Multi-level geothermal well collaborative scheduling method and system based on multi-time scale prediction

Abstract

The invention provides a multi-level geothermal well collaborative scheduling method and system based on multi-time scale prediction, and relates to the technical field of data processing. The method comprises the following steps: constructing a well group output model based on operation parameters of a shallow geothermal well group and a deep geothermal well group; constructing a multi-scale load prediction model based on the historical load data and the historical meteorological data; determining a load prediction result of the target time period by using the multi-scale load prediction model, wherein the load prediction result comprises a day-ahead load, a day-mid load and a real-time load; and performing joint calculation by using the well group output model, the load prediction result and the multi-objective optimization function to obtain optimal scheduling parameters of the shallow geothermal well group and the deep geothermal well group in the current scheduling period. According to the technical scheme, the output ratio of the shallow geothermal well and the deep geothermal well can be dynamically coordinated according to the predicted load requirements of different time scales, and efficient utilization of multi-level geothermal resources is achieved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a multi-level geothermal well collaborative scheduling method and system based on multi-time scale prediction. Background Art

[0002] Geothermal energy, as a stable, renewable, low-carbon energy source, has been widely used in building heating, regional energy stations, and integrated energy systems. Geothermal wells can be divided into shallow and deep categories based on the depth of development. Resources at different levels differ significantly in temperature levels, heat storage capacity, and adjustability. In actual projects, shallow geothermal wells have the advantages of fast response and suitability for daily fluctuating loads, but their heat storage capacity is limited and prone to temperature decay. Deep geothermal wells, on the other hand, have higher thermal grade and stable output capacity, and are often used to provide base loads or energy security in extreme weather conditions.

[0003] However, in related geothermal well scheduling technologies, shallow geothermal wells or deep geothermal wells are usually controlled individually, and dynamic coordination and complementary regulation of multiple heat sources cannot be achieved, which leads to resource redundancy and overload of some resources, reducing the operating efficiency and energy utilization of the overall energy system. Especially in regional energy supply scenarios with large load fluctuations, one type of well group may be in a high-load operation state for a long time, resulting in thermal field attenuation and operational fatigue, while another type of well group is in a redundant state and is not effectively scheduled, resulting in unbalanced resource utilization. Therefore, there is still room for improvement in the existing technology of geothermal well scheduling technology in terms of resource utilization efficiency and energy supply stability.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the Invention

[0005] The purpose of the embodiments of the present disclosure is to provide a multi-level geothermal well collaborative scheduling method based on multi-time scale prediction, a multi-level geothermal well collaborative scheduling system based on multi-time scale prediction, an electronic device and a computer-readable storage medium. By constructing a well group output model and a multi-scale load prediction model, and combining a multi-objective optimization function to jointly calculate the scheduling parameters of shallow geothermal well groups and deep geothermal well groups, the resource utilization efficiency and energy supply stability in the geothermal well scheduling process are improved at least to a certain extent.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by practice of the present disclosure.

[0007] According to a first aspect of an embodiment of the present disclosure, a multi-level geothermal well collaborative scheduling method based on multi-time-scale prediction is provided, the method comprising: constructing a well group output model based on the operating parameters of a shallow geothermal well group and a deep geothermal well group, the well group output model being able to characterize the unit thermal output capacity, heat storage capacity and temperature attenuation characteristics of each well group; constructing a multi-scale load forecasting model based on historical load data and historical meteorological data; determining the load forecast result for a target period using the multi-scale load forecasting model, the load forecast result including the day-ahead load, mid-day load and real-time load; and performing joint calculations using the well group output model, the load forecast result and a multi-objective optimization function to obtain the optimal scheduling parameters for the shallow geothermal well group and the deep geothermal well group within the current scheduling cycle.

[0008] In some example embodiments of the present disclosure, based on the aforementioned scheme, the construction of the well group output model based on the operating parameters of the shallow geothermal well group and the deep geothermal well group includes: obtaining the operating parameters of the shallow geothermal well group and the deep geothermal well group, the operating parameters including temperature field data, well output parameters, soil thermal conductivity, auxiliary equipment performance parameters and shallow geothermal well recharge parameters; constructing a temperature response function based on the temperature field data for characterizing the temperature change trend of each geothermal well during operation; constructing a temperature response function based on the well output parameters for characterizing the temperature change trend of each geothermal well during operation. An output function of the heat production capacity per unit time; a geothermal attenuation function is constructed based on the soil thermal conductivity to characterize the decay of the ground temperature of each geothermal well over time; an auxiliary energy supply function is constructed based on the performance parameters of the auxiliary equipment to characterize the output characteristics of the auxiliary equipment per unit time; a shallow heat storage function is constructed based on the reinjection parameters of the shallow geothermal well to characterize the heat storage capacity of the shallow geothermal well in the non-heating period; the well group output model is constructed based on the temperature response function, output function, geothermal attenuation function, auxiliary energy supply function and shallow heat storage function.

[0009] In some example embodiments of the present disclosure, based on the aforementioned scheme, the multi-scale load forecasting model is constructed based on historical load data and historical meteorological data, including: extracting features from the historical load data and the historical meteorological data to obtain structural indicator features and time series change features; based on the structural indicator features, constructing a day-ahead forecasting sub-model for outputting the load of a first time granularity; based on the time series change features, constructing a mid-day forecasting sub-model for outputting the load of a second time granularity and a real-time forecasting sub-model for outputting the load of a third time granularity respectively; wherein, the time interval of the first time granularity is longer than the time interval of the second time granularity, and the time interval of the second time granularity is longer than the time interval of the third time granularity.

[0010] In some example embodiments of the present disclosure, based on the aforementioned scheme, the feature extraction of the historical load data and the historical meteorological data to obtain structural indicator features and time series change features includes: extracting multi-type structural data based on the historical load data and the historical meteorological data, wherein the multi-type structural data includes any one or more of date type, month, energy supply area, historical peak load and average load indicators; discretizing the multi-type structural data to obtain the structural indicator features; and utilizing the time series coupling relationship between the historical load data and the historical meteorological data to construct the time series change features.

[0011] In some example embodiments of the present disclosure, based on the aforementioned scheme, the time series variation characteristics are constructed by utilizing the time series coupling relationship between the historical load data and the historical meteorological data, including: constructing a load change rate sequence based on the historical load data, and constructing a temperature change sequence and a humidity change sequence based on the historical meteorological data; cross-operating the load change rate sequence and the temperature change sequence to obtain a load-temperature cross sequence; concatenating and combining the load change rate sequence and the humidity change sequence to obtain a load-humidity joint sequence; and constructing the time series variation characteristics based on the load change rate sequence, the temperature change sequence, the humidity change sequence, the load-temperature cross sequence, and the load-humidity joint sequence.

[0012] In some example embodiments of the present disclosure, based on the aforementioned scheme, the well group output model, the load forecast results and the multi-objective optimization function are jointly calculated to obtain the optimal scheduling parameters of the shallow geothermal well group and the deep geothermal well group in the current scheduling period, including: constructing the multi-objective optimization function based on formation heat balance, operating cost, carbon emissions and exergy efficiency; obtaining multiple sets of candidate scheduling parameter sets in the current scheduling period based on the well group output model and the load forecast results; and using a target genetic algorithm to obtain the optimal scheduling parameters that meet the multi-objective optimization function from the multiple sets of candidate scheduling parameters.

[0013] In some example embodiments of the present disclosure, based on the aforementioned scheme, the multi-objective optimization function is constructed based on formation heat balance, operating cost, carbon emissions and exergy efficiency, including: constructing a temperature change rate function that reflects the impact of the heat extraction process on the formation temperature based on the thermal conductivity of the geological layer corresponding to the geothermal well group, the temperature difference between the reinjection fluid and the output fluid, and the temperature gradient between the wellhead and the bottom hole; determining, based on the temperature change rate function, a heat extraction upper limit value that makes the temperature change rate equal to a preset formation temperature change rate threshold; and constructing the multi-objective optimization function based on the heat extraction upper limit value, the operating cost function, the carbon emission function and the exergy efficiency function.

[0014] In some example embodiments of the present disclosure, based on the aforementioned scheme, the target genetic algorithm is a multi-objective genetic algorithm with non-dominated sorting, and the use of the target genetic algorithm to obtain the optimal scheduling parameters that satisfy the multi-objective optimization function from the multiple sets of candidate scheduling parameter sets includes: constructing an initial scheduling population based on the candidate scheduling parameter sets, each scheduling parameter individual in the initial scheduling population includes the output configuration variables of the shallow geothermal well group and the deep geothermal well group; using the multi-objective optimization function to perform a multi-objective fitness evaluation on the scheduling parameter individuals in the initial scheduling population, and dividing the non-dominated levels according to the non-dominated sorting principle based on the evaluation results, and calculating the corresponding congestion index within each level; based on the non-dominated levels and the congestion index, selecting some scheduling parameter individuals as parent individuals, performing crossover operations and mutation operations, and generating the next generation scheduling parameter population; repeating the multi-objective fitness evaluation and non-dominated sorting operations on the next generation scheduling parameter population, and selecting the optimal scheduling parameters from all current scheduling parameter individuals when a preset iteration termination condition is satisfied.

[0015] In some example embodiments of the present disclosure, based on the aforementioned scheme, the above-mentioned multi-level geothermal well collaborative scheduling method based on multi-time-scale prediction also includes: collecting the operating parameters of the shallow geothermal well group, the deep geothermal well group, the short-term heat storage equipment and the air source heat pump, and determining the operating status of each heat source unit based on the operating parameters; in response to the operating status of any of the heat source units being a fault, calling the standby output configuration strategy corresponding to the fault type, and adjusting the output ratio of each heat source unit in the scheduling parameters in combination with the current load forecast result and the standby output capacity; in non-heating periods, using the deep geothermal well group and / or building heat to replenish heat to the shallow geothermal well group; obtaining temperature distribution data of the shallow geothermal well, and updating the shallow geothermal well recharge parameters in the well group output model according to the temperature distribution data.

[0016] According to a second aspect of an embodiment of the present disclosure, a multi-level geothermal well collaborative scheduling system based on multi-time-scale prediction is provided, the system comprising: an output model construction module for constructing a well group output model based on the operating parameters of a shallow geothermal well group and a deep geothermal well group, wherein the well group output model can characterize the unit thermal output capacity, heat storage capacity and temperature attenuation characteristics of each well group; a prediction model construction module for constructing a multi-scale load prediction model based on historical load data and historical meteorological data; a load prediction module for determining the load prediction result of a target period using the multi-scale load prediction model, wherein the load prediction result includes the day-ahead load, mid-day load and real-time load; and an intelligent scheduling module for performing joint calculations using the well group output model, the load prediction result and a multi-objective optimization function to obtain the optimal scheduling parameters of the shallow geothermal well group and the deep geothermal well group within the current scheduling cycle.

[0017] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, a multi-level geothermal well collaborative scheduling method based on multi-time-scale prediction as in the first aspect is implemented.

[0018] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the multi-level geothermal well collaborative scheduling method based on multi-time scale prediction as in the first aspect is implemented.

[0019] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects: In the disclosed embodiment, a multi-level geothermal well collaborative scheduling method based on multi-time-scale prediction is proposed. By modeling the operating parameters of shallow geothermal well groups and deep geothermal well groups, a well group output model is constructed that can characterize the unit thermal output capacity, heat storage capacity, and temperature attenuation characteristics. The hierarchical difference characteristics of geothermal resources are introduced in the process of forming scheduling parameters. Compared with the scheduling method based on a single well type, the thermal output characteristics and operating boundaries of geothermal wells at different levels can be more accurately characterized, thereby improving the matching and allocation accuracy of the scheduling strategy for multiple types of geothermal resources. On the one hand, by constructing a multi-scale load forecasting model, using historical load data and historical meteorological data as input, load forecast results at the day-ahead, mid-day, and real-time granularity are generated respectively, so that the scheduling strategy can cover medium- and long-term operating trends and short-term load fluctuations, thereby overcoming the problems of the related scheduling methods with a single time scale and a delayed response to sudden load changes. On the other hand, based on the well cluster output model and load forecast results, combined with a multi-objective optimization function, it is possible to dynamically allocate heat output ratios while meeting load demand while comprehensively considering the heat storage capacity and temperature decay trends of the geothermal well cluster. This significantly improves the allocation efficiency and operational balance of geothermal resources. Furthermore, the introduction of a multi-objective optimization function enables the generation of scheduling parameters not only to meet load matching objectives but also to optimize energy supply based on indicators such as operating costs, carbon emissions, and exergy efficiency, effectively enhancing the stability and sustainability of geothermal utilization systems under different load scenarios and operating cycles.

[0020] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0022] Figure 1 A flow chart of a multi-level geothermal well coordinated scheduling method based on multi-time-scale prediction according to some embodiments of the present disclosure is schematically shown.

[0023] Figure 2 A schematic diagram of a process for obtaining optimal scheduling parameters according to some embodiments of the present disclosure is schematically shown.

[0024] Figure 3 The following schematically illustrates the structural composition of a multi-level geothermal well collaborative scheduling system based on multi-time-scale prediction according to some embodiments of the present disclosure.

[0025] Figure 4 A block diagram of a multi-level geothermal well collaborative scheduling system based on multi-time-scale prediction according to some embodiments of the present disclosure is schematically shown.

[0026] Figure 5 A schematic structural diagram of a computer system of an electronic device according to some embodiments of the present disclosure is schematically shown.

[0027] Figure 6 A schematic diagram of a computer-readable storage medium according to some embodiments of the present disclosure is schematically shown.

[0028] In the drawings, the same or corresponding reference numerals denote the same or corresponding parts. DETAILED DESCRIPTION

[0029] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with this specification. Rather, they are merely examples of apparatus and methods consistent with certain aspects of this specification, as detailed in the appended claims.

[0030] The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this specification. As used in this specification and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0031] It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, such information should not be limited to these terms. These terms are merely used to distinguish information of the same type from one another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information without departing from the scope of this specification. Depending on the context, the term "if" as used herein may be interpreted as "when," "when," or "in response to determining."

[0032] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0033] In addition, the described features, structures or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, well-known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present disclosure.

[0034] Furthermore, the drawings are schematic illustrations only and are not necessarily drawn to scale. The block diagrams shown in the drawings are merely functional entities and do not necessarily correspond to physically separate entities. In other words, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0035] In this example embodiment, a multi-level geothermal well coordinated scheduling method based on multi-time-scale prediction is first provided, which can be applied to heat exchange geothermal wells as well as hydrothermal geothermal wells. Figure 1 The following schematically illustrates a flow chart of a multi-level geothermal well coordinated scheduling method based on multi-time scale prediction according to some embodiments of the present disclosure. Figure 1 As shown, the multi-level geothermal well coordinated scheduling method based on multi-time scale prediction may include the following steps: Step S110: constructing a well group output model based on the operating parameters of the shallow geothermal well group and the deep geothermal well group. The well group output model can characterize the unit heat output capacity, heat storage capacity and temperature attenuation characteristics of each well group.

[0036] Step S120: constructing a multi-scale load forecasting model based on historical load data and historical meteorological data.

[0037] Step S130: Determine the load forecast result for the target period using the multi-scale load forecasting model. The load forecast result includes the day-ahead load, mid-day load, and real-time load.

[0038] Step S140 , using the well group output model, load forecast results and multi-objective optimization function to perform joint calculations to obtain the optimal scheduling parameters of the shallow geothermal well group and the deep geothermal well group in the current scheduling period.

[0039] According to the multi-level geothermal well coordinated scheduling method based on multi-time-scale prediction in this example embodiment, by modeling the operating parameters of shallow and deep geothermal well groups, a well group output model is constructed that can characterize the unit heat output capacity, heat storage capacity, and temperature decay characteristics. Introducing the hierarchical differences in geothermal resources in the process of forming scheduling parameters can more accurately characterize the heat output characteristics and operating boundaries of geothermal wells at different levels. On the one hand, by constructing a multi-scale load forecasting model, using historical load data and historical meteorological data as input, load forecast results at day-ahead, mid-day, and real-time granularity are generated, enabling the scheduling strategy to cover medium- and long-term operating trends and short-term load fluctuations. On the other hand, based on the well group output model and load forecast results, by jointly calculating with a multi-objective optimization function, it is possible to meet load demand while comprehensively considering the heat storage capacity and temperature decay trend of the geothermal well group, realize dynamic allocation of heat output ratios, and significantly improve the allocation efficiency and operational balance of geothermal resources. On the other hand, by introducing the multi-objective optimization function, the generation of scheduling parameters is not only limited to the load matching target, but can also achieve energy supply optimization among indicators such as operating costs, carbon emissions and exergy efficiency, effectively enhancing the stability and sustainability of the geothermal utilization system under different load scenarios and operating cycles.

[0040] The multi-level geothermal well coordinated scheduling method based on multi-time-scale prediction in this example embodiment will be further described below.

[0041] Step S110: constructing a well group output model based on the operating parameters of the shallow geothermal well group and the deep geothermal well group. The well group output model can characterize the unit heat output capacity, heat storage capacity and temperature attenuation characteristics of each well group.

[0042] Among them, a shallow geothermal well group can represent a collection of geothermal wells with a depth less than a first preset threshold, and the first preset threshold can be 200 meters, 300 meters, or other suitable values. A deep geothermal well group can represent a collection of high-temperature geothermal wells with a depth greater than a second preset threshold, and the second preset threshold can be 3000 meters, 3200 meters, or other suitable values. Of course, in other embodiments of the present disclosure, when the well depth is greater than the first preset threshold, the corresponding geothermal well can be classified as a deep geothermal well group. The well group output model can represent a mathematical function combination relationship established based on the operating parameters of the shallow geothermal well group and the deep geothermal well group, and serve as one of the input bases for the calculation of scheduling parameters. The unit heat output capacity can represent the effective heat that a single well group can output per unit time, which can be calculated through the flow parameters, heat exchange temperature difference, and geothermal heat transfer coefficient of the well group, reflecting the instantaneous energy supply capacity of geothermal resources. Thermal storage capacity represents the ability of the underground medium corresponding to a well cluster to store thermal energy during the non-heating season. This capacity is related to the thermal conductivity and specific heat capacity of the formation in the well area, as well as the temperature changes over time. Temperature decay characteristics describe the gradual decrease in the outlet water temperature of the well cluster over time under continuous operation.

[0043] In addition, the operating parameters can represent various real-time and historical data sets collected during the operation of shallow geothermal well groups and deep geothermal well groups. Exemplarily, the operating parameters may include one or more parameters such as temperature field data, well output parameters, pipe network pressure data, equipment operation data, formation parameters and auxiliary equipment performance. Among them, the temperature field data may include wellhead temperature, bottom hole temperature and geothermal gradient, etc., the well output parameters may include single well flow, inlet and outlet temperature difference, inlet and outlet pressure and inlet and outlet temperature, etc., the pipe network pressure data may include the pressure fluctuation value of the trunk pipe network and the temperature, pressure and flow information of key nodes, etc., the equipment operation data may include the instantaneous flow, operating pressure, temperature, operating status, operating power, power consumption and speed of the equipment, etc., the formation parameters may include the thermal conductivity of the soil or rock formation in the shallow area, etc., and the auxiliary equipment performance parameters may include the performance coefficient of the heat pump system and the thermal collection efficiency of the photothermal system, etc. Of course, in other embodiments of the present disclosure, the operating parameters may also include other suitable geothermal well operating parameters.

[0044] Step S120: constructing a multi-scale load forecasting model based on historical load data and historical meteorological data.

[0045] Among them, historical load data can represent a series of heating or cooling load data recorded in the geothermal well power supply area over a period of time. This historical load data can include information such as instantaneous load, daily average load, peak load, and load change rate at different time granularities. Historical meteorological data can represent a collection of meteorological monitoring data within the time period corresponding to the historical load data. This historical meteorological data includes indicators such as temperature, humidity, wind speed, and solar irradiance, which are used to characterize the factors affecting changes in load demand due to the external environment. A multi-scale load forecasting model can represent a mathematical model that can output multi-scale load forecast results for a target time period. Among them, the multi-scale load forecasting model can be constructed using a hybrid neural network.

[0046] Step S130: Determine the load forecast result for the target period using the multi-scale load forecasting model. The load forecast result includes the day-ahead load, mid-day load, and real-time load.

[0047] The load forecast results can represent the data output of heating or cooling demand during the target period, generated by a multi-scale load forecasting model. These forecasts are categorized into three types based on time granularity: day-ahead load, midday load, and real-time load. Day-ahead load refers to the forward forecast results generated based on historical load and meteorological data. These forecast results are based on a single day and have a 24-hour granularity, and are used to generate initial planning data for the heat load before the dispatch date. Midday load refers to the mid-term forecast results generated through rolling updates within the dispatch operation day. These forecast results are updated at a preset midday granularity, which can be 2 hours, 3 hours, 4 hours, or other suitable durations. Real-time load refers to the real-time load data generated by short-term forecasts based on historical data and the current state of the geothermal system during its operation cycle. These real-time load data have a minute-level granularity and can be updated at preset intervals, such as 5 minutes, 10 minutes, 15 minutes, or 30 minutes.

[0048] Step S140 , using the well group output model, load forecast results and multi-objective optimization function to perform joint calculations to obtain the optimal scheduling parameters of the shallow geothermal well group and the deep geothermal well group in the current scheduling period.

[0049] Among them, the multi-objective optimization function can represent a set of optimization objectives constructed based on the operating constraints of the geothermal system to guide the configuration of heat source output, which can include multiple objective function terms such as operating costs, carbon emissions, energy utilization efficiency, and formation heat balance constraints. The optimal scheduling parameters can represent a set of geothermal system operating configuration parameters calculated based on the well group output model, heat load prediction results, and the multi-objective optimization function within a specific scheduling period. The optimal scheduling parameters can be used to determine the start and stop status of shallow geothermal well groups and deep geothermal well groups, the heat output distribution ratio, the charging and discharging strategies of the heat storage units, and the activation conditions of the auxiliary energy units. It can achieve coordinated optimization among multiple objectives such as operating costs, carbon emissions, and energy efficiency under the premise of meeting the formation heat balance, user load requirements, and pipeline safety constraints.

[0050] The technical contents of the above embodiments are described in detail below.

[0051] In some embodiments, constructing a well group output model based on the operating parameters of the shallow geothermal well group and the deep geothermal well group includes: obtaining the operating parameters of the shallow geothermal well group and the deep geothermal well group, the operating parameters including temperature field data, well output parameters, soil thermal conductivity, auxiliary equipment performance parameters and shallow geothermal well recharge parameters; constructing a temperature response function based on the temperature field data to characterize the temperature change trend of each geothermal well during operation; constructing an output function based on the well output parameters to characterize the heat production capacity of each geothermal well per unit time; constructing a geothermal attenuation function based on the soil thermal conductivity to characterize the decay of the formation temperature of each geothermal well over time; constructing an auxiliary energy supply function based on the auxiliary equipment performance parameters to characterize the output characteristics of the auxiliary equipment per unit time; constructing a shallow heat storage function based on the shallow geothermal well recharge parameters to characterize the heat storage capacity of the shallow geothermal well in the non-heating period; constructing a well group output model based on the temperature response function, output function, geothermal attenuation function, auxiliary energy supply function and shallow heat storage function.

[0052] Among them, temperature field data can represent data used to characterize the temperature distribution state of geothermal wells at different depths. Well output parameters can represent operating data used to characterize the heat exchange capacity of geothermal wells per unit time. Soil thermal conductivity can represent a geological thermophysical property index used to characterize the heat conduction rate per unit length of shallow or deep formations. Auxiliary equipment performance parameters can represent data reflecting the performance characteristics of auxiliary energy supply equipment in the process of cold and heat regulation and energy storage. Shallow geothermal well recharge parameters can represent relevant data used to characterize the hydraulic and thermal characteristics of shallow well recharge, which can reflect the heat storage behavior and formation thermal recovery capacity of shallow geothermal wells during the non-heating season.

[0053] For example, the temperature response function can be constructed as: in, Indicates the number Geothermal wells at the moment The effective wellhead temperature; represents the initial temperature of the well; It represents the temperature attenuation coefficient, and its value can be calculated based on the wellhead temperature, bottomhole temperature and geothermal gradient.

[0054] The output function can be constructed as: in, Indicates the number Geothermal wells at the moment Thermal power output; Indicates that the well is at time Traffic volume; Indicates the temperature difference between the inlet and outlet of the well; is the specific heat constant.

[0055] The ground temperature attenuation function can be constructed as: in, Indicates the number The geothermal wells are at The formation temperature attenuation factor; Represents the thermal attenuation coefficient determined based on the thermal conductivity of the formation.

[0056] The shallow heat storage function can be constructed as: in, Shallow geothermal well At the moment Estimated thermal storage capacity; Indicates the recharge flow rate; Indicates the temperature difference between the recharge water and the ground temperature; is the heat storage efficiency coefficient.

[0057] The auxiliary energy supply function can represent the peak load regulation capability of auxiliary equipment (such as air source heat pumps), which can be constructed as follows: in, Indicates the number Auxiliary equipment at all times Available heat; Indicates the energy efficiency coefficient of the equipment, such as heating or cooling performance coefficient; Indicates the rated power of the equipment; Indicates the operating status coefficient, its value is between 0 and 1.

[0058] Of course, in other embodiments of the present disclosure, the temperature response function, output function, geothermal attenuation function, auxiliary energy supply function and shallow heat storage function can also be adaptively set according to actual application scenarios.

[0059] In some embodiments, a multi-scale load forecasting model is constructed based on historical load data and historical meteorological data, including the following technical steps: feature extraction of historical load data and historical meteorological data to obtain structural indicator features and time series change features; based on the structural indicator features, a day-ahead forecasting sub-model for outputting the load of a first time granularity is constructed; based on the time series change features, a mid-day forecasting sub-model for outputting the load of a second time granularity and a real-time forecasting sub-model for outputting the load of a third time granularity are constructed respectively; wherein, the time interval of the first time granularity is longer than the time interval of the second time granularity, and the time interval of the second time granularity is longer than the time interval of the third time granularity.

[0060] Among them, the structural indicator characteristics can represent the periodic or categorical structural characteristics in the load data and meteorological data. The time series change characteristics can represent the continuity characteristics constructed based on the numerical fluctuation trends in the historical load data and historical meteorological data. The first time granularity can represent the time interval unit of the longest forecast period used in the load forecast process, and the time interval can be 24 hours. The second time granularity can represent the time interval unit of the medium forecast period used in the load forecast process, and the time interval can be 3 to 6 hours, which is used to output the load forecast results in the mid-day phase. The third time granularity can represent the time interval unit of the shortest forecast period used in the load forecast process, and the time interval can be 10 minutes, 15 minutes, or 30 minutes, etc., which is used to output the short-term load forecast results at the real-time level. The day-ahead prediction sub-model can represent the prediction model used to output the load forecast results of the first time granularity. The day-ahead prediction sub-model can be constructed using a gradient boosting decision tree, a random forest, or other supervised learning model for static features. The mid-day prediction sub-model can represent a prediction model constructed based on time series change characteristics for outputting load prediction results of the second time granularity. The real-time prediction sub-model can represent a prediction model constructed based on time series change characteristics for outputting load prediction results of the third time granularity. The mid-day prediction sub-model and the real-time prediction sub-model can be constructed using other models suitable for time series data, such as gated recurrent neural networks and long short-term memory networks.

[0061] In this embodiment, targeted inputs are provided to forecast models of varying granularity. A day-ahead forecast sub-model is constructed based on structural indicator characteristics, effectively exploring the regularity and stability of daily heat loads and improving the planning and accuracy of feedforward scheduling strategies. Separately constructing mid-day and real-time forecast sub-models based on temporal variation characteristics further enhances adaptability to dynamic load fluctuations.

[0062] In some embodiments, feature extraction is performed on historical load data and historical meteorological data to obtain structural indicator features and time series change features, including the following technical steps: extracting multi-type structural data based on historical load data and historical meteorological data, wherein the multi-type structural data includes any one or more of date type, month, energy supply area, historical peak load and historical average load; discretizing the multi-type structural data to obtain structural indicator features; and utilizing the time series coupling relationship between historical load data and historical meteorological data to construct time series change features.

[0063] Among them, the date type can represent the calendar attributes corresponding to the load data, including weekdays, weekends or holidays, which are used to characterize the periodic variation characteristics of energy consumption behavior. The month can represent the monthly time mark to which the load data belongs, which is used to characterize the changing trend of the load in different seasons. The energy supply area can represent the geographical number of the geothermal well energy supply area, which is used to reflect the load distribution differences between regions. The historical peak load can represent the maximum load value that occurs within a given statistical period, which is used to characterize extreme energy demand. The historical average load can represent the average load level measured within a specified period. Discretization processing can represent the process of converting the original structural data into discrete input features through interval division or numerical mapping. The time series coupling relationship can represent the correspondence between historical load data and historical meteorological data in the time dimension.

[0064] Specifically, when discretizing multi-type structural data, the following technical steps can be used: the categorical data fields in the multi-type structural data are one-hot encoded to obtain corresponding category vectors. The numerical data fields in the multi-type structural data are then discretely divided according to preset numerical intervals to generate corresponding interval label vectors. The category vectors and the interval label vectors are concatenated and combined to obtain structural indicator features. In this embodiment, by discretizing multi-type structural data, heterogeneous information can be converted into unified structural indicator features, thereby improving the convergence speed and generalization ability of the model during the training phase and improving the prediction accuracy of the day-ahead prediction sub-model.

[0065] In some embodiments, the time series coupling relationship between historical load data and historical meteorological data is used to construct time series change characteristics, including the following technical steps: constructing a load change rate sequence based on historical load data, and constructing a temperature change sequence and a humidity change sequence based on historical meteorological data; cross-operating the load change rate sequence and the temperature change sequence to obtain a load-temperature cross sequence; splicing and combining the load change rate sequence and the humidity change sequence to obtain a load-humidity joint sequence; constructing time series change characteristics based on the load change rate sequence, the temperature change sequence, the humidity change sequence, the load-temperature cross sequence, and the load-humidity joint sequence.

[0066] The load change rate series can be a time series generated by performing differential or ratio calculations on heat load values at adjacent time points based on historical load data at set time intervals. This series is used to characterize the dynamic change trend of heat load within a unit of time. The temperature change series can be a time-sequential sequence of temperature values constructed based on external ambient temperature values recorded in historical meteorological data. The humidity change series can be a time-sequential sequence of humidity values constructed based on humidity values in historical meteorological data. The load-temperature crossover series is a series generated by performing a point-by-point crossover operation on the load change rate series and the temperature change series. This series can be used to characterize the relationship between load and temperature. The load-humidity joint series is a series constructed by concatenating the load change rate series and the humidity change series along a feature dimension. This series can be used to describe the synchronous changes between load and humidity. Furthermore, the time intervals of the load change rate series, temperature change series, humidity change series, and load-temperature crossover series can be set based on the time granularity of the corresponding prediction sub-model. Time series variation characteristics at different time granularities are used to construct different prediction sub-models.

[0067] In this embodiment, the load-temperature cross sequence and the load-humidity joint sequence can more accurately reflect the correlation between load changes and temperature and humidity conditions. Especially in weather with high humidity and rapid temperature changes, the model can identify the trend of load increase or decrease in advance, thereby improving the timeliness and matching of the prediction results.

[0068] In some embodiments, the day-ahead prediction sub-model can be constructed based on a gradient boosting decision tree. Specifically, first, a training data set is constructed based on the structural indicator characteristics, and each sample in the training data set contains a structural indicator characteristic and a corresponding historical load value. The structural indicator characteristic includes one or more of the date type, month number, energy supply area number, historical peak load and historical average load. Then, based on the training data set, a gradient boosting decision tree regression algorithm is used for modeling, and the first regression sub-tree is initialized to fit the initial residual of the sample. According to the preset number of iterations or error convergence conditions, multiple regression sub-trees are gradually constructed, and the output result of the overall model is updated in each iteration. Multiple regression sub-trees are integrated to obtain a day-ahead prediction sub-model for characterizing the mapping relationship between different structural indicator characteristics and the day-ahead heat load.

[0069] In some embodiments, the mid-day prediction submodel and the real-time prediction submodel can be constructed using a long short-term memory (LSTM) network. Specifically, a training dataset is first constructed based on temporal variation characteristics. The training dataset includes several sample sequences captured at a fixed time step. The sample sequences consist of a load change rate sequence, a temperature change sequence, a humidity change sequence, a load-temperature crossover sequence, and a load-humidity joint sequence. Next, a neural network structure is constructed, comprising an input layer, multiple LSTM network unit layers, a fully connected layer, and an output layer. The input layer receives the sample sequence as input, the LSTM network unit layer is used to extract the temporal correlation features in the sample sequence, the fully connected layer is used to transform the extracted results, and the output layer is used to output a feature embedding vector. Then, the actual load values within the historical time window are used as supervisory labels. The difference between the predicted and actual values is calculated based on a mean squared error loss function, and the weight parameters of the neural network structure are iteratively updated using a gradient descent algorithm. Finally, the aforementioned training process is repeated until the loss function meets the preset convergence condition, ultimately obtaining the mid-day prediction submodel for medium-time granularity load modeling and the real-time prediction submodel for short-time granularity load modeling, respectively.

[0070] In some embodiments, when determining the load forecast result for a target time period using a multi-scale load forecasting model, first, historical load data and historical meteorological data covering the current time point and a preset time period before it are obtained. The historical load data is used to characterize the dynamic change trend of the regional heat load, and the historical meteorological data includes ambient temperature, humidity, and other environmental data within the corresponding time period. Secondly, based on the historical load data and historical meteorological data, structural indicator features and time series variation features are extracted. The structural indicator features are then input into the trained day-ahead prediction sub-model to obtain a day-ahead load forecast result corresponding to the first time granularity. Next, the time series variation features are input into the trained mid-day prediction sub-model and real-time prediction sub-model, respectively, to obtain a mid-day load forecast result corresponding to the second time granularity and a real-time load forecast result corresponding to the third time granularity, respectively. Finally, based on the time granularity requirements of the current scheduling cycle, the day-ahead load forecast result, the mid-day load forecast result, and the real-time load forecast result are adaptively combined to generate the load forecast result for the target time period.

[0071] Furthermore, the adaptive combination of the day-ahead load forecast results, the mid-day load forecast results, and the real-time load forecast results can be performed through the following steps: First, based on the target time granularity corresponding to the current scheduling period, the forecast time range to be used is determined, and the target time range is divided into multiple forecast segments, with the time length of each forecast segment consistent with the target time granularity. Second, for forecast segments that fall after the current time point and have an interval greater than a preset duration (e.g., 12 hours), the forecast value at the corresponding time point in the day-ahead load forecast result is selected as the initial forecast value for that segment. Then, for forecast segments that fall after the current time point and have an interval within a short- to medium-term range (e.g., 1 to 12 hours), the forecast value at the corresponding time point in the mid-day load forecast result is selected as the initial forecast value for that segment. Finally, for forecast segments close to the current time point (e.g., with a granularity less than 1 hour), the forecast value at the corresponding time point in the real-time load forecast result is selected as the initial forecast value for that segment. Finally, after obtaining the prediction results of each granularity, for the prediction segments with time overlap, the output results of the prediction model with the smallest time granularity are retained first, and the sliding window weighted smoothing method is used to perform boundary transition processing to obtain continuous and consistent load forecast results for the target period.

[0072] In some embodiments, reference Figure 2 As shown in the figure, the optimal scheduling parameters of the shallow geothermal well group and the deep geothermal well group in the current scheduling period are obtained by joint calculation using the well group output model, load forecast results and multi-objective optimization function. The specific technical steps include the following: Step S210: construct a multi-objective optimization function based on formation heat balance, operating cost, carbon emissions and exergy efficiency.

[0073] Among them, formation heat balance can be used to represent the ability of the formation temperature field to maintain a dynamic stable state during the continuous operation of the geothermal well cluster. Operating costs can be used to represent the specific expenses incurred during the operation of various geothermal system equipment, including the geothermal well cluster, heat pump system, and thermal storage unit, during the scheduling cycle. Carbon emissions can be used to represent the carbon dioxide emissions caused by the consumption of external electricity or auxiliary fuel by various energy conversion equipment during the scheduling cycle. Exergy efficiency can be used to represent the ratio of the effective heat output per unit time to the total energy consumed by the system.

[0074] Step S220 , based on the well group output model and the load forecast result, obtain multiple sets of candidate scheduling parameter sets within the current scheduling period.

[0075] Among them, the scheduling parameters can represent the set of control variables used to regulate the operating status of shallow geothermal well groups and deep geothermal well groups in the current scheduling cycle. The scheduling parameters include but are not limited to: the start and stop status of each geothermal well; the target water outlet temperature of the geothermal well; the target heating flow rate of each well group; the participation ratio or working status of different energy equipment (such as heat pumps, heat storage units); and the energy supply ratio of the target energy supply load in the current scheduling cycle.

[0076] In the specific implementation process, first, based on the heat load forecast results corresponding to the current scheduling period, the target heating load value for that scheduling period is determined. The target heating load value represents the thermal power demand that must be met by each heat source unit. Second, based on the well group output model and combined with the current operating parameters of the shallow and deep geothermal well groups, the adjustable output boundaries of each well group within the current scheduling period are obtained. The adjustable output boundaries include minimum and maximum output limits. Then, based on the current operating scenario, including seasonality, load demand, and abnormal conditions, a set of adjustable devices that meet the start-stop constraints are selected from the geothermal system, short-term heat storage system, and air-source heat pump system to form a preliminary list of available devices. Finally, under the condition that the target heating load value is met, multiple sets of candidate scheduling parameters containing different device output ratios are generated using various combinations. Each set of candidate scheduling parameters includes the start-stop status, unit output level, and target energy supply ratio of each device within the current scheduling period.

[0077] Step S230 , using a target genetic algorithm to obtain optimal scheduling parameters that satisfy a multi-objective optimization function from multiple sets of candidate scheduling parameters.

[0078] The term "genetic algorithm" may refer to an optimization algorithm that simulates natural selection and biological evolution. In the disclosed embodiments, the genetic algorithm may be a non-dominated sorting-based multi-objective genetic optimization algorithm, a multi-objective particle swarm optimization algorithm, a multi-objective differential evolution algorithm, or other suitable genetic algorithms. The optimal scheduling parameters may represent a set of scheduling parameters obtained by screening a set of candidate scheduling parameters using a multi-objective optimization function within the current scheduling cycle.

[0079] In some embodiments, a multi-objective optimization function is constructed based on formation heat balance, operating cost, carbon emissions and exergy efficiency, specifically including the following technical steps: constructing a temperature change rate function reflecting the impact of the heat extraction process on the formation temperature based on the thermal conductivity of the geological layer corresponding to the geothermal well group, the temperature difference between the reinjection fluid and the output fluid, and the temperature gradient between the wellhead and the bottom hole; determining a heat extraction upper limit value that makes the temperature change rate equal to a preset rock formation temperature change rate threshold based on the temperature change rate function; and constructing a multi-objective optimization function based on the heat extraction upper limit value, the operating cost function, the carbon emission function and the exergy efficiency function.

[0080] The upper limit of heat extraction represents the maximum allowable heat extraction from a geothermal well cluster within the current scheduling cycle, while satisfying the formation's thermal balance constraints. The operating cost function represents a functional expression that reflects the cost relationship corresponding to the unit heat output of various heat source devices within the scheduling cycle. The carbon emission function represents a functional expression that reflects the total amount of carbon dioxide emissions generated during the operation of different heat source devices. The exergy efficiency function represents a functional expression used to measure the efficiency relationship between the unit input energy consumption and effective heat output of each heat source in a multi-heat source coordinated energy supply system.

[0081] For example, the temperature change rate function can be expressed as: in, It indicates the rate of change of formation temperature per unit time under the action of geothermal well; Indicates the thermal conductivity of the formation; Indicates the temperature gradient between the bottom hole temperature and the wellhead temperature; Indicates the density of the formation medium; Indicates the specific heat capacity of the formation medium; represents the heat affected volume; represents the thermal disturbance coefficient; Indicates the temperature difference between the outlet water temperature and the recharge water temperature.

[0082] According to the above temperature change rate function, the upper limit of the allowable annual temperature change rate of the rock formation is set to To avoid formation thermal imbalance, the following thermal balance constraints should be met: Under the premise of meeting the above constraints, combined with the length of the scheduling cycle , construct the upper limit function of heat: in, Indicates the maximum allowable heat extraction of the corresponding well group in the current scheduling cycle.

[0083] In some embodiments, the target genetic algorithm is a non-dominated sorting multi-objective genetic algorithm (NSGA-II), and the target genetic algorithm is used to obtain optimal scheduling parameters that satisfy a multi-objective optimization function from multiple sets of candidate scheduling parameter sets. The method specifically includes the following technical steps: constructing an initial scheduling population based on the candidate scheduling parameter sets, where each scheduling parameter individual in the initial scheduling population includes output configuration variables for a shallow geothermal well group and a deep geothermal well group; performing a multi-objective fitness evaluation on the scheduling parameter individuals in the initial scheduling population using the multi-objective optimization function, and dividing the scheduling parameter individuals into non-dominated levels according to the non-dominated sorting principle based on the evaluation results, and calculating the corresponding congestion index within each level; selecting some scheduling parameter individuals as parent individuals based on the non-dominated levels and congestion index, performing crossover and mutation operations, and generating a next-generation scheduling parameter population; repeating the multi-objective fitness evaluation and non-dominated sorting operations on the next-generation scheduling parameter population, and selecting the optimal scheduling parameter from all current scheduling parameter individuals when a preset iteration termination condition is satisfied.

[0084] Among them, the multi-objective genetic algorithm of non-dominated sorting is used as the target genetic algorithm. There is no need to set fixed weights for objectives such as operating costs, carbon emissions, and exergy efficiency, which avoids the scheduling parameters from being biased towards a certain goal. It also has low time complexity and good convergence, and is suitable for application scenarios of geothermal energy supply systems with short scheduling cycles and limited computing resources.

[0085] In some embodiments, the above-mentioned multi-level geothermal well coordinated scheduling method based on multi-time scale prediction may also include the following technical steps: collecting the operating parameters of shallow geothermal well groups, deep geothermal well groups, short-term heat storage equipment and air source heat pumps, and determining the operating status of each heat source unit based on the operating parameters; in response to the operating status of any heat source unit being a fault, calling the standby output configuration strategy corresponding to the fault type, and adjusting the output ratio of each heat source unit in the scheduling parameters in combination with the current load forecast results and the standby output capacity; during non-heating periods, using deep geothermal well groups and / or building heat to replenish heat to the shallow geothermal well groups; obtaining temperature distribution data of shallow geothermal wells, and updating the shallow geothermal well recharge parameters in the well group output model based on the temperature distribution data.

[0086] The "standby output configuration strategy" can represent a scheduling parameter adjustment rule pre-set to address specific heat source unit failure scenarios. This strategy allocates a target output ratio for alternative heat sources based on the operating capacity of currently available heat source units. Standby output capacity can represent the dispatchable output capacity of heat source units that are not currently operating but can be deployed in response to a failure. Standby heat source units can be any one or more of deep geothermal wells, short-term heat storage devices, and air-source heat pumps. Heat recharge can represent the process of recharging heat energy from deep geothermal wells and / or building heat loads into shallow geothermal wells during non-heating periods. Building heat can represent the recoverable heat energy generated during building operation due to equipment operation, human activity, solar radiation, and the heat storage and heat transfer effects of the building envelope. Shallow geothermal well recharge parameters can represent a set of parameters used to describe the operating characteristics of shallow geothermal wells during the heat recharge process, including but not limited to recharge temperature, recharge flow rate, recharge duration, and recharge pressure.

[0087] In a specific implementation, the operating parameters of the shallow geothermal well cluster, deep geothermal well cluster, short-term heat storage device, and air-source heat pump can be first obtained. These operating parameters include information such as outlet water temperature, return water temperature, flow rate, pressure, operating power, operating status indicator, and equipment alarm signals. The operating status of each heat source unit is analyzed based on the operating parameters. If any heat source unit's operating status indicator is abnormal or an equipment alarm signal is detected, the heat source unit is determined to be in a fault state. In response to a heat source unit failure, a backup output configuration strategy matching the fault type is invoked from a preset output configuration strategy library. The backup output configuration strategy may include the activation order of other heat source units to replace the currently failed unit, the target load distribution ratio, and scheduling priority information. Based on the current load forecast and the output capacity of the available backup heat source units, the backup output capacity of each backup heat source unit is determined, and the scheduling parameters are updated accordingly. Specifically, the target output ratio of the shallow geothermal well cluster, deep geothermal well cluster, short-term heat storage device, and air-source heat pump is adjusted to form a dynamic scheduling plan that matches the current operating status. For example, if a deep geothermal well group fails, the air source heat pump will be started first, and the operating power of the shallow geothermal well group will be increased; if the shallow geothermal well group fails, the circulation flow rate of the deep geothermal well group will be increased, and the air source heat pump will be called as a supplementary heat source; if the air source heat pump fails, the shallow and deep well groups will be combined to extract heat, and the short-term heat storage equipment will be activated to release the stored heat; if the short-term heat storage equipment fails, the output ratio of the shallow and deep geothermal wells will be redistributed according to their current heat extraction capacity, and the air source heat pump capacity will be fully mobilized to make up for the heat gap.

[0088] Furthermore, when updating the shallow geothermal well recharge parameters in the well group output model based on the temperature distribution data, the following steps can be performed: The first step is to calculate the heat received by the shallow geothermal well based on the water supply parameters of the replenishment heat source: in, It represents the total heat received by the shallow well per unit time. Indicates the number of heat sources involved in replenishment, represents the specific heat capacity of water, represents the density of water, Indicates the The flow rate of a heat source, Indicates the The water supply temperature of each heat source, Indicates the initial recharge temperature of shallow wells.

[0089] The second step is to collect temperature distribution data of shallow geothermal wells. , used to judge the degree of thermal field recovery, where Represents position in three-dimensional space and time The heat recovery rate of shallow geothermal wells is calculated by combining the replenishment heat and temperature rise: in, represents the thermal recovery rate, represents the effective heat exchange area of shallow wells, represents the average temperature increase, based on Calculate the difference and get: Indicates the time period for covering.

[0090] The third step is to update the shallow well heat storage capacity function using the heat recovery rate: in, Indicates time The total shallow heat storage Indicates the start time of hot refill. represents the integration variable.

[0091] In addition, in other embodiments of the present disclosure, when conducting multi-level geothermal well collaborative scheduling based on multi-time scale prediction, it is also possible to dynamically match different scheduling scenario strategies in combination with the actual operating season, ambient temperature range and load level, and generate a corresponding scheduling parameter set under the guidance of the strategy.

[0092] Specifically, in the winter heating scheduling scenario, in response to operating conditions where the external ambient temperature is between -15°C and 5°C, the load forecast model generates load forecast results for three time nodes: day-ahead, mid-day, and real-time, which serve as the input basis for building the equipment output model. Based on the equipment output model, the scheduling system can call for deep geothermal wells and plate heat exchangers for combined heating under low load conditions, call for shallow and deep geothermal wells for combined heating under medium load conditions, and further call for ground-source heat pump systems to provide energy supplement support under high load conditions. Parameters such as the underground temperature field, pipe network pressure difference, and user-end temperature change rate are collected with an update cycle of 15 minutes, and the output ratio of various heat source units is dynamically adjusted based on real-time feedback results.

[0093] In the summer cooling scheduling scenario, in response to the ambient temperature of 25℃ to 40℃ and the cooling load demand of 6MW to 18MW, the shallow well group is preferentially called to bear the basic cooling load, and the day and night heat storage and heat release functions of the short-term heat storage system and the elastic adjustment capability of the air source heat pump system are combined to complete the cooling load distribution.

[0094] Furthermore, during the seasonal scheduling phase, during the spring recovery period, based on the operating history of the shallow well group and the thermal balance state of the formation, a gradient of heat extraction intensity can be set for the shallow well group, the target recovery temperature of each well and formation can be calculated, and the deep wells can be controlled to replenish heat to the shallow wells, while the well group output model can be updated. During the summer cooling period, using the building cooling load transfer as a carrier, heat is replenished to the formation through shallow wells to achieve underground heat storage reconstruction. The deep well group will collaboratively start the heat penetration operation mode, and the dynamic soil thermal property database will be used to correct the heat conduction model in real time. During the autumn storage period, the heat storage regulation mechanism of the phase change heat storage unit will be triggered in combination with the seasonal transition load fluctuation characteristics. Combined with the preventive maintenance of the well group and the deep-to-shallow heat replenishment strategy, the system energy pre-charge regulation can be achieved. In addition, during the cross-seasonal energy storage process, the shallow well heat storage unit can be functionally replaced or supplemented by constructing aquifer heat storage, thereby enhancing the system's medium- and long-term heat storage capacity while ensuring the stability of the geothermal system's thermal field.

[0095] In extreme weather emergency dispatch scenarios, the dispatch system can activate the pre-stimulation mode of deep geothermal wells and inject high-temperature fluid into the short-term heat storage system to raise its output temperature to within the designed range. Simultaneously, it applies a shock heat extraction operation to the deep well cluster and activates the heat storage pulse release mechanism to provide rapid heat compensation at a rate of 15% every two hours. The air-source heat pump system serves as a backup heat source during this process, with its operating power limited to less than 20% of the total system load to achieve energy security and redundancy control.

[0096] In some embodiments, the scheduling method in the above embodiment can be performed as follows Figure 3Specifically, the collaborative scheduling system provided in this embodiment includes four functional closed loops: data collection, load forecasting, intelligent scheduling, and effectiveness evaluation. By building a multi-timescale load forecasting and multi-source heat energy optimization allocation mechanism, it supports the joint operation and optimal regulation of multi-level geothermal wells (including shallow and deep geothermal well clusters) in different operating scenarios.

[0097] The data acquisition module sequentially acquires local historical meteorological data, historical operating data for various systems, and other load data, including personnel activities, equipment status, and building characteristics. This raw data is archived in the data storage module and structured through business streamlining and data governance processes. The data service module provides data access to downstream modules based on unified standards, enabling the load forecasting and intelligent scheduling modules to access required information through consistent data interfaces.

[0098] The load forecasting module utilizes structured data to construct a two-layer structure consisting of feature extraction and algorithmic modeling. The feature extraction component extracts temporal, meteorological, and hysteresis features, characterizing the correlation between thermal load and meteorological conditions. The algorithmic modeling component, comprising models such as time series models, tree models, and BP neural networks, is collectively referred to as the load forecasting model. These models are used to construct load forecasting mechanisms at different time scales (day-ahead, midday, and real-time). Based on the feature inputs, the load forecasting model outputs load forecast results, which are then passed as input to the intelligent scheduling module.

[0099] In the intelligent scheduling module, a model system is constructed using equipment models, system models, and operation models to describe the operating mechanisms of the geothermal well system and auxiliary heat source system. This model then drives the intelligent scheduling strategy engine to perform multi-objective optimization control. After receiving the load forecast results, the intelligent scheduling strategy engine combines and calls the set cross-season energy storage strategy, peak-valley coordination strategy, daily energy storage strategy, and emergency linkage strategy to generate the optimal scheduling strategy. At the same time, the module integrates components such as boundary conditions, optimization objectives, and optimization algorithm construction. It completes the search and solution of the scheduling parameter space in the algorithm optimization unit and sends the optimized strategy to the actual operation system for execution.

[0100] The system's execution results are fed back to the effectiveness evaluation module, where they are evaluated by the energy efficiency evaluation model and engine. Evaluation metrics include energy efficiency, exergy efficiency, and power consumption per unit calorific value, respectively, assessing energy utilization efficiency, scheduling accuracy, and system economics. Furthermore, through a multi-strategy clustering approach, including optimal energy efficiency, minimum carbon emissions, optimal performance, minimum cost, and a comprehensive strategy, the current strategy results are compared, analyzed, and dynamically optimized. The evaluation results are then fed back to the intelligent scheduling module for strategy and algorithm optimization, enabling continuous iterative updates and optimization of scheduling results.

[0101] It should be noted that although the steps of the method disclosed herein are depicted in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in that particular order, or that all steps must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one, and / or one step may be decomposed into multiple steps.

[0102] In addition, in this exemplary embodiment, a multi-level geothermal well coordinated scheduling system based on multi-time scale prediction is also provided. Figure 4 As shown, the multi-level geothermal well coordinated scheduling system 400 based on multi-time scale prediction may include: an output model construction module 410, a prediction model construction module 420, a load prediction module 430 and an intelligent scheduling module 440. Among them: The output model construction module 410 can be used to construct a well group output model based on the operating parameters of the shallow geothermal well group and the deep geothermal well group. The well group output model can characterize the unit heat output capacity, heat storage capacity and temperature decay characteristics of each well group; The prediction model building module 420 may be used to build a multi-scale load prediction model based on historical load data and historical meteorological data; The load forecasting module 430 may be used to determine the load forecast results for the target period using a multi-scale load forecasting model. The load forecast results include day-ahead load, mid-day load, and real-time load. The intelligent scheduling module 440 can be used to perform joint calculations using the well group output model, load forecast results, and multi-objective optimization functions to obtain the optimal scheduling parameters for the shallow geothermal well group and the deep geothermal well group within the current scheduling cycle.

[0103] The specific details of each module of the above multi-level geothermal well collaborative scheduling system based on multi-time scale prediction have been described in detail in the corresponding multi-level geothermal well collaborative scheduling method based on multi-time scale prediction, so they will not be repeated here.

[0104] It should be noted that although the detailed description above mentions several modules or units of the multi-level geothermal well coordinated scheduling system based on multi-timescale prediction, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in a single module or unit. Conversely, the features and functions of a single module or unit described above can be further divided and embodied by multiple modules or units.

[0105] In addition, in an exemplary embodiment of the present disclosure, an electronic device is also provided that can implement the above-mentioned multi-level geothermal well coordinated scheduling method based on multi-time-scale prediction.

[0106] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods, or program products. Therefore, various aspects of the present disclosure may be implemented in the following forms: a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which may be collectively referred to herein as a "circuit," "module," or "system."

[0107] Refer to the following Figure 5 hereinafter, an electronic device 500 according to such an embodiment of the present disclosure is described. Figure 5 The electronic device 500 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0108] like Figure 5 As shown, electronic device 500 is implemented as a general-purpose computing device. Components of electronic device 500 may include, but are not limited to, the aforementioned at least one processing unit 510, the aforementioned at least one storage unit 520, a bus 530 connecting various system components (including storage unit 520 and processing unit 510), and a display unit 540.

[0109] The storage unit stores program code, which can be executed by the processing unit 510, causing the processing unit 510 to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of the present disclosure. The storage unit 520 may include a readable medium in the form of a volatile memory unit, such as a random access memory unit (RAM) 521 and / or a cache memory 522, and may further include a read-only memory unit (ROM) 523.

[0110] The storage unit 520 may also include a program / utility 524 having a set (at least one) of program modules 525, such program modules 525 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0111] Bus 530 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0112] The electronic device 500 can also communicate with one or more external devices 570 (e.g., a keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 500, and / or any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., a router, modem, etc.). This communication can occur via an input / output (I / O) interface 550. Furthermore, the electronic device 500 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 560. As shown, the network adapter 560 communicates with other modules of the electronic device 500 via a bus 530. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 500, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0113] Through the description of the above embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by combining software with necessary hardware.

[0114] In exemplary embodiments of the present disclosure, a computer-readable storage medium is also provided, on which is stored a program product capable of implementing the aforementioned methods of this specification. In some possible embodiments, various aspects of the present disclosure may also be implemented in the form of a program product, which includes program code. When the program product is executed on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the "Exemplary Methods" section of this specification.

[0115] refer to Figure 6 As shown, a program product 600 for implementing the multi-level geothermal well coordinated scheduling method based on multi-timescale prediction according to an embodiment of the present disclosure is described. This program product 600 can be implemented in a portable compact disc read-only memory (CD-ROM) and include program code, and can be executed on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0116] The program product may utilize any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0117] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0118] Furthermore, the figures above are merely illustrative of the processes included in the methods according to exemplary embodiments of the present disclosure and are not intended to be limiting. It is readily understood that the processes illustrated in the figures above do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0119] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A multi-level geothermal well coordinated scheduling method based on multi-time scale prediction, characterized in that: include: Based on the operating parameters of shallow and deep geothermal well clusters, a well cluster output model is constructed. The well cluster output model can characterize the unit heat output capacity, heat storage capacity, and temperature decay characteristics of each well cluster; Construct a multi-scale load forecasting model based on historical load data and historical meteorological data; Determine a load forecast result for a target period using the multi-scale load forecasting model, wherein the load forecast result includes day-ahead load, mid-day load, and real-time load; The well group output model, the load forecast result and the multi-objective optimization function are used to perform joint calculations to obtain the optimal scheduling parameters of the shallow geothermal well group and the deep geothermal well group in the current scheduling cycle.

2. The multi-level geothermal well coordinated scheduling method based on multi-time scale prediction according to claim 1 is characterized in that: The well group output model constructed based on the operating parameters of the shallow geothermal well group and the deep geothermal well group includes: Obtaining operating parameters of the shallow geothermal well group and the deep geothermal well group, the operating parameters including temperature field data, well output parameters, soil thermal conductivity, auxiliary equipment performance parameters, and shallow geothermal well recharge parameters; Constructing a temperature response function based on the temperature field data to characterize the temperature change trend of each geothermal well during operation; Constructing an output function based on the well output parameters to characterize the heat production capacity of each geothermal well per unit time; Based on the soil thermal conductivity, a geothermal attenuation function is constructed to characterize the attenuation of the formation temperature of each geothermal well over time; Based on the auxiliary equipment performance parameters, constructing an auxiliary energy supply function for characterizing the output characteristics of the auxiliary equipment per unit time; Based on the shallow geothermal well recharge parameters, constructing a shallow heat storage function for characterizing the heat storage capacity of the shallow geothermal well during a non-heating period; The well group output model is constructed based on the temperature response function, output function, geothermal attenuation function, auxiliary energy supply function and shallow heat storage function.

3. The multi-level geothermal well coordinated scheduling method based on multi-time scale prediction according to claim 1 is characterized in that: The multi-scale load forecasting model is constructed based on historical load data and historical meteorological data, including: Extracting features from the historical load data and the historical meteorological data to obtain structural indicator features and time series change features; Based on the structural indicator characteristics, constructing a day-ahead prediction sub-model for outputting the first time granularity load; Based on the time series variation characteristics, constructing a mid-day prediction sub-model for outputting the load at the second time granularity and a real-time prediction sub-model for outputting the load at the third time granularity respectively; The time interval of the first time granularity is longer than the time interval of the second time granularity, and the time interval of the second time granularity is longer than the time interval of the third time granularity.

4. The multi-level geothermal well coordinated scheduling method based on multi-time scale prediction according to claim 3 is characterized in that: The feature extraction of the historical load data and the historical meteorological data to obtain structural indicator features and time series change features includes: Extracting multi-type structure data based on the historical load data and the historical meteorological data, wherein the multi-type structure data includes any one or more of date type, month, energy supply area, historical peak load and average load indicators; Discretizing the multi-type structural data to obtain the structural indicator features; The time series variation characteristics are constructed by utilizing the time series coupling relationship between the historical load data and the historical meteorological data.

5. The multi-level geothermal well coordinated scheduling method based on multi-time scale prediction according to claim 4 is characterized in that: The constructing of the time series variation characteristics by utilizing the time series coupling relationship between the historical load data and the historical meteorological data includes: Constructing a load change rate sequence based on the historical load data, and constructing a temperature change sequence and a humidity change sequence based on the historical meteorological data; Performing a cross operation on the load change rate sequence and the temperature change sequence to obtain a load-temperature cross sequence; The load change rate sequence and the humidity change sequence are combined to obtain a load-humidity combined sequence; The time series variation feature is constructed based on the load change rate sequence, the temperature change sequence, the humidity change sequence, the load-temperature cross sequence, and the load-humidity joint sequence.

6. The multi-level geothermal well coordinated scheduling method based on multi-time scale prediction according to claim 1 is characterized in that: The method of performing a joint calculation using the well group output model, the load forecast result, and the multi-objective optimization function to obtain the optimal scheduling parameters of the shallow geothermal well group and the deep geothermal well group in the current scheduling period includes: Constructing the multi-objective optimization function based on formation heat balance, operating cost, carbon emissions and exergy efficiency; Based on the well group output model and the load forecast result, obtaining multiple sets of candidate scheduling parameter sets in the current scheduling period; An objective genetic algorithm is used to obtain optimal scheduling parameters that meet the multi-objective optimization function from the multiple sets of candidate scheduling parameters.

7. The multi-level geothermal well coordinated scheduling method based on multi-time scale prediction according to claim 6 is characterized in that: The multi-objective optimization function is constructed based on formation heat balance, operating cost, carbon emission and exergy efficiency, including: Based on the thermal conductivity of the geological layer corresponding to the geothermal well group, the temperature difference between the reinjection fluid and the output fluid, and the temperature gradient between the wellhead and the bottom hole, a temperature change rate function is constructed to reflect the impact of the heat extraction process on the formation temperature. Determining, based on the temperature change rate function, an upper limit of heat extraction that makes the temperature change rate equal to a preset rock formation temperature change rate threshold; The multi-objective optimization function is constructed based on the heat extraction upper limit value, the operation cost function, the carbon emission function and the exergy efficiency function.

8. The multi-level geothermal well coordinated scheduling method based on multi-time scale prediction according to claim 6 is characterized in that: The target genetic algorithm is a non-dominated sorting multi-objective genetic algorithm, and the use of the target genetic algorithm to obtain the optimal scheduling parameters that meet the multi-objective optimization function from the multiple sets of candidate scheduling parameters includes: constructing an initial scheduling population based on the candidate scheduling parameter set, wherein each scheduling parameter individual in the initial scheduling population includes output configuration variables of a shallow geothermal well group and a deep geothermal well group; Performing a multi-objective fitness evaluation on the scheduling parameter individuals in the initial scheduling population using the multi-objective optimization function, dividing the scheduling parameter individuals into non-dominated levels according to the non-dominated sorting principle based on the evaluation results, and calculating the corresponding congestion index within each level; Based on the non-dominated level and the congestion index, some scheduling parameter individuals are selected as parent individuals, and crossover and mutation operations are performed to generate the next generation scheduling parameter population; The multi-objective fitness evaluation and non-dominated sorting operations are repeatedly performed on the next generation scheduling parameter population, and the optimal scheduling parameter is selected from all current scheduling parameter individuals when a preset iteration termination condition is satisfied.

9. The multi-level geothermal well coordinated scheduling method based on multi-time scale prediction according to claim 1 is characterized in that: Also includes: collecting operating parameters of the shallow geothermal well group, the deep geothermal well group, the short-term heat storage device, and the air source heat pump, and determining the operating status of each heat source unit based on the operating parameters; In response to a failure in the operating state of any of the heat source units, a backup output configuration strategy corresponding to the failure type is called, and the output ratio of each heat source unit in the scheduling parameter is adjusted in combination with the current load forecast result and the backup output capacity; During non-heating periods, the deep geothermal well group and / or building heat are used to replenish the heat of the shallow geothermal well group; The temperature distribution data of the shallow geothermal wells is obtained, and the reinjection parameters of the shallow geothermal wells in the well group output model are updated according to the temperature distribution data.

10. A multi-level geothermal well coordinated scheduling system based on multi-time scale prediction, characterized in that: include: An output model construction module is used to construct a well group output model based on the operating parameters of the shallow geothermal well group and the deep geothermal well group. The well group output model can characterize the unit heat output capacity, heat storage capacity and temperature decay characteristics of each well group; A forecasting model building module is used to build a multi-scale load forecasting model based on historical load data and historical meteorological data; A load forecasting module, configured to determine a load forecast result for a target period using the multi-scale load forecasting model, wherein the load forecast result includes a day-ahead load, a mid-day load, and a real-time load; An intelligent scheduling module is used to perform joint calculations using the well group output model, the load forecast results, and a multi-objective optimization function to obtain optimal scheduling parameters for the shallow geothermal well group and the deep geothermal well group within the current scheduling cycle.

Images