Coal mine area green electricity direct connection planning method and system

Abstract

The present application belongs to the technical field of energy planning, and discloses a coal mine area green electricity direct connection planning method and system. The present application comprises: integrating geographic spatial information to obtain a three-dimensional geographic spatial information database, processing in combination with a land reuse evaluation model to obtain a heat map, quantitatively analyzing the heat map to obtain power generation; processing fusion by using a space-time convolutional neural network and a distributed intelligent sensing model to generate a meteorological database; analyzing by using a wind power and photovoltaic space-time output model to obtain a photovoltaic joint sample; processing by using a load prediction model to obtain a load prediction curve set; inputting a source load time sequence mismatch quantization model for analysis to obtain an energy storage collaborative configuration scheme; inputting a multi-objective line optimization model for analysis to obtain a direct connection line topology structure diagram; data-driven optimization decision optimization to obtain a source storage load collaborative optimization model, and coal mine area green electricity direct connection planning is carried out through the source storage load collaborative optimization model. The present application directly obtains green electricity and reduces cost.

Description

Technical Field

[0001] This invention relates to the field of energy planning technology, and in particular to a method and system for planning direct green electricity connections in coal mining areas. Background Technology

[0002] As the foundation of national economic and social development, coal mines face the arduous task of building low-carbon mines and achieving dual-carbon goals. In low-carbon coal mines, the use of clean energy sources such as wind and solar power to generate green electricity can effectively reduce carbon emissions. Therefore, integrating clean energy sources like wind and solar power into the energy system of low-carbon coal mines and increasing the proportion of green electricity in their energy consumption has become a crucial measure for carbon reduction. Currently, plans for green electricity integration in low-carbon coal mines often involve connecting clean energy sources like wind and solar power to the public power grid. However, since the public power grid also connects to non-clean energy sources such as thermal power, it is difficult to distinguish the proportion of each type of power source in the total electricity consumption, thus limiting the green energy demand of low-carbon coal mines.

[0003] Publication number CN119809157A discloses a method, system, and computer equipment for low-carbon energy planning in open-pit mines. This invention includes calculating the historical total energy consumption and historical total carbon emissions of the open-pit mine; inputting the historical total energy consumption and historical total carbon emissions into a time series prediction model to obtain time series prediction results for total energy consumption and total carbon emissions under a baseline scenario; and obtaining a low-carbon energy planning path based on the total carbon emissions under a green and low-carbon scenario. Although it calculates historical total energy consumption and carbon emissions, uses a time series prediction model for low-carbon energy planning, and considers methods such as battery swapping for heavy-duty trucks, zero-carbon photovoltaic and wind power technologies, and forest carbon sinks in spoil heaps, the planning method focuses more on the overall low-carbon transformation of open-pit mines. It lacks in-depth customization for the unique land resources, new energy output characteristics, load forecasting accuracy, energy storage configuration optimization, and direct connection line design of coal mining areas. While the prior art considers the integration of clean energy sources such as wind power and photovoltaics, it is difficult to distinguish them from the total electricity consumption.

[0004] Application number 202310363162.0 describes a method for optimizing the zoning layout of new energy sources considering spatiotemporal characteristics. This invention includes: establishing a spatiotemporal characteristic representation model for each zone, using the average photovoltaic output of each typical month as the equivalent output at each hour; establishing a new energy zoning layout optimization model considering spatiotemporal characteristics, with constraints including new energy scale constraints, curtailment rate constraints, power balance constraints, inter-zone tie-line power constraints, and unit output constraints; and using a genetic algorithm to solve the new energy zoning layout optimization model considering spatiotemporal characteristics, outputting the newly added photovoltaic capacity, newly added wind power capacity, and newly added wind and solar spatial layout for each zone. This reliance on the public power grid for green electricity transmission leads to an inability to physically distinguish green electricity from thermal power in total electricity consumption.

[0005] The green electricity direct connection of this invention refers to a model where new energy sources such as wind power, solar power, and biomass power generation are not directly connected to the public power grid, but instead supply power to a single electricity user through a dedicated direct connection line, achieving physical traceability of electricity. The framework for the green electricity direct connection model is clearly defined at the national level. The notice encourages model innovation and explicitly requires that, in principle, the load should be the primary responsible unit for green electricity direct connection projects. Various operating entities (excluding grid companies), including private enterprises, can invest in green electricity direct connection projects. The power source for the project can be invested by the load, or by the power generation company or a joint venture established by both parties. The dedicated direct connection line should, in principle, be invested by both the load and the power source entity. If the power source and load are not invested by the same entity, a multi-year power purchase agreement or energy performance contracting agreement should be signed, specifying matters such as power facility construction, ownership division, operation and maintenance, dispatching, settlement relationships, and liability for breach of contract. Enhancing system friendliness is encouraged, requiring grid-connected green electricity direct connection projects to fully improve their flexibility and adjustment capabilities by rationally allocating energy storage and tapping into the potential for flexible load adjustment, thereby minimizing system regulation pressure.

[0006] Therefore, how to provide a planning method and system for direct green power connection in coal mining areas is an urgent problem to be solved. Summary of the Invention

[0007] This invention provides a method and system for planning green electricity direct connection in coal mining areas, in order to solve the problem that the proportion of various power sources in the total electricity consumption in the prior art limits the green energy demand of low-carbon coal mines.

[0008] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or to describe the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0009] According to a first aspect of the present invention, a method for planning direct green power connections in coal mining areas is provided.

[0010] In one embodiment, the method for planning green electricity direct connection in a coal mining area includes:

[0011] Geographic information is integrated using a geographic information platform to obtain a three-dimensional geospatial information database. The three-dimensional geospatial information database is then processed using a land reuse assessment model to obtain a heat map. The heat map is then quantitatively analyzed to obtain the power generation.

[0012] The heat map, power generation and multi-source meteorological data are processed and fused sequentially using a spatiotemporal convolutional neural network and a distributed intelligent sensing model to generate a meteorological database; and the meteorological database is analyzed and processed using a wind power and photovoltaic spatiotemporal output model to obtain a photovoltaic joint sample.

[0013] The load forecasting model is used to process the photovoltaic joint sample and the pre-configured energy digital twin data in sequence to obtain a set of load forecasting curves;

[0014] The load forecast curve set, photovoltaic joint sample and pre-configured operating condition optimization data are sequentially input into the source-load time mismatch quantification model for analysis to obtain the energy storage collaborative configuration scheme.

[0015] The energy storage collaborative configuration scheme and the planning data of new energy power stations are input into the multi-objective line optimization model for analysis to obtain the topology diagram of the direct connection line.

[0016] By using data-driven optimization decision-making, the heat map, power generation, photovoltaic joint sample, load forecast curve set and direct connection line topology diagram are optimized in sequence to obtain the source-storage-load collaborative optimization model. The green power direct connection planning of coal mining areas is carried out through the source-storage-load collaborative optimization model.

[0017] In one embodiment, the geospatial information includes:

[0018] Topographic maps of the mining area, satellite remote sensing images, geological exploration data, and land ownership information.

[0019] In one embodiment, geospatial information is integrated using a geographic information platform to obtain a three-dimensional geospatial information database. This database is then processed using a land reuse assessment model to generate a heat map. The heat map is then quantitatively analyzed to determine the power generation, which includes:

[0020] By integrating geospatial information through a geographic information platform, a three-dimensional geospatial information database is obtained, and potential sites available for the deployment of new energy facilities are identified.

[0021] By combining historical subsidence monitoring data and geological stability prediction models, subsidence areas were screened to identify those that met the standards.

[0022] The roof area, load-bearing limit, and shadow shading data are obtained by calculating the building structure drawings and on-site surveys through a geographic information platform.

[0023] Geographic information spatial analysis tools were used to screen the slope angle, slope aspect, sunshine duration, rock mass stability, and soil and water conservation requirements of the slope area to obtain the south-facing slope.

[0024] The land reuse assessment model is used to evaluate the industrial sites with reuse potential, generate heat maps, and quantify the industrial sites with reuse potential for analysis to obtain power generation.

[0025] In one embodiment, a spatiotemporal convolutional neural network and a distributed intelligent sensing model are sequentially used to process and fuse heat maps, power generation, and multi-source meteorological integrated data to generate a meteorological database; then, a wind power and photovoltaic spatiotemporal output model is used to analyze and process the meteorological database to obtain a photovoltaic joint sample, including:

[0026] A meteorological database is generated by using a spatiotemporal convolutional neural network to correct heat maps, power generation, spatiotemporal references of multi-source data, and ground station data.

[0027] Dynamic parameter capture of meteorological databases is performed using a distributed intelligent sensing model.

[0028] Robust optimization of pre-configured power output scenarios was calculated using spatiotemporal power output models of wind power and photovoltaic power to obtain a combined meteorological database photovoltaic sample.

[0029] In one embodiment, the load forecasting model sequentially processes the photovoltaic joint sample and pre-configured energy digital twin data to obtain a set of load forecasting curves, including:

[0030] Based on the linkage between rigid loads, adjustable loads, and flexible loads, virtual and real data are obtained to generate energy digital twin data;

[0031] Extract photovoltaic joint samples and set dynamic path constraint windows to align the power step edge morphological inflection points, while introducing device state masks;

[0032] By analyzing energy digital twin data and extracted photovoltaic joint samples using a load forecasting model, a set of load forecasting curves is obtained.

[0033] In one embodiment, the load forecast curve set, photovoltaic joint samples, and pre-configured operating condition optimization data are sequentially input into the source-load time-series mismatch quantification model for analysis, resulting in an energy storage collaborative configuration scheme including:

[0034] The sliding time window algorithm is used to calculate the pre-configured working condition optimization data and extract the inertia deficit of the fluctuation index.

[0035] The effective inertia deficit of the fluctuation index is optimized using a multi-objective optimization model to obtain pre-configured operating condition optimization data;

[0036] By analyzing the load forecast curve set, photovoltaic joint samples, and pre-configured operating condition optimization data through the source-load time mismatch quantification model, an energy storage collaborative configuration scheme is obtained.

[0037] In one embodiment, the new energy power station planning data includes:

[0038] Spatial distribution of new energy power stations, installed capacity parameters, energy storage layout coordinates, and load center location.

[0039] In one embodiment, the energy storage collaborative configuration scheme and new energy power station planning data are input into a multi-objective line optimization model for analysis, resulting in a direct connection line topology diagram including:

[0040] The triangular network algorithm is used to connect new energy nodes, energy storage aggregation points and load hubs. Combined with a three-dimensional geographic information model, it avoids high-risk areas of mining subsidence, blasting vibration impact zones and ecological restoration protection zones. The minimum spanning tree algorithm is used to iteratively generate an initial radial or ring network topology.

[0041] The dynamic capacity margin method is used to calculate the line current carrying capacity by considering the remaining line, conductor selection, comprehensive economic current density, short-circuit thermal stability limit, special mining conditions, and voltage level configuration.

[0042] In one embodiment, data-driven optimization decision-making is used to sequentially optimize the heat map, power generation, photovoltaic joint sample, load forecast curve set, and direct connection line topology diagram to obtain a source-storage-load collaborative optimization model. The planning of green power direct connections in coal mining areas using this source-storage-load collaborative optimization model includes:

[0043] The 3D geographic information platform processes heat maps and power generation data to construct a digital twin model of the land.

[0044] Based on photovoltaic joint sample data, a regional equivalent power output model is constructed, and a neural network is used to predict the nonlinear relationship between historical power output and meteorology.

[0045] Based on the load forecast curve set, data on rigid load, adjustable load and flexible load are extracted respectively. Combined with production scheduling logs and time-of-use electricity price signals, a load adjustment potential matrix is ​​constructed, and a reinforcement learning algorithm is used to dynamically update the load forecast model.

[0046] The optimal topology is automatically generated based on the direct connection line topology diagram, and the line length and impedance parameters are calculated. Voltage fluctuations and harmonic distortion rates are monitored through electromagnetic transient simulation, and the capacity of reactive power compensation equipment is adjusted accordingly.

[0047] According to a second aspect of the present invention, a green power direct connection planning system for coal mining areas is provided.

[0048] In one embodiment, the coal mining area green power direct connection planning system includes:

[0049] The data acquisition module is used to integrate geospatial information using a geographic information platform to obtain a three-dimensional geospatial information database. The three-dimensional geospatial information database is then processed using a land reuse assessment model to obtain a heat map. The heat map is then quantitatively analyzed to obtain the power generation.

[0050] The processing and generation module is used to process and fuse heat maps, power generation and multi-source meteorological data in sequence using spatiotemporal convolutional neural networks and distributed intelligent sensing models to generate a meteorological database; and to analyze and process the meteorological database using wind power and photovoltaic spatiotemporal output models to obtain photovoltaic joint samples.

[0051] The curve acquisition module is used to process the photovoltaic joint sample and the pre-configured energy digital twin data in sequence using the load forecasting model to obtain a set of load forecasting curves;

[0052] The optimization analysis module is used to sequentially input the load forecast curve set, photovoltaic joint sample and pre-configured operating condition optimization data into the source-load time-series mismatch quantification model for analysis, and obtain the energy storage collaborative configuration scheme.

[0053] The analysis and acquisition module is used to input the energy storage collaborative configuration scheme and the new energy power station planning data into the multi-objective line optimization model for analysis, and obtain the direct connection line topology diagram.

[0054] The model building module is used to optimize the heat map, power generation, photovoltaic joint sample, load forecast curve set and direct connection line topology diagram in sequence using data-driven optimization decision-making to obtain the source-storage-load collaborative optimization model. The source-storage-load collaborative optimization model is then used to plan green power direct connection in coal mining areas.

[0055] According to a third aspect of the present invention, a computer device is provided.

[0056] In some embodiments, the computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described above.

[0057] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0058] 1) Based on the specific conditions of coal mining areas, this invention proposes specific steps and technical solutions, such as land resource analysis based on GIS system, new energy output analysis based on high-precision meteorological data, refined load forecasting, multi-type energy storage collaborative configuration and direct connection line optimization, so as to realize the physical traceability and efficient utilization of green electricity, meet the special needs of coal mining areas, and enable coal mines to utilize land such as subsidence areas and slopes to build new energy power stations such as photovoltaic and wind power.

[0059] 2) This invention takes into account key factors such as land resources in coal mining areas, the characteristics of new energy output, load forecasting, energy storage configuration and direct connection line design, and proposes specific planning steps and technical solutions to achieve physical traceability and efficient utilization of green electricity, obtain stable green electricity through direct connection, reduce energy costs, and meet carbon emission reduction requirements.

[0060] 3) The direct connection mode of this invention ensures that green electricity reaches the mining load directly through a dedicated line, meets the certification requirements of international carbon tariffs for the verifiable proportion of green electricity, realizes physical traceability of green electricity, and is conducive to breaking through international carbon tariff barriers and achieving green transformation.

[0061] 4) This invention aims to achieve physical traceability and efficient utilization of green electricity through multiple aspects such as land resource analysis, new energy output analysis, load forecasting, energy storage configuration and direct connection line design.

[0062] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0063] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0064] Figure 1 This is one of the flowcharts illustrating a green power direct connection planning method for coal mining areas according to an exemplary embodiment;

[0065] Figure 2 This is a schematic diagram illustrating the principle of a green electricity direct connection planning system for a coal mining area, according to an exemplary embodiment.

[0066] Figure 3 This is a schematic diagram of the structure of a computer device according to an exemplary embodiment;

[0067] Figure 4 This is the second flowchart of a green power direct connection planning method for coal mining areas, as illustrated in an exemplary embodiment.

[0068] Figure 5 This is a schematic diagram of the land resource structure of a coal mine, illustrating a green power direct connection planning method for a coal mining area according to an exemplary embodiment.

[0069] Figure 6 This is a schematic diagram illustrating the analysis of new energy output in a green power direct connection planning method for coal mining areas, according to an exemplary embodiment.

[0070] Figure 7 This is a schematic diagram illustrating load forecasting in a green power direct connection planning method for coal mining areas according to an exemplary embodiment;

[0071] Figure 8 This is a schematic diagram illustrating energy storage analysis in a green power direct connection planning method for coal mining areas according to an exemplary embodiment;

[0072] Figure 9 This is a schematic diagram illustrating the analysis of direct connection lines in a green power direct connection planning method for coal mining areas, according to an exemplary embodiment. Detailed Implementation

[0073] The following description and accompanying drawings fully illustrate specific embodiments described herein to enable those skilled in the art to practice them. Some embodiments may include or substitute parts and features of other embodiments. The scope of the embodiments herein encompasses the entire scope of the claims and all available equivalents thereof. Throughout this document, the terms “first,” “second,” etc., are used only to distinguish one element from another without requiring or implying any actual relationship or order between the elements. Indeed, a first element can also be referred to as a second element, and vice versa. Furthermore, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a structure, apparatus, or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a structure, apparatus, or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the structure, apparatus, or device that includes said element. The various embodiments described herein are presented in a progressive manner, with each embodiment focusing on its differences from other embodiments; similar or identical parts between embodiments can be referred to interchangeably.

[0074] The terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer" used in this document to indicate orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings. They are used solely for the convenience of describing the document and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In the description herein, unless otherwise specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly. For example, they can refer to mechanical or electrical connections, or internal connections between two elements; they can be direct connections or indirect connections through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms according to the specific circumstances.

[0075] In this document, unless otherwise stated, the term "multiple" means two or more.

[0076] In this article, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0077] In this article, the term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0078] It should be understood that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order constraint on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the diagram may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0079] The modules in the apparatus or system of this application can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0080] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0081] Figure 1 An embodiment of a green power direct connection planning method for coal mining areas according to the present invention is shown.

[0082] In this optional embodiment, a method for planning green power direct connection in coal mining areas includes:

[0083] Step S101: Integrate geospatial information using a geographic information platform to obtain a three-dimensional geospatial information database. Process the three-dimensional geospatial information database using a land reuse assessment model to obtain a heat map. Quantitatively analyze the heat map to obtain the power generation.

[0084] Step S102: The heat map, power generation and multi-source meteorological data are processed and fused sequentially using a spatiotemporal convolutional neural network and a distributed intelligent sensing model to generate a meteorological database; and the meteorological database is analyzed and processed using a wind power and photovoltaic spatiotemporal output model to obtain a photovoltaic joint sample.

[0085] Step S103: The load forecasting model is used to process the photovoltaic joint sample and the pre-configured energy digital twin data in sequence to obtain the load forecasting curve set;

[0086] Step S104: Input the load forecast curve set, photovoltaic joint sample and pre-configured operating condition optimization data into the source-load time mismatch quantification model for analysis to obtain the energy storage collaborative configuration scheme;

[0087] Step S105: Input the energy storage collaborative configuration scheme and the new energy power station planning data into the multi-objective line optimization model for analysis to obtain the direct connection line topology diagram;

[0088] Step S106: Using data-driven optimization decision-making, the heat map, power generation, photovoltaic joint sample, load forecast curve set and direct connection line topology diagram are optimized in sequence to obtain the source-storage-load collaborative optimization model. The green power direct connection planning of coal mining area is carried out through the source-storage-load collaborative optimization model.

[0089] In this optional embodiment, the geospatial information includes: topographic maps of the mining area, satellite remote sensing images, geological exploration data, and land ownership information.

[0090] In this optional embodiment, geospatial information is integrated using a geographic information platform to obtain a three-dimensional geospatial information database. A land reuse assessment model is then used to process the three-dimensional geospatial information database to obtain a heat map. The heat map is then quantitatively analyzed to obtain the power generation figures, including:

[0091] By integrating geospatial information through a geographic information platform, a three-dimensional geospatial information database is obtained, and potential sites available for the deployment of new energy facilities are identified.

[0092] By combining historical subsidence monitoring data and geological stability prediction models, subsidence areas were screened to identify those that met the standards.

[0093] The roof area, load-bearing limit, and shadow shading data are obtained by calculating the building structure drawings and on-site surveys through a geographic information platform.

[0094] Geographic information spatial analysis tools were used to screen the slope angle, slope aspect, sunshine duration, rock mass stability, and soil and water conservation requirements of the slope area to obtain the south-facing slope.

[0095] The land reuse assessment model is used to evaluate the industrial sites with reuse potential, generate heat maps, and quantify the industrial sites with reuse potential for analysis to obtain power generation.

[0096] Specifically, in the initial stage of the green power direct connection planning method for low-carbon coal mines, a systematic land resource analysis needs to be carried out. This process involves high-precision spatial modeling and multi-dimensional evaluation of the entire mining area based on a Geographic Information System (GIS) platform. For example... Figure 5 As shown, the model assesses slope changes, water accumulation risk, and soil structural properties. The geological stability prediction model is a mathematical assessment tool built upon the principles of mining area geomechanics and settlement monitoring data. It is used to quantitatively predict surface settlement trends and the evolution of soil and rock bearing capacity. The model takes historical settlement monitoring data as input and outputs results such as settlement trend prediction, bearing capacity assessment, and risk classification. It calculates available roof area, load-bearing limits, and shading conditions, prioritizing buildings with high structural strength and ideal orientation. For slope angle, based on the digital elevation model of the mining area and airborne lidar scanning data, a slope distribution map was generated using GIS spatial analysis tools. The natural breakpoint method was used to divide the slope range, with 0-15° being a suitable area, 15-25° requiring reinforcement, and slopes greater than 25° excluded. For slope aspect sunshine duration, meteorological satellite radiation data and topographic shading models were integrated, and the annual sunshine distribution of 8760 hours was simulated using a solar trajectory algorithm. Taking due south as the baseline, the annual effective irradiance per unit area (kWh / m²) was quantified, excluding north-facing slopes with an average daily effective sunshine duration of less than 4 hours. For rock mass stability assessment, geological exploration borehole data and microseismic monitoring system were combined, and a dual-model verification of rock mass quality indicators and slope safety factors was used. For soil and water conservation analysis, a general soil loss equation was applied, and soil erodibility factors, rainfall erosivity factors, and vegetation cover factors were input to calculate the annual soil erosion modulus (t / ha). A threshold of less than or equal to 200 t / ha was set as the standard area.

[0097] In addition, the reuse potential of abandoned industrial sites such as waste rock dump remediation areas and closed wellhead reclamation areas is assessed simultaneously, excluding ecological protection zones, active mining areas, and high-risk areas above underground mining voids. Land assessment indicators cover usable area, solar radiation, accessibility, grid connection distance, and ecological restoration costs (land reuse assessment model), generating a tiered land resource distribution heat map and quantifying the annual equivalent green electricity generation per unit area (kWh / m²) for each block. This analysis provides core spatial constraint parameters for subsequent calculation of the upper limit of new energy installed capacity, equipment selection, and power line topology optimization, ensuring the coordinated optimization of land resource utilization, ecological restoration, and safe production.

[0098] In this optional embodiment, a spatiotemporal convolutional neural network and a distributed intelligent sensing model are sequentially used to process and fuse heat maps, power generation, and multi-source meteorological integrated data to generate a meteorological database; and a wind power and photovoltaic spatiotemporal output model is used to analyze and process the meteorological database to obtain a photovoltaic joint sample including:

[0099] A meteorological database is generated by using a spatiotemporal convolutional neural network to correct heat maps, power generation, spatiotemporal references of multi-source data, and ground station data.

[0100] Dynamic parameter capture of meteorological databases is performed using a distributed intelligent sensing model.

[0101] Robust optimization of pre-configured power output scenarios was calculated using spatiotemporal power output models of wind power and photovoltaic power to obtain a combined meteorological database photovoltaic sample.

[0102] Specifically, the analysis of new energy output requires the construction of spatiotemporal output models for wind power and photovoltaic power based on high-precision meteorological data and the environmental characteristics of mining areas. For example... Figure 6 As shown, a customized meteorological database for the mining area was established by integrating multi-source meteorological data: the data were integrated from the past 5 years of measured data from meteorological stations in and around the mining area, including irradiance, wind speed, temperature, humidity, cloud cover and atmospheric transmittance, satellite remote sensing surface radiation data, and mesoscale numerical weather prediction (WRF) prediction data downscaled to a 1km×1km grid (i.e., multi-source meteorological related data). In addition, parameters such as dust concentration and local wind field turbulence intensity were collected in real time from the microclimate monitoring network of the mining area, which are special to the coal mine environment.

[0103] The integration and downscaling of multi-source meteorological data are achieved through a fusion architecture: a meteorological data platform for the mining area is established at the basic data layer, connecting 10 surrounding meteorological stations and the mining area's self-built micro meteorological station, retrieving 5 years of historical datasets, using spatiotemporal interpolation to compensate for missing data, and using a wavelet transform-Kalman filter joint algorithm to eliminate sensor noise, generating a 1km×1km grid reference meteorological field; at the satellite data enhancement layer, satellite surface radiation products are called, and surface albedo and cloud optical thickness are inverted through visible light and infrared band fusion technology, and topographic circulation is simulated to output a 1km grid 15-minute wind speed and irradiance forecast sequence; at the spatiotemporal alignment layer, a spatiotemporal convolutional neural network is used to unify the spatiotemporal reference of multi-source data, and satellite data is used to correct ground station data to correct historical datasets, generating a spatially continuous and temporally synchronized meteorological database for the mining area.

[0104] The coal mine microclimate monitoring network achieves dynamic parameter capture through a distributed intelligent sensing system. For dust monitoring, laser scattering dust sensors are deployed at intervals of less than 200m in high-risk areas such as mining areas, conveyor belts, and spoil heaps, collecting data every 5 seconds. For wind field turbulence analysis, three-dimensional ultrasonic anemometer arrays are deployed at high points such as mine shafts and coal washing plant roofs, measuring wind speed components at height gradients of 1m / 5m / 10m with a sampling frequency of 20Hz, and calculating turbulence intensity in real time based on the Reynolds decomposition principle.

[0105] To achieve high precision and robustness in new energy power generation modeling, multi-source data was integrated. A spatiotemporal convolutional neural network was used to dynamically couple second-level monitoring data from ground meteorological stations and satellite surface radiation products to generate a meteorological field for the mining area with a spatial resolution of 1 km and a temporal resolution of 15 minutes. Based on real-time dust concentration data captured by a laser scattering dust sensor network, and utilizing turbulence intensity distribution maps measured by a three-dimensional ultrasonic anemometer array, wind power turbulence parameters were optimized using a Reynolds stress correction function. A stochastic algorithm was applied to uncover the implicit correlation between dust concentration and boundary layer height, generating a parameter generalization model for unmonitored areas. The integrated dataset was used as input. Photovoltaic power generation modeling employed a hybrid approach combining physical mechanisms and machine learning: 1. A component-level model was constructed based on simulation software, inputting the total radiation of the tilted surface, component temperature, and dust loss rate to calculate theoretical power output. 2. A neural network was used to learn the nonlinear relationship between historical power output and meteorological elements, compensating for fluctuations that physical models struggle to accurately capture, such as snow cover and transient cloud cover. The wind power output analysis focuses on addressing the impact of complex terrain: based on lidar scanning data from the meteorological tower and computational fluid dynamics (CFD) simulation, a 50m resolution 3D wind resource map of the mining area is generated. Simulation software is used for wind turbine adaptive selection and layout optimization, simulating wind power curves of different turbine types, such as low-wind-speed and turbulence-resistant types, at specific locations, and quantifying the array efficiency loss caused by wake effects. A set of 8760-hour annual output curves with a 15-minute time resolution and spatial resolution corresponding to the coordinates of each renewable energy station is output. Probabilistic output scenarios are simultaneously generated for robust optimization, and the equivalent utilization hours and output volatility of renewable energy in the mining area are calculated, providing a quantitative benchmark for subsequent energy storage configuration and direct connection line design. The generation of probabilistic output scenarios and the calculation of key indicators such as the equivalent utilization hours and output volatility of renewable energy in the mining area are achieved through a multi-source stochastic-physical hybrid model. 1000 sets of photovoltaic joint probability samples are generated based on a fused meteorological database, and a 15-minute photovoltaic output scenario is output by coupling a physical attenuation model. Wind power probabilistic scenarios are generated by sampling combined with the wind turbine adaptive transfer function. The equivalent utilization hours of new energy sources are calculated by the annual cumulative ratio of the actual output time-series average to the rated capacity. Output volatility is quantified in two levels: short-term volatility is calculated by the standard deviation of power ramp-up at the 15-minute level, and daily volatility index is calculated by the intraday peak-to-valley difference rate.

[0106] In this optional embodiment, the load forecasting model is used to process the photovoltaic joint sample and pre-configured energy digital twin data sequentially to obtain a load forecasting curve set including:

[0107] Based on the linkage between rigid loads, adjustable loads, and flexible loads, virtual and real data are obtained to generate energy digital twin data;

[0108] Extract photovoltaic joint samples and set dynamic path constraint windows to align the power step edge morphological inflection points, while introducing device state masks;

[0109] By analyzing energy digital twin data and extracted photovoltaic joint samples using a load forecasting model, a set of load forecasting curves is obtained.

[0110] Specifically, load forecasting is a prerequisite for ensuring the economical and reliable operation of green electricity direct-connection systems. It involves establishing refined forecasting models (i.e., load forecasting models) specifically tailored to the high energy consumption, strong fluctuations, and multiple constraints inherent in coal mine power consumption scenarios. For example... Figure 7 As shown, based on the electricity consumption characteristics of the entire mining production chain, the load is divided into three categories: rigid loads, such as key equipment that needs to operate continuously for 24 hours, such as mine ventilation / drainage systems and safety monitoring equipment, whose power curves are directly driven by safety thresholds such as underground gas concentration and hydrogeological parameters; adjustable loads, such as coal crushers, belt conveyors, and washing equipment that operate in conjunction with the mining plan, which can be shifted or compressed within a range of ±30% through production scheduling; and flexible loads, such as heating and cooling systems for mine office buildings, charging piles, and water storage tanks, which can respond to electricity price signals or new energy output and have adjustment capabilities ranging from minutes to hours. An energy digital twin module is used to integrate real-time power data, equipment ledger rated parameters, production scheduling logs, and meteorological data from the mine's SCADA system (i.e., data acquisition and monitoring control system) for virtual-real linkage (i.e., energy digital twin data). The data foundation integrates real-time power data from the mine's SCADA system, equipment ledger rated parameters, production scheduling logs, and meteorological data. It then uses simulation and re-expansion techniques to predict future loads: a baseline load curve is constructed, and a modified Dynamic Time Warping (DTW) algorithm is used to align load sequences from similar historical operating conditions, eliminating random fluctuations and extracting typical daily and monthly patterns. When aligning load sequences from similar historical operating conditions using the modified DTW algorithm, the temporal characteristics of the load sequence, equipment-related parameters, and environmental factors are extracted. A dynamic path constraint window is set to force alignment of morphological inflection points such as power step edges. Equipment state masks are introduced, and standard DTW is used to coarsely align peak mining periods. Fine-grained matching of details such as conveyor belt heavy-load transition points is achieved through dynamic time warping entropy, effectively filtering out power spikes caused by equipment failures. After eliminating high-frequency noise using Gaussian moving average, a smooth typical load pattern curve is output. For mines with expansion plans, multi-agent simulation is used by superimposing expansion factors to simulate the mine's expansion plans. The impact of coupled control strategies is assessed, and the correction amount of the demand-side response to the baseline load is quantified. The output includes a set of hourly load curves for the next 5 years with a 95% confidence interval, and simultaneously marks the time window for load adjustment potential, high-risk periods with a daily peak-valley difference rate of ≥40%, and regional electricity density heat maps, providing dynamic boundary conditions for source-storage synergistic optimization.

[0111] In this optional embodiment, the load forecast curve set, photovoltaic joint samples, and pre-configured operating condition optimization data are sequentially input into the source-load time-series mismatch quantification model for analysis, resulting in an energy storage collaborative configuration scheme including:

[0112] The sliding time window algorithm is used to calculate the pre-configured operating condition optimization data and extract the inertia deficit of the fluctuation index.

[0113] The effective inertia deficit of the fluctuation index is optimized using a multi-objective optimization model to obtain pre-configured operating condition optimization data;

[0114] By analyzing the load forecast curve set, photovoltaic joint samples, and pre-configured operating condition optimization data through the source-load time mismatch quantification model, an energy storage collaborative configuration scheme is obtained.

[0115] Specifically, energy storage analysis is a step in green electricity direct-connection systems to mitigate volatility and improve self-consumption rates. Based on the dynamic matching relationship between renewable energy output curves and load forecast data, and combined with the constraints of special coal mine operating conditions, it designs multi-type (i.e., operating condition optimization data) collaborative energy storage configuration schemes. For example... Figure 5As shown, a source-load time-series mismatch quantification model is constructed: A sliding time window algorithm is used to calculate the net power difference between photovoltaic (PV), wind power output, and mining loads daily. The frequency of negative differences (i.e., new energy deficit) lasting 4 hours or more per day and the distribution characteristics of single sustained peak values ​​of positive differences (i.e., new energy surplus) exceeding 6MW are statistically analyzed. Key fluctuation indicators are extracted, including the maximum ramp rate at 15-minute intervals, the peak-to-valley difference rate on the load side, and the system's equivalent inertia deficit. The specific implementation steps of the sliding time window algorithm are as follows: parameter initialization settings; the sliding time window algorithm uses a fixed 24-hour time window (e.g., 00:00 to 23:45) and slides along the 8760 hours of data throughout the year with a 15-minute step. The core definition of the net power difference is the total real-time output of PV and wind power minus the power superposition value of the three types of mining loads. The difference dynamically reflects the supply and demand relationship between new energy and loads, providing a data foundation for subsequent event statistics. The system captures renewable energy deficit events by initiating a continuous timing mechanism when the net power difference is continuously negative. If the cumulative duration is greater than or equal to 4 hours, it is marked as a deficit event. The system synchronously records the event frequency, peak deficit power (unit: MW), and precise time period, and correlates this with mine safety logs to analyze the event's causes. It also extracts renewable energy surplus characteristics by identifying net power deficits exceeding 6MW as surplus peak events, statistically analyzing the maximum duration (unit: hours) of a single event and its annual frequency, and specifically highlighting the distribution patterns of high-intensity events exceeding 8MW to provide quantitative basis for energy storage consumption design. Key fluctuation indicators are analyzed. For ramp-up risk, the system calculates the net power change rate within a 15-minute window, taking the average of the top 5% absolute values ​​as the ramp-up rate indicator (unit: kW / min) to warn of sudden power fluctuation risks. For load fluctuation, the system statistically analyzes the daily peak and trough values ​​of total load power within a window, calculates the percentage of peak-to-trough difference to the daily average load, and marks the distribution of high-risk periods exceeding 40%. Inertia gap, negative slope of net integral power change, output equivalent inertia deficit (unit: MWh), quantifying potential grid frequency instability.

[0116] In addition, energy storage selection and capacity optimization are performed: for power-type needs, lithium titanate batteries or flywheel energy storage systems can be configured, with power density meeting 2C rate charge / discharge requirements and passing mining explosion-proof certification; for energy-type needs, lithium iron phosphate batteries or compressed air energy storage can be selected. Capacity configuration is solved using a multi-objective optimization model. The objective function includes minimizing the life-cycle cost (LCOES), maximizing the green electricity self-consumption rate (with the annual proportion meeting the policy requirements of the coal mine location), and grid interaction power smoothness. Constraints are embedded in coal mine safety rules, equipment spatial layout, and cycle life decay models. The system outputs a technical parameter package for the energy storage system, including power, capacity, response time, and efficiency curves; as well as a full-scenario charge / discharge scheduling template and economic evaluation report, allowing comparison of peak-valley arbitrage benefits, diesel generator replacement costs, and carbon emission reduction subsidies; and provides boundary inputs for the capacity design and collaborative optimization model of direct connection lines.

[0117] In this optional embodiment, the planning data for new energy power stations includes: spatial distribution of new energy power stations, installed capacity parameters, energy storage layout coordinates, and load center location.

[0118] In this optional embodiment, the energy storage collaborative configuration scheme and new energy power station planning data are input into a multi-objective line optimization model for analysis, resulting in a direct connection line topology diagram including:

[0119] The triangular network algorithm is used to connect new energy nodes, energy storage aggregation points and load hubs. Combined with a three-dimensional geographic information model, it avoids high-risk areas of mining subsidence, blasting vibration impact zones and ecological restoration protection zones. The minimum spanning tree algorithm is used to iteratively generate an initial radial or ring network topology.

[0120] The dynamic capacity margin method is used to calculate the line current carrying capacity by considering the remaining line, conductor selection, comprehensive economic current density, short-circuit thermal stability limit, special mining conditions, and voltage level configuration.

[0121] Specifically, direct connection line analysis is the physical carrier design stage for achieving efficient source-load matching in green power direct connection systems. Based on the spatial distribution of new energy power plants, installed capacity parameters, energy storage layout coordinates, and load center locations (i.e., new energy power plant planning data), a multi-objective line optimization model is constructed under the complex geological constraints of coal mines. For example... Figure 8 As shown, a topology generation framework is established: The triangular mesh algorithm is used to initially connect new energy nodes, energy storage aggregation points, and load hubs. Combined with a 3D geographic information model (GIS) of the mining area, high-risk areas of mining subsidence, blasting vibration impact zones, and ecological restoration protection zones are automatically avoided. The initial radial or ring network topology is then iteratively generated using the minimum spanning tree (MST) algorithm. The specific steps of the triangular mesh algorithm are as follows:

[0122] Discrete node set construction: The location coordinates of new energy power stations, energy storage aggregation points and load centers are abstracted as topological nodes. Based on the three-dimensional geographic information model (GIS) of the mining area, the spatial location data of each node is accurately extracted to form an initial node coordinate set, which lays the geometric foundation for subsequent network construction.

[0123] Geological safety constraint embedding stage: The geological stability prediction model is called to automatically generate a 200-meter radius restricted construction buffer zone in the high-risk area of ​​mining subsidence (area with a settlement rate greater than 30 mm / year); at the same time, a 500-meter dynamic isolation circle is delineated around the blasting operation point in accordance with the "Coal Mine Safety Regulations", and the vector boundary of the ecological restoration area is superimposed to force the topological path to detour around all restricted areas.

[0124] The core calculation stage of triangulation: The initial mesh is generated using the triangulation method: the convex hull boundary of the node set is calculated, and the triangular network is initialized according to the maximum empty circle criterion; nodes are inserted point by point and the mesh structure is optimized to ensure that the circumcircle of each triangle does not contain other discrete points; the intersection of mesh edges and restricted areas is detected in real time during the triangulation process, and illegal edges are automatically deleted and adjacent triangles are recombined.

[0125] Topology connectivity optimization stage: The edge weights of the triangular network generated by the partitioning are reorganized: the path weights are calculated by combining the node spacing and elevation difference, and the edges with a slope of more than 25° are given a 10 times penalty weight to avoid steep slope areas; the backbone topology is extracted based on the constrained minimum spanning tree algorithm, and a tree network is generated with new energy nodes as roots and load centers as leaves, or redundant edges are added as needed to build a ring power supply loop.

[0126] In the coal mine engineering adaptation output stage: Line segments requiring rock mass reinforcement are automatically identified, generating a topology report containing node coordinates, edge weights, avoidance area statistics, and slope warnings; the output line path coordinate set and safety risk layer directly support subsequent electrical parameter design. This has been emphasized in the text.

[0127] Detailed electrical parameter design is implemented: Based on the peak output of the aforementioned renewable energy sources and the peak load demand, the dynamic capacity margin method is used to calculate the line current carrying capacity, setting the remaining line capacity to carry 120% of the maximum transferred load under N-1 fault conditions; conductor selection considers economic current density, short-circuit thermal stability limits, and special mining conditions; voltage level configuration is optimized based on the transmission distance-capacity relationship: for capacities less than 5MW and distances less than or equal to 3km, 10kV direct connection is used; for capacities greater than 10MW or cross-mining area transmission, voltage is boosted to 35kV. The specific method of the dynamic capacity margin method is as follows:

[0128] Basic current carrying capacity calculation: Based on the peak output of new energy sources and the maximum load demand, the initial current carrying capacity of the conductor is calculated. Taking into account the conductor material (such as aluminum alloy stranded wire), laying method (overhead / cable trench) and reference ambient temperature (35℃ in coal mining areas), the upper limit of steady-state current carrying capacity is determined through the heat balance equation.

[0129] N-1 Fault Dynamic Margin Enhancement: Simulates a scenario where any segment of the line is disconnected due to a fault, and calculates the load transfer amount that the remaining line needs to bear: extracts the maximum load value on the fault transfer path; sets the margin coefficient K=1.2, requiring the remaining line current carrying capacity to be greater than or equal to 1.2×fault transfer load; dynamically adjusts the conductor cross-sectional area.

[0130] Adaptation to Special Coal Mine Operating Conditions: Dust Heat Dissipation Reduction: Based on real-time dust concentration monitoring data, a thermal resistance correction coefficient is introduced (current carrying capacity is reduced by 8% when dust concentration exceeds 80 μg / m³). Temperature Rise Early Warning Mechanism: In the vicinity of high-temperature points (above 50℃) in the goaf, the current carrying capacity is forcibly reduced to 70% of the standard value. Explosion-proof Certification Constraints: For underground sections of the line, an additional 20% capacity margin is reserved according to the requirements of GB3836 standard.

[0131] Power quality was verified through transient simulation using PSCAD / EMTDC electromagnetic (i.e., electromagnetic transient program and DC system simulation program): the voltage fluctuation rate, harmonic distortion rate and fault ride-through capability of the new energy access point were monitored. The output included a direct-connection line technical parameter package containing path coordinates, tower type, cable specifications, relay protection settings and dynamic compensation device capacity, providing a basis for network loss calculation and reliability constraint boundary for the source-storage-load collaborative optimization model.

[0132] In this optional embodiment, data-driven optimization decisions are used to sequentially optimize the heat map, power generation, photovoltaic joint sample, load forecast curve set, and direct connection line topology diagram to obtain a source-storage-load collaborative optimization model. The planning of green power direct connections in coal mining areas using this source-storage-load collaborative optimization model includes:

[0133] The 3D geographic information platform processes heat maps and power generation data to construct a digital twin model of the land.

[0134] Based on photovoltaic joint sample data, a regional equivalent power output model is constructed, and a neural network is used to predict the nonlinear relationship between historical power output and meteorology.

[0135] Based on the load forecast curve set, data on rigid load, adjustable load and flexible load are extracted respectively. Combined with production scheduling logs and time-of-use electricity price signals, a load adjustment potential matrix is ​​constructed, and a reinforcement learning algorithm is used to dynamically update the load forecast model.

[0136] The system automatically generates the optimal topology based on the direct connection line topology diagram, calculates the line length and impedance parameters, monitors voltage fluctuations and harmonic distortion rates through electromagnetic transient simulation, and adjusts the capacity of reactive power compensation equipment accordingly.

[0137] Specifically, such as Figure 9 As shown, the source-storage-load collaborative optimization model is the core decision engine for green electricity direct connection planning. It needs to integrate spatial constraints from land resource analysis, fluctuation characteristics of new energy output, load adjustment potential, dynamic response capability of energy storage, and loss parameters of direct connection lines. It adopts data-driven optimization decision-making to build a dynamic optimization framework with low carbon, economy, and reliability as its goals.

[0138] The model design encompasses a three-tiered structure: the equipment layer defines decision variables (including photovoltaic / wind power installation coordinates and capacity, energy storage system power / capacity matrix, and direct-connection line topology switch status); the operation layer establishes an 8760-hour time-series optimization model (coupling new energy output curves, load forecast curves, and energy storage charging / discharging state variables in 15-minute steps); and the strategy layer embeds coal mine production scheduling rules, such as load shifting instructions driven by mining plans and demand response triggered by time-of-use pricing strategies. The objective function adopts a three-axis optimization architecture: the first axis represents the economic objective, the second axis represents the low-carbon objective, and the third axis represents the reliability objective. The constraint system innovatively introduces exclusive rules for green electricity direct connections, including constraints on the annual self-consumption ratio of new energy, the continuous power supply capacity of critical loads under N-1 faults in direct-connection lines, the limited charging / discharging depth of energy storage systems, and hard constraints on coal mine safety. The solution algorithm employs an improved quantum genetic algorithm (QGA): utilizing qubits to encode multidimensional decision variables, dynamically adjusting the search step size through an adaptive rotating door mechanism, and designing a coal mine safety verification layer. The output includes the optimal equipment configuration scheme, hourly scheduling strategy throughout the year, and sensitivity analysis report, and simultaneously generates a dynamic expansion path map for direct connection lines. This model achieves a synergistic gain of increased green electricity penetration and reduced cost per kilowatt-hour through multi-objective Pareto front analysis, and also enables physical traceability of green electricity generation.

[0139] like Figure 4 As shown, a land resource analysis of low-carbon coal mines is conducted, using a GIS system to identify available sites, which can be categorized into subsidence areas, rooftops, slopes, etc. New energy output analysis is performed, generating wind / solar power output curves based on meteorological data. Load forecasting is conducted, classifying the electricity load of low-carbon coal mines into three categories, acquiring historical load data, and analyzing future loads through simulation and expansion methods. Energy storage analysis is performed, combining new energy output fluctuations with load forecasts to determine the type and capacity of energy storage. Direct connection line analysis is conducted, determining the capacity and model of direct connection lines based on the location and capacity of new energy sources. A source-storage-load collaborative optimization model is established and solved using a dynamic optimization algorithm. During the solution process, special requirements for green electricity direct connection are considered, such as the lower limit of the proportion of annual self-generated and self-consumed electricity from new energy sources to total power generation.

[0140] Figure 2 An embodiment of a green power direct connection planning system for coal mining areas according to the present invention is shown.

[0141] In this optional embodiment, a green power direct connection planning system for coal mining areas includes:

[0142] The data acquisition module 201 is used to integrate geospatial information using a geographic information platform to obtain a three-dimensional geospatial information database, process the three-dimensional geospatial information database using a land reuse assessment model to obtain a heat map, and perform quantitative analysis on the heat map to obtain the power generation.

[0143] The processing and generation module 202 is used to process and fuse heat maps, power generation and multi-source meteorological integrated data in sequence using spatiotemporal convolutional neural networks and distributed intelligent sensing models to generate a meteorological database; and to analyze and process the meteorological database using wind power and photovoltaic spatiotemporal output models to obtain photovoltaic joint samples.

[0144] The curve acquisition module 203 is used to process the photovoltaic joint sample and the pre-configured energy digital twin data in sequence using the load forecasting model to obtain a set of load forecasting curves;

[0145] The optimization analysis module 204 is used to sequentially input the load forecast curve set, photovoltaic joint sample and pre-configured operating condition optimization data into the source-load time mismatch quantification model for analysis, and obtain the energy storage collaborative configuration scheme.

[0146] The analysis and acquisition module 205 is used to input the energy storage collaborative configuration scheme and the new energy power station planning data into the multi-objective line optimization model for analysis, and obtain the direct connection line topology diagram.

[0147] The model building module 206 is used to optimize the heat map, power generation, photovoltaic joint sample, load forecast curve set and direct connection line topology diagram in sequence using data-driven optimization decision-making to obtain the source-storage-load collaborative optimization model, and to carry out green power direct connection planning in coal mining areas through the source-storage-load collaborative optimization model.

[0148] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores static and dynamic information data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps in the above method embodiments.

[0149] Those skilled in the art will understand that Figure 3The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device to which the present invention is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0150] In addition, the present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0151] In addition, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0152] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0153] This invention is not limited to the structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this invention is limited only by the appended claims.

Claims

1. A method for planning direct green power connections in coal mining areas, characterized in that, include: Geographic information is integrated using a geographic information platform to obtain a three-dimensional geospatial information database. The three-dimensional geospatial information database is then processed using a land reuse assessment model to obtain a heat map. The heat map is then quantitatively analyzed to obtain the power generation. The heat map, power generation and multi-source meteorological data are processed and fused sequentially using a spatiotemporal convolutional neural network and a distributed intelligent sensing model to generate a meteorological database; and the meteorological database is analyzed and processed using a wind power and photovoltaic spatiotemporal output model to obtain a photovoltaic joint sample. The load forecasting model is used to process the photovoltaic joint sample and the pre-configured energy digital twin data in sequence to obtain a set of load forecast curves. Specifically, this includes: performing virtual-real linkage based on rigid load, adjustable load and flexible load to obtain energy digital twin data; extracting photovoltaic joint samples and setting dynamic path constraint windows to align the power step along the inflection point of the shape, while introducing equipment status masks; and analyzing the energy digital twin data and the extracted photovoltaic joint samples through the load forecasting model to obtain a set of load forecast curves. The load forecast curve set, photovoltaic joint sample and pre-configured operating condition optimization data are sequentially input into the source-load time mismatch quantification model for analysis to obtain the energy storage collaborative configuration scheme. The energy storage collaborative configuration scheme and the planning data of new energy power stations are input into the multi-objective line optimization model for analysis to obtain the topology diagram of the direct connection line. Using data-driven optimization decision-making, heat maps, power generation, photovoltaic joint samples, load forecast curve sets, and direct connection line topology maps are optimized sequentially to obtain a source-storage-load collaborative optimization model. This model is then used for green power direct connection planning in coal mining areas. Specifically, this includes: processing heat maps and power generation data using a 3D geographic information platform to construct a land digital twin model; constructing a zoned equivalent output model based on photovoltaic joint sample data and using neural networks to predict the nonlinear relationship between historical output and meteorological conditions; extracting data on rigid load, adjustable load, and flexible load from the load forecast curve set, combining production scheduling logs and time-of-use electricity price signals to construct a load adjustment potential matrix, and dynamically updating the load forecast model using reinforcement learning algorithms; automatically generating the optimal topology based on the direct connection line topology map, calculating line length and impedance parameters, and monitoring voltage fluctuations and harmonic distortion rates through electromagnetic transient simulation to adjust the reactive power compensation equipment capacity.

2. The method for planning green power direct connection in coal mining areas according to claim 1, characterized in that, The geospatial information includes: Topographic maps of the mining area, satellite remote sensing images, geological exploration data, and land ownership information.

3. The method for planning green power direct connection in coal mining areas according to claim 2, characterized in that, The process involves integrating geospatial information using a geographic information platform to obtain a three-dimensional geospatial information database. This database is then processed using a land reuse assessment model to generate a heat map. The heat map is then quantitatively analyzed to determine the power generation, which includes: By integrating geospatial information through a geographic information platform, a three-dimensional geospatial information database is obtained, and potential sites available for the deployment of new energy facilities are identified. By combining historical subsidence monitoring data and geological stability prediction models, subsidence areas were screened to identify those that met the standards. The roof area, load-bearing limit, and shadow shading data are obtained by calculating the building structure drawings and on-site surveys through a geographic information platform. Geographic information spatial analysis tools were used to screen the slope angle, slope aspect, sunshine duration, rock mass stability, and soil and water conservation requirements of the slope area to obtain the south-facing slope. The land reuse assessment model is used to evaluate the industrial sites with reuse potential, generate heat maps, and quantify the industrial sites with reuse potential for analysis to obtain power generation.

4. The method for planning green power direct connection in coal mining areas according to claim 1, characterized in that, The process sequentially utilizes a spatiotemporal convolutional neural network and a distributed intelligent sensing model to process and fuse heat maps, power generation, and multi-source meteorological data to generate a meteorological database. Furthermore, the meteorological database was analyzed and processed using spatiotemporal output models of wind power and photovoltaics to obtain a joint photovoltaic sample, including: A meteorological database is generated by using a spatiotemporal convolutional neural network to correct heat maps, power generation, spatiotemporal references of multi-source data, and ground station data. Dynamic parameter capture of meteorological databases is performed using a distributed intelligent sensing model. Robust optimization of pre-configured power output scenarios was calculated using spatiotemporal power output models of wind power and photovoltaic power to obtain a combined meteorological database photovoltaic sample.

5. The method for planning green power direct connection in coal mining areas according to claim 1, characterized in that, The process involves sequentially inputting the load forecast curve set, photovoltaic joint samples, and pre-configured operating condition optimization data into the source-load time-series mismatch quantification model for analysis, resulting in an energy storage collaborative configuration scheme including: The sliding time window algorithm is used to calculate the pre-configured operating condition optimization data and extract the inertia deficit of the fluctuation index. The effective inertia deficit of the fluctuation index is optimized using a multi-objective optimization model to obtain pre-configured operating condition optimization data; By analyzing the load forecast curve set, photovoltaic joint samples, and pre-configured operating condition optimization data through the source-load time mismatch quantification model, an energy storage collaborative configuration scheme is obtained.

6. The method for planning green power direct connection in coal mining areas according to claim 1, characterized in that, The planning data for the new energy power stations includes: Spatial distribution of new energy power stations, installed capacity parameters, energy storage layout coordinates, and load center location.

7. The method for planning green power direct connection in coal mining areas according to claim 6, characterized in that, The process of inputting energy storage collaborative configuration schemes and new energy power station planning data into a multi-objective line optimization model for analysis, resulting in a direct-connection line topology diagram, includes: The triangular network algorithm is used to connect new energy nodes, energy storage aggregation points and load hubs. Combined with a three-dimensional geographic information model, it avoids high-risk areas of mining subsidence, blasting vibration impact zones and ecological restoration protection zones. The minimum spanning tree algorithm is used to iteratively generate an initial radial or ring network topology. The dynamic capacity margin method is used to calculate the line current carrying capacity by considering the remaining line, conductor selection, comprehensive economic current density, short-circuit thermal stability limit, special mining conditions, and voltage level configuration.

8. A green power direct connection planning system for coal mining areas, used to implement the green power direct connection planning method for coal mining areas as described in any one of claims 1-7, characterized in that, include: The data acquisition module is used to integrate geospatial information using a geographic information platform to obtain a three-dimensional geospatial information database. The three-dimensional geospatial information database is then processed using a land reuse assessment model to obtain a heat map. The heat map is then quantitatively analyzed to obtain the power generation. The processing and generation module is used to process and fuse heat maps, power generation and multi-source meteorological data in sequence using spatiotemporal convolutional neural networks and distributed intelligent sensing models to generate a meteorological database; and to analyze and process the meteorological database using wind power and photovoltaic spatiotemporal output models to obtain photovoltaic joint samples. The curve acquisition module is used to process the photovoltaic joint sample and the pre-configured energy digital twin data in sequence using the load forecasting model to obtain a set of load forecasting curves; The optimization analysis module is used to sequentially input the load forecast curve set, photovoltaic joint sample and pre-configured operating condition optimization data into the source-load time-series mismatch quantification model for analysis, and obtain the energy storage collaborative configuration scheme. The analysis and acquisition module is used to input the energy storage collaborative configuration scheme and the new energy power station planning data into the multi-objective line optimization model for analysis, and obtain the direct connection line topology diagram. The model building module is used to optimize the heat map, power generation, photovoltaic joint sample, load forecast curve set and direct connection line topology diagram in sequence using data-driven optimization decision-making to obtain the source-storage-load collaborative optimization model. The source-storage-load collaborative optimization model is then used to plan green power direct connection in coal mining areas.

Images