Geothermal coupling heat supply system dynamic regulation and control method and system based on multistage load prediction

Abstract

The invention provides a geothermal coupling heat supply system dynamic regulation and control method and system based on multistage load prediction, and belongs to the technical field of smart energy regulation and control. According to the method, a load prediction value is obtained through hyper-parameter optimization and cross validation by collecting a system operation state and environmental parameters and utilizing a multi-stage load prediction model pool containing multiple candidate models; and load intervals are divided, a multi-equipment cooperative regulation and control strategy is generated in combination with resource, equipment and energy efficiency constraints, an execution mechanism is controlled to be linked, and closed-loop regulation and control are formed through real-time feedback and dynamic correction. The system comprises a data acquisition module, a load prediction module and the like, technologies such as recharge temperature protection are integrated, intelligent and accurate regulation and control of the geothermal coupling heat supply system are achieved, and the energy utilization rate and the operation stability are improved.

Description

Technical Field

[0001] This application relates to the field of smart energy regulation technology, and more specifically, to a dynamic regulation method and system for geothermal coupled heating systems based on multi-level load forecasting. Background Technology

[0002] Geothermal energy, as a clean and renewable energy source, plays a crucial role in achieving the "dual carbon" goal when applied in the heating sector. Existing geothermal coupled heating systems largely rely on basic automated control combined with manual experience-based regulation, lacking a robust load forecasting mechanism and a comprehensive coordinated control strategy, making it difficult to adapt to the complex and ever-changing end-user heating demands.

[0003] The current system suffers from several problems: First, the load forecast accuracy is insufficient, failing to anticipate changes in heating demand and leading to an imbalance between energy supply and demand. Second, equipment control lacks coordination; the operating parameters of heat exchange equipment, heat pump units, geothermal wells, and external energy stations are not optimized in a coordinated manner, causing heat pumps to operate inefficiently and resulting in low geothermal resource utilization. Third, data acquisition reliability is lacking, with an ineffective data verification mechanism affecting the accuracy of control strategies. Fourth, the system has limited functionality, failing to fully explore the multi-scenario application potential of geothermal waste heat, and issues such as reinjection temperature control and frequent equipment start-ups and shutdowns remain unresolved, hindering the system's efficient and stable operation. Therefore, a dynamic control scheme with accurate load forecasting and global coordinated control capabilities is urgently needed to improve the operational efficiency and reliability of geothermal coupled heating systems. Summary of the Invention

[0004] This invention aims to address the technical problems of low control precision, poor equipment coordination, and insufficient energy utilization in existing geothermal coupled heating systems. It provides a dynamic control method and system for geothermal coupled heating systems based on multi-level load forecasting. This method collects system operating status data and environmental parameters, utilizes a multi-level load forecasting model pool containing various candidate models, and obtains load forecast values ​​through hyperparameter optimization and cross-validation. Based on the load forecast values, load intervals are divided, and a multi-equipment coordinated control strategy is generated by combining resource supply, equipment characteristics, and energy efficiency constraints to control the coordinated operation of various actuators. The prediction model and control strategy are dynamically corrected through real-time feedback data, forming a closed-loop control system. Simultaneously, this method incorporates technologies such as geothermal reinjection temperature protection, heat pump energy efficiency optimization, and multi-scenario linkage. The system includes modules for data acquisition, multi-level load forecasting, dynamic control decision-making, equipment execution, and feedback optimization. This invention achieves intelligent and precise control of geothermal coupled heating systems, improving energy utilization efficiency and system operational stability.

[0005] This application provides a dynamic control method for geothermal coupled heating systems based on multi-level load forecasting, including the following steps: Collect operational status data and environmental parameters of heat exchange equipment, heat pump units, geothermal wells, external energy stations and end users in the geothermal coupled heating system; Based on a pre-set multi-level load prediction model pool, the heating load within a pre-set time period is predicted to obtain the load prediction value; Based on the load forecast values, load intervals are divided, and a multi-equipment coordinated control strategy is generated by combining geothermal resource supply capacity, equipment operating characteristics and energy efficiency constraints. Based on the aforementioned multi-device collaborative control strategy, the actions of each actuator are controlled to achieve the coordinated operation of heat exchange equipment, heat pump units, geothermal well flow regulating actuators, and external energy stations. Real-time system operation feedback data after regulation is collected, and the load prediction model and multi-device collaborative regulation strategy are dynamically corrected.

[0006] In the dynamic control method for geothermal coupled heating system based on multi-level load forecasting described in this application, the method of forecasting the heating load within a preset time period based on a pre-set multi-level load forecasting model pool to obtain the load forecast value is as follows: The multi-level load forecasting model pool includes a time series model, a tree model fusion model, and a BP neural network model; The optimal prediction model that best suits the current working conditions is selected through hyperparameter optimization and cross-validation. The hyperparameter optimization employs a Bayesian optimization algorithm, and the cross-validation uses a nested cross-validation method to improve load prediction accuracy by avoiding the risk of overfitting.

[0007] In the dynamic control method for geothermal coupled heating system based on multi-level load forecasting described in this application, the step of dividing the load interval according to the load forecast value specifically includes: Based on the predicted load value and the system's preset load interval division rules, low load interval, medium load interval, high load interval, and overload interval are obtained; Each of the aforementioned load intervals is associated with a preset equipment combination scheme; During load interval switching, a hysteresis switching mechanism is adopted, and a first hysteresis threshold is set according to the system equipment operation stability requirements to realize load interval switching control.

[0008] In the dynamic control method for geothermal coupled heating systems based on multi-level load forecasting described in this application, the generation of a multi-device collaborative control strategy specifically includes: Based on system load demand, equipment operating characteristics and energy supply capacity, a coordinated control strategy is derived for switching combinations, geothermal well flow regulation parameters, and external energy station supplementary energy supply parameters. According to the geothermal reinjection temperature control requirements, the reinjection temperature is controlled to the preset target range by pre-cooling the outlet of the four-stage heat exchange equipment. When the reinjection temperature exceeds the preset threshold, a forced load adjustment command is triggered.

[0009] In the dynamic control method for geothermal coupled heating systems based on multi-level load forecasting described in this application, the coordinated control strategy further includes: A dual temperature and load regulation mechanism is adopted to dynamically adjust the number and combination of heat pump units in operation, ensuring that the load rate of the heat pump units is maintained within the preset optimal energy efficiency range.

[0010] In the dynamic control method for geothermal coupled heating system based on multi-level load forecasting described in this application, the supplementary energy supply from the external energy station further includes: When the local heating system reaches its maximum power supply capacity but still cannot meet the load demand, an external energy station is activated, and the load gap is supplemented by adjusting the flow rate of the coupling main actuator.

[0011] In the dynamic control method for geothermal coupled heating system based on multi-level load prediction described in this application, the acquisition of operating status data includes: Based on the data collection reliability requirements, a triple data verification mechanism was established; The system acquires real-time data collected by the sensors on the device itself, redundant backup data collected by the independent calibration instrument, and calibration data calculated based on the thermodynamic energy balance formula. The collection and verification of operational status parameters are achieved through the collaborative verification of three types of data.

[0012] The dynamic control method for geothermal coupled heating systems based on multi-level load prediction described in this application further includes: Establish a linkage mechanism with the intelligent snow melting system based on the system's multi-scenario energy supply needs; When the environmental monitoring parameters reach the preset snow melting trigger conditions, the geothermal waste heat distribution parameters are adjusted according to the snow melting load demand, and the actuator of the snow melting circulation pipeline is activated in conjunction with the mechanism.

[0013] Secondly, this application provides a dynamic control system for a geothermal coupled heating system based on multi-level load forecasting, characterized in that it includes: Data acquisition module: used to collect operating status data and environmental parameters of heat exchange equipment, heat pump units, geothermal wells, external energy stations and end users. The data acquisition module integrates a triple data verification unit. Multi-level load forecasting module: includes a preset model pool and hyperparameter optimization unit, used to predict the heating load within a preset time period and output the load forecast value; Dynamic control decision module: used to divide the load range according to the load forecast value, and generate a multi-equipment coordinated control strategy by combining the geothermal resource supply capacity, equipment operating characteristics and energy efficiency constraints; Equipment execution module: includes heat exchange equipment, heat pump unit, flow regulation actuator and external energy station interface, used to receive the coordinated control strategy and execute corresponding actions; Feedback optimization module: Used to collect system operation feedback data after regulation and dynamically correct the prediction model of the multi-level load prediction module and the regulation strategy of the dynamic regulation decision module.

[0014] The system also includes a memory and a processor. The memory contains a program for a dynamic control method of a geothermal coupled heating system based on multi-level load forecasting. When the program for the dynamic control method of a geothermal coupled heating system based on multi-level load forecasting is executed by the processor, it implements the following steps: Collect operational status data and environmental parameters of heat exchange equipment, heat pump units, geothermal wells, external energy stations and end users in the geothermal coupled heating system; Based on a pre-set multi-level load prediction model pool, the heating load within a pre-set time period is predicted to obtain the load prediction value; Based on the load forecast values, load intervals are divided, and a multi-equipment coordinated control strategy is generated by combining geothermal resource supply capacity, equipment operating characteristics and energy efficiency constraints. Based on the aforementioned multi-device collaborative control strategy, the actions of each actuator are controlled to achieve the coordinated operation of heat exchange equipment, heat pump units, geothermal well flow regulating actuators, and external energy stations. Real-time system operation feedback data after regulation is collected, and the load prediction model and multi-device collaborative regulation strategy are dynamically corrected.

[0015] As can be seen from the above, the dynamic control method and system for geothermal coupled heating systems based on multi-level load forecasting provided by this invention aims to solve the technical problems of low control accuracy, poor equipment coordination, and insufficient energy utilization in existing geothermal coupled heating systems, and provides a dynamic control method and system for geothermal coupled heating systems based on multi-level load forecasting. This method first collects operating status data and environmental parameters from heat exchange equipment, heat pump units, geothermal wells, external energy stations, and end users, and ensures data reliability through a triple data verification mechanism; based on a multi-level load forecasting model pool including time-series models, tree model fusion models, and BP neural network models, it uses Bayesian optimization algorithms and nested cross-validation to select the optimal model, achieving accurate load forecasting within a preset future time period; according to the load forecast value and preset rules, it divides the system into low, medium, high, and overload zones, and associates each zone with corresponding equipment combination schemes, using a lag switching mechanism to avoid frequent equipment start-ups and shutdowns; combined with system load... Based on load demand, equipment operating characteristics, and energy supply capacity, a coordinated control strategy is generated, including equipment switching combinations, geothermal well flow regulation parameters, and external energy station supplementary energy supply parameters. This strategy incorporates a dual protection logic for geothermal reinjection temperature and a dual regulation mechanism for heat pump temperature and load, ensuring that the reinjection temperature meets standards and the heat pump operates within its optimal energy efficiency range. The control strategy controls the coordinated operation of various actuators and establishes a linkage mechanism with the intelligent snow melting system to realize multi-scenario utilization of geothermal waste heat. Finally, by collecting real-time system operation feedback data, the load prediction model and control strategy are dynamically corrected to form a closed-loop control system. The corresponding system includes a data acquisition module, a multi-level load prediction module, a dynamic control decision module, an equipment execution module, and a feedback optimization module. These modules work collaboratively to achieve intelligent, precise, and efficient operation of the geothermal coupled heating system.

[0016] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A high-level flowchart of a dynamic control method for a geothermal coupled heating system based on multi-level load prediction, provided in an embodiment of this application, is used to control geothermal coupled heating.

[0019] Figure 2 A flowchart of a dynamic control method for a geothermal coupled heating system based on multi-level load prediction provided in an embodiment of this application; Figure 3 A flowchart illustrating the division of load zones in a dynamic control method for a geothermal coupled heating system based on multi-level load prediction, provided in an embodiment of this application. Figure 4 A flowchart illustrating the generation of a multi-device collaborative control strategy for a geothermal coupled heating system dynamic control method based on multi-level load prediction, provided in an embodiment of this application. Figure 5 The diagram shows the structure of the dynamic control system for a geothermal coupled heating system based on multi-level load prediction, as provided in the embodiments of this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0021] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first" and "second" are used only to distinguish descriptions and should not be construed as indicating or implying relative importance. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0022] Please refer to Figure 1 , Figure 1This is a high-level flowchart of a dynamic control method for a geothermal coupled heating system based on multi-level load forecasting, as described in some embodiments of this application. The high-level flowchart can be summarized as follows: First, operating status parameters and environmental monitoring parameters of heat exchange equipment, heat pump units, geothermal wells, external energy stations, and end users in the geothermal coupled heating system are acquired through a sensor network, and data reliability is ensured through a triple data verification mechanism. Then, the multi-level load forecasting stage is entered. Relying on a preset model pool including time-series models, tree model fusion models, and BP neural network models, the optimal model suitable for the current operating conditions is selected through Bayesian optimization algorithms and nested cross-validation, outputting the load forecast value for a preset future period. Next, based on the load forecast value and preset rules, low, medium, high, and overload zones are divided, taking into account geothermal resource supply capacity, equipment operating characteristics, and... Energy efficiency constraints are used to generate multi-device collaborative control strategies that cover parameters such as equipment switching combinations, geothermal well flow regulation, and external energy station supplementary energy supply. These strategies incorporate key technologies such as geothermal reinjection temperature protection and heat pump energy efficiency optimization. The equipment execution module then receives control commands and controls the coordinated operation of various actuators, while also supporting multi-scenario linkage with the intelligent snow melting system. Finally, the feedback optimization module collects real-time system operation data after control, calculates the deviation between predicted and measured values, and dynamically corrects the load prediction model parameters and collaborative control strategies, forming a closed-loop process of data collection, prediction, decision-making, execution, feedback, and correction to ensure the system continuously achieves intelligent and precise operation.

[0023] Please refer to Figure 2 , Figure 2 This is a flowchart of a dynamic control method for a geothermal coupled heating system based on multi-level load prediction in some embodiments of this application.

[0024] The dynamic control method for geothermal coupled heating systems based on multi-level load forecasting disclosed in the first aspect of this invention is used in terminal devices, such as computers and mobile terminals. This dynamic control method for geothermal coupled heating systems based on multi-level load forecasting includes the following steps: S201. Collect operating status data and environmental parameters of heat exchange equipment, heat pump units, geothermal wells, external energy stations and end users in the geothermal coupling heating system; S202. Based on the preset multi-level load prediction model pool, the heating load within the preset time period is predicted to obtain the load prediction value; S203. Divide the load interval according to the load forecast value, and generate a multi-equipment coordinated control strategy by combining the geothermal resource supply capacity, equipment operating characteristics and energy efficiency constraints. S204. Based on the multi-device collaborative control strategy, control the actions of each actuator to achieve the coordinated operation of heat exchange equipment, heat pump unit, geothermal well flow regulating actuator and external energy station; S205. Collect system operation feedback data after real-time control and dynamically correct the load prediction model and multi-device collaborative control strategy.

[0025] This technical solution centers on closed-loop intelligent control. First, it uses a sensor network comprised of temperature transmitters, pressure transmitters, and ultrasonic flow meters to collect operational status parameters (including medium temperature, pressure, flow rate, and equipment power consumption) and environmental monitoring parameters (including ambient temperature, humidity, and snowfall) from the heat exchange equipment, heat pump units, geothermal wells, external energy stations, and end-users in the geothermal coupled heating system. Then, it employs a triple data verification mechanism (real-time data acquisition from equipment sensors, redundant backup data from independently calibrated instruments, and verification data calculated based on thermodynamic energy balance formulas) for collaborative verification. To ensure the reliability of the collected data, a multi-level load prediction model pool (including time-series models, tree model fusion models, and BP neural network models) is used. A Bayesian optimization algorithm combined with nested cross-validation is employed to optimize hyperparameters, selecting the optimal prediction model suitable for the current operating conditions. This model predicts the heating load for a preset future period and outputs the predicted load value. Subsequently, based on the predicted load value and preset system rules, the system divides the load into low-load, medium-load, high-load, and overload zones. Each zone is associated with a preset equipment combination scheme, and a 5%~10% setting is used when switching zones. The hysteresis threshold switching mechanism, combined with the maximum geothermal resource supply capacity, equipment rated operating characteristics, and energy efficiency constraints, generates a multi-equipment collaborative control strategy. This strategy includes the switching combination of heat exchange equipment and heat pump units, geothermal well flow regulation parameters, and external energy station supplementary energy supply parameters. It incorporates a dual protection logic for geothermal reinjection temperature (controlling the reinjection temperature to a preset target range through pre-cooling at the outlet of the four-stage heat exchange equipment, triggering a forced load adjustment command when the reinjection temperature exceeds the threshold) and a dual regulation mechanism for heat pump temperature and load (dynamically adjusting the number and combination of heat pumps to ensure their load rate remains within the optimal energy efficiency range). External energy station supplementary energy supply follows the principles of geothermal priority and peak-shaving supplementation. The aforementioned collaborative control strategy is then converted into equipment control commands and sent to the heat exchangers. The system includes actuators such as on / off valve groups, heat pump unit controllers, geothermal well submersible pump frequency converters, geothermal well reinjection flow regulating valves, and external energy station coupling interface valve groups. It controls the coordinated operation of each actuator and supports linkage with the intelligent snow melting system based on multi-scenario energy supply needs (adjusting geothermal waste heat distribution parameters and activating the snow melting circulation pipeline actuators when environmental parameters reach preset snow melting trigger conditions). Finally, it collects real-time system operation feedback data after regulation, calculates the deviation between the feedback data and the load forecast value, and dynamically corrects the parameters of the multi-level load forecast model and the adaptability of the multi-device collaborative regulation strategy based on this deviation. This forms a closed-loop regulation process encompassing data acquisition, load forecasting, strategy generation, execution control, and feedback correction, ensuring continuous, stable, and efficient system operation.

[0026] According to an embodiment of the present invention, the method of predicting the heating load within a preset time period based on a preset multi-level load prediction model pool to obtain a load prediction value specifically includes: The multi-level load forecasting model pool includes a time series model, a tree model fusion model, and a BP neural network model; The optimal prediction model that best suits the current working conditions is selected through hyperparameter optimization and cross-validation. The hyperparameter optimization employs a Bayesian optimization algorithm, and the cross-validation uses a nested cross-validation method to improve load prediction accuracy by avoiding the risk of overfitting.

[0027] The system integrates various candidate prediction models, including time-series models, tree model fusion models, and BP neural network models, into a pre-defined multi-level load prediction model pool to adapt to the load prediction needs of the geothermal coupled heating system under different operating conditions. During the prediction process, candidate models in the pool are first screened using a combination of hyperparameter optimization and cross-validation. Hyperparameter optimization employs a Bayesian optimization algorithm to efficiently find the optimal hyperparameter combination for each candidate model. Cross-validation uses a nested cross-validation approach to effectively avoid overfitting risks during model training, thereby improving the accuracy and reliability of load prediction. Finally, the optimal prediction model suitable for the current system operating conditions is determined through this screening process. This optimal model is then used to calculate the heating load for a pre-defined future period, outputting a load prediction value that accurately reflects changes in end-user heating demand. This provides data support for subsequent load interval division and multi-device collaborative control strategies, ensuring a precise match between the overall control plan and actual heating demand.

[0028] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the division of load intervals in a dynamic control method for a geothermal coupled heating system based on multi-level load forecasting, as described in some embodiments of this application. According to an embodiment of the present invention, the division of load intervals based on the load forecast value specifically involves: S301. Based on the load forecast value and the system's preset load interval division rules, the low load interval, medium load interval, high load interval, and overload interval are obtained. S302, Each load interval is associated with a preset equipment combination scheme; S303. During the load interval switching process, a hysteresis switching mechanism is adopted. The first hysteresis threshold is set according to the system equipment operation stability requirements to realize load interval switching control.

[0029] Firstly, based on the total heating capacity of the geothermal coupled heating system, the rated operating parameters of the equipment, and the characteristics of the end-user heat demand, a pre-defined load range division rule is established, dividing the system's heating load into four levels: low load, medium load, high load, and overload. For each load range, a pre-configured equipment combination scheme is tailored to the load demand of that range. Specifically, the low load range corresponds to a specific combination of basic heat exchange equipment and heat pump units; the medium load range adds some heat exchange equipment or heat pump units to the basic combination; the high load range utilizes all core heat exchange equipment and heat pump units; and the overload range operates with full geothermal equipment and is supplemented by external energy stations, ensuring precise matching between load demand and equipment power supply capacity in each range. During system operation, when the predicted load or actual operating load triggers the range switching condition, a delayed switching mechanism is used to avoid frequent equipment start-ups and shutdowns. This is based on the operational stability requirements of core equipment such as heat pump units and heat exchange equipment within the system, for example, setting a 5%~10% delay. The first lag threshold is used to execute the load interval switching operation only when the load change continues to exceed the lag threshold and the interval switching judgment condition is met. At the same time, the preset equipment combination scheme of the corresponding interval is activated to ensure the system's operational stability and control continuity during load fluctuations and avoid equipment wear and power supply fluctuations caused by frequent switching.

[0030] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating the generation of a multi-device coordinated control strategy for a geothermal coupled heating system dynamic control method based on multi-level load prediction, as described in some embodiments of this application. According to an embodiment of the present invention, the generation of the multi-device coordinated control strategy specifically includes: S401. Based on the system load demand, equipment operating characteristics and energy supply capacity, a coordinated control strategy is obtained for the switching combination, geothermal well flow regulation parameters, and external energy station supplementary energy supply parameters. S402. According to the geothermal reinjection temperature control requirements, the reinjection temperature is controlled to the preset target range by pre-cooling the outlet of the four-stage heat exchange equipment. S403. When the reinjection temperature exceeds the preset threshold, a forced load adjustment command is triggered.

[0031] In generating a multi-device coordinated control strategy, the system first comprehensively considers the current real-time load demand (based on load forecasts and end-user heat feedback), the operating characteristics of core equipment (including the COP of heat pump units, the optimal load rate range of 60%-90%, the heat transfer efficiency of heat exchange equipment, and the operating parameter constraints of geothermal well submersible pumps), and the energy supply capacity boundaries (maximum water output of geothermal wells, the limit of cascade utilization of geothermal resources, and the maximum supplementary energy supply load of external energy stations). After solving the problem using a multi-objective optimization algorithm, a coordinated control strategy is formed that covers the switching combination scheme of heat exchange equipment and heat pump units (equipment start-up and shutdown combinations adapted to different load ranges), geothermal well flow regulation parameters (submersible pump variable frequency operating frequency, reinjection flow regulation valve opening parameters), and external energy station supplementary energy supply parameters (coupling main pipe electric regulating valve opening, supplementary heating and flow parameters). This ensures that the strategy meets both load demand and energy supply requirements. This collaborative control strategy integrates a dual protection logic for geothermal reinjection temperature to meet both the requirements for efficient equipment operation and compliance with geothermal reinjection temperature standards. The first layer is active control protection, which uses a four-stage heat exchange system with cascaded heat extraction and outlet pre-cooling design to precisely control the temperature of the geothermal water after cascaded utilization to a preset target range (e.g., 20±1℃), achieving pre-control of geothermal reinjection temperature. The second layer is passive trigger protection, which collects reinjection temperature data in real time through temperature monitoring points on the geothermal reinjection main pipe. When the reinjection temperature is detected to exceed a preset threshold (e.g., 22℃) for a preset duration (e.g., 5 minutes), a forced load adjustment command is automatically triggered to reduce the system operating load by a preset ratio (e.g., 10%-15% of the current load) until the reinjection temperature falls below the preset threshold, ensuring the compliance and stability of the geothermal reinjection process and preventing the impact of excessive reinjection temperature on the balance of underground heat storage and the safety of system operation.

[0032] According to an embodiment of the present invention, the coordinated regulation strategy further includes: A dual temperature and load regulation mechanism is adopted to dynamically adjust the number and combination of heat pump units in operation, ensuring that the load rate of the heat pump units is maintained within the preset optimal energy efficiency range.

[0033] This system combines the dynamic load characteristics of the geothermal coupled heating system, the coefficient of performance (COP) characteristics of the heat pump units, and ambient temperature fluctuations to construct a dual-dimensional linkage regulation mechanism for temperature and load. The load dimension is based on load forecasts and real-time load feedback data. When the system load increases, the number of operating heat pump units is dynamically increased according to preset priorities, or a higher-capacity unit combination is switched. When the system load decreases, the number of operating units is gradually reduced, or a combination of units suitable for low loads is switched, preventing any single unit from operating at a low load rate for an extended period. The temperature dimension uses the target supply water temperature at the condenser outlet of the heat pump unit, the inlet and outlet temperatures of the evaporator, and the ambient temperature as the basis for regulation. The target operating temperature parameters of the heat pump units are dynamically adjusted according to the heating demand in different load ranges. Through coordinated regulation of temperature and load, the actual load rate (actual heating capacity / load capacity) of each operating heat pump unit is optimized. The rated heating capacity (100%) is stably maintained within the preset optimal energy efficiency range (e.g., 60%-90%). At the same time, in conjunction with the heat pump unit start-stop protection logic (e.g., minimum operating interval ≥30 minutes, start-stop ≤2 times per hour), it ensures that the heat pump unit is always in a high-efficiency operating state to reduce the overall power consumption of the system, and extends the service life of the heat pump unit, avoiding the risk of inefficient operation or failure shutdown of the unit due to load and temperature mismatch.

[0034] According to an embodiment of the present invention, the external energy station's supplementary energy supply further includes: When the local heating system reaches its maximum power supply capacity but still cannot meet the load demand, an external energy station is activated, and the load gap is supplemented by adjusting the flow rate of the coupling main actuator.

[0035] Among them, the multi-equipment coordinated control strategy clearly defines the energy supply principle of prioritizing geothermal energy and supplementing peak demand. This is achieved by real-time monitoring of the actual energy output of the geothermal system (calculated by combining geothermal well water output, heat exchange equipment efficiency, and heat pump unit heating capacity) and the maximum energy supply capacity of geothermal resources (determined based on long-term geothermal well operation test data, reservoir replenishment capacity, and the rated energy supply limit of the equipment). When it is determined that the actual energy supply capacity of the geothermal system has reached a preset proportion of the maximum energy supply capacity (e.g., 95%), and still cannot meet the current system load demand (load forecast or real-time load feedback value exceeds the maximum energy supply capacity of the geothermal system), It automatically triggers the start command of the external energy station; by adjusting the opening of the flow regulating actuator (such as an electric regulating valve) on the coupling main pipe between the geothermal system and the external energy station, it precisely controls the supplementary energy supply flow of the external energy station according to the preset supplementary ratio (such as 105%-110%) of the load gap (the difference between the current load demand and the actual energy supply capacity of the geothermal system), so as to achieve seamless coupling and connection between geothermal energy and external supplementary energy, ensuring that the total energy supply of the system can match the end-user heating demand in real time, avoiding the problem of insufficient end-user temperature due to insufficient energy supply, and avoiding energy waste caused by excessive energy supply from the external energy station.

[0036] According to an embodiment of the present invention, the collection of the operating status data includes: Based on the data collection reliability requirements, a triple data verification mechanism was established; The system acquires real-time data collected by the sensors on the device itself, redundant backup data collected by the independent calibration instrument, and calibration data calculated based on the thermodynamic energy balance formula. The collection and verification of operational status parameters are achieved through the collaborative verification of three types of data.

[0037] In accordance with the data reliability requirements of geothermal coupled heating system regulation, a triple data verification mechanism covering data acquisition, backup, and calculation verification is established. The first layer of data consists of real-time data collected by sensors on the equipment itself. These sensors, deployed at heat exchange equipment, heat pump units, geothermal wells, external energy stations, and end-user locations, collect core status parameters during system operation in real time, including temperature, pressure, flow rate, and electrical parameters. The second layer consists of redundant backup data collected by independent calibration instruments. At key monitoring points (such as geothermal well inlets and outlets, heat pump unit inlets and outlets, and reinjection mains), additional independent calibration instruments of the same type and with the same accuracy as the main sensors are configured to collect data synchronously as redundant backups. The third layer consists of verification data calculated based on the thermodynamic energy balance formula. Based on the first law of thermodynamics and the system's energy transfer characteristics, the calculation... By combining energy input (e.g., heat pump power consumption, geothermal fluid heat content) and output (e.g., terminal heating, heat loss) data from all aspects of the system, theoretical verification values ​​of key operating parameters are derived through a preset energy balance calculation model. Through collaborative verification of these three types of data, data deviation thresholds are set (e.g., deviation between the main sensor and independent calibration instrument data ≤ ±3%, deviation between the main sensor and calculated calibration data ≤ ±5%). When the deviations of the three types of data are within the threshold range, real-time data from the main sensor is used as the basis for control. When the deviations of any two types of data exceed the threshold, a data anomaly alarm is triggered, and the system automatically switches to data with acceptable deviations as the temporary control basis. This ensures that the collected operating status parameters are accurate and reliable, providing precise data support for load forecasting, strategy generation, and closed-loop correction, and avoiding control decision errors caused by single data acquisition anomalies.

[0038] According to an embodiment of the present invention, it further includes: Establish a linkage mechanism with the intelligent snow melting system based on the system's multi-scenario energy supply needs; When the environmental monitoring parameters reach the preset snow melting trigger conditions, the geothermal waste heat distribution parameters are adjusted according to the snow melting load demand, and the actuator of the snow melting circulation pipeline is activated in conjunction with the mechanism.

[0039] Specifically, combining the waste heat utilization potential of the geothermal coupled heating system with the regional energy supply needs across multiple scenarios, a collaborative linkage mechanism between the geothermal heating system and the intelligent snow melting system is constructed. This linkage mechanism pre-defines the priority of geothermal waste heat allocation, parameter adjustment rules, and linkage logic of the execution mechanism for snow melting scenarios. Environmental monitoring parameters (including ambient temperature, humidity, snowfall, and road snow thickness) are collected in real time by environmental sensors deployed in road areas, and snow melting trigger conditions are preset (e.g., snowfall ≥ 2 mm / h and ambient temperature ≤ 2℃). When the monitored environmental parameters meet the preset snow melting trigger conditions, the system automatically calculates the load demand required for snow melting. Based on the current energy reserve of the geothermal system and the terminal heating guarantee threshold, it dynamically adjusts the geothermal waste heat allocation parameters (including the proportion of geothermal fluid flow in the snow melting circulation pipeline, temperature control parameters, etc., for example, allocating 10%-15% of the geothermal system's capacity). The system utilizes the residual heat of the geothermal system. Simultaneously, it sends linkage control commands to the actuators of the intelligent snow melting system (including the electric circulation pumps and on / off valve groups of the snow melting circulation pipeline) to open the snow melting circulation pipeline, enabling the geothermal residual heat to be transferred through the internal circulation pipeline of the road to complete the snow melting and ice removal operation. During the snow melting process, the system synchronizes the operating status data of the snow melting system with the energy supply data of the geothermal system in real time to ensure that the distribution of geothermal residual heat meets the snow melting needs without affecting the stability of the conventional heating at the end, thus realizing the efficient utilization of geothermal resources in multiple scenarios.

[0040] According to an embodiment of the present invention, the method further includes; Establish a communication and linkage mechanism with the regional energy management platform to receive regional energy supply and demand balance instructions, renewable energy consumption requirements, and cross-system coordination parameters; Based on the received parameters, local load forecasts, real-time geothermal resource supply capacity, equipment operating characteristics, and energy efficiency constraints, the energy supply priority and regulation response threshold for the appropriate regional dispatch are obtained, and the multi-equipment collaborative control strategy is modified across systems. By dynamically adjusting geothermal well flow regulation parameters, the proportion of supplementary energy supply from external energy stations, and waste heat distribution strategies for multiple scenarios, the coordinated operation of the local system and the regional energy network can be achieved.

[0041] The system establishes a two-way communication and linkage mechanism between the local geothermal coupled heating system and the regional energy management platform based on industrial Ethernet communication protocols (such as IEC 61850). It receives real-time energy supply and demand balance instructions (such as regional total load peak shaving / valley filling requirements), renewable energy consumption requirements (such as the proportion of wind power / photovoltaic surplus electricity used for heating), and cross-system coordination parameters (such as regional energy allocation coefficients and response time requirements) issued at the regional level. Based on the received regional level parameters, combined with locally acquired load forecasts, real-time geothermal resource supply capacity (calculated based on real-time geothermal well output and thermal storage temperature monitoring data), equipment operating characteristics (including the rated adjustment range of heat pump units and heat exchange equipment), and energy efficiency constraints (such as a system comprehensive energy efficiency ratio ≥ 3.5), a multi-objective optimization algorithm is used to solve for the local system's energy supply priority (such as lowering the local system's energy supply priority during regional peak shaving periods and increasing its priority during valley filling periods) and adjustment response thresholds (such as regional instruction response). The system ensures a delay of ≤10 minutes and an energy supply adjustment range of ≤20% per instance. Based on this, the original multi-equipment collaborative control strategy is adapted and modified across systems. By dynamically adjusting the geothermal well flow regulation parameters (submersible pump frequency conversion frequency, reinjection flow valve opening), the proportion of external energy station supplementary energy supply (reducing the proportion of external energy station energy supply when the region requires high absorption), and the multi-scenario waste heat distribution strategy (prioritizing end-point heating when the region's energy supply is tight, and temporarily suspending waste heat distribution in snow melting scenarios), the system achieves coordinated linkage between the local geothermal coupled heating system and the regional energy network, accurately responding to regional energy dispatch needs, without violating the core constraints such as local system reinjection temperature control and optimal equipment energy efficiency operation.

[0042] Please refer to Figure 5 , Figure 5 This is a structural block diagram of the dynamic control system of the geothermal coupling heating system based on multi-level load prediction provided in the embodiments of this application.

[0043] The second aspect of this invention also discloses a dynamic control system for a geothermal coupled heating system based on multi-level load prediction, comprising: Data acquisition module 501: used to collect operating status data and environmental parameters of heat exchange equipment, heat pump units, geothermal wells, external energy stations and end users. The data acquisition module integrates a triple data verification unit. Multi-level load forecasting module 502: includes a preset model pool and hyperparameter optimization unit, used to forecast the heating load within a preset time period and output the load forecast value; Dynamic regulation and control decision module 503: used to divide the load range according to the load forecast value, and generate a multi-equipment coordinated regulation and control strategy in combination with geothermal resource supply capacity, equipment operating characteristics and energy efficiency constraints; Equipment execution module 504 includes heat exchange equipment, heat pump unit, flow regulation actuator and external energy station interface, used to receive the coordinated control strategy and execute corresponding actions; Feedback optimization module 505: Used to collect system operation feedback data after regulation and dynamically correct the prediction model of the multi-level load prediction module and the regulation strategy of the dynamic regulation decision module.

[0044] The system also includes a memory and a processor. The memory includes a program for a dynamic control method for a geothermal coupled heating system based on multi-level load prediction. When the program for the dynamic control method for a geothermal coupled heating system based on multi-level load prediction is executed by the processor, it implements the steps of the dynamic control method for a geothermal coupled heating system based on multi-level load prediction as described in any one of the first aspects.

[0045] This invention discloses a dynamic control method and system for geothermal coupled heating systems based on multi-level load forecasting. The method establishes a comprehensive data acquisition process with a triple data verification mechanism. It relies on real-time data from equipment sensors, redundant backup data from independently calibrated instruments, and verification data calculated using thermodynamic energy balance formulas for collaborative verification. This ensures the reliability of operational data and environmental parameters across all stages, including heat exchange equipment, heat pump units, geothermal wells, external energy stations, and end-users. Simultaneously, it establishes a linkage mechanism with intelligent snow melting systems and regional energy management platforms to meet the needs of multi-scenario energy supply and regional energy dispatching. Utilizing a multi-level load forecasting model pool comprising time-series models, tree models, and BP neural network models, it employs Bayesian hyperparameter optimization and nested cross-validation to select the optimal model, accurately predicting future heating loads for preset periods while avoiding overfitting. The method divides the load forecast into four categories: low, medium, high, and overload, matching corresponding equipment combinations and setting lag conditions. The post-switching threshold ensures stable switching between regions. A multi-device collaborative control strategy is generated by combining geothermal resource supply capacity, equipment operating characteristics, and energy efficiency constraints. This strategy dynamically adjusts geothermal well flow parameters, the number and combination of heat pump units, and the proportion of external energy station supplementary energy supply. Combined with a dual protection logic for geothermal reinjection temperature through pre-cooling of four-stage heat exchange equipment and forced load regulation, precise energy supply adaptation is achieved. Simultaneously, real-time system operation feedback data after regulation is collected, continuously and dynamically correcting the load prediction model and control strategy to form a closed-loop optimization mechanism. A dedicated system is built, consisting of a data acquisition module, a multi-level load prediction module, a dynamic control decision module, an equipment execution module, and a feedback optimization module. These modules work collaboratively to effectively solve problems such as unreliable data, difficult load adaptation, and poor equipment coordination in geothermal heating. This achieves multi-level linkage between equipment, systems, and regional energy networks, providing comprehensive technical support for the efficient and stable operation of geothermal coupled heating.

[0046] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0047] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0048] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0049] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory, random access memory, magnetic disks, or optical disks.

[0050] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A dynamic control method for geothermal coupled heating systems based on multi-level load forecasting, characterized in that, Includes the following steps: Collect operational status data and environmental parameters of heat exchange equipment, heat pump units, geothermal wells, external energy stations and end users in the geothermal coupled heating system; Based on a pre-set multi-level load prediction model pool, the heating load within a pre-set time period is predicted to obtain the load prediction value; Based on the load forecast values, load intervals are divided, and a multi-equipment coordinated control strategy is generated by combining geothermal resource supply capacity, equipment operating characteristics and energy efficiency constraints. Based on the aforementioned multi-device collaborative control strategy, the actions of each actuator are controlled to achieve the coordinated operation of heat exchange equipment, heat pump units, geothermal well flow regulating actuators, and external energy stations. Real-time system operation feedback data after regulation is collected, and the load prediction model and multi-device collaborative regulation strategy are dynamically corrected.

2. The dynamic control method for geothermal coupled heating system based on multi-level load prediction according to claim 1, characterized in that, The pre-set multi-level load prediction model pool predicts the heating load within a pre-set time period to obtain the load prediction value, specifically: The multi-level load forecasting model pool includes a time series model, a tree model fusion model, and a BP neural network model; The optimal prediction model that best suits the current working conditions is selected through hyperparameter optimization and cross-validation. The hyperparameter optimization employs a Bayesian optimization algorithm, and the cross-validation uses a nested cross-validation method to improve load prediction accuracy by avoiding the risk of overfitting.

3. The dynamic control method for geothermal coupled heating system based on multi-level load prediction according to claim 1, characterized in that, The process of dividing the load interval based on the load forecast value specifically involves: Based on the predicted load value and the system's preset load interval division rules, low load interval, medium load interval, high load interval, and overload interval are obtained; Each of the aforementioned load intervals is associated with a preset equipment combination scheme; During load interval switching, a hysteresis switching mechanism is adopted, and a first hysteresis threshold is set according to the system equipment operation stability requirements to realize load interval switching control.

4. The dynamic control method for geothermal coupled heating system based on multi-level load prediction according to claim 1, characterized in that, The multi-device collaborative control strategy is specifically as follows: Based on system load demand, equipment operating characteristics and energy supply capacity, a coordinated control strategy is derived for switching combinations, geothermal well flow regulation parameters, and external energy station supplementary energy supply parameters. According to the geothermal reinjection temperature control requirements, the reinjection temperature is controlled to the preset target range by pre-cooling the outlet of the four-stage heat exchange equipment. When the reinjection temperature exceeds the preset threshold, a forced load adjustment command is triggered.

5. The dynamic control method for geothermal coupled heating system based on multi-level load prediction according to claim 4, characterized in that, The coordinated regulation strategy also includes: A dual temperature and load regulation mechanism is adopted to dynamically adjust the number and combination of heat pump units in operation, ensuring that the load rate of the heat pump units is maintained within the preset optimal energy efficiency range.

6. The dynamic control method for geothermal coupled heating system based on multi-level load prediction according to claim 4, characterized in that, The external energy station's supplementary energy supply also includes: When the local heating system reaches its maximum power supply capacity but still cannot meet the load demand, an external energy station is activated, and the load gap is supplemented by adjusting the flow rate of the coupling main actuator.

7. The dynamic control method for geothermal coupled heating system based on multi-level load prediction according to claim 1, characterized in that, The collection of the operational status data includes: Based on the data collection reliability requirements, a triple data verification mechanism was established; The system acquires real-time data collected by the sensors on the device itself, redundant backup data collected by the independent calibration instrument, and calibration data calculated based on the thermodynamic energy balance formula. The collection and verification of operational status parameters are achieved through the collaborative verification of three types of data.

8. The dynamic control method for geothermal coupled heating system based on multi-level load prediction according to claim 1, characterized in that, Also includes: Establish a linkage mechanism with the intelligent snow melting system based on the system's multi-scenario energy supply needs; When the environmental monitoring parameters reach the preset snow melting trigger conditions, the geothermal waste heat distribution parameters are adjusted according to the snow melting load demand, and the actuator of the snow melting circulation pipeline is activated in conjunction with the mechanism.

9. A dynamic control system for a geothermal coupled heating system based on multi-level load forecasting, characterized in that, include: Data acquisition module: used to collect operating status data and environmental parameters of heat exchange equipment, heat pump units, geothermal wells, external energy stations and end users. The data acquisition module integrates a triple data verification unit. Multi-level load forecasting module: includes a preset model pool and hyperparameter optimization unit, used to predict the heating load within a preset time period and output the load forecast value; Dynamic control decision module: used to divide the load range according to the load forecast value, and generate a multi-equipment coordinated control strategy by combining the geothermal resource supply capacity, equipment operating characteristics and energy efficiency constraints; Equipment execution module: includes heat exchange equipment, heat pump unit, flow regulation actuator and external energy station interface, used to receive the coordinated control strategy and execute corresponding actions; Feedback optimization module: Used to collect system operation feedback data after regulation and dynamically correct the prediction model of the multi-level load prediction module and the regulation strategy of the dynamic regulation decision module.

10. A dynamic control system for geothermal coupled heating systems based on multi-level load forecasting, characterized in that, The system also includes a memory and a processor. The memory contains a program for a dynamic control method of a geothermal coupled heating system based on multi-level load forecasting. When the program for the dynamic control method of a geothermal coupled heating system based on multi-level load forecasting is executed by the processor, it implements the following steps: Collect operational status data and environmental parameters of heat exchange equipment, heat pump units, geothermal wells, external energy stations and end users in the geothermal coupled heating system; Based on a pre-set multi-level load prediction model pool, the heating load within a pre-set time period is predicted to obtain the load prediction value; Based on the load forecast values, load intervals are divided, and a multi-equipment coordinated control strategy is generated by combining geothermal resource supply capacity, equipment operating characteristics and energy efficiency constraints. Based on the aforementioned multi-device collaborative control strategy, the actions of each actuator are controlled to achieve the coordinated operation of heat exchange equipment, heat pump units, geothermal well flow regulating actuators, and external energy stations. Real-time system operation feedback data after regulation is collected, and the load prediction model and multi-device collaborative regulation strategy are dynamically corrected.

Images