Distributed photovoltaic developable capacity prediction method and system

Abstract

The invention relates to the technical field of distributed photovoltaic, in particular to a distributed photovoltaic developable capacity prediction method and system, and the method comprises the following steps: S1, collecting the spatial data and related meteorological data of a house roof in a prediction region, and obtaining the social economic data and user behavior mode data to form a basic data set; s2, generating roof area data which can be actually used; s3, calculating the theoretical development capacity of the distributed photovoltaic system; s4, correcting in combination with actual installation case data, and generating technology development capacity data; s5, calculating the distributed photovoltaic economic development capacity under the current economic condition; and S6, comprehensively considering power grid planning requirements and economic feasibility, and optimizing the economic development capacity calculated in the step S5. According to the method, through comprehensive application of data fusion, image processing and multi-objective optimization technologies, the prediction precision and economic benefits of the development capacity of the distributed photovoltaic system are remarkably improved, and meanwhile, the stability of a power grid is optimized.

Description

Technical Field

[0001] The present invention relates to the field of distributed photovoltaic technology, and in particular to a method and system for predicting developable capacity of distributed photovoltaics. Background Art

[0002] With the growth of global energy demand and the enhancement of environmental awareness, distributed photovoltaic systems have been widely used in various places, especially in urban and rural areas. Rooftop photovoltaic systems have become an important means of renewable energy utilization due to their advantages such as energy saving, environmental protection, easy installation and maintenance. However, how to make full use of the roof area of ​​buildings to maximize the power generation potential of photovoltaic systems has become a key issue in the current development of distributed photovoltaics. In addition, due to the significant differences in lighting conditions, meteorological factors and building structures in various places, traditional photovoltaic capacity prediction methods often cannot accurately reflect the actual situation, resulting in restrictions on the installation and operation efficiency of photovoltaic systems.

[0003] In the existing technology, there are many difficulties in predicting distributed photovoltaic capacity, such as the inability to effectively combine the lighting conditions, meteorological data and actual structure of the buildings in the area, resulting in significant deviations between the predicted results and the actual development capacity. In addition, the current method lacks comprehensive consideration of economic feasibility and the impact of grid load, and cannot provide the optimal capacity distribution plan, resulting in the inability to balance the economic benefits of the photovoltaic system and the stability of grid operation.

[0004] Therefore, there is an urgent need for a distributed photovoltaic development capacity prediction method that can combine actual data, fully consider economic and technical factors, and provide an optimized capacity distribution plan to solve these technical problems and ensure the efficient utilization and economic returns of photovoltaic systems. Summary of the invention

[0005] Based on the above objectives, the present invention provides a method and system for predicting the developable capacity of distributed photovoltaics.

[0006] Distributed photovoltaics can develop a capacity prediction method, including the following steps:

[0007] S1: Based on satellite images, municipal planning maps and historical meteorological data, spatial data of house roofs and related meteorological data in the forecast area are collected, and socio-economic data and user behavior pattern data are obtained. The collected data are integrated through data fusion technology to form a basic data set;

[0008] S2: Based on the basic data set formed in S1, use image recognition and data processing technology to analyze the available area of ​​the house roof, identify and eliminate areas that are not suitable for installing photovoltaic systems, and generate data on the actual roof area that can be used;

[0009] S3: Based on the actual usable roof area data generated by S2, combined with lighting conditions and meteorological data, calculate the theoretical development capacity of distributed photovoltaics;

[0010] S4: Based on the theoretical development capacity calculated in S3, combined with the existing photovoltaic installation technology level, evaluate the photovoltaic capacity that can actually be installed, and make corrections based on actual installation case data to generate technical development capacity data;

[0011] S5: Based on the technical development capacity data generated by S4, combined with regional socio-economic conditions and market data, evaluate its economic feasibility and calculate the economic development capacity of distributed photovoltaics under current economic conditions;

[0012] S6: Using a multi-objective optimization algorithm, the economic development capacity calculated in S5 is optimized to determine the optimal distributed photovoltaic capacity distribution plan by comprehensively considering the grid planning requirements and economic feasibility.

[0013] Optionally, the S1 specifically includes:

[0014] S11: Use high-resolution satellite images to obtain roof space data of houses in the predicted area, and pre-process the satellite images through remote sensing image processing technology, including image segmentation, object classification, and edge detection to identify the outline and roof shape of the building and generate preliminary roof space data;

[0015] S12: extracting information related to the house structure from the municipal planning map, including building height, roof structure type, and relative position of the building, and matching and correcting it with the roof space data generated in S11 to improve the accuracy of the roof space data;

[0016] S13: Obtain historical meteorological data related to the forecast area from the meteorological database, including annual average solar radiation intensity, sunshine duration, temperature and precipitation;

[0017] S14: Obtaining socioeconomic data and user behavior pattern data in the region from statistical databases, survey reports and market research literature, wherein the socioeconomic data includes per capita income level, energy prices and policy subsidy information; the user behavior pattern data includes residents' electricity usage habits, acceptance of renewable energy and expected investment returns;

[0018] S15: Data fusion technology, including spatial data fusion and time series fusion, is used to integrate all the data collected from S11 to S14 in a multi-level and multi-dimensional manner to form a unified basic data set.

[0019] Optionally, the S2 specifically includes:

[0020] S21: Based on the basic data set formed in S1, the satellite image and the municipal planning map are preprocessed first, and the noise in the image is removed by applying a noise filtering algorithm, including a median filter or a Gaussian filter, to enhance the edge features of the building roof; then the edge detection algorithm is used to identify and extract the outline of the house roof to generate a roof outline image;

[0021] S22: Segment the roof outline image generated in S21 into different regions, and classify the segmented regions to distinguish between regions suitable for installing a photovoltaic system and regions not suitable, including shadow areas, irregular roofs, and skylights, and mark each region with a corresponding label.

[0022] S23: According to the classification result of S22, the areas that are not suitable for installing the photovoltaic system are eliminated, and the area of ​​each area is calculated by applying a geometric analysis algorithm. According to a preset threshold, the areas that meet the conditions for installing the photovoltaic system are screened out, and the screened areas are defined as the roof area data that can actually be used;

[0023] S24: Based on the screened qualified areas, the area data of all qualified areas are integrated to generate roof area data that can actually be used.

[0024] Optionally, the S23 specifically includes:

[0025] Application of geometric analysis algorithm: Based on the classified roof area data in S22, the area A of each area is calculated using the geometric analysis algorithm. i ;

[0026] Area screening: Based on the area A of each roof area calculated in S231 i , and the preset minimum area threshold A min For comparison, only regions that meet the following conditions will be retained: A i ≥A min , where A min The minimum area threshold required for installing a photovoltaic system;

[0027] Slope screening: For areas that pass the area screening, the roof slope is used to screen whether they are suitable for installing a photovoltaic system. The average slope of the area is θ i , and the preset slope threshold θ max For comparison, only regions that meet the following conditions will be retained: θ i ≤θ max , where θ max The maximum slope threshold allowed for the installation of PV systems;

[0028] Definition of actual usable area: The roof area that passes the area and slope screening is defined as the actual usable roof area data Ausable .

[0029] Optionally, the S3 specifically includes:

[0030] Acquisition of lighting conditions: Obtain historical lighting condition data of the forecast area from the meteorological database t , including sunshine intensity, sunshine duration and annual average solar radiation, and perform time series analysis on the lighting data to screen out the lighting conditions corresponding to the roof area data;

[0031] S32: Obtain historical meteorological data M of the region t , including temperature, humidity, precipitation and wind speed, and analyze the impact of meteorological conditions on the efficiency of the photovoltaic system. Specifically, the weighted average method is used to integrate the impact of meteorological factors into the correction coefficient K m , used to correct photovoltaic power generation efficiency under lighting conditions;

[0032] S33: Using the illumination condition data I filtered in S31 t and the correction factor K obtained in S32 m , combined with the actual available roof area data A usable , calculate the theoretical development capacity C of distributed photovoltaic t h eo , the calculation formula is: C theo =A usable I t ·η·K m , where C theo To develop capacity for theory; A usable The actual roof area data that can be used; t is the lighting condition data; η is the efficiency of the photovoltaic module.

[0033] Optionally, the S4 specifically includes:

[0034] S41: Theoretical development capacity C calculated based on S3 t h eo , the existing photovoltaic installation technology level is evaluated. The specific evaluation takes into account the conversion efficiency, installation angle and shading parameters of the photovoltaic modules. The photovoltaic capacity C that can be installed is preliminarily calculated by the following formula install :C install =C theo ·η actual ·cos(θ install )·(1-α s h ade ), where C install represents the actual installed PV capacity according to preliminary assessment; η actual Indicates the actual conversion efficiency of the current photovoltaic module; θinstall Indicates the installation angle of the photovoltaic system; α s h ade Indicates the proportion of power loss caused by shading factors;

[0035] S42: Integrate the existing photovoltaic system installation case data and extract case data sets D similar to the prediction area case , including the capacity of the historically installed PV system, the actual power generation, the installation location and angle information, and by matching it with the data of the forecast area, obtain the correction factor β in the actual case adjust ;

[0036] S43: The initial evaluation capacity C in S41 install Correction coefficient β with case data adjust Combine to generate the final technology development capacity C tech , the specific formula is: C tech =C install β adjust .

[0037] Optionally, the S5 specifically includes:

[0038] S51: Collect socio-economic data E related to the region, including energy prices, government subsidy policies, loan interest rates, and residents’ income levels, standardize the economic data, and integrate it with market data to form a socio-economic data set E. soc ;

[0039] S52: Obtain data M related to the photovoltaic market, including photovoltaic module costs, installation costs, maintenance costs, and market demand forecast data, and integrate the data M into the socioeconomic conditions dataset E after standardization and denoising. soc ;

[0040] S53: Based on C tech and E soc , construct an economic feasibility assessment model, which comprehensively considers the initial investment cost C init 、Annualized return R annual 、Return cycle T return And the economic indicator of net present value NPV, the specific formula is: Among them, R annual =P energy ×C tech ×h represents the annualized return, h is the average annual sunshine hours; r is the discount rate; T is the predicted payback period; C init =C panel +C install -S subsidy represents the initial investment cost;

[0041] S54: Calculate the economic development capacity C based on the economic feasibility assessment model constructed in S53 econ , the specific formula is: Among them, C econ Develop capacity for optimal economy under current economic conditions.

[0042] Optionally, the S6 specifically includes:

[0043] S61: Economic development capacity C calculated based on S5 econ , define a multi-objective optimization problem, the optimization objectives include maximizing the economic benefit f1(C econ ) and minimize the negative impact on the power grid f2(C econ ), where the optimization variable is the photovoltaic capacity distribution x in each region i ,Constraints include the upper limit of grid capacity, voltage stability requirements, and land or roof area restrictions in each region;

[0044] S62: Construct objective function of multi-objective optimization;

[0045] Define the economic benefit target f1(C econ )for: Among them, R annual,i is the annualized return of the ith region; C maintain,i is the maintenance cost of the ith area;

[0046] Define the objective function f2(C econ ), considering the voltage deviation and power quality issues, the formula is expressed as: Among them, V i is the voltage level of the ith region; V nominal is the nominal voltage of the power grid; w i The weight of each area's impact on the grid voltage;

[0047] S63: Select a particle swarm optimization algorithm to solve the defined optimization problem. Specifically, the optimal solution is searched by simulating the movement of particles in the problem space, where each particle represents a capacity distribution scheme. The particle swarm optimization algorithm iteratively searches for the best photovoltaic capacity distribution scheme by continuously updating the speed and position of the particles.

[0048] S64: After the iteration of the particle swarm optimization algorithm is completed, the best particle position is selected as the optimal photovoltaic capacity distribution solution.

[0049] Optionally, the S63 specifically includes:

[0050] S631: Initialize a particle swarm in the problem space. Each particle represents a photovoltaic capacity distribution scheme. Specifically, the particle swarm consists of m particles. The current position of each particle is represented by a vector X i (t) = [x i1 (t), x i2 (t), ..., x in (t)], where x ij (t) represents the capacity distribution of the i-th particle in the j-th region, and t represents the number of iterations;

[0051] S632: Assign an initial velocity V to each particle i (t) = [v i1 (t), v i2 (t), ..., v in (t)], where v ij (t) represents the velocity of the i-th particle in the j-th region, which is used to control the moving direction and distance of the particle in the problem space;

[0052] S633: Calculate the fitness value for each particle. The fitness function is based on two objective functions f1(C econ ) and f2(C econ ) is used to evaluate the quality of each particle. The specific calculation formula is:

[0053] F i (t) = w1·f1(X i (t))+w2·f2(X i (t)), where F i (t) represents the fitness value of the i-th particle; w1 and w2 are the weights of the economic benefit target and the grid impact target respectively; f1(X i (t)) and f2(X i (t)) represent the economic benefits and grid impact of particles under the current capacity distribution, respectively;

[0054] S634: In each iteration, the speed and position of each particle are updated according to the historical optimal position and the global optimal position of the particle;

[0055] S635: Repeat S633 and S634, update the speed and position of the particles, and iteratively search for the optimal solution. When the maximum number of iterations is reached or the global optimal position of the particle swarm no longer changes, the algorithm converges and outputs the optimal photovoltaic capacity distribution plan.

[0056] The distributed photovoltaic developable capacity prediction system is used to implement the above-mentioned distributed photovoltaic developable capacity prediction method, and includes the following modules:

[0057] Data collection and integration module: used to collect satellite images, municipal planning maps, meteorological data and socio-economic data, and integrate them through data fusion technology to generate basic data sets;

[0058] Image processing and area analysis module: Based on the basic data set generated by the data acquisition and integration module, it identifies the areas suitable for installing photovoltaic systems through image segmentation and geometric analysis, calculates the actual roof area data that can be used, and eliminates areas that are not suitable for installation;

[0059] Theoretical development capacity calculation module: Based on the actual usable roof area data generated by the image processing and area analysis module, combined with lighting conditions and meteorological data, the theoretical development capacity of distributed photovoltaics is calculated;

[0060] Technical development capacity assessment module: Based on the theoretical development capacity calculation module, combined with the current photovoltaic installation technology level and actual installation case data, the theoretical development capacity is corrected to generate technical development capacity data that conforms to the actual situation;

[0061] Economic feasibility assessment module: Based on the data generated by the technical development capacity assessment module, combined with regional socio-economic conditions and market data, the economic feasibility of the photovoltaic system is assessed, and the optimal economic development capacity is determined by calculating the economic indicators of net present value and payback period;

[0062] Capacity optimization and distribution module: Using a multi-objective optimization algorithm, the economically exploitable capacity is optimized to generate the optimal photovoltaic capacity distribution plan by comprehensively considering the grid planning requirements and economic feasibility.

[0063] Beneficial effects of the present invention:

[0064] The present invention, by integrating advanced data fusion technology, image processing technology and economic feasibility analysis, greatly improves the accuracy of the prediction of the development potential of distributed photovoltaic systems. It allows the accurate determination of the available roof area of ​​each building, thereby maximizing the installation potential of photovoltaic devices. This comprehensive technical application not only optimizes the planning process of photovoltaic projects, but also improves the ability to quickly evaluate the economic benefits and feasibility of photovoltaic projects in different regions.

[0065] The present invention effectively balances the economic benefits of the photovoltaic system and the stability of the power grid by utilizing a multi-objective optimization algorithm. This optimization ensures the high compatibility of the photovoltaic system with the power grid, while optimizing the economic return, providing investors and power operators with a solution for achieving maximum economic benefits while ensuring the stability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0067] Figure 1 A schematic diagram of a photovoltaic developable capacity prediction system according to an embodiment of the present invention;

[0068] Figure 2 The figure is a schematic diagram of the process of predicting the developable capacity of distributed photovoltaic power generation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0070] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0071] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0072] like Figure 1 As shown, a distributed photovoltaic capacity prediction method can be developed, including the following steps:

[0073] S1: Based on satellite images, municipal planning maps and historical meteorological data, spatial data of house roofs and related meteorological data in the forecast area are collected, and socio-economic data and user behavior pattern data are obtained. The collected data are integrated through data fusion technology to form a basic data set;

[0074] S2: Based on the basic data set formed in S1, use image recognition and data processing technology to analyze the available area of ​​the house roof, identify and eliminate areas that are not suitable for installing photovoltaic systems, such as roof shadow areas or irregular areas, and generate data on the actual roof area that can be used;

[0075] S3: Based on the actual usable roof area data generated by S2, combined with lighting conditions and meteorological data, the theoretical development capacity of distributed photovoltaics is calculated, taking into account factors such as the roof's tilt angle, orientation, and local shadows to ensure the accuracy of the calculation results;

[0076] S4: Based on the theoretical development capacity calculated in S3, combined with the existing photovoltaic installation technology level, evaluate the photovoltaic capacity that can actually be installed, and make corrections based on actual installation case data to generate technical development capacity data;

[0077] S5: Based on the technical development capacity data generated by S4, combined with regional socio-economic conditions and market data, evaluate its economic feasibility and calculate the economic development capacity of distributed photovoltaics under current economic conditions;

[0078] S6: Using a multi-objective optimization algorithm, the economic development capacity calculated in S5 is optimized to determine the optimal distributed photovoltaic capacity distribution plan by comprehensively considering the grid planning requirements and economic feasibility.

[0079] S1 specifically includes:

[0080] S11: Use high-resolution satellite images to obtain roof space data of houses in the predicted area, and pre-process the satellite images through remote sensing image processing technology, including image segmentation, object classification, and edge detection to identify the outline and roof shape of the building and generate preliminary roof space data;

[0081] S12: extracting information related to the house structure from the municipal planning map, including building height, roof structure type, and relative position of the building, and matching and correcting it with the roof space data generated in S11 to improve the accuracy of the roof space data;

[0082] S13: Obtain historical meteorological data related to the forecast area from the meteorological database, including annual average solar radiation intensity, sunshine duration, temperature and precipitation, remove outliers and incomplete data through data screening and cleaning technology to ensure the accuracy and completeness of meteorological data, and associate these data with the roof space data generated in S11 and S12;

[0083] S14: Obtain socioeconomic data and user behavior pattern data in the region from statistical databases, survey reports, and market research literature. Socioeconomic data include per capita income level, energy prices, and policy subsidy information; user behavior pattern data include residents' electricity usage habits, acceptance of renewable energy, and expected investment returns. These data are structured through data mining technology and integrated with the data in steps S11 to S13.

[0084] S15: Data fusion technology, including spatial data fusion and time series fusion, is used to integrate all the data collected from S11 to S14 in multiple levels and dimensions to form a unified basic data set;

[0085] The specific integration steps include:

[0086] First, through spatial data fusion technology, the roof space data and municipal planning map information are integrated to generate an accurate three-dimensional roof model;

[0087] Assume that the two-dimensional coordinates of the roof outline are (x i ,y i ), where x represents the horizontal coordinate, y represents the vertical coordinate, and i represents the serial number of the coordinate point; then the coordinate point set can be expressed as: P = {(x1, y1), (x2, y2), ..., (x n ,y n )};

[0088] Extract the building height information H from the municipal planning map and combine it with the two-dimensional coordinate point set P to generate a three-dimensional point set (x i ,y i , z i ), where z represents the height;

[0089] The roof space data D r and municipal planning map information D g The fusion is performed through spatial registration technology, and the error function E is set as: Among them, (x i ′,y i ′,z i ′) represents the position coordinates after registration. Through optimization and solution, the best registration parameters are obtained, data fusion is completed, and an accurate three-dimensional roof model is generated;

[0090] Then, through time series fusion technology, historical meteorological data and user behavior pattern data are synchronously integrated to ensure the temporal and spatial consistency of the data;

[0091] Data standardization: Let the historical meteorological data be T (such as solar radiation intensity and sunshine duration), and the user behavior pattern data be B (such as electricity usage habits). The standardized data are T′ and B′ respectively: Among them, μ T represents the mean of meteorological data, σ T Indicates the standard deviation of meteorological data; μ B represents the mean of user behavior data, σ B Indicates the standard deviation of user behavior data;

[0092] Time series synchronization: For data with different time steps, synchronization is performed using linear interpolation. The interpolation formula is: Among them, T t ″ represents the interpolated meteorological data, and t represents the time axis;

[0093] Time series fusion: The synchronized time series data are fused to form an information matrix F containing spatiotemporal consistency, whose elements are F(t, k), where t is time and k is different data dimensions. The formula is:

[0094] F(t, k) = α·T t ″+β·B t ′, where α and β are weighting coefficients, which are determined through training or expert experience to ensure the effectiveness of data fusion;

[0095] Ultimately, the resulting basic dataset has a high degree of temporal and spatial resolution and completeness;

[0096] Through the coordination of the above steps, a complete and accurate basic data set is formed, providing reliable data support for the subsequent distributed photovoltaic development capacity forecast.

[0097] S2 specifically includes:

[0098] S21: Based on the basic data set formed in S1, the satellite image and the municipal planning map are preprocessed first, and the noise in the image is removed by applying a noise filtering algorithm, including a median filter or a Gaussian filter, to enhance the edge features of the building roof; then the edge detection algorithm (such as Canny edge detection) is used to identify and extract the outline of the house roof to generate a roof outline image;

[0099] S22: Segment the roof outline image generated in S21 into different regions, and classify the segmented regions to distinguish between regions suitable for installing a photovoltaic system and regions not suitable, including shadow areas, irregular roofs, and skylights, and mark each region with a corresponding label.

[0100] S23: According to the classification result of S22, the areas that are not suitable for installing the photovoltaic system are eliminated. Specifically, the geometric analysis algorithm is applied to calculate the area of ​​each area, and according to the preset threshold (such as the minimum area requirement or slope requirement), the areas that meet the conditions for installing the photovoltaic system are screened out, and the screened areas are defined as the roof area data that can actually be used;

[0101] Assume that the roof contour point set is (X i , Y i ), combined with the height information H in the municipal planning map through projection transformation i , calculate the actual area A of each region i , the formula is: Among them, A i represents the actual area of ​​the i-th roof area; n represents the total number of roof contour point sets; X i Represents the horizontal coordinate of the i-th point in the roof contour point set; Y i Indicates the ordinate of the i-th point in the roof contour point set; Y i+1 Indicates the ordinate of the i+1th point in the roof contour point set; Y i-1 Represents the ordinate of the i-1th point in the roof contour point set; Indicates the sum operation of all points in the roof contour point set; |X i ·(Y i+1 -Y i-1 )| represents the core part of area calculation, where (Y i+1 -Y i-1 ) represents the longitudinal change, while X i Represents the horizontal coordinate, which is used to calculate the area formed between adjacent points;

[0102] S24: Based on the screened qualified areas, the area data of all qualified areas are integrated to generate roof area data that can actually be used, and the data is stored in the final basic data set.

[0103] Areas that are not suitable for installing photovoltaic systems in S23 include:

[0104] Application of geometric analysis algorithm: Based on the classified roof area data in S22, the geometric analysis algorithm is used to calculate the area of ​​each area. Assume that the roof outline of a certain area is composed of n points, and the point set is (X i , Y i ), the area A of each roof area is obtained by point-by-point calculation and summation i ;

[0105] Area screening: Based on the area A of each roof area calculated in S231 i , and the preset minimum area threshold A minFor comparison, only regions that meet the following conditions will be retained: A i ≥A min , where A min The minimum area threshold required for installing a photovoltaic system; when the area A of a certain area i If it is less than the threshold, it will be eliminated;

[0106] Slope screening: For areas that pass the area screening, the roof slope is used to screen whether they are suitable for installing a photovoltaic system. The average slope of the area is θ i , and the preset slope threshold θ max For comparison, only regions that meet the following conditions will be retained: θ i ≤θ max , where θ max The maximum slope threshold allowed for installing a photovoltaic system. If the slope of an area is θ i If the threshold is exceeded, the area will be eliminated;

[0107] Definition of actual usable area: The roof area that passes the area and slope screening is defined as the actual usable roof area data A usable , which is used for subsequent photovoltaic system installation evaluation and capacity prediction. The final generated A usable The data will serve as basic input for further analysis;

[0108] Through the above steps, the roof area suitable for installing photovoltaic systems can be accurately identified and calculated to ensure the efficiency and economy of the photovoltaic system. The combination of geometric analysis algorithm and slope screening technology can effectively eliminate areas that are not suitable for installation, improve the accuracy of prediction, and reduce prediction deviation, providing a scientific basis and technical support for the planning and optimization of distributed photovoltaic systems.

[0109] S3 specifically includes:

[0110] Acquisition of lighting conditions: Obtain historical lighting condition data of the forecast area from the meteorological database t , including sunshine intensity, sunshine duration and annual average solar radiation, and perform time series analysis on the lighting data to screen out the lighting conditions corresponding to the roof area data;

[0111] S32: Obtain historical meteorological data M of the region t , including temperature, humidity, precipitation and wind speed, and analyze the impact of meteorological conditions on the efficiency of the photovoltaic system. Specifically, the weighted average method is used to integrate the impact of meteorological factors into the correction coefficient K m , used to correct the photovoltaic power generation efficiency under lighting conditions; the specific formula is: K m =α·T t +β·H t +γ·Wt +δ·P t , where T t is temperature; H t is humidity; W t is wind speed; P t is the precipitation; α, β, γ, δ are the weight coefficients of various meteorological factors, which are determined according to specific environmental conditions and empirical data;

[0112] S33: Using the illumination condition data I filtered in S31 t and the correction factor K obtained in S32 m , combined with the actual available roof area data A usable , calculate the theoretical development capacity C of distributed photovoltaic t h eo , the calculation formula is: C theo =A usable I t ·η·K m , where C theo To develop capacity for theory; A usable The actual roof area data that can be used; t is the illumination condition data; η is the efficiency of the photovoltaic module, which is determined according to the module type and installation conditions; through the above steps, based on the actual available roof area data, combined with the illumination conditions and comprehensive meteorological data, the theoretical development capacity of distributed photovoltaics is calculated. This method can provide reliable capacity prediction results, optimize the photovoltaic system design, and effectively improve the resource utilization efficiency.

[0113] S4 specifically includes:

[0114] S41: Theoretical development capacity C calculated based on S3 t h eo , the existing photovoltaic installation technology level is evaluated. The specific evaluation takes into account the conversion efficiency, installation angle and shading parameters of the photovoltaic modules. The photovoltaic capacity C that can be installed is preliminarily calculated by the following formula install :C install =C theo ·η actual ·cos(θ install )·(1-α shade ), where C install represents the actual installed PV capacity according to preliminary assessment; η actual Indicates the actual conversion efficiency of the current photovoltaic module; θ install Indicates the installation angle of the photovoltaic system, which is related to the roof inclination angle; α shade Indicates the proportion of power loss caused by shading factors;

[0115] S42: Integrate the existing photovoltaic system installation case data and extract case data sets D similar to the prediction area case , including the capacity of the historically installed PV system, the actual power generation, the installation location and angle information, and by matching it with the data of the forecast area, obtain the correction factor β in the actual case adjust , the formula is:

[0116] S43: The initial evaluation capacity C in S41 install Correction coefficient β with case data adjust Combine to generate the final technology development capacity C tech , the specific formula is: C tech =C install β adjust ; and the generated technology development capacity C tech Verify with the actual power generation data of local or similar areas to ensure the accuracy and reliability of the capacity forecast. According to the verification results, if the deviation is large, the correction factor β can be adjusted. adjust Or other parameters to adjust again;

[0117] Through the above steps, the theoretical development capacity is revised by combining the photovoltaic installation technology level with actual case data, and the generated technical development capacity is more in line with the actual situation. This method improves the accuracy of capacity prediction, helps to rationally plan the installation and application of photovoltaic systems, and enhances the efficiency and reliability of resource utilization.

[0118] S5 specifically includes:

[0119] S51: Collect socio-economic data E related to the region, including energy prices, government subsidy policies, loan interest rates, and residents’ income levels, standardize the economic data, and integrate it with market data to form a socio-economic data set E. soc ;

[0120] S52: Obtain data M related to the photovoltaic market, including photovoltaic module costs, installation costs, maintenance costs, and market demand forecast data, and integrate the data M into the socioeconomic conditions dataset E after standardization and denoising. soc ;

[0121] S53: Based on C tech and E soc , construct an economic feasibility assessment model that comprehensively considers the initial investment cost C init 、Annualized return R annual 、Return cycle T return And the economic indicator of net present value NPV, the specific formula is: Among them, Rannual =P energy ×C tech ×h represents the annualized return, h is the average annual sunshine hours; r is the discount rate (usually equal to the loan interest rate R loan );T is the predicted return period; C init =C panel +C install -S subsidy represents the initial investment cost;

[0122] S54: Calculate the economic development capacity C based on the economic feasibility assessment model constructed in S53 econ , the specific formula is: Among them, C econ It is the optimal economic development capacity under current economic conditions, that is, the maximum economic benefit that can be achieved by the technical development capacity under the premise of meeting economic feasibility; through the above steps, combined with regional socio-economic conditions and market data, the economic feasibility of the technical development capacity was evaluated, and finally the distributed photovoltaic economic development capacity under current economic conditions was calculated. This method can not only ensure the technical feasibility of the photovoltaic system, but also maximize its economic benefits, providing decision makers with a scientific investment reference.

[0123] S6 specifically includes:

[0124] S61: Economic development capacity C calculated based on S5 econ , define a multi-objective optimization problem, the optimization objectives include maximizing the economic benefit f1(C econ ) and minimize the negative impact on the power grid f2(C econ ), where the optimization variable is the photovoltaic capacity distribution x in each region i ,Constraints include the upper limit of grid capacity, voltage stability requirements, and land or roof area restrictions in each region;

[0125] S62: Construct objective function of multi-objective optimization;

[0126] Define the economic benefit target f1(C econ )for: Among them, R annual,i is the annualized return of the ith region; C maintain,i is the maintenance cost of the ith area;

[0127] Define the objective function f2(C econ ), considering the voltage deviation and power quality issues, the formula is expressed as: Among them, V i is the voltage level of the ith region; V nominal is the nominal voltage of the power grid; w iThe weight of each area's impact on the grid voltage;

[0128] S63: Select the particle swarm optimization algorithm (PSO) to solve the defined optimization problem. Specifically, the optimal solution is searched by simulating the movement of particles in the problem space. Each particle represents a capacity distribution scheme. The particle swarm optimization algorithm iteratively searches for the best photovoltaic capacity distribution scheme by continuously updating the speed and position of the particles.

[0129] S64: After the iteration of the particle swarm optimization algorithm is completed, the best particle position is selected as the optimal photovoltaic capacity distribution plan, which will achieve the best balance between economic benefits and grid stability and meet all constraints. The final capacity distribution plan will be used to guide the installation and deployment of the photovoltaic system; through the above steps, the particle swarm optimization algorithm (PSO) is used to comprehensively consider the grid planning needs and economic feasibility, and effectively optimize the economic development capacity. The optimal photovoltaic capacity distribution plan finally determined can ensure economic benefits while minimizing the negative impact on the grid, providing a scientific decision-making basis for the reasonable layout and operation of the photovoltaic system.

[0130] S63 specifically includes:

[0131] S631: Initialize a particle swarm in the problem space. Each particle represents a photovoltaic capacity distribution scheme. Specifically, the particle swarm consists of m particles. The current position of each particle is represented by a vector X i (t) = [x i1 (t), x i2 (t), ..., x in (t)], where x ij (t) represents the capacity distribution of the i-th particle in the j-th region, and t represents the number of iterations;

[0132] S632: Assign an initial velocity V to each particle i (t) = [v i1 (t), v i2 (t), ..., v in (t)], where v ij (t) represents the velocity of the i-th particle in the j-th region, which is used to control the moving direction and distance of the particle in the problem space;

[0133] S633: Calculate the fitness value for each particle. The fitness function is based on two objective functions f1(C econ ) and f2(C econ ) is used to evaluate the quality of each particle. The specific calculation formula is:

[0134] Fi (t) = w1·f1(X i (t))+w2·f2(X i (t)), where F i (t) represents the fitness value of the i-th particle; w1 and w2 are the weights of the economic benefit target and the grid impact target respectively; f1(X i (t)) and f2(X i (t)) represent the economic benefits and grid impact of particles under the current capacity distribution, respectively;

[0135] S634: In each iteration, the speed and position of each particle are updated according to the historical optimal position and the global optimal position of the particle; the speed update formula is: V i (t+1)=ω·V i (t)+c1·r1·(P best,i -X i (t))+c2·r2·(G best -X i (t)), where ω is the inertia weight, which controls the particle's inheritance of the current velocity; c1 and c2 are learning factors, which respectively represent the particle's historical optimal position P best,i and the global optimal position G best learning ability; r1 and r2 are random numbers between 0 and 1, used to increase the randomness of the algorithm; the position update formula is: X i (t+1)=X i (t)+V i (t+1), where X i (t+1) represents the new position of the particle in the next iteration;

[0136] S635: Repeat S633 and S634, update the speed and position of the particles, and iteratively search for the optimal solution. When the maximum number of iterations is reached or the global optimal position of the particle swarm no longer changes, the algorithm converges and outputs the optimal photovoltaic capacity distribution plan. Through the above steps, the PSO algorithm can dynamically adjust the photovoltaic capacity distribution of each area by simulating the movement of particles in the problem space and iterative search. This method can effectively find the optimal balance between economic benefits and grid stability, and ensure the efficient operation of the photovoltaic system in a real environment.

[0137] like Figure 2 As shown, the distributed photovoltaic developable capacity prediction system is used to implement the above-mentioned distributed photovoltaic developable capacity prediction method, including the following modules:

[0138] Data collection and integration module: used to collect satellite images, municipal planning maps, meteorological data and socio-economic data, and integrate them through data fusion technology to generate basic data sets as input for subsequent analysis;

[0139] Image processing and area analysis module: Based on the basic data set generated by the data acquisition and integration module, it identifies the areas suitable for installing photovoltaic systems through image segmentation and geometric analysis, calculates the actual roof area data that can be used, and eliminates areas that are not suitable for installation;

[0140] Theoretical development capacity calculation module: Based on the actual usable roof area data generated by the image processing and area analysis module, combined with lighting conditions and meteorological data, the theoretical development capacity of distributed photovoltaics is calculated;

[0141] Technical development capacity assessment module: Based on the theoretical development capacity calculation module, combined with the current photovoltaic installation technology level and actual installation case data, the theoretical development capacity is corrected to generate technical development capacity data that conforms to the actual situation;

[0142] Economic feasibility assessment module: Based on the data generated by the technical development capacity assessment module, combined with regional socio-economic conditions and market data, the economic feasibility of the photovoltaic system is assessed, and the optimal economic development capacity is determined by calculating the economic indicators of net present value and payback period;

[0143] Capacity optimization and distribution module: Using a multi-objective optimization algorithm, the economically exploitable capacity is optimized to generate the optimal photovoltaic capacity distribution plan by comprehensively considering the grid planning requirements and economic feasibility.

[0144] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0145] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for predicting the exploitable capacity of distributed photovoltaics, characterized in that: The following steps are involved: S1: Based on satellite images, municipal planning maps and historical meteorological data, spatial data of house roofs and related meteorological data in the forecast area are collected, and socio-economic data and user behavior pattern data are obtained. The collected data are integrated through data fusion technology to form a basic data set; S2: Based on the basic data set formed in S1, use image recognition and data processing technology to analyze the available area of ​​the house roof, identify and eliminate areas that are not suitable for installing photovoltaic systems, and generate data on the actual roof area that can be used; S3: Based on the actual usable roof area data generated by S2, combined with lighting conditions and meteorological data, calculate the theoretical development capacity of distributed photovoltaics; S4: Based on the theoretical development capacity calculated in S3, combined with the existing photovoltaic installation technology level, evaluate the photovoltaic capacity that can actually be installed, and make corrections based on actual installation case data to generate technical development capacity data; S5: Based on the technical development capacity data generated by S4, combined with regional socio-economic conditions and market data, evaluate its economic feasibility and calculate the economic development capacity of distributed photovoltaics under current economic conditions; S6: Using a multi-objective optimization algorithm, the economic development capacity calculated in S5 is optimized to determine the optimal distributed photovoltaic capacity distribution plan by comprehensively considering the grid planning requirements and economic feasibility.

2. The method for predicting the exploitable capacity of distributed photovoltaic power generation according to claim 1, characterized in that: The S1 specifically includes: S11: Use high-resolution satellite images to obtain roof space data of houses in the predicted area, and pre-process the satellite images through remote sensing image processing technology, including image segmentation, object classification, and edge detection to identify the outline and roof shape of the building and generate preliminary roof space data; S12: extracting information related to the house structure from the municipal planning map, including building height, roof structure type, and relative position of the building, and matching and correcting it with the roof space data generated in S11 to improve the accuracy of the roof space data; S13: Obtain historical meteorological data related to the forecast area from the meteorological database, including annual average solar radiation intensity, sunshine duration, temperature and precipitation; S14: Obtaining socioeconomic data and user behavior pattern data in the region from statistical databases, survey reports and market research literature, wherein the socioeconomic data includes per capita income level, energy prices and policy subsidy information; the user behavior pattern data includes residents' electricity usage habits, acceptance of renewable energy and expected investment returns; S15: Data fusion technology, including spatial data fusion and time series fusion, is used to integrate all the data collected from S11 to S14 in a multi-level and multi-dimensional manner to form a unified basic data set.

3. The method for predicting the exploitable capacity of distributed photovoltaic power generation according to claim 1, characterized in that: The S2 specifically includes: S21: Based on the basic data set formed in S1, the satellite image and the municipal planning map are preprocessed first, and the noise in the image is removed by applying a noise filtering algorithm, including a median filter or a Gaussian filter, to enhance the edge features of the building roof; then the edge detection algorithm is used to identify and extract the outline of the house roof to generate a roof outline image; S22: Segment the roof outline image generated in S21 into different regions, and classify the segmented regions to distinguish between regions suitable for installing a photovoltaic system and regions not suitable, including shadow areas, irregular roofs, and skylights, and mark each region with a corresponding label; S23: According to the classification result of S22, the areas that are not suitable for installing the photovoltaic system are eliminated, and the area of ​​each area is calculated by applying a geometric analysis algorithm. According to a preset threshold, the areas that meet the conditions for installing the photovoltaic system are screened out, and the screened areas are defined as the roof area data that can actually be used; S24: Based on the screened qualified areas, the area data of all qualified areas are integrated to generate roof area data that can actually be used.

4. The method for predicting the exploitable capacity of distributed photovoltaic power generation according to claim 3 is characterized in that: The S23 specifically includes: Application of geometric analysis algorithm: Based on the classified roof area data in S22, the area A of each area is calculated using the geometric analysis algorithm. i ; Area screening: Based on the area A of each roof area calculated in S231 i , and the preset minimum area threshold A min For comparison, only regions that meet the following conditions will be retained: A i ≥A min , where A min The minimum area threshold required for installing a photovoltaic system; Slope screening: For areas that pass the area screening, the roof slope is used to screen whether they are suitable for installing a photovoltaic system. The average slope of the area is θ i , and the preset slope threshold θ max For comparison, only regions that meet the following conditions will be retained: θ i ≤θ max , where θ max The maximum slope threshold allowed for the installation of PV systems; Definition of actual usable area: The roof area that passes the area and slope screening is defined as the actual usable roof area data A usable .

5. The method for predicting the exploitable capacity of distributed photovoltaic power generation according to claim 4 is characterized in that: The S3 specifically includes: Acquisition of lighting conditions: Obtain historical lighting condition data of the forecast area from the meteorological database t , including sunshine intensity, sunshine duration and annual average solar radiation, and perform time series analysis on the lighting data to screen out the lighting conditions corresponding to the roof area data; S32: Obtain historical meteorological data M of the region t , including temperature, humidity, precipitation and wind speed, and analyze the impact of meteorological conditions on the efficiency of the photovoltaic system. Specifically, the weighted average method is used to integrate the impact of meteorological factors into the correction coefficient K m , used to correct photovoltaic power generation efficiency under lighting conditions; S33: Using the light condition data I filtered in S31 t and the correction factor K obtained in S32 m , combined with the actual available roof area data A usable , calculate the theoretical development capacity C of distributed photovoltaic t h eo , the calculation formula is: C theo =A usable I t ·η·K m , where C theo To develop capacity for theory; A usable The actual roof area data that can be used; t is the lighting condition data; η is the efficiency of the photovoltaic module.

6. The method for predicting the exploitable capacity of distributed photovoltaic power generation according to claim 5, characterized in that: The S4 specifically includes: S41: Theoretical development capacity C calculated based on S3 t h eo , the existing photovoltaic installation technology level is evaluated. The specific evaluation takes into account the conversion efficiency, installation angle and shading parameters of the photovoltaic modules. The photovoltaic capacity C that can be installed is preliminarily calculated by the following formula install :C install =C theo ·η actual ·cos(θ install )·(1-α s h ade ), where C install represents the actual installed PV capacity according to preliminary assessment; η actual Indicates the actual conversion efficiency of the current photovoltaic module; θ install Indicates the installation angle of the photovoltaic system; α s h ade Indicates the proportion of power loss caused by shading factors; S42: Integrate the existing photovoltaic system installation case data and extract case data sets D similar to the prediction area case , including the capacity of the historically installed PV system, the actual power generation, the installation location and angle information, and by matching it with the data of the forecast area, obtain the correction factor β in the actual case adjust ; S43: The initial evaluation capacity C in S41 install Correction coefficient β with case data adjust Combine to generate the final technology development capacity C tech , the specific formula is: C tech =C install β adjust .

7. The method for predicting the exploitable capacity of distributed photovoltaic power generation according to claim 6, characterized in that: The S5 specifically includes: S51: Collect socio-economic data E related to the region, including energy prices, government subsidy policies, loan interest rates, and residents’ income levels, standardize the economic data, and integrate it with market data to form a socio-economic data set E. soc ; S52: Obtain data M related to the photovoltaic market, including photovoltaic module costs, installation costs, maintenance costs, and market demand forecast data, and integrate the data M into the socioeconomic conditions dataset E after standardization and denoising. soc ; S53: Based on C tech and E soc , construct an economic feasibility assessment model, which comprehensively considers the initial investment cost C init 、Annualized return R annual 、Return cycle T return And the economic indicator of net present value NPV, the specific formula is: Among them, R annual =P energy ×C tech ×h represents the annualized return, h is the average annual sunshine hours; r is the discount rate; T is the predicted payback period; C init =C panel +C install -S subsidy represents the initial investment cost; S54: Calculate the economic development capacity C based on the economic feasibility assessment model constructed in S53 econ , the specific formula is: Among them, C econ Develop capacity for optimal economy under current economic conditions.

8. The method for predicting the exploitable capacity of distributed photovoltaic power generation according to claim 1, characterized in that: The S6 specifically includes: S61: Economic development capacity C calculated based on S5 econ , define a multi-objective optimization problem, the optimization objectives include maximizing the economic benefit f1(C econ ) and minimize the negative impact on the power grid f2(C econ ), where the optimization variable is the photovoltaic capacity distribution x in each region i ,Constraints include the upper limit of grid capacity, voltage stability requirements, and land or roof area restrictions in each region; S62: Construct objective function of multi-objective optimization; Define the economic benefit target f1(C econ )for: Among them, R annual,i is the annualized return of the ith region; C maintain,i is the maintenance cost of the ith area; Define the objective function f2(C econ ), considering the voltage deviation and power quality issues, the formula is expressed as: Among them, V i is the voltage level of the ith region; V nominal is the nominal voltage of the power grid; w i The weight of each area's impact on the grid voltage; S63: Select a particle swarm optimization algorithm to solve the defined optimization problem. Specifically, the optimal solution is searched by simulating the movement of particles in the problem space, where each particle represents a capacity distribution scheme. The particle swarm optimization algorithm iteratively searches for the best photovoltaic capacity distribution scheme by continuously updating the speed and position of the particles. S64: After the iteration of the particle swarm optimization algorithm is completed, the best particle position is selected as the optimal photovoltaic capacity distribution solution.

9. The method for predicting the exploitable capacity of distributed photovoltaic power generation according to claim 1, characterized in that: The S63 specifically includes: S631: Initialize a particle swarm in the problem space. Each particle represents a photovoltaic capacity distribution scheme. Specifically, the particle swarm consists of m particles. The current position of each particle is represented by a vector X i (t) = [x i1 (t), x i2 (t), ..., x in (t)], where x ij (t) represents the capacity distribution of the i-th particle in the j-th region, and t represents the number of iterations; S632: Assign an initial velocity V to each particle i (t) = [v i1 (t), v i2 (t), ..., v in (t)], where v ij (t) represents the velocity of the i-th particle in the j-th region, which is used to control the moving direction and distance of the particle in the problem space; S633: Calculate the fitness value for each particle. The fitness function is based on two objective functions f1(C econ ) and f2(C econ ) is used to evaluate the quality of each particle. The specific calculation formula is: F i (t) = w1·f1(X i (t))+w2·f2(X i (t)), where F i (t) represents the fitness value of the i-th particle; w1 and w2 are the weights of the economic benefit target and the grid impact target respectively; f1(X i (t)) and f2(X i (t)) represent the economic benefits and grid impact of particles under the current capacity distribution; S634: In each iteration, the speed and position of each particle are updated according to the historical optimal position and the global optimal position of the particle; S635: Repeat S633 and S634, update the speed and position of the particles, and iteratively search for the optimal solution. When the maximum number of iterations is reached or the global optimal position of the particle swarm no longer changes, the algorithm converges and outputs the optimal photovoltaic capacity distribution plan.

10. A distributed photovoltaic exploitable capacity prediction system, used to implement the distributed photovoltaic exploitable capacity prediction method according to any one of claims 1 to 9, characterized in that: Includes the following modules: Data collection and integration module: used to collect satellite images, municipal planning maps, meteorological data and socio-economic data, and integrate them through data fusion technology to generate basic data sets; Image processing and area analysis module: Based on the basic data set generated by the data acquisition and integration module, it identifies the areas suitable for installing photovoltaic systems through image segmentation and geometric analysis, calculates the actual roof area data that can be used, and eliminates areas that are not suitable for installation; Theoretical development capacity calculation module: Based on the actual usable roof area data generated by the image processing and area analysis module, combined with lighting conditions and meteorological data, the theoretical development capacity of distributed photovoltaics is calculated; Technical development capacity assessment module: Based on the theoretical development capacity calculation module, combined with the current photovoltaic installation technology level and actual installation case data, the theoretical development capacity is corrected to generate technical development capacity data that conforms to the actual situation; Economic feasibility assessment module: Based on the data generated by the technical development capacity assessment module, combined with regional socio-economic conditions and market data, the economic feasibility of the photovoltaic system is assessed, and the optimal economic development capacity is determined by calculating the economic indicators of net present value and payback period; Capacity optimization and distribution module: Using a multi-objective optimization algorithm, the economically exploitable capacity is optimized to generate the optimal photovoltaic capacity distribution plan by comprehensively considering the grid planning requirements and economic feasibility.

Images