Deep and shallow layer geothermal energy coupling scheduling method and system based on thermoelectric linkage

Abstract

The invention provides a deep and shallow layer geothermal energy coupling scheduling method and system based on thermoelectric linkage, and relates to the technical field of power distribution. The method comprises the following steps: determining a thermal load prediction value of a target energy supply park; predicting the response deviation probability of the shallow geothermal energy in the target time period; an adjusting deviation time period is recognized from the target time periods, and a heat supply compensation value needed by the adjusting deviation time period is determined; screening out a coincidence deviation time period in which the available residual electric quantity meets the heat supply compensation value from the adjustment deviation time periods; determining a target adjustment time period before each coincidence deviation time period, and determining the credibility of the available residual electric quantity in the coincidence deviation time period; and based on the credibility, screening out a reliable adjustment time period from the target adjustment time period, and transmitting the deep geothermal energy to the shallow geothermal energy by using the available residual electric quantity in the reliable adjustment time period. According to the technical scheme, the new energy utilization rate and the cooperative scheduling efficiency and response timeliness between deep and shallow heat sources can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of power distribution, and in particular to a method and system for coupling scheduling of deep and shallow geothermal energy based on thermoelectric linkage. Background Art

[0002] Among existing energy utilization technologies, geothermal energy, due to its clean, stable, and abundant resources, is considered a key pillar of future low-carbon energy supply. Shallow geothermal energy, due to its shallow burial depth and high heat transfer efficiency, offers excellent rapid response capabilities and is widely used in operational scenarios with frequent load fluctuations. In contrast, deep geothermal energy, while offering advantages such as stable output and a long energy supply cycle, suffers from high system inertia and high response delay, making it difficult to meet rapidly fluctuating heat load demands.

[0003] However, in actual energy supply scenarios where both shallow and deep geothermal energy are available, existing technologies typically use static ratios or preset priority rules to schedule and allocate shallow and deep geothermal energy. This fails to fully account for the differences in their response characteristics, resulting in insufficient coordination between shallow and deep heat sources and delayed thermal energy regulation. Furthermore, the geothermal energy scheduling process typically fails to consider the remaining power of new energy equipment in the energy supply scenario, leading to insufficient utilization of renewable energy and failure to achieve heat-power synergy.

[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 deep-shallow geothermal energy coupling scheduling method based on heat and power linkage, a deep-shallow geothermal energy coupling scheduling system based on heat and power linkage, an electronic device and a computer-readable storage medium. By introducing a multi-level judgment mechanism of heat load prediction, response deviation identification and remaining power credibility assessment, deep geothermal energy is called upon in advance by utilizing the remaining power of new energy, thereby at least to a certain extent improving the utilization rate of new energy and the coordinated scheduling efficiency and response timeliness between deep and shallow heat sources.

[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 method for coupling scheduling of deep and shallow geothermal energy based on heat and power linkage is provided, the method comprising: determining a heat load forecast value of the target energy supply park in multiple target time periods in the future based on historical heat load data, historical environmental data, and current environmental data of the target energy supply park; predicting a response deviation probability of the shallow geothermal energy in the target energy supply park in the target time period based on the heat load forecast value and multiple adjustment deviation state data of the shallow geothermal energy in the target energy supply park at the current capacity; identifying an adjustment deviation time period in which the response deviation probability exceeds a preset threshold value from the target time period, and determining the adjustment deviation time period. The method comprises the following steps: determining the available remaining power of the new energy equipment in the energy supply park during the adjustment deviation period, and screening out the coincidence deviation period in which the available remaining power meets the heating compensation value from the adjustment deviation period; determining the target adjustment period before each coincidence deviation period, and determining the credibility of the available remaining power in the coincidence deviation period corresponding to each target adjustment period based on historical remaining power data; screening out a reliable adjustment period from the target adjustment period based on the credibility, and utilizing the available remaining power to transmit deep geothermal energy to shallow geothermal energy during the reliable adjustment period.

[0008] According to a second aspect of the embodiment of the present disclosure, a deep-shallow geothermal energy coupling scheduling system based on heat-electricity linkage is provided, which can be used to implement the above-mentioned deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage, and the system includes: a load prediction module for determining the heat load prediction value of the target energy supply park in multiple target time periods in the future based on the historical heat load data, historical environmental data and current environmental data of the target energy supply park; a deviation prediction module for predicting the response deviation probability of the shallow geothermal energy in the target energy supply park in the target time period based on the heat load prediction value and multiple adjustment deviation state data of the shallow geothermal energy in the target energy supply park at the current capacity; a compensation determination module for identifying the adjustment deviation time when the response deviation probability exceeds a preset threshold value from the target time period; segment, and determine the heat supply compensation value required for the adjustment deviation period; a coincidence period determination module, used to determine the available remaining power of the new energy equipment in the energy supply park during the adjustment deviation period, and screen out the coincidence deviation period in which the available remaining power meets the heat supply compensation value from the adjustment deviation period; a credibility determination module, used to determine the target adjustment period before each of the coincidence deviation periods, and determine the credibility of the available remaining power in the coincidence deviation period corresponding to each of the target adjustment periods based on historical remaining power data; a deep scheduling module, used to screen out a reliable adjustment period from the target adjustment period based on the credibility, and use the available remaining power to transmit deep geothermal energy to the shallow geothermal energy within the reliable adjustment period.

[0009] 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, the deep-shallow geothermal energy coupling scheduling method based on thermoelectric linkage as in the first aspect is implemented.

[0010] 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 method for coupling scheduling of deep and shallow geothermal energy based on thermoelectric linkage as in the first aspect is implemented.

[0011] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects: The deep-shallow geothermal energy coupled scheduling method based on heat-power integration in this disclosed embodiment first achieves accurate prediction of the target park's future heat load, avoiding the scheduling lag caused by related technologies relying on static rules. First, by combining the regulation deviation status data of the shallow geothermal energy at its current capacity, the probability of its response deviation within the target period is determined. This allows the risk interval of regulation failure to be predicted during the load forecasting phase, thereby rationally planning the compensation effect of the deep geothermal energy. Second, by combining the historical remaining power of new energy equipment with environmental data, the available remaining power within the regulation deviation period is predicted, effectively coordinating the matching relationship between load demand and new energy output, and reducing reliance on external power grid replenishment. Furthermore, by evaluating the reliability of the available remaining power corresponding to each target regulation period and selecting reliable regulation periods accordingly, time windows with high success rates can be prioritized in scheduling decisions, improving the reliability of the coordinated operation of deep and shallow geothermal energy. Finally, during the highly reliable target regulation period, the available remaining power of the new energy equipment is used to drive the water pump, transferring deep geothermal energy to the shallow geothermal energy, achieving pre-regulation of heat supply compensation. Thus, the utilization rate of new energy and the coordinated scheduling efficiency and response timeliness between deep and shallow heat sources can be improved to a certain extent.

[0012] 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

[0013] 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.

[0014] Figure 1A flow chart of a method for coupling scheduling deep and shallow geothermal energy based on thermoelectricity according to some embodiments of the present disclosure is schematically shown.

[0015] Figure 2 A schematic diagram showing a comparison between the support vector machine model and the granular support vector machine model in an embodiment of the present disclosure is schematically shown.

[0016] Figure 3 The figure schematically shows a calculation flow diagram of a granular support vector machine algorithm according to some embodiments of the present disclosure.

[0017] Figure 4 The flowchart of screening the coincidence deviation period according to some embodiments of the present disclosure is schematically shown.

[0018] Figure 5 A flow chart of a gated recurrent unit neural network model according to some embodiments of the present disclosure is schematically shown.

[0019] Figure 6 The following schematically shows the composition of a deep-shallow geothermal energy coupling scheduling system based on heat-electricity linkage according to some embodiments of the present disclosure.

[0020] Figure 7 A schematic structural diagram of a computer system of an electronic device according to some embodiments of the present disclosure is schematically shown.

[0021] Figure 8 A schematic diagram of a computer-readable storage medium according to some embodiments of the present disclosure is schematically shown.

[0022] In the drawings, the same or corresponding reference numerals denote the same or corresponding parts. DETAILED DESCRIPTION

[0023] 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.

[0024] 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.

[0025] 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."

[0026] 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.

[0027] 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.

[0028] 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.

[0029] In this example embodiment, a method for coupling scheduling of deep and shallow geothermal energy based on heat and power linkage is first provided. Figure 1 The following schematically illustrates a flow chart of a method for coupling deep and shallow geothermal energy based on heat and power integration according to some embodiments of the present disclosure. Figure 1 As shown, the deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage may include the following steps: Step S110, determining the heat load forecast value of the target energy supply park in multiple target time periods in the future based on the historical heat load data, historical environmental data and current environmental data of the target energy supply park; Step S120, predicting the response deviation probability of shallow geothermal energy in a target period based on the heat load prediction value and multiple regulation deviation state data of shallow geothermal energy in the target energy supply park at the current capacity; Step S130, identifying an adjustment deviation period in which the response deviation probability exceeds a preset threshold from the target period, and determining a heating compensation value required for the adjustment deviation period; Step S140, determining the available remaining power of the new energy equipment in the energy supply park during the adjustment deviation period, and screening out the overlapping deviation period in which the available remaining power meets the heating compensation value from the adjustment deviation period; Step S150, determining a target adjustment period before each overlap deviation period, and determining the credibility of the available remaining power within the overlap deviation period corresponding to each target adjustment period based on historical remaining power data; Step S160 , selecting a reliable regulation period from the target regulation period based on the credibility, and using the available remaining power to transfer the deep geothermal energy to the shallow geothermal energy within the reliable regulation period.

[0030] The deep-shallow geothermal energy coupling scheduling method based on heat-power integration in this example embodiment first achieves accurate prediction of the target park's future heat load. First, by combining the shallow geothermal energy's regulation deviation status data at its current capacity, its response deviation probability within the target period is determined. This allows for the predicted risk interval of regulation failure during the load forecasting phase, allowing for the rational planning of deep geothermal energy's compensation effect. Second, by combining the historical remaining power of new energy devices with environmental data, the available remaining power within the regulation deviation period is predicted, effectively coordinating the matching relationship between load demand and new energy output, reducing reliance on external power grid replenishment. Furthermore, by evaluating the reliability of the available remaining power corresponding to each target regulation period and selecting reliable regulation periods accordingly, scheduling decisions can prioritize time windows with high success rates, improving the reliability of the coordinated operation of deep and shallow geothermal energy. Finally, during the highly reliable target regulation period, the available remaining power of the new energy devices is used to drive water pumps, transferring deep geothermal energy to the shallow geothermal energy source, achieving pre-regulation of heat supply compensation. This, to a certain extent, improves the utilization rate of new energy resources and the efficiency and timeliness of the coordinated scheduling between deep and shallow heat sources.

[0031] Furthermore, the shallow geothermal energy in the present disclosure can refer to a geothermal system with a burial depth of no more than about 200 meters, which has good heat exchange efficiency and relatively fast response characteristics. It can be further subdivided into shallow geothermal systems and medium-shallow geothermal systems, wherein the shallow geothermal system can refer to geothermal resources with a burial depth between 0 and 100 meters, and the medium-shallow geothermal system can refer to geothermal resources with a burial depth between 100 and 200 meters. The deep geothermal energy in the present disclosure can refer to a geothermal system with a burial depth of more than 200 meters, which has the characteristics of large heat storage capacity and high heat production stability. It can be further subdivided into medium-deep geothermal systems and deep geothermal systems, wherein the medium-deep geothermal system can refer to geothermal resources with a burial depth between 200 and 1500 meters, and the deep geothermal system can refer to high-temperature geothermal resources with a burial depth of more than 1500 meters.

[0032] Next, the deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage in this example embodiment will be further described.

[0033] Step S110 , based on the historical heat load data, historical environmental data and current environmental data of the target energy supply park, determining the heat load forecast value of the target energy supply park in multiple target time periods in the future.

[0034] Among them, the target energy supply park can represent an energy supply area that has the ability to jointly supply shallow geothermal energy and deep geothermal energy, and includes new energy equipment and transmission systems. Historical heat load data can represent the record of heat energy demand provided by the target energy supply park to the target load area within a given historical period. It can be recorded at a daily, hourly or shorter time granularity, and a time association is established with the environmental parameters of the corresponding period. Historical environmental data can represent meteorological condition information collected during the time period corresponding to the historical heat load data, including but not limited to parameters such as ambient temperature, humidity, wind speed, and light intensity, which are used to analyze the impact of environmental changes on heat load. Current environmental data can represent real-time meteorological information collected at the time of prediction calculation, and its parameter type is consistent with historical environmental data. The heat load prediction value can represent the heat energy demand value of multiple target time periods in the future output by the prediction model based on historical heat load data, historical environmental data and current environmental data. Exemplarily, the prediction model can be constructed based on other suitable algorithms such as long short-term memory networks, random forests, and support vector machines.

[0035] Step S120 , based on the heat load prediction value and multiple adjustment deviation state data of the shallow geothermal energy in the target energy supply park at the current capacity, predict the response deviation probability of the shallow geothermal energy in the target time period.

[0036] Shallow geothermal energy represents a readily accessible thermal energy resource at a shallow depth, relying on geothermal gradients within shallow geological structures. It exhibits excellent heat exchange efficiency and rapid response characteristics. Current capacity represents the stable heat output capability of a shallow geothermal energy system under current operating conditions and equipment capabilities. Regulation deviation status data represents the deviation between the actual shallow geothermal energy output and the corresponding heat load demand during different operating periods. Regulation deviation status can include satisfied and unsatisfied. The response deviation probability quantifies the probability that the shallow geothermal energy system will fail to meet the predicted heat load during a future target period due to current capacity limitations or operational inertia. This probability can be derived from historical regulation deviation status data and a predictive model. This step allows for an assessment of the shallow geothermal energy system's ability to cope with future heat load changes under current capacity constraints, helping to identify risk periods when it may be unable to meet heat load demand, thereby providing a basis for supplementary scheduling of deep geothermal energy or other heat sources.

[0037] Step S130 , identifying an adjustment deviation period in which the response deviation probability exceeds a preset threshold from the target period, and determining a heating compensation value required for the adjustment deviation period.

[0038] Among them, the preset threshold value can represent a parameter used to determine whether the heating capacity of shallow geothermal energy is insufficient. Preferably, the preset threshold value is 0.2. Of course, in other embodiments of the present disclosure, the preset threshold value can also be other suitable values such as 0.1, 0.3 and 0.4. The adjustment deviation period can represent the time period in the target period when the predicted shallow geothermal energy response deviation probability exceeds the preset threshold value. During the adjustment deviation period, the shallow geothermal energy cannot meet the heat load demand. The heating compensation value can be expressed as the amount of heat energy supplement required to compensate for the insufficient heating of shallow geothermal energy during the adjustment deviation period. The specific value can be calculated based on the difference between the heat load prediction value and the heating output data of shallow geothermal energy at the current capacity.

[0039] Step S140 , determining the available remaining power of the new energy equipment in the energy supply park during the adjustment deviation period, and selecting the overlapping deviation period in which the available remaining power meets the heating compensation value from the adjustment deviation period.

[0040] Among them, new energy equipment can refer to power generation devices that have power generation capabilities and use renewable energy sources such as wind energy, solar energy, and hydropower as their main energy sources. New energy equipment can be local equipment deployed in the target energy supply park, or collaborative equipment in other parks that have a power connection relationship with the target energy supply park. Available surplus electricity can represent the dispatchable electricity remaining after deducting the power load from the actual power generation of the new energy equipment. The overlapping deviation period can represent a candidate time period in the adjustment deviation period, and the corresponding available surplus electricity can meet the deep geothermal energy transmission demand determined based on the heating compensation value. This step achieves accurate matching of new energy electricity and deep geothermal energy by identifying the overlapping deviation period when the available surplus electricity meets the heating compensation value, effectively avoiding electricity waste.

[0041] Step S150 , determining a target adjustment period before each coincidence deviation period, and determining the credibility of the available remaining power within the coincidence deviation period corresponding to each target adjustment period based on historical remaining power data.

[0042] The target adjustment period can represent a time period preceding the corresponding overlap deviation period for pre-emptive heat adjustment. The credibility can be expressed as a value obtained based on analysis of historical residual power data, used to measure the reliability of the available residual power within the overlap deviation period corresponding to the target adjustment period. The credibility can be derived based on the confidence score output by the time series model. This step ensures the reliability of the deep geothermal energy pre-start process by determining the target adjustment period in advance before the overlap deviation period and evaluating its energy supply stability in combination with historical residual power data. This effectively avoids heat load gaps caused by real-time response delays and improves the continuity and stability of overall thermal energy scheduling.

[0043] Step S160 , selecting a reliable regulation period from the target regulation period based on the credibility, and using the available remaining power to transfer the deep geothermal energy to the shallow geothermal energy within the reliable regulation period.

[0044] The reliable regulation period represents the time period within the target regulation period when the reliability of the available surplus power exceeds a preset threshold. This ensures the stability of renewable energy output and the reliability of deep geothermal energy scheduling. Deep geothermal energy refers to thermal energy obtained by mining geothermal resources at great depths underground, which offers stable output and long-term sustainable heating.

[0045] The technical contents of the above embodiments are described in detail below.

[0046] In some embodiments, based on the historical heat load data, historical environmental data and current environmental data of the target energy supply park, the heat load forecast value of the target energy supply park in multiple target time periods in the future is determined, which can be done through the following technical steps: feature extraction and normalization of the historical heat load data and historical environmental data of the target energy supply park to generate a heat load sample set; based on the heat load sample set, constructing and training a granular support vector machine model; inputting the current environmental data into the granular support vector machine model to obtain the heat load forecast value of the target energy supply park in multiple target time periods in the future.

[0047] Among them, the heat load sample set can represent a data set constructed by extracting features and normalizing the historical heat load data and corresponding historical environmental data of the target energy supply park, wherein each sample data contains a feature vector representing the historical heat load change law and the environmental parameters of the corresponding time period, which are used to train the prediction model. The Granular Support Vector Machine (GSVM) model can represent a time series prediction model that integrates the support vector regression mechanism and the input variable granularity refinement strategy. It performs granular division and weighted modeling on each feature dimension in the input sample data to improve the model's ability to fit and predict complex heat load change trends at multiple time scales. This embodiment obtains heat load prediction values through a granular support vector machine model, which can achieve high-precision prediction of heat energy demand for multiple target time periods in the future based on full consideration of the nonlinear correlation characteristics between historical heat load and environmental changes.

[0048] Furthermore, the comparison diagram of the granular support vector machine (GSVM) model and the support vector machine (SVM) model is shown in the figure below. Figure 2 As shown in the figure, it can be seen that the SVM model constructs the decision boundary based only on the boundary sample points between the first and second categories. The decision boundary is mainly affected by a small number of samples near the boundary and may ignore the overall structure of the sample distribution within each category. The GSVM model introduces intra-class granularity information in the first and second categories respectively, and uses the circular coverage area shown in the figure to perform granular modeling on the samples of each category. In the construction process of the decision boundary, not only the location of the boundary sample points is considered, but also the clustering characteristics of the sample distribution of each category are reflected. This improves the robustness and classification accuracy of the model under sample uncertainty.

[0049] In addition, the calculation flow diagram of the granular support vector machine algorithm can be shown as follows: Figure 3 The specific technical steps include the following: Step S310: Data granulation. The original dataset is divided into information granules of varying sizes. These granules serve as the basis for subsequent granularity hierarchy construction, forming a multi-scale sample representation structure. The granulation results serve as input for both steps S320 and S340, supporting multi-level model training and final decision fusion.

[0050] Step S320: Granularity hierarchy construction. A multi-level granularity structure is constructed, forming a granularity hierarchy tree. Each level corresponds to a set of information abstractions at a specific granularity level. The granularity hierarchy serves as input for local SVM training in step S330, indicating the scope of classification tasks at different granularity levels. This hierarchy also serves as the hierarchical basis for the fusion rules in step S340.

[0051] Step S330: Local SVM training. Train an SVM classifier at each granularity level. Use the granularity structure output from step S320 and the granulated data from step S310 as training inputs to establish local classification models, extracting discriminant features at each granularity level. The trained local SVM models serve as input for global fusion in step S340.

[0052] Step S340: Global decision fusion. The local SVM classification results from multiple granularity levels in step S330 are integrated, and a fusion mechanism based on the granularity hierarchy is used to generate the final global decision result. This fusion process can also reference the boundaries of the original granularity information from step S310 to enhance the robustness of the fusion result to abnormal samples.

[0053] Step S350: Outputting the prediction results. The discrimination result obtained by the global decision fusion in step S340, that is, the prediction result of the granular support vector machine model, is used as the final output.

[0054] In some embodiments, based on the heat load prediction value and multiple adjustment deviation status data of shallow geothermal energy in the target energy supply park at the current capacity, the response deviation probability of shallow geothermal energy in the target time period is predicted, which specifically includes the following technical steps: the heat load prediction value and multiple adjustment deviation status data of shallow geothermal energy in the target energy supply park at the current capacity are input into the weighted time-decayed residual structure long short-term memory network model to obtain the response deviation probability of shallow geothermal energy in the target time period.

[0055] Among them, the training process of the weighted time-decayed residual structure long short-term memory network model includes: dividing the historical heat load data of the target energy supply park and the historical adjustment deviation state data of the corresponding period into a training set and a validation set, inputting the training set into the weighted time-decayed residual structure long short-term memory network model to be trained, performing network parameter initialization operations, and constructing a prediction path including a residual connection structure and a time weight decay mechanism; iteratively training the network parameters based on the forward propagation and backpropagation methods, and dynamically adjusting the learning rate parameters of the model using a warm-up strategy; updating the network parameters using an adaptive moment estimation optimizer, constructing a loss function based on the adjustment deviation prediction error, and evaluating the model's prediction performance using a validation set; when the model's prediction performance on the validation set meets the preset convergence criteria, a trained weighted time-decayed residual structure long short-term memory network model is obtained.

[0056] In this embodiment, the Weighted Temporal Decay Residual Structured Long Short-Term Memory Network (WTD-RS-LSTM) model represents a deep neural network model that integrates a residual connection structure and a temporal weight decay mechanism based on the standard LSTM model. This model is used to improve time series learning capabilities and training stability in modeling heat load changes and regulation deviations. This model can be used to perform multi-time series correlation modeling on input heat load forecast values and regulation deviation state data, and output response deviation probability prediction results. The residual connection structure can represent the introduction of a cross-layer identity mapping path in the neural network, which is used to directly transfer low-level features to high-level networks, thereby alleviating the vanishing gradient problem in deep network training and improving the convergence rate and stability of the regulation deviation prediction path. The temporal weight decay mechanism can be used to assign different time weights to different historical moments in the time series input data, with the weights decreasing with the degree of time delay, thereby enhancing the model's sensitivity to recent heat load fluctuations and regulation deviations. A warm-up strategy can be described as a dynamic adjustment mechanism that updates parameters with a small learning rate at the beginning of model training and gradually increases the learning rate as training progresses. This is used to prevent early training from falling into local optimal solutions. The Adaptive Moment Estimation Optimizer (Adam) can be described as a parameter update algorithm used during neural network training. It automatically adjusts the learning rate of each parameter, thereby accelerating convergence and enhancing the model's adaptability to sparse gradients.

[0057] Furthermore, the loss function constructed by combining the adjustment deviation prediction error is: in, The neural network parameters to be optimized; The optimal parameters after optimization; Total number of samples; No. input samples; No. The true output label corresponding to each sample; Neural network models are based on parameters For samples The predicted output of The loss function is used to measure the error between the predicted output and the true label; Norm functions (such as or norm), used to calculate the parameters Regularization value of ; Regularization coefficient, used to adjust the weight between the loss term and the regularization term; Constraints on the regularization term to prevent the model from overfitting.

[0058] In some embodiments, determining the heating compensation value required for the adjustment deviation period specifically includes the following technical steps: determining the average heating data per unit time of shallow geothermal energy at the current capacity; determining the heating output data corresponding to the adjustment deviation period based on the average heating data per unit time; and determining the heating compensation value based on the heating output data and the heat load forecast value.

[0059] The average heating data represents the amount of thermal energy that shallow geothermal energy can continuously output per unit time under given capacity conditions. This data can be derived from historical operating data at fixed time intervals, such as 5 minutes, 15 minutes, or 1 hour. The heating output data represents the total heating capacity of the shallow geothermal energy system during the target regulation deviation period, calculated based on the average heating data and the duration of the regulation deviation period. This data is used to compare with the heat load forecast to calculate the required heating compensation value.

[0060] In some embodiments, reference Figure 4 As shown, determining the available remaining power of the new energy equipment in the energy supply park during the adjustment deviation period, and screening out the coincident deviation period in which the available remaining power meets the heating compensation value from the adjustment deviation period, specifically includes the following steps: Step S410 : constructing a remaining power estimation model using historical remaining power data and historical environmental data of new energy equipment in the target energy supply park.

[0061] Among them, the historical remaining power data can represent the remaining power data of the new energy equipment in the target energy supply park within a given historical period, which has a time synchronization relationship with the environmental parameters. The remaining power estimation model can represent a mathematical model obtained by training based on the historical remaining power data and historical environmental data for predicting the available remaining power of new energy equipment in future time periods. Preferably, the remaining power estimation model can be constructed based on a granular support vector machine algorithm. Of course, in other embodiments of the present disclosure, the remaining power estimation model can also be constructed based on other suitable algorithms such as long short-term memory networks and random forest regression algorithms.

[0062] Step S420 , inputting the current environment data into a remaining power estimation model to determine the available remaining power during the adjustment deviation period.

[0063] Step S430: determining the deep geothermal energy transmission demand corresponding to the heating compensation value, and calculating the target driving power for driving the water pump to meet the transmission demand.

[0064] The deep geothermal energy transmission demand can be expressed as the target heat output by the deep geothermal energy system during the corresponding time period to meet the heating compensation value within the regulation deviation period. The target driving power represents the electrical energy required to meet the deep geothermal energy transmission demand. This is primarily determined by the power consumed by the water pumps, but also includes the power consumption of other equipment such as monitoring and control equipment.

[0065] Exemplarily, the target driving power can be obtained by the following steps: Based on the deep geothermal energy transmission demand, combined with the temperature, specific heat capacity and outflow rate per unit time of the thermal fluid in the current operating state of the deep geothermal energy system, the transmission volume data that needs to be transmitted during the adjustment deviation period is calculated. The transmission volume data is used to represent the total amount of geothermal fluid transport required to meet the heat transmission. Based on the transmission volume data and the water pump parameter information, the actual operating time of the water pump during the target adjustment period is determined, and then the power consumed by the water pump operation is calculated and recorded as the water pump driving power. The auxiliary operating equipment parameters of the auxiliary equipment linked to the water pump in the deep geothermal energy system include the operating power parameters of the flow control controller, automatic valve actuator and heating cable. Based on the auxiliary operating equipment parameters and the actual operating time, the power consumption of the auxiliary equipment during the adjustment deviation period is calculated and recorded as the auxiliary driving power. The water pump driving power and the auxiliary driving power are summed to obtain the target driving power used to drive the water pump to meet the transmission demand.

[0066] Step S440 selects, from the adjustment deviation period, periods where the available remaining power meets the target driving power, as the overlap deviation period. This step effectively selects overlap deviation periods with driving capability by matching the available remaining power of the new energy equipment within the adjustment deviation period with the target driving power required for deep geothermal energy transmission. This enables targeted activation of the deep geothermal system under power support conditions, improving the scheduling reliability and resource utilization efficiency of the geothermal energy system.

[0067] In some embodiments, a target adjustment period preceding each overlapping deviation period is determined, specifically including the following technical steps: obtaining the transmission time required to transmit deep geothermal energy to shallow geothermal energy in the target energy supply park, the transmission time including the water pump start-up time and the geothermal fluid transmission time; based on the start time of each overlapping deviation period, tracing back the transmission time to generate the target adjustment period.

[0068] The geothermal fluid transfer time represents the time interval required to extract thermal fluid from the deep geothermal energy system and transport it through pipelines to the shallow geothermal energy system. In this embodiment, by predetermining the target adjustment period before each overlap deviation period, it is possible to pre-schedule the deep geothermal energy transfer process, ensuring the deep geothermal system has sufficient response time to complete heat transfer and system preheating. This effectively improves the shallow geothermal system's heat supply guarantee capability during the overlap deviation period and reduces energy efficiency losses and power surge burdens caused by response lags.

[0069] In some embodiments, the credibility of the available remaining power in the overlapping deviation period corresponding to each target adjustment period is determined based on the historical remaining power data, specifically including the following technical steps: using the historical remaining power data of the energy park to construct a gated recurrent unit neural network model, wherein the gated recurrent unit neural network model uses an ultra-bandwidth automatic parameter adjustment algorithm to iteratively screen and determine the optimal hyperparameter combination in a preset hyperparameter space; the available remaining power in the overlapping deviation period corresponding to the target adjustment period is input into the gated recurrent unit neural network model to obtain the credibility corresponding to the available remaining power.

[0070] Among them, the Gated Recurrent Unit (GRU) neural network model can represent a recurrent neural network structure for processing time series data. By introducing reset gates and update gate mechanisms, it selectively memorizes and forgets the previous state and current input information at each moment, thereby improving the model's learning ability for long-distance dependencies and reducing the risk of gradient vanishing. The input of the GRU model is the sequence of available remaining power within the overlapping deviation period corresponding to the target adjustment period, and the output is the credibility prediction value corresponding to the input available remaining power. The historical remaining power data of the energy park has obvious time series characteristics. The GRU neural network model can effectively model its temporal dependencies and fluctuation patterns through the update gate and reset gate mechanisms. It is suitable for capturing power change trends and improving the accuracy of subsequent credibility judgments.

[0071] The Hyperband algorithm is a resource allocation optimization algorithm that evaluates different hyperparameter combinations in parallel within a set resource budget and, through early performance judgment, gradually eliminates low-performing configurations to accelerate the search efficiency of the hyperparameter space. The optimal hyperparameter combination is the set of parameter configurations that, after multiple rounds of screening and performance verification by the Hyperband algorithm within the preset hyperparameter search space, achieves the best prediction performance for the target neural network model on the validation set.

[0072] Furthermore, the computational flow of the gated recurrent unit neural network model can be as follows: Figure 5 shown.

[0073] Step S501: Dataset construction: historical remaining power data and related time series label information are acquired and sorted, and a data set construction operation is performed to generate input and output sample data sets for training, verification, and testing.

[0074] Step S502: GRU neural network. Specifically, based on the dataset constructed in step S501, the GRU neural network structure is initialized, the input layer nodes are defined, the hidden layer including the reset gate and update gate mechanism is set, the output layer dimension is configured, and basic parameters such as the activation function and time step are set.

[0075] Step S503: Calculate the error value. Input the training set into the constructed GRU neural network, perform forward propagation to obtain the predicted output, and calculate the error value based on the true label. This error value is used to measure the current training accuracy of the model and serves as the basis for subsequent tuning and optimization.

[0076] Step S504: Define the types and ranges of hyperparameters. Using the Hyperband algorithm, set multiple hyperparameters including the learning rate, number of hidden units, batch size, and weight decay coefficient, and configure corresponding search intervals for each hyperparameter to construct a complete hyperparameter search space.

[0077] Step S505: Allocate computing power to the current hyperparameter configuration. Based on the hyperparameter range defined in step S504, the Hyperband algorithm's resource allocation mechanism is used to select several sets of hyperparameter configurations and allocate a corresponding computing budget to each set, forming the current candidate hyperparameter set.

[0078] Step S506: Optimize the GRU neural network. For each set of current hyperparameter configurations, rebuild the GRU neural network model, perform forward propagation and backpropagation training, update the network weights and bias parameters, and form a corresponding optimized model version.

[0079] Step S507: Evaluate the GRU neural network prediction loss. Apply the GRU neural network model optimized in step S506 to the training set samples used in step S503, perform a forward propagation operation, and calculate the prediction loss value based on the difference between the network output and the true label value. This prediction loss value is used to measure the generalization performance of the GRU neural network model under the current hyperparameter configuration.

[0080] Step S508: Update the hyperparameter range. Based on the prediction loss result obtained in step S507, all candidate hyperparameter configurations are sorted, and configuration combinations with better performance are retained, while configurations with larger errors are eliminated. Based on this, the search interval is narrowed and the hyperparameter range used in the next iteration is updated.

[0081] Step S509: Determine whether the number of iterations has reached the maximum. Determine whether the number of hyperparameter search rounds currently executed has reached the set maximum number of iterations. If not, return to step S505 to continue the next round of search optimization. If it has reached the upper limit, stop the Hyperband algorithm search process and proceed to step S510.

[0082] Step S510: Test the resulting GRU neural network. The final optimal hyperparameter configuration is used to fully train the GRU neural network. The validation set or test set is then fed into the model for prediction and output, assessing the model's generalization and error performance on other samples.

[0083] Step S511: Model Verification. The GRU neural network model that passed the evaluation in step S510 is further verified and tested using a simulation platform, including dimensions such as boundary data responsiveness and long-term temporal stability, to confirm that it meets the credibility estimation requirements, ultimately forming a deployable model version.

[0084] In some embodiments, a reliable adjustment period is screened out from the target adjustment period based on the credibility, and the deep geothermal energy is transferred to the shallow geothermal energy by using the available remaining power within the reliable adjustment period, specifically including the following technical steps: comparing the credibility corresponding to each target adjustment period with a confidence threshold; in response to the credibility being greater than the confidence threshold, the corresponding target adjustment period is used as a reliable adjustment period, and the available remaining power is used to drive a water pump to transfer the deep geothermal energy to the shallow geothermal energy within the reliable adjustment period; in response to the credibility being less than the confidence threshold, the corresponding target adjustment period is used as a grid-side support period, and the grid side is controlled to provide energy replenishment power within the grid-side support period, so as to drive the water pump together with the available remaining power to transfer the deep geothermal energy to the shallow geothermal energy.

[0085] Among them, the confidence threshold can represent a value used to determine whether the stability of the available remaining power in the current target regulation period meets the preset reliability requirements. Exemplarily, the confidence threshold can be set to other suitable values such as 0.6, 0.7, and 0.75. The grid-side support period can represent a time period in the target regulation period when the confidence threshold requirements are not met and the output stability of the available remaining power is insufficient. During this time period, it is necessary to control the power grid side to provide power for energy replenishment, so as to complete the transmission operation of deep geothermal energy to shallow geothermal energy in combination with the available remaining power. In this embodiment, by comparing the credibility of the available remaining power in the target regulation period with the preset confidence threshold, the target regulation period is divided into a reliable regulation period and a grid-side support period based on the comparison result. On the one hand, when the stability of the available remaining power is high, the water pump is directly driven to complete the transmission of deep geothermal energy, reducing the burden on the grid; on the other hand, when the available remaining power is insufficient to support the transmission demand alone, grid energy replenishment is reasonably introduced to ensure scheduling continuity and system reliability.

[0086] In some embodiments, the above-mentioned deep-shallow geothermal energy coupling scheduling method based on heat-electric linkage may also include the following technical steps: screening out energy supply gap periods in which the available surplus electricity does not meet the heating compensation value from the adjustment deviation period; determining the pre-heat storage period corresponding to the energy supply gap period based on the distribution data of the energy supply gap period; and within the pre-heat storage period, using the available surplus electricity to drive a water pump to transfer deep geothermal energy to shallow geothermal energy.

[0087] The energy gap period can represent the time period during the regulation deviation period when the available remaining power is insufficient to meet the corresponding heating compensation value. The distribution data can represent a data set consisting of the start and end times, durations, and gap amplitudes of multiple energy gap periods, which is used to reflect the distribution characteristics of the energy gap periods on the time axis and the energy gap values. The pre-heat storage period can represent a time period selected based on the distribution data of the energy gap period for preemptive deep geothermal energy utilization. In addition, when the pre-heat storage period conflicts with the target regulation period, the scheduling strategy corresponding to the target regulation period takes precedence.

[0088] In some embodiments, based on the distribution data of the energy supply gap period, the pre-heat storage period corresponding to the energy supply gap period is determined, which can be done through the following technical steps: obtaining the start time, end time, gap duration and corresponding heat compensation value of each energy supply gap period, and constructing a distribution data set containing multiple energy supply gap periods. Based on the distribution data set, the distribution density of each energy supply gap period on the time axis is determined, and clusters of energy supply gap time periods that appear continuously or frequently are identified. For each energy supply gap time period cluster, the earliest start time corresponding to each gap period in the cluster and the sum of the heat compensation values of all gap periods are calculated, and the earliest start time is traced back to the set heating preset time length to generate a target pre-heat storage period. Determine the available remaining power within the target pre-heat storage period and the device driving power required to meet the heat compensation sum value. The time period in which the available remaining power within the target pre-heat storage period is not less than the device driving power is used as the pre-heat storage period.

[0089] 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.

[0090] In addition, in this exemplary embodiment, a deep-shallow geothermal energy coupling scheduling system based on thermal power linkage is also provided. Figure 6 As shown, the deep-shallow geothermal energy coupling scheduling system 600 based on heat-power linkage may include: a load prediction module 610, a deviation prediction module 620, a compensation determination module 630, a coincidence period determination module 640, a credibility determination module 650, and a deep scheduling module 660. Among them: The load forecasting module 610 may be used to determine the thermal load forecast value of the target energy supply park in multiple target time periods in the future based on the historical thermal load data, historical environmental data, and current environmental data of the target energy supply park.

[0091] The deviation prediction module 620 can be used to predict the response deviation probability of shallow geothermal energy in a target period based on the heat load prediction value and multiple adjustment deviation status data of shallow geothermal energy in the target energy supply park at the current capacity.

[0092] The compensation determination module 630 may be configured to identify, from the target period, an adjustment deviation period in which the response deviation probability exceeds a preset threshold, and determine a heating compensation value required for the adjustment deviation period.

[0093] The overlap period determination module 640 can be used to determine the available remaining power of the new energy equipment in the energy park during the adjustment deviation period, and select the overlap deviation period in which the available remaining power meets the heating compensation value from the adjustment deviation period.

[0094] The credibility determination module 650 may be configured to determine a target adjustment period preceding each coincidence deviation period, and determine the credibility of the available remaining power within the coincidence deviation period corresponding to each target adjustment period based on historical remaining power data.

[0095] The deep scheduling module 660 can be used to filter out reliable regulation periods from the target regulation period based on credibility, and use the available remaining power to transfer deep geothermal energy to shallow geothermal energy within the reliable regulation period.

[0096] The specific details of each module in the above deep-shallow geothermal energy coupling scheduling system based on heat and power linkage have been described in detail in the corresponding deep-shallow geothermal energy coupling scheduling method based on heat and power linkage, so they will not be repeated here.

[0097] It should be noted that while the detailed description above mentions several modules or units within the deep-shallow geothermal energy coupling scheduling system based on heat and power integration, this division is not mandatory. In fact, depending on 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.

[0098] In addition, in an exemplary embodiment of the present disclosure, an electronic device is also provided that can implement the above-mentioned deep-shallow geothermal energy coupling scheduling method based on thermoelectricity linkage.

[0099] 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."

[0100] Refer to the following Figure 7 7 to describe an electronic device 700 according to such an embodiment of the present disclosure. Figure 7 The electronic device 700 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0101] like Figure 7 As shown, electronic device 700 is implemented as a general-purpose computing device. Components of electronic device 700 may include, but are not limited to, the aforementioned at least one processing unit 710, the aforementioned at least one storage unit 720, a bus 730 connecting various system components (including storage unit 720 and processing unit 710), and a display unit 740.

[0102] The storage unit stores program code, which can be executed by the processing unit 710, causing the processing unit 710 to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of the present disclosure. The storage unit 720 may include a readable medium in the form of a volatile memory unit, such as a random access memory unit (RAM) 721 and / or a cache memory unit 722, and may further include a read-only memory unit (ROM) 723.

[0103] The storage unit 720 may also include a program / utility 724 having a set (at least one) of program modules 725, such program modules 725 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.

[0104] Bus 730 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.

[0105] The electronic device 700 can also communicate with one or more external devices 770 (e.g., a keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 700, and / or any device that enables the electronic device 700 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 750. Furthermore, the electronic device 700 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 760. As shown, the network adapter 760 communicates with other modules of the electronic device 700 via a bus 730. 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 700, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0106] 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.

[0107] 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.

[0108] refer to Figure 8 As shown, a program product 800 for implementing the above-mentioned deep-shallow geothermal energy coupling scheduling method based on heat-electricity integration according to an embodiment of the present disclosure is described. This program product can be 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 can be any tangible medium containing or storing a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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 method for coupling scheduling of deep and shallow geothermal energy based on heat and power linkage, characterized in that: include: Determining a heat load forecast value of the target energy supply park in multiple target time periods in the future based on historical heat load data, historical environmental data, and current environmental data of the target energy supply park; Based on the heat load prediction value and a plurality of regulation deviation state data of the shallow geothermal energy in the target energy supply park at the current capacity, predicting the response deviation probability of the shallow geothermal energy in the target time period; Identifying, from the target period, an adjustment deviation period in which the response deviation probability exceeds a preset threshold, and determining a heating compensation value required for the adjustment deviation period; Determining the available remaining power of the new energy equipment in the energy supply park during the adjustment deviation period, and screening out the coincident deviation period in which the available remaining power meets the heating compensation value from the adjustment deviation period; Determining a target adjustment period before each of the coincidence deviation periods, and determining the credibility of the available remaining power within the coincidence deviation period corresponding to each of the target adjustment periods based on historical remaining power data; A reliable adjustment period is selected from the target adjustment period based on the credibility, and the deep geothermal energy is transmitted to the shallow geothermal energy by using the available remaining power within the reliable adjustment period.

2. The deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage according to claim 1 is characterized in that: The step of determining the heat load forecast value of the target energy supply park in multiple target time periods in the future based on the historical heat load data, historical environmental data, and current environmental data of the target energy supply park includes: Performing feature extraction and normalization processing on the historical heat load data and the historical environmental data of the target energy supply park to generate a heat load sample set; Based on the heat load sample set, constructing and training a granular support vector machine model; The current environmental data is input into the granular support vector machine model to obtain the heat load prediction value of the target energy supply park in the multiple target time periods in the future.

3. The deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage according to claim 1 is characterized in that: The predicting of the response deviation probability of the shallow geothermal energy in the target time period based on the heat load prediction value and a plurality of adjustment deviation state data of the shallow geothermal energy in the target energy supply park at the current capacity includes: Inputting the heat load forecast value and multiple regulation deviation state data of the shallow geothermal energy in the target energy supply park at the current capacity into a weighted time-decayed residual structure long short-term memory network model to obtain the response deviation probability of the shallow geothermal energy in the target period; The training process of the weighted time-decayed residual structure long short-term memory network model includes: The historical heat load data of the target energy supply park and the historical regulation deviation status data of the corresponding period are divided into a training set and a validation set. Inputting the training set into a weighted time-decayed residual structure long short-term memory network model to be trained, performing a network parameter initialization operation, and constructing a prediction path including a residual connection structure and a time weight decay mechanism; Iteratively training the network parameters based on forward propagation and backpropagation methods, and dynamically adjusting the learning rate parameters of the model using a warm-up strategy; Using an adaptive moment estimation optimizer to update the network parameters, constructing a loss function in combination with the adjustment bias prediction error, and using the validation set to evaluate the prediction performance of the model; When the prediction performance of the model on the validation set meets the preset convergence standard, the trained weighted time-decayed residual structure long short-term memory network model is obtained.

4. The deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage according to claim 1 is characterized in that: Determining the heating compensation value required for the adjustment deviation period includes: Determine the average heating data per unit time of the shallow geothermal energy at the current capacity; Determining the heating output data corresponding to the adjustment deviation period based on the average heating data per unit time; The heating compensation value is determined based on the heating output data and the heat load prediction value.

5. The deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage according to claim 1 is characterized in that: The determining of the available remaining power of the new energy equipment in the energy supply park during the adjustment deviation period, and screening out a coincidence deviation period in which the available remaining power meets the heating compensation value from the adjustment deviation period, includes: Constructing a remaining power estimation model using historical remaining power data of new energy equipment in the target energy supply park and the historical environmental data; Inputting the current environmental data into the remaining power estimation model to determine the available remaining power during the adjustment deviation period; determining a deep geothermal energy transmission demand corresponding to the heating compensation value, and calculating a target driving power for driving a water pump to meet the transmission demand; A period in which the available remaining power meets the target driving power is selected from the adjustment deviation period as the coincidence deviation period.

6. The deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage according to claim 1 is characterized in that: The determining of the target adjustment period preceding each of the overlap deviation periods comprises: Obtaining the transmission time required to transmit the deep geothermal energy to the shallow geothermal energy in the target energy supply park, wherein the transmission time includes the water pump startup time and the geothermal fluid transmission time; Based on the start time of each of the coincidence deviation periods, the transmission duration is traced back to generate the target adjustment period.

7. The deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage according to claim 1 is characterized in that: The determining, based on the historical remaining power data, the credibility of the available remaining power within the coincidence deviation period corresponding to each target adjustment period includes: A gated recurrent unit neural network model is constructed using the historical remaining power data of the energy supply park, wherein the gated recurrent unit neural network model uses an ultra-bandwidth automatic parameter tuning algorithm to iteratively screen and determine the optimal hyperparameter combination within a preset hyperparameter space; The available remaining power within the coincidence deviation period corresponding to the target adjustment period is input into the gated recurrent unit neural network model to obtain the credibility corresponding to the available remaining power.

8. The deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage according to claim 1 is characterized in that: The method of selecting a reliable adjustment period from the target adjustment period based on the credibility, and transmitting the deep geothermal energy to the shallow geothermal energy by using the available remaining power within the reliable adjustment period, includes: Comparing the credibility corresponding to each target adjustment period with a preset credibility threshold; In response to the credibility being greater than the confidence threshold, using the corresponding target regulation period as the reliable regulation period, and using the available remaining power to drive a water pump to transfer the deep geothermal energy to the shallow geothermal energy within the reliable regulation period; In response to the credibility being less than the confidence threshold, the corresponding target adjustment period is used as the grid-side support period, and the grid side is controlled to provide energy replenishment power during the grid-side support period to drive the water pump together with the available remaining power to transfer the deep geothermal energy to the shallow geothermal energy.

9. The deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage according to claim 1 is characterized in that: Also includes: Filtering out the energy supply gap period in which the available remaining power does not meet the heating compensation value from the adjustment deviation period; Determining a pre-heat storage period corresponding to the energy supply gap period based on the distribution data of the energy supply gap period; During the pre-heat storage period, the available surplus electricity is used to drive a water pump to transfer the deep geothermal energy to the shallow geothermal energy.

10. A deep-shallow geothermal energy coupling scheduling system based on heat-electricity linkage, used to implement the deep-shallow geothermal energy coupling scheduling method based on heat-electricity linkage according to any one of claims 1 to 9, characterized in that: include: A load forecasting module, configured to determine a heat load forecast value of the target energy supply park in multiple target time periods in the future based on historical heat load data, historical environmental data, and current environmental data of the target energy supply park; a deviation prediction module, configured to predict a response deviation probability of the shallow geothermal energy in the target time period based on the heat load prediction value and a plurality of adjustment deviation state data of the shallow geothermal energy in the target energy supply park at the current capacity; a compensation determination module, configured to identify, from the target period, an adjustment deviation period in which the response deviation probability exceeds a preset threshold, and determine a heating compensation value required for the adjustment deviation period; a coincidence period determination module, configured to determine the available remaining power of the new energy equipment in the energy supply park during the adjustment deviation period, and to select a coincidence deviation period in which the available remaining power meets the heating compensation value from the adjustment deviation period; a credibility determination module, configured to determine a target adjustment period preceding each of the coincidence deviation periods, and determine the credibility of the available remaining power within the coincidence deviation period corresponding to each of the target adjustment periods based on historical remaining power data; A deep scheduling module is used to screen out a reliable adjustment period from the target adjustment period based on the credibility, and use the available remaining power to transmit deep geothermal energy to the shallow geothermal energy within the reliable adjustment period.

Images