Battery layer array arrangement optimization system for photovoltaic power generation

Abstract

The invention discloses a photovoltaic power generation battery layer array arrangement optimization system, and particularly relates to the technical field of photovoltaic power generation, which comprises a site determination module, an arrangement module, a parameter acquisition module, a parameter processing module and an optimization design module. According to the method, through elevation data modeling and terrain analysis before arrangement design, a target site is accurately classified into a flat site, a unified slope site and a complex site; a special arrangement point layout scheme, a full-dimensional parameter acquisition strategy and a nonlinear evaluation model are adapted for different site types, and a photovoltaic power generation coefficient and a fault risk coefficient are accurately calculated; according to the invention, intelligent optimization screening is carried out based on the arrangement value index of multi-parameter fusion, and an optimal arrangement space is generated, so that accurate fitting of arrangement design with site topography and illumination characteristics is realized, arrangement failure and measurement deviation caused by site difference are significantly reduced, a scientific basis is provided for design decision of a photovoltaic power station, and the design efficiency of the photovoltaic power station is improved. And the core requirements of cost reduction and benefit increase in the industry are met.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power generation technology, and more specifically, to a system for optimizing the arrangement of cell arrays in photovoltaic power generation. Background Technology

[0002] Early photovoltaic arrays adopted a one-size-fits-all design with fixed tilt angles and equal spacing, only considering minimal shading and completely ignoring dynamic lighting and component differences. As photovoltaic subsidies were phased out, the industry shifted towards cost reduction and efficiency improvement. Array layout, as a core part of system design, directly affects land utilization, cable loss, and operation and maintenance costs. By optimizing the array layout of the battery layers, land utilization can be improved while reducing cable loss, becoming a key tool for controlling the cost per kilowatt-hour.

[0003] Traditional battery array layout systems are based on static planning using empirical formulas and macroscopic data. The entire process relies on manual calculations and basic rules, without dynamic optimization or adaptation to complex scenarios. Specifically, this includes: Data acquisition: collecting the latitude, longitude, and average annual sunshine duration of the project location; Determining the tilt angle: determined based on the local latitude, calculated using industry-standard empirical formulas; Calculating component spacing: calculated using empirical formulas; Array layout and circuit connection: laid out in a row × column grid, with the number of rows and columns simply calculated based on the total installed capacity and power per component; Planning verification: engineers check for obvious obstructions and circuit continuity through hand-drawn diagrams or simple on-site measurements.

[0004] However, in practical use, it still has some shortcomings. First, the traditional photovoltaic cell array layout is mainly based on empirical formulas and fixed parameter design, relying on macroscopic static data and manual planning. However, the array power generation efficiency is affected by multiple dynamic factors such as changes in solar trajectory, terrain shading, and differences in component performance. The monitoring scope and design dimensions of the existing system are relatively narrow, which cannot provide sufficient data support for efficient power generation. Power generation efficiency and land utilization still need to be improved. Second, due to the limited experience, when engineers find power loss or shading problems caused by the layout, they need to check the causes such as tilt angle adaptation and spacing redundancy one by one. Due to the lack of monitoring indicators and optimization tools, the process of troubleshooting and adjusting may consume a lot of time, which is not conducive to the overall benefits of the power station. The efficiency of layout design and optimization still needs to be further improved. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a photovoltaic cell array layout optimization system. By collecting basic parameters and site parameters, the system calculates the photovoltaic power generation coefficient and fault risk coefficient differently for different site types, thereby selecting the layout area to generate the optimal layout space, reducing design and operation and maintenance costs, and effectively solving the problems raised in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: Site determination module: Determines the target site type based on the location of the battery layer, including flat sites, sites with uniform slope, and complex sites. Layout module: Layout several layout points according to the site type, and number the layout points in a preset order. Then, extract the layout area corresponding to the site according to the numbering order and mark them as 1, 2, ..., n respectively. Parameter acquisition module: Collects basic parameters of the layout area corresponding to the target site, and collects site parameters for different site types; Parameter processing module: Based on the basic parameters and site parameters of different sites, the module aggregates the basic indicators into photovoltaic power generation coefficient and fault risk coefficient through a nonlinear evaluation model; The optimization design module uses the photovoltaic power generation coefficient and the fault risk coefficient as inputs to construct the layout value index, and arranges the layout comprehensive index corresponding to each layout area in descending order, thereby generating the optimal layout space.

[0007] The technical effects and advantages of this invention are as follows: 1. This invention conducts a preliminary assessment of the terrain features of the target site before layout design to determine the site type. Then, in the actual layout design, parameters are flexibly collected and processed according to the site type. A dedicated layout point arrangement scheme is designed for different site types, so that the layout design can better fit the terrain and illumination characteristics of the target site. This maximizes the reliability and accuracy of the design as a benchmark for subsequent power generation efficiency improvement and risk control. As a result, the layout failure problem caused by site differences is significantly reduced during the optimization design, power generation loss and failure risk are reduced, and the overall benefits of photovoltaic array layout are improved. 2. After completing the initial layout optimization through basic parameters and site parameters, this invention further strengthens the data-driven and automated processing of the entire process. Then, it uses the precise quantitative evaluation results (photovoltaic power generation coefficient, fault risk coefficient) to iteratively optimize the layout value. On the one hand, the full-dimensional parameter collection and model calculation can provide the most realistic layout data to ensure the timeliness and accuracy of the optimization scheme. On the other hand, the optimal space is selected through the subsequent ranking results of the layout value index, which not only ensures that the focus is on high-value areas to improve power generation efficiency, but also ensures construction feasibility through spatial integration and boundary correction. Attached Figure Description

[0008] Figure 1 This is a schematic diagram of the overall structure of the present invention.

[0009] Figure 2 A flowchart illustrating the process of obtaining the influence of parameters in this invention.

[0010] Figure 3This is a flowchart illustrating the optimal layout space generation process of the present invention. Detailed Implementation

[0011] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] like Figures 1-3 The photovoltaic power generation cell array layout optimization system shown includes a site determination module, a layout module, a parameter acquisition module, a parameter processing module, and an optimization design module.

[0013] The specific embodiments of the present invention include the following: Site determination module: Determines the target site type based on the location of the battery layer, including flat sites, sites with uniform slope, and complex sites.

[0014] In this embodiment, the determination of the target site type is specifically explained as follows: Collect geographic data on the location of the battery layer, including but not limited to site elevation data and terrain contour data, and generate an elevation model.

[0015] It should be added that the geographical data of the battery layer location can be obtained through drone aerial photography or satellite remote sensing. When collecting data, drone equipment with an accuracy of ≥1cm / px should be selected, and the flight altitude should be controlled between 50-80 meters to ensure full coverage of the site and generate an initial elevation point cloud. The terrain contour data is used to generate an orthophoto map of the site through drone aerial photography, marking the site boundaries, natural terrain transitions (such as earthen embankments, the starting point of gentle slopes), and the locations of artificial obstacles (such as walls, ditches). The elevation model generated based on the elevation data, terrain contour data, etc., can intuitively show the height changes of the site terrain.

[0016] The average slope and slope change rate are calculated using terrain analysis algorithms on the elevation model. The slope represents the degree of inclination of a point on the site relative to the horizontal plane, and in the elevation model, it is represented by the rate of change of the elevation value of each cell relative to its neighboring cells.

[0017] It should be added that the specific method for calculating the average slope involves traversing all pixels in the elevation model. For each pixel, its slope value Sl is calculated using the following formula: ,in and These represent the rates of change of elevation in the east-west x direction and the north-south y direction, respectively, and π represents the natural constant. After obtaining the slope values ​​of all pixels within the entire elevation model range, the slope values ​​of all pixels are arithmetically averaged, i.e., average slope = Σ(slope value of each pixel) / total number of pixels. The slope variation rate reflects the undulation of the slope and the complexity of the terrain within the site. The higher the value, the more fragmented and irregular the terrain. The specific calculation method is to obtain the slope deviation by subtracting the slope value of each pixel from the average pixel value, square each deviation, sum them up and divide by the total number of pixels to obtain the variance of the slope value, and take the square root of the variance to obtain the slope variation rate.

[0018] It should be explained that the above calculation process is completed entirely automatically by the system without human intervention. Users only need to input elevation data, and the system can output the average slope and slope change rate.

[0019] The calculated average slope and slope change rate are compared with preset thresholds to automatically classify the site type, which includes flat site, uniform slope site, and complex site. If the average slope is less than 5% and the slope change rate is less than 3%, it is determined to be a flat site. If the average slope is greater than or equal to 5% and the slope change rate is less than 8%, it is determined to be a uniform slope site. If the average slope is greater than or equal to 5% and the slope change rate is greater than or equal to 8%, it is determined to be a complex site.

[0020] Layout module: Layout several layout points according to the site type, and number the layout points in a preset order. Then, extract the layout area corresponding to the site according to the numbering order and mark them as 1, 2, ..., n respectively.

[0021] In this embodiment, the specific layout of the arrangement points is as follows: If the site type is flat, a regular grid is used to divide the entire rectangular or approximately rectangular site into regular square grids according to the site area. A layout point is placed at the intersection of each grid. The advantage of this method is that the points are evenly distributed, the data coverage is comprehensive, and it can efficiently construct a flatness model of the site and accurately define the boundaries. It is suitable for scenarios with flat terrain and no significant elevation changes. Then, a rectangular coordinate system is established for numbering. For example, a plane rectangular coordinate system is established with the southwest corner of the site as the origin, and the layout points are numbered in the order of first east (X-axis) and then north (Y-axis). If the site type is a site with the same slope aspect, a contour map is generated using the contour line method. The layout points are set up along the key contour lines, which are usually at certain elevation intervals, such as 5 meters or 10 meters. When laying out the points, the contour lines at the top, bottom, and middle of the slope need to be densely laid out. This method can accurately capture the overall trend and uniformity of the slope, ensuring the accuracy of the subsequent array layout based on the contour lines (such as arranging the array along the contour lines to keep the support flat). The contour lines are numbered according to their elevation. For example, the elevation of the contour lines is from high to low as the main order. Within the same contour line, the lines are numbered in the order from west to east or from one endpoint to another. If the site type is complex, the terrain feature point method is used to lay out feature points in the site. Feature points include ridgelines, valley lines, slope tops, slope toes, and abrupt changes in slope. Among them, ridgelines are the highest ridgelines of the mountain range, valley lines are the lowest water catchment lines and the areas with the most severe shading, slope tops are the highest points in a local area, slope toes are the lowest points in a local area, and abrupt changes in slope are the turning points where the terrain changes from gentle to steep or from steep to gentle. This layout method can accurately delineate the complex terrain structure with the fewest control points, providing the most critical data for subsequent identification of photovoltaic rich areas and avoidance of severe shading. The layout points are numbered according to the terrain features. For example, the layout priority is set as follows: first priority is ridgelines, second priority is slope tops, third priority is abrupt changes in slope, fourth priority is valley lines, and fifth priority is slope toes. The system traverses all feature points in this priority order and numbers them.

[0022] It should be further explained that the specific steps for extracting the layout area are as follows: Using the pre-deployed layout points at the target site as centers and a preset distance as the radius, a layout circle is constructed. The preset distance can be the average spacing between adjacent control points or the design spacing value. Then, a geometric intersection operation is performed on the layout circles corresponding to adjacent layout points. Finally, the effective layout area of ​​the photovoltaic cell array is defined by the intersection operation result of each adjacent layout circle.

[0023] It should be explained that this deployment method can be precisely adapted to the site topography and boundary constraints based on the spatial distribution of the deployment points, ensuring that the deployment area covers the effective lighting range while avoiding overlap with site obstacles or ineffective areas.

[0024] Parameter acquisition module: Collects basic parameters for the layout area corresponding to the target site, and collects site parameters for different site types.

[0025] In this embodiment, it should be specifically explained that the parameter acquisition module includes a basic parameter acquisition unit, a differentiated site parameter acquisition unit, and a data transmission unit. The basic parameter acquisition unit collects solar irradiance, solar altitude angle, and solar azimuth angle in real time based on a silicon-based light sensor in the unobstructed area at the center of the site, and collects the temperature of the component back panel in real time through a temperature and humidity sensor attached to the back panel of the component. The solar irradiance, solar altitude angle, and solar azimuth angle are based on the latitude and longitude of the center of the site, and the acquisition frequency is set to once every 10 minutes.

[0026] The differentiated site parameter acquisition unit adapts to the needs of flat sites, sites with uniform slope, and complex sites through targeted equipment: For flat sites, 1080P low-altitude cameras deployed in sensitive areas of the site edge acquire image data of dynamic obstructions, thereby obtaining the dynamic obstruction area. The dynamic obstructions include, but are not limited to, clouds and swaying trees. At the same time, the height of fixed obstructions around the site and the fixed obstruction area at the edge of the site are measured. The fixed obstructions include buildings and trees. The low-altitude cameras are installed with the edge of the site as the installation reference, with the lens facing the direction of the obstruction, and take continuous pictures. For sites with uniform slope aspect, the height difference and slope aspect angle of adjacent slope layers are collected by lidar, and the soil bearing capacity is measured by a soil bearing capacity tester. The lidar is deployed at the edge of each slope layer unit, and the scanning direction is perpendicular to the contour line. The soil bearing capacity is collected at 3 points each at the upper 1 / 3, middle 1 / 3 and lower 1 / 3 of the slope, and the bearing capacity value is recorded. For complex sites, a high-precision UAV with dynamic positioning is used to acquire micro-topographic zoning data, and soil moisture content is collected using a soil moisture meter. The UAV establishes a three-dimensional coordinate system based on the highest elevation point of the site, dividing the site into micro-topographic units such as "steep slope area, gentle slope area, and depression area". A zoning collection point is set at the center of each unit. The micro-topographic zoning data includes the zoning sunshine duration, zoning shading angle, and zoning area. The soil moisture detection selects two measurement points in each micro-topographic unit, and collects data once each at 8:00 and 18:00 every day. The data transmission unit transmits basic parameters such as solar irradiance and component current and voltage, as well as differentiated site parameters for flat sites, sites with uniform slope, and complex sites, to the site parameter preprocessing module via a wireless network. The data is encrypted using the SSL protocol during transmission to ensure data integrity.

[0027] It should be explained that solar irradiance and solar altitude angle are the core basis for calculating the solar radiation reception efficiency of the modules. The accuracy of these data directly determines the accuracy of power generation prediction. Abnormal fluctuations in irradiance usually indicate cloud cover or sensor malfunction, requiring timely calibration to avoid optimization deviations. Module backsheet temperature is a key indicator for assessing hot spot risk. When the temperature exceeds 85℃, the module power degradation rate will increase by more than 10%, and may even cause module burnout. Real-time monitoring can provide early warning of hot spot failures. Shading data from flat sites can simulate the shadow projection range at different times, preventing the array layout from falling into fixed shadow areas. Image data and horizontal distance from flat sites directly determine the adaptive spacing. If the measurement deviation of the fixed shading object height is 0.5m from the optimization direction, it may lead to an error in the calculation of the shadow coverage area on the winter solstice, resulting in shading loss. If there is a large deviation in the slope height difference of a site with uniform slope aspect, the annual power generation of the lower slope layer may be reduced, and insufficient soil bearing capacity may lead to settlement of the support foundation, increasing the risk of failure. Due to the complexity of the site, if the depression area and the steep slope area are not distinguished, uniform arrangement will lead to water accumulation in the module in the depression area and unsuitable tilt angle of the module in the steep slope area. Therefore, choosing to monitor the above-mentioned basic parameters and differentiated site parameters can comprehensively cover the core needs of the two major optimization objectives of photovoltaic power generation and failure risk, and provide accurate data support for subsequent modeling and algorithm optimization.

[0028] Parameter processing module: Based on the basic parameters and site parameters of different sites, the module aggregates the basic indicators into photovoltaic power generation coefficient and fault risk coefficient through a nonlinear evaluation model.

[0029] In this embodiment, it is important to explain that the parameter processing module determines the influence of each parameter based on the parameters of different sites, performs normalization processing, and performs weighted calculations to construct a nonlinear evaluation model, thereby obtaining the photovoltaic power generation coefficient and fault risk coefficient corresponding to different site types, as specifically represented below: For flat sites, the photovoltaic power generation factor C1 is specifically expressed as follows: , Where S d H represents the dynamic occlusion area. s S represents the solar altitude angle. g S represents the fixed shading area. t I represents the total area of ​​the site. f Indicates solar irradiance, I 标 This represents the standard solar irradiance, specifically 1000 W / m². 2 e represents the natural constant, w c11 w c12 w c13 and w c14 These represent the degree of influence corresponding to dynamic shading area, solar altitude angle, fixed shading area, and solar irradiance, respectively. The failure risk coefficient Q1 is specifically represented as follows: , Where T b Sv represents the temperature of the module backsheet, and w represents the total area of ​​the modules in the site. q11 and w q12 These represent the degree of impact corresponding to the component backsheet temperature and the shading area, respectively. Photovoltaic power generation coefficient C2 for sites with the same slope aspect: , Where θ p Indicates the slope angle, A s The solar azimuth angle and slope aspect deviation angle are represented by Hg, the average slope layer height difference, and L, which represents the slope length. z Indicates the duration of occlusion, t 标 This indicates the total duration of sunshine at the site throughout the day, w c21 w c22 w c23 and w c24 These represent the degree of influence corresponding to slope aspect angle, deviation angle, average slope layer height difference, and duration of shading, respectively. The failure risk factor Q2 is specifically represented as follows: , Where σ represents the actual soil bearing capacity, σs represents the preset soil bearing capacity, Fz represents the actual stress on the photovoltaic support, Fm represents the ultimate stress on the photovoltaic support, and w q21 w q22 and w q23 These represent the degree of influence of soil load-bearing capacity, slope angle, and photovoltaic support stress, respectively. Photovoltaic power generation coefficient C3 for complex sites: , Where m represents the total number of micro-topographic zones, j represents the micro-topographic zone number, and t zj t represents the duration of sunshine in a given area. 标 α represents the total duration of sunshine at the site throughout the day. j S represents the occlusion angle of the partition. r w represents the area of ​​occlusion in a partition. c31 and w c32 These represent the degree of impact corresponding to the sunshine duration and shading angle of the respective zones; The failure risk factor Q3 is specifically represented as follows: , Where w zj Indicates the soil moisture content of a zone, w 标 This indicates the warning value for moisture content, wq31 and w q32 These represent the degree of influence corresponding to soil moisture content and soil load-bearing capacity, respectively.

[0030] It should be noted that the photovoltaic power generation coefficient reflects the efficiency of the array in receiving sunlight and converting it into electrical energy, while the failure risk coefficient reflects the probability of the array failing due to terrain, obstruction, and environment. When processing parameters, the photovoltaic power generation coefficient and failure risk coefficient for different site types are calculated separately by using each parameter, thereby avoiding analysis bias caused by different sites.

[0031] It should be further explained that the degree of influence of each parameter is determined according to the parameter priority, as follows: Based on the parameter priorities corresponding to flat sites, sites with uniform slope, and complex sites, the random forest algorithm is used to calculate the contribution of each parameter to the target coefficient. The contribution percentage is the initial value of the influence level. For example, for flat site C1: through simulation, the contribution of If is 35%, Hs is 25%, Sd is 20%, and Sg is 20%, and the initial influence level is set to 0.35, 0.25, 0.2, and 0.2, respectively.

[0032] It should be added that the parameter priority analysis is as follows: Flat site: Solar irradiance is the core of solar energy input and has the highest priority. Solar altitude angle directly affects the angle at which the module receives sunlight and has the next highest priority. Dynamic shading area and fixed shading area indirectly affect power generation by reducing effective sunlight and have a relatively low priority. Excessive temperature of the module backsheet will cause hot spot failure and directly lead to module damage and has the highest priority. The total area of ​​the module affects heat distribution (the larger the area, the slower the heat dissipation) and has the next highest priority. For sites with uniform slope aspect: the slope aspect angle, solar azimuth angle and slope aspect deviation angle directly determine the average daily effective sunshine duration and have the highest priority. The average slope height difference and shading duration only affect local sunshine reception and have the next highest priority. The actual soil bearing capacity determines the stability of the support foundation and is the core to avoid support collapse and has the highest priority. The actual stress on the photovoltaic support affects structural safety and has the next highest priority. For complex sites: the duration of sunshine in each zone directly determines the power generation of each zone, so it has the highest priority; the shading angle of a zone affects the local light utilization rate, so it has the second highest priority; if the soil moisture content in a zone exceeds the warning value, it will cause water accumulation in the components and corrosion of the support structure, so it has the highest priority; the soil bearing capacity decreases as the soil moisture content increases, so it is greatly affected by the moisture content, so it has the second highest priority.

[0033] The initial influence level is normalized to ensure that the sum of the influence levels of all parameters is 1, adapting to the calculation logic of the nonlinear model. The normalization calculation formula is specifically expressed as follows: , Where wp represents the degree of influence corresponding to the normalized parameter p, w p，初始 This indicates the initial degree of influence of parameter p, where c is the total number of parameters.

[0034] Finally, the normalized impact level is substituted into the nonlinear evaluation model of the corresponding site to calculate the photovoltaic power generation coefficient and failure risk coefficient of each site.

[0035] The optimization design module uses the photovoltaic power generation coefficient and the fault risk coefficient as inputs to construct the layout value index, and arranges the layout comprehensive index corresponding to each layout area in descending order, thereby generating the optimal layout space.

[0036] In this embodiment, it is necessary to specifically explain the following process by which the optimization design module generates the optimal layout space: The photovoltaic power generation coefficient and fault risk coefficient corresponding to the site type of the layout area are combined with the distribution density of the layout points to calculate the layout value index of each layout area, which is specifically expressed as follows: F i =C i 1，2，3 ×Q i 1，2，3 ×D / D max Where Fi represents the layout value index corresponding to the i-th layout area, and C i 1，2，3 Q represents the photovoltaic power generation coefficient corresponding to the i-th arrangement area, whether it is a flat site, a site with a uniform slope, or a complex site. i 1，2，3 This represents the failure risk coefficient corresponding to the i-th layout area, whether it is a flat site, a site with a uniform slope, or a complex site. D represents the average layout point distribution density, where the distribution density is the number of layout points per unit area. max This indicates the maximum distribution density of the arrangement points; All effective layout areas are sorted in descending order based on the layout value index to form a regional value priority list. Based on the sorted list of regions, the top 70% of regions are selected as optimized layout regions. The selected optimized layout regions are then spatially integrated to remove overlapping parts between regions. A polygon fitting method is used to correct the boundaries of irregular regions. The selected optimized layout areas and related analysis results are fitted into a structured optimization report and transmitted to the user terminal.

[0037] It should be added that the relevant analysis results include basic regional information: the total area of ​​the optimized layout area, the spatial coordinate range (based on GPS data of the layout points), and the number of areas; Comprehensive index analysis: The distribution range and average F value of the optimized layout area are compared with the F value differences of the non-selected areas (e.g., the average F value of the optimized area is 0.78, while that of the non-selected areas is 0.42). Key parameters and metrics: average C-value and average Q-value corresponding to the optimized layout area, quantifying the optimization effect (e.g., an average C-value of 0.85 in the optimized area is 18% higher than the average level of the entire area; an average Q-value of 0.92 reduces the risk of failure by 20%). Layout recommendations: For the optimized area, supplement the basic layout parameters such as component arrangement density and recommended tilt angle.

[0038] Secondly: The accompanying drawings of the embodiments disclosed in this invention only involve the structures involved in the embodiments disclosed in this invention. Other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of this invention can be combined with each other. In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A photovoltaic power generation cell array layout optimization system, characterized in that, include: Site determination module: Determines the target site type based on the location of the battery layer, including flat sites, sites with uniform slope, and complex sites. Layout module: Layout several layout points according to the site type, and number the layout points in a preset order. Then, extract the layout area corresponding to the site according to the numbering order and mark them as 1, 2, ..., n respectively. Parameter acquisition module: Collects basic parameters of the layout area corresponding to the target site, and collects site parameters for different site types; Parameter processing module: Based on the basic parameters and site parameters of different sites, the module aggregates the basic indicators into photovoltaic power generation coefficient and fault risk coefficient through a nonlinear evaluation model; The optimization design module uses the photovoltaic power generation coefficient and the fault risk coefficient as inputs to construct the layout value index, and arranges the layout comprehensive index corresponding to each layout area in descending order, thereby generating the optimal layout space.

2. The photovoltaic power generation cell array arrangement optimization system according to claim 1, characterized in that: The target site type is determined as follows: Collect geographic data on the location of the battery layer, including but not limited to site elevation data and terrain contour data, and generate an elevation model from it; The average slope and slope change rate are calculated for the elevation model using terrain analysis algorithms. The slope represents the degree of inclination of a point on the site relative to the horizontal plane, and in the elevation model, it is represented as the rate of change of the elevation value of each cell relative to its neighboring cells. The calculated average slope and slope change rate are compared with preset thresholds to automatically classify the site type, which includes flat site, uniform slope site, and complex site. If the average slope is less than 5% and the slope change rate is less than 3%, it is determined to be a flat site. If the average slope is greater than or equal to 5% and the slope change rate is less than 8%, it is determined to be a uniform slope site. If the average slope is greater than or equal to 5% and the slope change rate is greater than or equal to 8%, it is determined to be a complex site.

3. The photovoltaic power generation cell array layout optimization system according to claim 1, characterized in that: The specific layout of the arrangement points is as follows: If the site type is flat, a regular grid is used to divide the entire rectangular or approximately rectangular site into regular square grids according to the site area. A layout point is set at the intersection of each grid, and then a rectangular coordinate system is established for numbering. If the site type is a site with the same slope aspect, the contour line method is used to generate a contour map, and the points are arranged along the key contour lines and numbered according to the contour line elevation. If the site type is complex, the topographic feature point method is used to lay out the feature points in the site. The feature points include ridge lines, valley lines, slope tops, slope toes, and places where the slope changes abruptly. The layout points are numbered according to the topographic features.

4. The photovoltaic power generation cell array arrangement optimization system according to claim 1, characterized in that: The specific steps for extracting the layout area are as follows: Using the pre-deployed layout points at the target site as centers and a preset distance as the radius, a layout circle is constructed. The preset distance can be the average spacing between adjacent control points or the design spacing value. Then, a geometric intersection operation is performed on the layout circles corresponding to adjacent layout points. Finally, the effective layout area of ​​the photovoltaic cell array is defined by the intersection operation result of each adjacent layout circle.

5. The photovoltaic power generation cell array layout optimization system according to claim 1, characterized in that: The parameter acquisition module includes a basic parameter acquisition unit, a differentiated site parameter acquisition unit, and a data transmission unit. The basic parameter acquisition unit collects solar irradiance, solar altitude angle, and solar azimuth angle in real time based on a silicon-based light sensor in the unobstructed area at the center of the site, and collects the temperature of the component back panel in real time through a temperature and humidity sensor attached to the back panel of the component. The differentiated site parameter acquisition unit adapts to the needs of flat sites, sites with uniform slope, and complex sites through targeted equipment: For flat sites, it acquires image data of dynamic obstructions by deploying 1080P low-altitude cameras in the sensitive area of ​​site edge shading, thereby obtaining the dynamic shading area, and at the same time measures the height of fixed obstructions around the site and the fixed shading area at the edge of the site. For sites with uniform slope aspect, the height difference and slope aspect angle of adjacent slope layers are collected by lidar, and the soil bearing capacity is measured by a soil bearing capacity tester. For complex sites, a high-precision UAV with dynamic positioning is used to acquire micro-topographic zoning data, and a soil moisture meter is used to collect soil moisture content. The UAV establishes a three-dimensional coordinate system based on the highest elevation point of the site, and divides the site into micro-topographic units. Each unit has a zoning collection point at its center. The micro-topographic zoning data includes the zoning sunshine duration, zoning shading angle, and zoning area.

6. The photovoltaic power generation cell array arrangement optimization system according to claim 1, characterized in that: The parameter processing module determines the influence of each parameter based on the parameters of different sites, performs normalization processing, and performs weighted calculations to construct a nonlinear evaluation model, thereby obtaining the photovoltaic power generation coefficient and fault risk coefficient corresponding to different site types.

7. The photovoltaic power generation cell array layout optimization system according to claim 6, characterized in that: The degree of influence of each parameter is determined according to its priority, as follows: Based on the parameter priorities corresponding to flat sites, sites with uniform slope aspect, and complex sites, the random forest algorithm is used to calculate the contribution of each parameter to the target coefficient, and the contribution ratio is the initial value of the influence. The initial impact level is normalized, and the normalization calculation formula is as follows: ， Where w p w represents the degree of influence corresponding to the normalized parameter p. p，初始 This indicates the initial degree of influence of parameter p, where c is the total number of parameters; Finally, the normalized impact level is substituted into the nonlinear evaluation model of the corresponding site to calculate the photovoltaic power generation coefficient and failure risk coefficient of each site.

8. The photovoltaic power generation cell array layout optimization system according to claim 1, characterized in that: The optimization design module generates the optimal layout space through the following process: The photovoltaic power generation coefficient and fault risk coefficient corresponding to the site type of the layout area are combined with the distribution density of the layout points to calculate the layout value index of each layout area, which is specifically expressed as follows: F i =C i 1，2，3 ×Q i 1，2，3 ×D / D max Where Fi represents the layout value index corresponding to the i-th layout area, and C i 1，2，3 Q represents the photovoltaic power generation coefficient corresponding to the i-th arrangement area, whether it is a flat site, a site with a uniform slope, or a complex site. i 1，2，3 This represents the failure risk coefficient corresponding to the i-th layout area, whether it is a flat site, a site with a uniform slope, or a complex site. D represents the average layout point distribution density, where the distribution density is the number of layout points per unit area. max This indicates the maximum distribution density of the arrangement points; All effective layout areas are sorted in descending order based on the layout value index to form a regional value priority list. Based on the sorted list of regions, the top 70% of regions are selected as optimized layout regions. The selected optimized layout regions are then spatially integrated to remove overlapping parts between regions. A polygon fitting method is used to correct the boundaries of irregular regions. The selected optimized layout areas and related analysis results are fitted into a structured optimization report and transmitted to the user terminal.

Images