Method and system for calculating power generation based on wind and light resources and equipment data

Abstract

The application relates to the technical field of new energy power generation, and discloses a power generation capacity calculation method and system based on wind and light resources and equipment data. The application collects and fuses wind and light resource data and equipment performance parameters to construct a standardized data set; based on the data set, a resource-equipment dynamic coupling potential field is established, the potential field accurately represents the comprehensive power generation potential in the time and space dimensions by fusing resource space gradients and equipment response characteristics; then, triple integral calculation is carried out on the potential field, and an adaptive algorithm is used to control errors; finally, model verification and parameter optimization are carried out to realize self-calibration of the system. The application overcomes the defects of the traditional method, such as insufficient data fusion, static model, contradiction between calculation accuracy and efficiency, and the like, and significantly improves the accuracy, adaptive capacity and engineering practical value of the power generation capacity calculation.

Description

Technical Field

[0001] This invention relates to the field of new energy power generation technology, and in particular to a method and system for calculating power generation based on wind and solar resources and equipment data. Background Technology

[0002] With the increasing global demand for renewable energy, the accuracy of wind and solar power generation forecasts is crucial for the stable operation of the power grid, the optimization of power dispatch, and energy trading decisions, as important clean energy sources. However, wind and solar power generation is characterized by significant intermittency, volatility, and uncertainty. Their power output is affected by multiple complex factors, such as meteorological conditions and equipment performance, which poses a significant challenge to accurate estimation.

[0003] Existing methods for calculating wind and solar power generation have significant limitations: most models lack sufficient data fusion and fail to integrate multi-source heterogeneous meteorological and equipment data; moreover, they often employ static or quasi-static assumptions, making it difficult to characterize the coupling relationship between spatiotemporal fluctuations of resources and dynamic responses of equipment, resulting in decreased accuracy in complex scenarios; in addition, existing methods provide coarse descriptions of key physical processes such as resource field gradients and equipment response delays, have large integral calculation errors, and lack effective adaptive optimization mechanisms to cope with equipment aging and climate change.

[0004] In summary, existing technologies have shortcomings in data fusion, dynamic coupling modeling, computational accuracy, and model adaptability, making it difficult to meet the engineering requirements for high-precision power generation assessment. Therefore, there is an urgent need for a novel computational method that can deeply integrate multi-source data, accurately describe the dynamic coupling process, and possess online optimization capabilities to support the efficient consumption of renewable energy and the safe and stable operation of the power grid. Summary of the Invention

[0005] The technical problem to be solved by this invention is the shortcomings of the prior art. To address this, we propose a method and system for calculating power generation based on wind and solar resources and equipment data.

[0006] To achieve the above objectives, this application adopts the following technical solution: a power generation calculation method based on wind and solar resources and equipment data, comprising the following steps: Step 1: Data acquisition and fusion processing: acquiring wind and solar resource data of the target area, including spatiotemporal distribution data of wind speed, wind direction, solar irradiance, and ambient temperature; simultaneously acquiring performance parameter data of power generation equipment, including wind turbine power curves, photovoltaic module efficiency characteristics, and equipment geographical location information; preprocessing the acquired data to form a standardized dataset; Step 2: Dynamic coupling potential field construction: based on the standardized dataset, constructing a resource-equipment dynamic coupling potential field through a dynamic coupling algorithm, wherein the potential field is spatiotemporally continuous. The field quantity is used to characterize the comprehensive power generation potential at any spatial location and time point; the dynamic coupling algorithm establishes a power generation capacity assessment model that considers spatiotemporal correlation by integrating resource fluctuation characteristics and equipment response characteristics; Step 3: Power generation potential field integral calculation and verification: triple integral operation is performed on the dynamic coupling potential field in the target spatial region and calculation period, and the total power generation is solved by numerical calculation method; an integral error compensation mechanism is established, and an adaptive step size algorithm is used to improve the calculation accuracy, and finally the calibrated total power generation estimate is output; Step 4: Model verification and optimization: power generation data of typical time periods are selected for model verification, the model is established, the optimization priority is determined, and the model parameters are updated in real time.

[0007] Preferably, data acquisition and fusion processing specifically includes: wind and solar resource data acquisition: obtaining gridded resource data through meteorological monitoring stations, satellite remote sensing equipment, and numerical weather prediction systems, with a temporal resolution of no less than 1 hour and a spatial resolution of no less than 1 kilometer; equipment parameter acquisition: obtaining detailed technical parameters of power generation equipment from equipment monitoring systems and manufacturer databases, including rated power, efficiency curves, and operating limitations; data preprocessing specifically includes: quality control of resource data, removing obvious outliers, and filling in missing data using Kriging interpolation; standardization of equipment parameters, unifying data formats and units; and establishing a spatiotemporal index to ensure spatiotemporal matching between resource data and equipment data.

[0008] Preferably, the processing of wind and solar resource data in step one also includes: establishing a spatiotemporal correlation analysis model for resource data, and extracting the main spatiotemporal feature patterns using the empirical orthogonal function decomposition method; establishing a Weiber distribution model for wind speed data and a Beta distribution model for irradiance data to quantify the uncertainty characteristics of resources; using wavelet transform and Fourier analysis methods to study the time-frequency characteristics of resources and identify the fluctuation patterns at different time scales; and establishing quality control standards for resource data, including data integrity, accuracy, and consistency inspection specifications.

[0009] Preferably, the processing of equipment parameter data in step one also includes: smoothing the wind turbine power curve and using an S-shaped function to fit the transition characteristics of the cut-in, rated, and cut-out wind speed ranges; establishing a temperature correction model for photovoltaic module efficiency, considering the influence of irradiance and ambient temperature on conversion efficiency; establishing an equipment aging model and dynamically adjusting equipment performance parameters based on operating years and maintenance records; and designing an equipment parameter verification process to ensure parameter accuracy through comparative analysis of measured data and theoretical parameters.

[0010] Preferably, the dynamic coupling potential field construction in step two specifically includes: potential field initialization step: calculating the theoretical power generation of each grid point based on standardized data as the initial value of the potential field; spatiotemporal coupling calculation step: considering the spatiotemporal correlation of resources and the dynamic response characteristics of equipment, correcting the initial potential field through a coupling algorithm; potential field optimization step: using a regularization method to smooth the potential field distribution, eliminate abnormal fluctuations, and ensure the physical rationality of the potential field.

[0011] Preferably, a dynamically coupled potential field Defined by the following formula: ;in It is a spatial position vector. It is a time variable; For position and time Theoretical power generation capacity at the location; The spatial gradient mode of the resource field; This is the device response time constant; Coupling strength coefficient; theoretical power generation. Calculations are made separately based on equipment type: For wind power generation equipment: ,in This is a function representing the power curve of the wind turbine. For wind speed; for photovoltaic power generation equipment: ,in Irradiance, Let be the efficiency function. For temperature; resource field spatial gradient mode The central difference method is used for calculation, considering wind speed gradient for wind power and irradiance gradient for photovoltaic power; the equipment response time constant is also considered. The coupling strength coefficient is determined based on the equipment type: 5-15 seconds for wind turbines and 1-5 seconds for photovoltaic inverters. The values ​​are obtained through training on historical data and range from 0.1 to 1.0.

[0012] Preferably, the integral calculation of the power generation potential field in step three specifically includes: a numerical integration step: spatial integration is performed using the Gaussian quadrature method, and time integration is performed using the Runge-Kutta method to ensure calculation accuracy and stability; an error control step: an integration error estimation model is established, and the integration step size is adaptively adjusted according to the smoothness of the potential field; boundary effects are handled, and the mirror extension method is used to reduce integration errors; a result verification step: historical power generation data is collected to establish a verification dataset; the deviation statistics between the predicted value and the actual value are calculated; and an error correction function is established to systematically correct the deviation of the integration results.

[0013] The preferred numerical calculation method for determining the total power generation is as follows: ;in This is the spatial integration region; The region is the time integration region; The weighting function takes into account equipment density and grid connection conditions; the integral calculation adopts a stratified sampling method, with denser sampling points in high gradient regions. Indicates a spatial region Time period Perform triple integrals on the above. For spatial differential elements, For time-differential elements, and Together, they constitute the infinitesimal element of the spatiotemporal integral. The product of the resource-equipment coupled potential field and the weighting function is continuously accumulated at every location within the target space and at every moment within the target time range, thereby directly obtaining the total power generation; the weighting function The calculation method is as follows: ;in, For the spatial distribution density of equipment; This is a time-weighted coefficient that takes into account day-night and seasonal variations. This is the grid connection capacity factor, reflecting the absorption capacity of the local power grid.

[0014] Preferably, model validation and optimization specifically include: Model validation steps: Select typical historical periods, compare the differences between calculated values ​​and actual power generation, calculate statistical indicators such as root mean square error and mean absolute percentage error, and evaluate model accuracy; Parameter optimization steps: Use genetic algorithms to optimize model parameters, minimize prediction errors, establish a parameter sensitivity analysis model, identify key parameters, and optimize them accordingly; Model update steps: Establish an online learning mechanism to dynamically update model parameters based on new data, and periodically retrain the model to adapt to the impact of equipment aging and climate change.

[0015] This invention provides another technical solution: a power generation calculation system based on wind and solar resources and equipment data, comprising: a data acquisition module, including: a resource data acquisition unit, integrating multi-source meteorological data and satellite remote sensing data to achieve comprehensive acquisition of wind and solar resource data; an equipment data acquisition unit, acquiring equipment operating status and performance parameters in real time; a data quality monitoring unit, automatically detecting data anomalies and triggering alarm and processing mechanisms, recording data quality problems and processing results; a data storage management unit, optimizing the data organization structure, adopting a hierarchical storage strategy to improve data access efficiency; a core computing module, including: a potential field calculation acceleration unit, using GPU parallel computing technology to improve computing efficiency; an integration optimization unit, implementing an adaptive integration algorithm, dynamically adjusting the integration strategy according to the calculation accuracy requirements; a memory management unit, using memory pool technology to optimize memory allocation and release during large-scale data processing; and a result output module, providing multiple output formats, including data reports, trend charts, and spatial distribution maps, and also used for result export and interface calls.

[0016] The technical effects and advantages of this invention are as follows: This invention collects wind and solar resource data and power generation equipment performance parameter data to form standardized multi-source data. Through a dynamic coupling algorithm, it integrates resource fluctuation characteristics and equipment response characteristics to establish a power generation capacity assessment model that considers spatiotemporal correlation. This model more realistically reflects the complex dynamic relationship between resources and equipment, improving the accuracy of power generation potential assessment. A triple integral operation is used to solve the dynamic coupling potential field, and an integral error compensation mechanism is established. An adaptive step-size algorithm improves calculation accuracy, ultimately outputting a calibrated total power generation estimate, effectively reducing calculation errors and improving the robustness of the results. During data acquisition, potential field construction, and integral calculation, meteorological factors such as wind speed, wind direction, irradiance, and temperature are comprehensively considered, as well as equipment and system factors such as wind turbine power curves, photovoltaic module efficiency, equipment aging, and grid connection capabilities, making the power generation estimate closer to reality. Through model verification and optimization steps, the model can adapt to the effects of equipment aging and climate change, maintaining high accuracy over a long period. Attached Figure Description

[0017] The disclosure of this invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. In the drawings, the same reference numerals are used to refer to the same parts:

[0018] Figure 1 This is a schematic diagram of the process of the present invention; Figure 2 This is a module topology diagram of the present invention. Detailed Implementation

[0019] It is readily understood that, based on the technical solution of this invention, those skilled in the art can propose various interchangeable structural methods and implementations without altering the essential spirit of the invention. Therefore, the following detailed embodiments and accompanying drawings are merely illustrative examples of the technical solution of this invention and should not be considered as the entirety of the invention or as limitations or restrictions on the technical solution of this invention.

[0020] Reference Figures 1-2 As shown, this invention provides a method and system for calculating power generation based on wind and solar resources and equipment data, aiming to solve the problems of insufficient prediction accuracy and poor model robustness in existing technologies. This method achieves high-precision estimation of wind and solar power generation through multi-source data fusion, dynamic coupling potential field construction, and refined integral calculation.

[0021] Example 1: This example describes in detail the specific steps of the power generation calculation method of the present invention.

[0022] Step 1: Data Acquisition and Fusion Processing: Obtain comprehensive, accurate, and standardized input data. Specifically, this includes: Wind and Solar Resource Data Acquisition: Acquire wind and solar resource data for the target area through multiple channels. Utilize ground observation data provided by meteorological monitoring stations, combined with satellite remote sensing equipment to obtain large-scale, high spatial resolution data such as irradiance and cloud cover. Also, utilize numerical weather prediction systems to obtain gridded meteorological forecast data for the future period, including wind speed, wind direction, solar irradiance, and ambient temperature. To ensure calculation accuracy, the temporal resolution of this resource data is no less than 1 hour, and the spatial resolution is no less than 1 kilometer. Equipment Parameter Acquisition: Obtain real-time operating status data of the power generation equipment from the monitoring system, such as the wind turbine's speed, blade angle, and output power, and the photovoltaic module's current and voltage. Simultaneously, obtain detailed technical parameters of the power generation equipment from the manufacturer's database or equipment nameplate, including the wind turbine's rated power, power curve, cut-in / cut-out wind speed, the photovoltaic module's rated power, efficiency curve, temperature coefficient, maximum output power, minimum operating temperature, etc., as well as the equipment's precise geographical location information.

[0023] The collected raw data undergoes quality control and standardization: Resource data quality control: The collected wind and solar resource data is quality-verified, and outliers that are significantly outside the physical range or statistically abnormal are removed, such as negative wind speeds or irradiance exceeding the theoretical maximum. For missing data, spatial interpolation techniques such as Kriging interpolation are used to fill in the gaps to ensure data continuity and integrity. Equipment parameter standardization: Equipment parameters from different sources and in different formats are standardized to unify data formats and units, ensuring data consistency. All power units are unified to MW, and temperature units are unified to degrees Celsius. Spatiotemporal index establishment: A spatiotemporal index is established for resource data and equipment data to ensure accurate spatiotemporal matching between the two. For any point in time and spatial location, the corresponding resource data and equipment data can be accurately found.

[0024] In a preferred embodiment, the processing of wind and solar resource data further includes: establishing a spatiotemporal correlation model: establishing a spatiotemporal correlation model for the resource data, and using the empirical orthogonal function decomposition method to extract the main spatiotemporal features of the resource field, which helps to capture the overall evolution trend and spatial structure of the wind field and irradiance field, providing a deeper understanding for subsequent dynamic coupling; quantifying resource uncertainty: establishing a Weiber distribution model for wind speed data and a Beta distribution model for irradiance data to quantify resource uncertainty, which can better describe the random fluctuation characteristics of wind speed and irradiance; analyzing time-frequency characteristics: using wavelet transform to analyze the time-frequency characteristics of resources, identifying the periodic fluctuation patterns of resources, such as daily cycles and seasonal cycles, which facilitates understanding the internal mechanism of resource changes and provides periodic feature inputs for the prediction model.

[0025] In another preferred embodiment, the processing of equipment parameter data further includes: wind turbine power curve smoothing: smoothing the wind turbine power curve by using an S-shaped function to fit the transition characteristics of the cut-in, rated, and cut-out wind speed ranges, more accurately describing the output power of the wind turbine at different wind speeds, especially the dynamic response when wind speed changes drastically; photovoltaic module efficiency temperature correction: establishing a temperature correction model for photovoltaic module efficiency, considering the influence of irradiance and ambient temperature on conversion efficiency. For example, efficiency decreases as temperature increases, and this model can accurately quantify this influence; equipment aging model establishment: establishing an equipment aging model, dynamically adjusting equipment performance parameters based on operating years and maintenance records. For example, the efficiency of photovoltaic modules gradually decays over operating time, and wear and tear on the mechanical components of the wind turbine affects its power output. This model can reflect these long-term changes.

[0026] Step Two: Dynamic Coupled Potential Field Construction: Deeply integrate resource fluctuation characteristics with equipment response characteristics to form a spatiotemporally continuous comprehensive power generation potential field. This includes: Potential field initialization steps: Based on a standardized dataset, calculate the theoretical power generation of each grid point or equipment location at each time point. For wind power generation equipment, the theoretical power generation is calculated based on the wind turbine power curve function. Calculation, where For position and time For photovoltaic power generation equipment, the theoretical power generation capacity is determined by the wind speed at the location and the irradiance. and efficiency function Calculation, where The ambient temperature is used as the initial value for the dynamic coupling potential field. The spatiotemporal coupling step considers the spatiotemporal correlation of resources and the dynamic response characteristics of equipment. The initial potential field is corrected by a dynamic coupling algorithm that integrates factors such as the spatial gradient of the resource field and the response time of the equipment to more realistically reflect the power generation potential.

[0027] In a preferred embodiment, the dynamically coupled potential field Defined by the following formula: ;in: It is a spatial position vector. It is a time variable; For position and time The theoretical power generation capacity at each location is calculated separately based on the type of equipment. The spatial gradient mode of the resource field characterizes the degree of drastic change of resources in space. For wind power, the wind speed gradient is mainly considered, and for photovoltaics, the irradiance gradient is mainly considered. The gradient mode is calculated using the central difference method. The equipment response time constant reflects the speed at which the equipment responds to changes in resources, such as wind turbine blade adjustment and inverter response. It is determined according to the type of equipment; for wind turbines, it is usually 5-15 seconds, and for photovoltaic inverters, it is usually 1-5 seconds. The coupling strength coefficient is a parameter that adjusts the degree of influence of resource gradient and device response on the potential field. This coefficient is obtained through training with historical data and has a value range of 0.1-1.0 to ensure that the model can adapt to different regions and device characteristics. The potential field optimization sub-step involves using regularization methods to smooth the potential field distribution, eliminate abnormal fluctuations caused by data noise or local instability of the model, and ensure the physical rationality of the potential field. For example, Gaussian smoothing, Laplace smoothing, and other methods can be used.

[0028] Step 3: Power Generation Potential Field Integration Calculation: Accumulate the potential of the dynamic coupled potential field within a specific spatiotemporal range to obtain the final estimated total power generation. This specifically includes: Numerical integration steps: Calculate the potential of the dynamic coupled potential field within the target spatial region. and calculation cycle The system performs triple integration to solve for the total power generation.

[0029] In a preferred embodiment, the total power generation Calculated using the following integral formula: ;in: The spatial integration region is the geographical area where the wind and solar power plants are located. This refers to the time integration region, which is the period during which power generation needs to be calculated, such as a day, a week, or a month. The weighting function takes into account factors such as equipment density and grid connection conditions. The integral calculation adopts a stratified sampling method, which densifies the sampling points in the high gradient region. Specifically, the spatial integral adopts the Gaussian quadrature method, which has high accuracy for a given number of sampling points, and the time integral adopts the Runge-Kutta method, which has good stability and accuracy when processing time series integrals. Indicates a spatial region Time period Perform triple integrals on the above. For spatial differential elements, For time-differential elements, and Together they form the infinitesimal element of the spatiotemporal integral. The product of the resource-equipment coupling potential field and the weighting function is continuously accumulated at each location within the target space and at each moment within the target time range, thereby directly obtaining the total power generation.

[0030] In a preferred embodiment, the weighting function The calculation method is as follows: ;in: The spatial distribution density of equipment indicates its spatial location. The number or capacity of equipment per unit area in the vicinity reflects the power generation potential density of the area; The time-weighted coefficient takes into account the impact of day-night and seasonal variations on power generation. For example, the weighting coefficient for photovoltaic power generation will decrease at night or in winter. The grid connection capacity factor reflects the local grid's absorption capacity. In areas where grid absorption capacity is limited, even if the power generation potential is high, the actual output will be limited. This factor is used to quantify this limitation.

[0031] Error compensation steps: Establish an integral error estimation model and adaptively adjust the integral step size according to the smoothness of the potential field. In regions with drastic changes in the potential field, a smaller step size is used to capture details; in regions with a gentle potential field, a larger step size is used to improve computational efficiency; boundary effects are addressed by using the mirror extension method to reduce integral errors, which helps avoid errors caused by data truncation at the boundaries of the integration region.

[0032] The calibration process involves establishing an error correction function based on historical data, correcting systematic deviations in the integral results, identifying and quantifying systematic deviations by comparing historical calculated values ​​with actual power generation, and applying these deviations to future predictions to improve accuracy.

[0033] Example 2: This example describes the process of verifying and continuously optimizing the above-mentioned power generation calculation method.

[0034] Model validation steps: Select typical historical periods, such as high wind speed, low wind speed, high irradiance, low irradiance, seasonal changes, etc., and compare the differences between the calculated values ​​and the actual power generation; calculate statistical indicators such as root mean square error and mean absolute percentage error to evaluate the accuracy and stability of the model and quantify the deviation between the model's predicted values ​​and the actual values.

[0035] Parameter optimization steps: Intelligent optimization algorithms such as genetic algorithms and particle swarm optimization are used to optimize key parameters in the model, such as the coupling strength coefficient. The coefficients in the weighting function are used to minimize the prediction error; a parameter sensitivity analysis model is established to identify the key parameters that have the greatest impact on the model output, and these parameters are optimized and finely adjusted.

[0036] Model update steps: Establish an online learning mechanism to dynamically update model parameters based on new real-time data and historical operating data. The model can continuously learn from new data over time and adapt to factors such as equipment aging, climate change, and changes in power grid structure. The model is retrained regularly to adapt to the impact of equipment aging and climate change. For example, the entire model is retrained using the latest historical data every once in a while to ensure the long-term effectiveness of the model.

[0037] Example 3: This invention provides a power generation calculation system based on wind and solar resources and equipment data. It is characterized by comprising: a data acquisition module, including: a resource data acquisition unit that integrates multi-source meteorological data and satellite remote sensing data to achieve comprehensive acquisition of wind and solar resource data; an equipment data acquisition unit that acquires equipment operating status and performance parameters in real time; a data quality monitoring unit that automatically detects data anomalies and triggers alarm and processing mechanisms, recording data quality issues and processing results; a data storage management unit that optimizes the data organization structure, adopts a hierarchical storage strategy, and improves data access efficiency; a core computing module, including: a potential field calculation acceleration unit that uses GPU parallel computing technology to improve computing efficiency; an integration optimization unit that implements an adaptive integration algorithm and dynamically adjusts the integration strategy according to the calculation accuracy requirements; a memory management unit that uses memory pool technology to optimize memory allocation and release during large-scale data processing; and a result output module that provides multiple output formats, including data reports, trend charts, and spatial distribution maps, and is also used for result export and interface calls. Data reports can provide detailed power generation values, trend charts can display the temporal changes in power generation, and spatial distribution maps can intuitively display the power generation potential of different regions.

[0038] The technical scope of this invention is not limited to the content described above. Those skilled in the art can make various modifications and variations to the above embodiments without departing from the technical concept of this invention, and all such modifications and variations should fall within the protection scope of this invention.

Claims

1. A method for calculating power generation based on wind and solar resource and equipment data, characterized in that, The method comprises the following steps: step Step 1: Data Acquisition and Fusion Processing: Collect wind and solar resource data for the target area, including the spatiotemporal distribution data of wind speed, wind direction, solar irradiance, and ambient temperature; simultaneously collect performance parameter data of power generation equipment, including wind turbine power curves, photovoltaic module efficiency characteristics, and equipment geographical location information; preprocess the collected data to form a standardized dataset; Step 2: Dynamic Coupled Potential Field Construction: Based on the standardized dataset, construct a resource-equipment dynamic coupled potential field using a dynamic coupling algorithm. This potential field is a spatiotemporally continuous field quantity used to characterize the comprehensive power generation potential at any spatial location and time point; the dynamic coupling algorithm establishes a power generation capacity assessment model considering spatiotemporal correlation by integrating resource fluctuation characteristics and equipment response characteristics; Step 3: Power Generation Potential Field Integral Calculation and Verification: Calculate and verify the dynamic coupled potential field in the target spatial area... The process involves three integral operations within the domain and computation cycle to solve for the total power generation using numerical methods. An integral error compensation mechanism is established, and an adaptive step-size algorithm is employed to improve computational accuracy. The final output is a calibrated estimate of the total power generation. Step four: Model verification and optimization. Power generation data from typical time periods are selected for model verification. The model is established, optimization priorities are determined, and model parameters are updated in real time. The dynamic coupling potential field construction in step two specifically includes: Potential field initialization: Calculating the theoretical power generation of each grid point based on standardized data as the initial value of the potential field; Spatiotemporal coupling calculation: Considering the spatiotemporal correlation of resources and the dynamic response characteristics of equipment, the initial potential field is corrected using a coupling algorithm; Potential field optimization: A regularization method is used to smooth the potential field distribution, eliminate abnormal fluctuations, and ensure the physical rationality of the potential field. The dynamic coupling potential field... Defined by the following formula: ;in It is a spatial position vector. It is a time variable; For position and time Theoretical power generation capacity at the location; The spatial gradient mode of the resource field; This is the device response time constant; Coupling strength coefficient; theoretical power generation. Calculations are made separately based on equipment type: For wind power generation equipment: ,in This is a function representing the power curve of the wind turbine. For wind speed; for photovoltaic power generation equipment: ,in Irradiance, Let be the efficiency function. For temperature; resource field spatial gradient mode The central difference method is used for calculation, considering wind speed gradient for wind power and irradiance gradient for photovoltaic power; the equipment response time constant is also considered. According to the device type determination, the fan takes 5-15 seconds, the photovoltaic inverter takes 1-5 seconds, and the coupling strength coefficient The value range is 0.1-1.0; the power generation potential field integral calculation in step three specifically includes: a numerical integral step: spatial integration is performed using the Gauss quadrature method, and time integration is performed using the Runge-Kutta method to ensure calculation accuracy and stability; an error control step: an integral error estimation model is established, and the integral step size is adaptively adjusted according to the potential field smoothness; boundary effects are handled, and the mirror continuation method is used to reduce integral errors; a result verification step: collect historical power generation data to establish a verification data set; calculate the deviation statistics of the predicted value and the actual value; establish an error correction function to systematically correct the integral results; the numerical calculation method for solving the total power generation is specifically: ; wherein is the spatial integral region; is the time integral region; is the weight function, considering the device density and grid access conditions; the integral calculation uses a hierarchical sampling method to encrypt sampling points in high gradient areas; represents triple integration in the spatial region time period , is a spatial differential element, is a time differential element, and together constitute the infinitesimal of the space-time integral, and the product of the resource-device coupling potential field and the weight function is continuously added up at each position in the target spatial range and at each time in the target time range. Contribution, thus directly obtaining the total power generation; the calculation method of the weight function is: ; wherein, is the device spatial distribution density; is the time weight coefficient, considering the day and night and seasonal changes; is the grid access ability factor, reflecting the local grid's consumption capacity.

2. The method for calculating the power generation amount based on wind and light resources and equipment data according to claim 1, characterized in that: The data acquisition and fusion processing specifically comprises: wind and light resource data acquisition: obtaining grid resource data through meteorological monitoring stations, satellite remote sensing equipment and numerical weather prediction systems, with a time resolution of not less than 1 hour and a spatial resolution of not less than 1 kilometer; parameter acquisition of equipment: obtaining detailed technical parameters of power generation equipment from the equipment monitoring system and the manufacturer database, including rated power, efficiency curve, operating limit condition; data preprocessing specifically comprises: quality control of resource data, elimination of obvious outliers, and filling of missing data by using Kriging interpolation method; standardization processing of equipment parameters, unification of data format and unit; establishment of time and space index to ensure the time and space matching of resource data and equipment data.

3. The method for calculating the power generation amount based on wind and light resources and equipment data according to claim 2, characterized in that: The processing of wind and light resource data in step one further comprises: establishing a time and space correlation analysis model of resource data, and extracting main time and space characteristic patterns by using empirical orthogonal function decomposition method; establishing a Weibull distribution model for wind speed data and a Beta distribution model for irradiance data to quantify the uncertainty characteristics of resources; using wavelet transform and Fourier analysis method to study the time-frequency characteristics of resources and identify the fluctuation rules of different time scales; establishing quality control standards for resource data, including data integrity, accuracy and consistency check specifications.

4. The method for calculating the power generation amount based on wind and light resources and equipment data according to claim 2, characterized in that: The processing of equipment parameter data in step one further comprises: smoothing the wind turbine power curve, and using S-shaped function to fit the transition characteristics of the cut-in, rated and cut-out wind speed intervals; establishing a temperature correction model for photovoltaic module efficiency, considering the influence of irradiance and ambient temperature on conversion efficiency; establishing an equipment aging model to dynamically adjust equipment performance parameters according to operating time and maintenance records; designing a device parameter verification process to ensure parameter accuracy by comparing and analyzing measured data with theoretical parameters.

5. The method for calculating the power generation amount based on wind and light resources and equipment data according to claim 1, characterized in that: The model verification and optimization specifically comprises: model verification step: selecting a historical typical period, comparing the difference between calculated value and actual power generation, calculating the root mean square error and average absolute percentage error statistical indicators to evaluate the model accuracy; parameter optimization step: using genetic algorithm to optimize model parameters, minimizing prediction error, establishing parameter sensitivity analysis model, identifying key parameters and performing key optimization; model updating step: establishing an online learning mechanism to dynamically update model parameters according to new data, regularly retraining the model to adapt to the influence of equipment aging and climate change.

6. A system for calculating the power generation based on wind and solar resources and equipment data, for implementing the method for calculating the power generation based on wind and solar resources and equipment data according to any one of claims 1 to 5, characterized in that, The method comprises: The data acquisition module comprises: a resource data acquisition unit, which integrates multi-source meteorological data and satellite remote sensing data to realize all-around acquisition of wind and light resource data; an equipment data acquisition unit, which acquires equipment running state and performance parameters in real time; a data quality monitoring unit, which automatically detects data abnormalities and triggers an alarm and a processing mechanism, and records data quality problems and processing results; a data storage management unit, which optimizes data organization structure, adopts a hierarchical storage strategy, and improves data access efficiency; the core calculation module comprises: a potential field calculation acceleration unit, which adopts GPU parallel computing technology to improve calculation efficiency; an integral optimization unit, which realizes an adaptive integral algorithm and dynamically adjusts an integral strategy according to calculation precision requirements; a memory management unit, which adopts a memory pool technology to optimize memory allocation and release in a large-scale data processing process; and a result output module, which provides multiple output formats, including data reports, trend charts and spatial distribution maps, and is also used for result export and interface calling.

Images