The method of acquiring indoor and outdoor environmental sensing data for each heated room using indoor sensing devices and outdoor monitoring channels includes: Temperature sensors and humidity sensors are installed in each of the heating rooms, and indoor environmental perception data of each heating room are obtained using the temperature sensors and humidity sensors. Based on the geographical location of each heating room, the outdoor temperature, wind speed, and light intensity of each heating room are obtained through a weather forecast data interface to obtain outdoor environmental perception data for each heating room.

3. The geothermal heating temperature control method based on environmental perception according to claim 2, characterized in that, The step of predicting the indoor temperature change trend of each of the heating rooms based on the preprocessed indoor and outdoor environmental sensing data to obtain a temperature prediction change curve includes: Using the historical data of indoor and outdoor environmental perception of each of the heating rooms, a training dataset and a test dataset are constructed respectively. The training dataset and the test dataset both include the historical data of indoor environmental perception and the corresponding historical data of outdoor environmental perception of each of the heating rooms. The long short-term memory network model is trained and tested using the training dataset and the test dataset until the convergence target of the long short-term memory network model is reached, thereby obtaining the temperature prediction model. The preprocessed indoor and outdoor environmental perception data are used as input data for the temperature prediction model. The temperature prediction model is then used to predict the future temperature change trend of each of the heating rooms, resulting in the temperature prediction change curve.

4. The geothermal heating temperature control method based on environmental perception according to claim 3, characterized in that, The goal is to minimize the preset comfortable room temperature and geothermal heating energy consumption. Based on the predicted temperature change curve, the control parameters of the geothermal heating system used in each of the heated rooms are optimized to obtain the optimal geothermal control parameters, including: Collect geothermal heating energy consumption data of the geothermal heating system under different control parameters, and fit the relationship function between the control parameters and energy consumption of the geothermal heating system based on the geothermal heating energy consumption data under different control parameters. Based on the relationship function between the control parameters and energy consumption, an energy consumption objective function is constructed with the goal of minimizing geothermal heating energy consumption. Using the preset comfortable room temperature as the target, a comfort deviation penalty function is constructed. The energy consumption target function and the comfort deviation penalty function are then merged to construct a target evaluation function. Using the maximum power and water temperature safety threshold of the geothermal heating system as constraints, the control parameters of the geothermal heating system are evaluated and optimized according to the target evaluation function until the evaluation target value or the maximum number of searches is reached, so as to obtain the optimal geothermal control parameters. The optimal geothermal control parameters are the optimal combination of values ​​of each control parameter of the geothermal heating system when the target evaluation result is maximized.

5. The geothermal heating temperature control method based on environmental perception according to claim 4, characterized in that, The step of fitting a relationship function between the control parameters and energy consumption of the geothermal heating system based on the geothermal heating energy consumption data under different control parameters includes: Based on the geothermal heating energy consumption data under different control parameters, a regression analysis method was used to fit the relationship function between the control parameters and energy consumption.

6. The geothermal heating temperature control method based on environmental perception according to claim 4, characterized in that, The step of constructing a comfort deviation penalty function with the preset comfortable room temperature as the target includes: With the preset comfortable room temperature as the target, multiple deviation ranges and corresponding penalty values ​​are set; Based on the multi-level deviation ranges and corresponding penalty values, the comfort deviation penalty function is constructed.

7. The geothermal heating temperature control method based on environmental perception according to claim 4, characterized in that, The process of evaluating and optimizing the control parameters of the geothermal heating system based on the objective evaluation function, using the maximum power and water temperature safety threshold of the geothermal heating system as constraints, includes: Using the maximum power, minimum safe water temperature threshold, and maximum safe water temperature threshold of the geothermal heating system as constraints, a genetic optimization algorithm is used to optimize the control parameters of the geothermal heating system according to the objective evaluation function.

8. The geothermal heating temperature control method based on environmental perception according to any one of claims 1 to 7, characterized in that, The preprocessing of the indoor and outdoor environmental perception data includes: Set the window size for the sliding window; Based on the window size of the sliding window, the indoor and outdoor environmental perception data are processed using a moving average filter.

9. The geothermal heating temperature control method based on environmental perception according to claim 8, characterized in that, The size of the sliding window ranges from 5 to 10 data points in the indoor and outdoor environmental perception data.

10. A geothermal heating temperature control system based on environmental perception, characterized in that, For implementing the geothermal heating temperature control method based on environmental perception according to any one of claims 1 to 9, the geothermal heating temperature control system based on environmental perception comprises: The sensing data acquisition module is connected to the indoor sensing devices and outdoor monitoring channels of each heating room, and is used to acquire indoor and outdoor environmental sensing data of each heating room using the indoor sensing devices and the outdoor monitoring channels. The sensing data preprocessing module is used to preprocess the indoor and outdoor environmental sensing data; The temperature curve acquisition module is used to predict the indoor temperature change trend of each heating room based on the preprocessed indoor and outdoor environmental sensing data, and obtain the predicted temperature change curve. The geothermal parameter acquisition module is used to optimize the control parameters of the geothermal heating system used in each of the heating rooms based on the temperature prediction curve when the fluctuation of the temperature prediction curve reaches the adjustment requirements, with the goal of minimizing the preset comfortable room temperature and geothermal heating energy consumption. The parameter dynamic adjustment module is used to dynamically adjust the control parameters of the geothermal heating system according to the optimal geothermal control parameters.

Images