Building photovoltaic integrated space deployment method and system under visual and performance dual constraints

Abstract

The application belongs to the technical field of building integrated photovoltaics, and discloses a building photovoltaic integrated space deployment method under the double constraints of vision and performance. The application uses grid division and target point selection technology to screen photovoltaic deployment building surfaces. This method can make the layout of photovoltaic components more scientific and reasonable, avoid the problem of improper building surface selection caused by only relying on illumination conditions or simple experience judgment in traditional methods, and ensure that the photovoltaic system can maximize the reception of solar energy. At the same time, a dynamic shadow blocking calculation method is adopted, the blocking effect of the surrounding environment is considered, and the photovoltaic potential of the building surface is fully evaluated and tapped. Through a multi-objective optimization method, the power generation performance and visual impact of the photovoltaic system are comprehensively considered to find the best balance point. This not only guarantees the efficient operation of the photovoltaic system, but also reduces its negative impact on the visual environment, and improves the scientificity and practicality of the installation scheme.

Description

Technical Field

[0001] This invention belongs to the field of building-integrated photovoltaics (BIPV) technology, and particularly relates to a spatial deployment method and system for building-integrated photovoltaics under the dual constraints of visual and performance requirements. Background Technology

[0002] Driven by both improved photovoltaic efficiency and reduced module costs, coupled with efficient use of building space, Building-integrated Photovoltaics (BIPV) has become a core pathway to achieving building carbon neutrality. BIPV enhances building aesthetics while maintaining building energy self-sufficiency, thus leading to its widespread adoption.

[0003] However, the currently deployed photovoltaic panels are predominantly dark blue, which is difficult to match with the colors and materials of modern building facades, resulting in damage to architectural aesthetics. This is particularly noticeable in historical buildings or high-end commercial buildings, and has a significant visual impact on people. Furthermore, when installing photovoltaic systems, the focus is often on their power generation performance and output, while their visual impact is ignored. At the same time, existing BIPV design and layout methods mainly rely on lighting conditions or simple experience-based judgments, lacking a quantitative assessment of the relationship between building surface visibility, photovoltaic morphology parameters, and visual salience.

[0004] Based on the above analysis, the problems and shortcomings of the existing technology are as follows:

[0005] (1) The photovoltaic panels currently deployed are mainly dark blue, which is difficult to match with the color and material of modern building facades, resulting in damage to architectural aesthetics. This has a significant impact on historical buildings or high-end commercial buildings, and also has a greater visual impact on people. When installing photovoltaics, people often focus on their power generation performance and power generation while ignoring their visual impact.

[0006] (2) At the same time, existing BIPV design and layout methods mainly rely on lighting conditions or simple experience judgments, lacking quantitative assessment of the relationship between the visibility of building surfaces, photovoltaic morphology parameters and visual salience. Summary of the Invention

[0007] To address the problems existing in the prior art, this invention provides a method for spatial deployment of building-integrated photovoltaics under the dual constraints of visual and performance requirements.

[0008] This invention is implemented as follows: a method for spatial deployment of building-integrated photovoltaics under dual constraints of visual appeal and performance includes:

[0009] S1: For the scene model under study, implement mesh generation and target point extraction of the building surface for building photovoltaic integration;

[0010] S2: Using a visibility algorithm, the frequency of visibility of the building surface, including the roof and facade, from the observation points of pedestrians and indoor users is counted, thereby calculating the cumulative visibility of each building surface and quantifying the visibility assessment of the building appearance.

[0011] S3: Obtain photovoltaic morphology parameters and building surface data, and combine them with the building's visualization level in S2 to construct a visual impact representation model of building photovoltaic integration;

[0012] S4: Collect key GIS data of the research scenario and process it in geographic information system software to construct a three-dimensional model of the research area;

[0013] S5: Calculate the effective radiation intensity of the building surface based on the regional spatial data in S4 and the local meteorological data, and combine it with the visual impact quantification model in S3 to comprehensively evaluate the solar energy potential and visual threshold of the building surface;

[0014] S6: Using a multi-objective optimization method, considering both the visual impact and performance benefits of photovoltaics as optimization objectives, the optimal three-dimensional deployment strategy for photovoltaics on building surfaces is obtained through comparative analysis.

[0015] Furthermore, in step S1, the mesh density can be dynamically adjusted according to the curvature of the building surface. A finer mesh is used in areas with greater curvature, a coarser mesh is used in flat areas, and a uniform mesh is used for regular surfaces.

[0016] In step S2, the visibility of the building surface is determined by the unobstructed connectivity between the target point and the observation point. If there are no obstacles between the target point and the observation point on the building surface, it means that the surface is visible to the observation point.

[0017] Furthermore, step S3, which involves a visual quantitative assessment of building-integrated photovoltaics (BIPV), specifically includes the following steps:

[0018] S301: Collect data on building surface and photovoltaic morphology parameters, including building surface appearance shape, emissivity, photovoltaic coverage, and texture complexity; generate state information and effect models of changes before and after the installation of solar photovoltaic panels on the building surface;

[0019] S302: Import a visual saliency model based on computer information technology and cognitive psychology, perform point-by-point in-depth analysis on a two-dimensional image containing three-dimensional architectural scene information, consider multiple evaluation factors, and generate a corresponding visual saliency map.

[0020] S303: Conduct eye-tracking experiments on observers to generate dynamic eye-tracking heatmaps, establish a quantitative correlation model between photovoltaic morphological parameters and visual interference, and perform cross-validation by coupling with visual saliency maps to optimize model parameters;

[0021] The appearance of a building surface can be determined by measuring it on-site using a spectrometer, while the reflectance can be referenced from the conventional constants of the wall.

[0022] Based on the visibility assessment in step S2, the viewing angle is set to the building viewing angle that is most likely to be observed by outdoor pedestrians and indoor users, and a cloudy sky model that conforms to the International Commission on Illumination (ICI) standard is adopted.

[0023] To ensure accurate quantitative assessment of visual impact, three key evaluation factors—color, brightness, and line direction—are considered, and different weights are assigned to them in the model. Simultaneously, based on different Gaussian smoothing parameters, renderings and corresponding visual saliency maps of various building-integrated photovoltaic (BIPV) design schemes are generated.

[0024] An eye-tracking experiment was used to record dynamic gaze point heatmaps, saccade paths, and pupil diameter changes of the observer. Segmentation and clustering algorithms were employed to extract the first gaze duration, gaze duration, and visual interference values ​​of the photovoltaic modules on the building surface.

[0025] Furthermore, in step S4, building vector data and road vector data are collected, and data cleaning and organization work such as spatial topology checking, coordinate transformation, and building outline transformation is performed in geographic information software.

[0026] Furthermore, step S5, which involves a visual quantitative assessment of building-integrated photovoltaics (BIPV), specifically includes the following steps:

[0027] S501: Using the three-dimensional spatial data from step S4, and through image acquisition and sky visibility factors, determine the photovoltaic usable area on the building surface;

[0028] S502: Acquire local solar altitude angle, azimuth angle, incident angle and other data. Based on this data, calculate the effective proportion of direct sunlight area and the effective radiation intensity of building surface through real-time dynamic shading calculation method, and analyze the photovoltaic potential of building surface.

[0029] The method for calculating photovoltaic solar radiation in real-time dynamic shading is as follows:

[0030] G b,t =BHI·R b (1)

[0031]

[0032] G g,t = (1-SAR)·G b,t +SVF·G d,t +G r,t (5)

[0033] Among them G g,tRepresents the total radiation from photovoltaic systems;

[0034] G b,t The amount of direct solar radiation received by the photovoltaic system;

[0035] G d,t This refers to the amount of solar diffuse radiation received by the photovoltaic system.

[0036] G r,t The amount of solar radiation received by a photovoltaic system;

[0037] BHI stands for direct horizontal solar radiation.

[0038] R b Impact factor;

[0039] θ inc The angle of incidence of the sun;

[0040] θ z The solar zenith angle;

[0041] DHI stands for horizontally diffused solar radiation.

[0042] β is the photovoltaic tilt angle;

[0043] F1 is the solar luminance coefficient;

[0044] F2 is the horizontal brightness coefficient;

[0045] GHI stands for total horizontal solar radiation.

[0046] ρ is the ground albedo;

[0047] SAR is the ratio of photovoltaic shading area;

[0048] SVF stands for Sky Visibility Factor;

[0049] S503: Combining the visual impact quantification model in Visual S3, this study comprehensively evaluates the solar energy potential and visual threshold of the entire surface of buildings in the research area by integrating multiple simulation platforms and programming tools such as Grasshopper-Rhion, LadybugTools, and Python.

[0050] Furthermore, in step S6, under the given constraints of photovoltaic power generation and solar radiation, the photovoltaic performance effect and visual impact are simultaneously used as optimization objectives to maximize photovoltaic performance and minimize visual salience. The NSGA-II algorithm is used to generate the Pareto optimal solution set curve to determine the optimal installation location of building photovoltaics in the study area.

[0051] Two ranking methods based on total energy priority and energy intensity priority are used for comparative analysis to verify the optimization effect of the multi-objective optimization method.

[0052] Another object of the present invention is to provide a building-integrated photovoltaic (BIPV) spatial deployment system under the dual constraints of visual appeal and performance, comprising:

[0053] The target point extraction module is used to perform mesh generation and target point extraction on the building surface of building photovoltaic integration for the scene model under study.

[0054] The visibility assessment module is used to employ visibility algorithms to count the frequency of visibility of building surfaces, including the roof and facade, from the observation points of pedestrians and indoor users, thereby calculating the cumulative visibility of each building surface and quantifying the visibility assessment of the building's appearance.

[0055] The characterization model construction module is used to acquire photovoltaic morphology parameters and building surface data, and combine them with the visualization level of buildings in S2 to construct a visual impact characterization model of building photovoltaic integration.

[0056] The 3D model building module is used to collect key GIS data of the research scene and process it in geographic information system software to build a 3D model of the research area.

[0057] The calculation module is used to calculate the effective radiation intensity of the building surface based on the regional spatial data in S4 and the local meteorological data, and to comprehensively evaluate the solar energy potential and visual threshold of the building surface in combination with the visual impact quantification model in S3.

[0058] The optimization module is used to simultaneously consider the visual impact and performance benefits of photovoltaics as optimization objectives using a multi-objective optimization method, and obtain the optimal three-dimensional deployment strategy for photovoltaics on building surfaces through comparative analysis.

[0059] Another object of the present invention is to provide a computer device including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the building-integrated photovoltaic spatial deployment method under dual constraints of vision and performance.

[0060] Another object of the present invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the building-integrated photovoltaics spatial deployment method under dual constraints of vision and performance.

[0061] Another objective of this invention is to provide an information data processing terminal for implementing the building-integrated photovoltaic spatial deployment system under both visual and performance constraints.

[0062] Based on the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solution to be protected by this invention are as follows:

[0063] This invention quantifies the visual impact and simultaneously considers the performance and visual impact of building-integrated photovoltaics (BIPV) for multi-objective optimization, resulting in a refined spatial installation strategy for BIPV.

[0064] (1) This invention utilizes grid division and target point selection technology to screen building surfaces for photovoltaic deployment. This method enables a more scientific and reasonable layout of photovoltaic modules, avoiding the problem of improper building surface selection caused by relying solely on lighting conditions or simple experience judgments in traditional methods, thus ensuring that the photovoltaic system can maximize the reception of solar energy. At the same time, a dynamic shading calculation method is adopted to take into account the shading effect of the surrounding environment, fully evaluating and exploring the photovoltaic potential of the building surface.

[0065] (2) From the perspective of pedestrians and indoor users, the visibility of the building was quantified, taking into account the observer's perspective to the greatest extent. A quantitative correlation model between photovoltaic morphological parameters and visual salience was established, and parameters such as the size, color, and tilt angle of the photovoltaic system were optimized. This allows the photovoltaic system to better coordinate with the building's appearance and reduce visual interference to the surrounding environment.

[0066] (3) By using a multi-objective optimization method, the optimal balance point is found by comprehensively considering the power generation performance and visual impact of the photovoltaic system. This ensures the efficient operation of the photovoltaic system while reducing its negative impact on the visual environment, thus improving the scientific nature and practicality of the installation scheme. Attached Figure Description

[0067] Figure 1 This is a flowchart of a method for spatial deployment of building-integrated photovoltaics under dual constraints of vision and performance, provided by an embodiment of the present invention.

[0068] Figure 2 This is a structural block diagram of a building-integrated photovoltaic spatial deployment system under both visual and performance constraints, provided by an embodiment of the present invention.

[0069] Figure 3 This is a flowchart illustrating the visual impact quantification of building-integrated photovoltaics (BIPV) provided in an embodiment of the present invention.

[0070] Figure 4 This is a flowchart of multi-objective optimization under dual constraints of vision and performance provided in the embodiments of the present invention. Detailed Implementation

[0071] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0072] like Figure 1As shown, an embodiment of the present invention provides a method for spatial deployment of building-integrated photovoltaics under dual constraints of vision and performance, comprising the following steps:

[0073] S1: For the scene model under study, implement mesh generation and target point extraction of the building surface for building photovoltaic integration;

[0074] S2: Using a visibility algorithm, the frequency of visibility of the building surface, including the roof and facade, from the observation points of pedestrians and indoor users is counted, thereby calculating the cumulative visibility of each building surface and quantifying the visibility assessment of the building appearance.

[0075] S3: Obtain photovoltaic morphology parameters and building surface data, and combine them with the building's visualization level in S2 to construct a visual impact representation model of building photovoltaic integration;

[0076] S4: Collect key GIS data of the research scenario and process it in geographic information system software to construct a three-dimensional model of the research area;

[0077] S5: Calculate the effective radiation intensity of the building surface based on the regional spatial data in S4 and the local meteorological data, and combine it with the visual impact quantification model in S3 to comprehensively evaluate the solar energy potential and visual threshold of the building surface;

[0078] S6: Using a multi-objective optimization method, considering both the visual impact and performance benefits of photovoltaics as optimization objectives, the optimal three-dimensional deployment strategy for photovoltaics on building surfaces is obtained through comparative analysis.

[0079] In step S1 provided in this embodiment of the invention, the mesh density can be dynamically adjusted according to the curvature of the building surface. A finer mesh is used in areas with large curvature, a coarser mesh is used in flat areas, and a uniform mesh is used for regular surfaces.

[0080] In step S2, the visibility of the building surface is determined by the unobstructed connectivity between the target point and the observation point. If there are no obstacles between the target point and the observation point on the building surface, it means that the surface is visible to the observation point.

[0081] Step S3 of this invention, which involves visual quantitative evaluation of building-integrated photovoltaics, specifically includes the following steps:

[0082] S301: Collect data on building surface and photovoltaic morphology parameters, including building surface appearance shape, emissivity, photovoltaic coverage, and texture complexity; generate state information and effect models of changes before and after the installation of solar photovoltaic panels on the building surface;

[0083] S302: Import a visual saliency model based on computer information technology and cognitive psychology, perform point-by-point in-depth analysis on a two-dimensional image containing three-dimensional architectural scene information, consider multiple evaluation factors, and generate a corresponding visual saliency map.

[0084] S303: Conduct eye-tracking experiments on observers to generate dynamic eye-tracking heatmaps, establish a quantitative correlation model between photovoltaic morphological parameters and visual interference, and perform cross-validation by coupling with visual saliency maps to optimize model parameters;

[0085] The appearance of a building surface can be determined by measuring it on-site using a spectrometer, while the reflectance can be referenced from the conventional constants of the wall.

[0086] Based on the visibility assessment in step S2, the viewing angle is set to the building viewing angle that is most likely to be observed by outdoor pedestrians and indoor users, and a cloudy sky model that conforms to the International Commission on Illumination (ICI) standard is adopted.

[0087] To ensure accurate quantitative assessment of visual impact, three key evaluation factors—color, brightness, and line direction—are considered, and different weights are assigned to them in the model. Simultaneously, based on different Gaussian smoothing parameters, renderings and corresponding visual saliency maps of various building-integrated photovoltaic (BIPV) design schemes are generated.

[0088] An eye-tracking experiment was used to record dynamic gaze point heatmaps, saccade paths, and pupil diameter changes of the observer. Segmentation and clustering algorithms were employed to extract the first gaze duration, gaze duration, and visual interference values ​​of the photovoltaic modules on the building surface.

[0089] In step S4 of this embodiment of the invention, building vector data and road vector data are collected, and data cleaning and organization work such as spatial topology checking, coordinate transformation, and building outline transformation is performed in geographic information software.

[0090] Step S5 in this embodiment of the invention, which involves visual quantitative evaluation of building-integrated photovoltaics, specifically includes the following steps:

[0091] S501: Using the three-dimensional spatial data from step S4, and through image acquisition and sky visibility factors, determine the photovoltaic usable area on the building surface;

[0092] S502: Acquire local solar altitude angle, azimuth angle, incident angle and other data. Based on this data, calculate the effective proportion of direct sunlight area and the effective radiation intensity of building surface through real-time dynamic shading calculation method, and analyze the photovoltaic potential of building surface.

[0093] The method for calculating photovoltaic solar radiation in real-time dynamic shading is as follows:

[0094] Gb,t =BHI·R b (1)

[0095]

[0096] G g,t = (1-SAR)·G b,t +SVF·G d,t +G r,t (5)

[0097] Among them G g,t Represents the total radiation from photovoltaic systems;

[0098] G b,t The amount of direct solar radiation received by the photovoltaic system;

[0099] G d,t This refers to the amount of solar diffuse radiation received by the photovoltaic system.

[0100] G r,t The amount of solar radiation received by a photovoltaic system;

[0101] BHI stands for direct horizontal solar radiation.

[0102] R b Impact factor;

[0103] θ inc The angle of incidence of the sun;

[0104] θ z The solar zenith angle;

[0105] DHI stands for horizontally diffused solar radiation.

[0106] β is the photovoltaic tilt angle;

[0107] F1 is the solar luminance coefficient;

[0108] F2 is the horizontal brightness coefficient;

[0109] GHI stands for total horizontal solar radiation.

[0110] ρ is the ground albedo;

[0111] SAR is the ratio of photovoltaic shading area;

[0112] SVF stands for Sky Visibility Factor;

[0113] S503: Combining the visual impact quantification model in Visual S3, this study comprehensively evaluates the solar energy potential and visual threshold of the entire surface of buildings in the research area by integrating multiple simulation platforms and programming tools such as Grasshopper-Rhion, LadybugTools, and Python.

[0114] In step S6 of this embodiment, under the given constraints of photovoltaic power generation and solar radiation, photovoltaic performance effect and visual impact are simultaneously used as optimization objectives to maximize photovoltaic performance and minimize visual salience. The NSGA-II algorithm is used to generate a Pareto optimal solution set curve to determine the optimal installation location of building-integrated photovoltaics (BIPV) within the study area, supporting multiple options such as "high aesthetics-medium efficiency" or "high efficiency-low aesthetics." Furthermore, the principle of total energy priority (maximizing the annual total power generation of the building surface photovoltaic system and maximizing the coverage area) and the principle of energy intensity priority (maximizing the power generation efficiency per unit area) are adopted, selecting areas with the highest radiation for concentrated deployment. These two rule-based ranking methods are compared and analyzed from multiple indicators, such as roof coverage, photovoltaic power generation, photovoltaic power generation efficiency, and visual interference, to verify the optimization performance of the multi-objective optimization method.

[0115] like Figure 2 As shown, an embodiment of the present invention provides a building-integrated photovoltaic (BIPV) spatial deployment system under dual constraints of vision and performance, comprising:

[0116] The target point extraction module is used to perform mesh generation and target point extraction on the building surface of building photovoltaic integration for the scene model under study.

[0117] The visibility assessment module is used to employ visibility algorithms to count the frequency of visibility of building surfaces, including the roof and facade, from the observation points of pedestrians and indoor users, thereby calculating the cumulative visibility of each building surface and quantifying the visibility assessment of the building's appearance.

[0118] The characterization model construction module is used to acquire photovoltaic morphology parameters and building surface data, and combine them with the visualization level of buildings in S2 to construct a visual impact characterization model of building photovoltaic integration.

[0119] The 3D model building module is used to collect key GIS data of the research scene and process it in geographic information system software to build a 3D model of the research area.

[0120] The calculation module is used to calculate the effective radiation intensity of the building surface based on the regional spatial data in S4 and the local meteorological data, and to comprehensively evaluate the solar energy potential and visual threshold of the building surface in combination with the visual impact quantification model in S3.

[0121] The optimization module is used to simultaneously consider the visual impact and performance benefits of photovoltaics as optimization objectives using a multi-objective optimization method, and obtain the optimal three-dimensional deployment strategy for photovoltaics on building surfaces through comparative analysis.

[0122] Another object of the present invention is to provide a computer device including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the building-integrated photovoltaic spatial deployment method under dual constraints of vision and performance.

[0123] Another object of the present invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the building-integrated photovoltaics spatial deployment method under dual constraints of vision and performance.

[0124] Another objective of this invention is to provide an information data processing terminal for implementing the building-integrated photovoltaic spatial deployment system under both visual and performance constraints.

[0125] Specific implementation of the present invention:

[0126] See Figure 3 and Figure 4 A method for spatial deployment of building-integrated photovoltaics (BIPV) under dual constraints of visual appeal and performance includes the following steps:

[0127] S1: Collect and input the geometric data of all building surfaces in the study area, and mesh the building surfaces in the study area. Dynamically adjust the mesh density according to the curvature of the building surface; use a finer mesh for areas with greater curvature, a coarser mesh for flat areas, and a uniform mesh for regular surfaces. Label the mesh attributes based on multiple factors, and select suitable target points for installing photovoltaic modules from the mesh according to the set screening criteria, covering key areas of the building surface, and excluding building surfaces with poor orientation or insufficient area;

[0128] S2: A visibility algorithm is employed. The visibility of a building surface is determined by the unobstructed connectivity between the target point and the observation point. If there are no obstacles between the target point and the observation point, the surface is considered visible to the observation point. The frequency of visibility of the building surface (including the roof and facade) from pedestrian and indoor user observation points is statistically analyzed to calculate the cumulative visibility of each building surface, quantifying the visibility assessment of the building's appearance. Computer graphics algorithms, such as hidden surface removal algorithms, can be used to calculate the proportion of unobstructed area from the viewpoint to the building surface, serving as a quantitative indicator of visibility. The visibility value ranges from 0 to 1, with higher values ​​indicating greater visibility of the building surface.

[0129] S3: Acquire photovoltaic morphology parameters and building surface data, and combine this with the building visualization level from S2 to construct a visual impact representation model of building-integrated photovoltaics (BIPV). This includes the following steps:

[0130] S301: Collect data on building surface and photovoltaic morphology parameters, including building surface shape, emissivity, photovoltaic coverage, and texture complexity. The building surface shape is determined through on-site measurement using a spectrometer, and the reflectivity is referenced to the conventional constant of the wall. Simultaneously, based on the visibility assessment in step S2, the viewing angle is set to the perspective from which outdoor pedestrians and indoor users are most likely to observe the building, and a cloudy sky model conforming to the International Commission on Illumination (ICIII) standards is used. Finally, a state information and effect model of the changes before and after the installation of solar photovoltaic panels on the building surface are generated.

[0131] S302: Import the state information and effect model before and after building photovoltaic installation into a visual saliency model based on computer information technology and cognitive psychology. Perform in-depth point-by-point analysis on the two-dimensional image containing three-dimensional building scene information. To ensure the accuracy of the quantitative assessment of visual impact, consider three key evaluation factors: color, brightness, and line direction. Calculate color difference, geometric adaptability, and light and shadow, and set different weights for them in the model. At the same time, based on different Gaussian smoothing parameters, generate renderings and corresponding visual saliency maps of various building photovoltaic integrated design schemes, and compare the visual saliency values ​​of different photovoltaic installation schemes under controlled variables.

[0132] S303: Using an eye-tracking experimenter, dynamic gaze point heatmaps of multiple photovoltaic schemes were obtained, recording saccade paths and pupil diameter changes. Segmentation and clustering algorithms were used to extract the first gaze duration, gaze duration, and visual interference values ​​of photovoltaic modules on the building surface, forming a dynamic eye-tracking heatmap. A quantitative correlation model between photovoltaic morphological parameters and visual interference was established. Based on the coupling degree between the visual saliency map and the eye-tracking heatmap, the visual saliency model was cross-validated, thereby optimizing the model parameters.

[0133] S4: Collect building and road vector data, and perform data cleaning and organization tasks such as spatial topology checks, coordinate transformations, and building outline transformations in geographic information software to construct a 3D model of the study area. Topology checks: Ensure the logical consistency and geometric accuracy of geographic data, avoiding spatial relationship errors such as overlapping features, gaps, and hanging lines. Coordinate transformations: Transform geographic data to the same coordinate system, ensuring spatial alignment of multi-source data. Building outline transformations: Preserve key building features while reducing redundant nodes, improving data usability.

[0134] S5: Calculate the effective radiation intensity of the building surface based on the regional spatial data and local meteorological data in S4, and comprehensively evaluate the solar energy potential and visual threshold of the building surface by combining the visual impact quantification model in S3. The specific steps are as follows:

[0135] S501: Obtain building facade reflectance and material type information from multispectral imagery, and identify occlusions from panoramic photographs for calculating sky visibility factor. Based on the Grasshopper platform, the SVF distribution is automatically calculated after inputting a 3D model using Ladybug Tools.

[0136] S502: Acquire local solar altitude angle, azimuth angle, incident angle and other data. Based on this data, use real-time dynamic shading calculation method to calculate the effective proportion of direct sunlight area and the effective radiation intensity of building surface, including direct radiation, diffuse radiation and reflected radiation, and analyze the photovoltaic potential of building surface.

[0137] The method for calculating photovoltaic solar radiation in real-time dynamic shading is as follows:

[0138] G b,t =BHI·R b (1)

[0139]

[0140]

[0141] G g,t = (1-SAR)·G b,t +SVF·G d,t +G r,t (5)

[0142] Among them G g,t Represents the total radiation from photovoltaic systems;

[0143] G b,t The amount of direct solar radiation received by the photovoltaic system;

[0144] G d,t This refers to the amount of solar diffuse radiation received by the photovoltaic system.

[0145] G r,t The amount of solar radiation received by a photovoltaic system;

[0146] BHI stands for direct horizontal solar radiation.

[0147] R b Impact factor;

[0148] θ inc The angle of incidence of the sun;

[0149] θ z The solar zenith angle;

[0150] DHI stands for horizontally diffused solar radiation.

[0151] β is the photovoltaic tilt angle;

[0152] F1 is the solar luminance coefficient;

[0153] F2 is the horizontal brightness coefficient;

[0154] GHI stands for total horizontal solar radiation.

[0155] ρ is the ground albedo;

[0156] SAR is the ratio of photovoltaic shading area;

[0157] SVF stands for Sky Visibility Factor;

[0158] S503: Combining the visual impact quantification model in Visual S3, and integrating multiple simulation platforms and programming tools such as Grasshopper-Rhion, LadybugTools, and Python, this method calculates the surface radiation of buildings and runs a visual saliency model to comprehensively evaluate the solar energy potential and visual threshold of the entire surface of buildings in the study area.

[0159] S6: Under the given constraints of photovoltaic power generation and solar radiation, the optimization objectives simultaneously consider photovoltaic performance effects and visual impact, maximizing photovoltaic performance and minimizing visual salience. The NSGA-II algorithm is used to generate Pareto optimal solution set curves to determine the optimal installation location for building-integrated photovoltaics (BIPV) within the study area, supporting multiple options such as "high aesthetics-medium efficiency" or "high efficiency-low aesthetics." Furthermore, the optimization employs two priority principles: maximizing the total annual power generation of the building surface PV system (maximizing coverage area) and maximizing the power generation efficiency per unit area (maximizing radiation efficiency). These two ranking methods are compared and analyzed using multiple indicators, such as roof coverage, photovoltaic power generation, photovoltaic power generation efficiency, and visual interference, to verify the optimization performance of the multi-objective optimization method.

[0160] It should be noted that embodiments of the present invention can be implemented in hardware, software, or a combination of both. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by a suitable instruction execution system, such as a microprocessor or dedicated-design hardware. Those skilled in the art will understand that the above-described devices and methods can be implemented using computer-executable instructions and / or included in processor control code, for example, such code provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The devices and modules of the present invention can be implemented by hardware circuitry such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field-programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of the above-described hardware circuitry and software, such as firmware.

[0161] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions, and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention, and within the spirit and principles of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for spatial deployment of building-integrated photovoltaics under dual constraints of vision and performance, characterized in that, The method for spatial deployment of building-integrated photovoltaics under both visual and performance constraints includes the following steps: S1: For the scene model under study, implement mesh generation and target point extraction of the building surface for building photovoltaic integration; S2: Using a visibility algorithm, the frequency of visibility of the building surface, including the roof and facade, from the observation points of pedestrians and indoor users is counted, thereby calculating the cumulative visibility of the building surface and quantifying the visibility assessment of the building appearance. S3: Obtain photovoltaic morphology parameters and building surface data, and combine them with the cumulative visibility of building surfaces in S2 to construct a quantitative model of the visual impact of building photovoltaic integration; S4: Collect key GIS data of the research scenario and process it in geographic information system software to construct a three-dimensional model of the research area; S5: Calculate the effective radiation intensity of the building surface based on the regional spatial data in S4 and the local meteorological data, and comprehensively evaluate the solar energy potential and visual impact of the building surface in combination with the visual impact quantification model in S3. S6: Using a multi-objective optimization method, considering both the visual impact and performance benefits of photovoltaics as optimization objectives, the optimal three-dimensional deployment strategy for photovoltaics on building surfaces is obtained through comparative analysis. Step S3, constructing a visual impact quantification model for building-integrated photovoltaics (BIPV), specifically includes the following steps: S301: Collect data on building surface and photovoltaic morphology parameters, including building surface appearance shape, reflectivity, photovoltaic coverage, and texture complexity; generate state information and effect models of changes before and after the installation of solar photovoltaic panels on the building surface; S302: Import a visual saliency model based on computer information technology and cognitive psychology, perform point-by-point in-depth analysis on a two-dimensional image containing three-dimensional architectural scene information, consider multiple evaluation factors, and generate a corresponding visual saliency map. S303: Conduct eye-tracking experiments on observers to generate dynamic eye-tracking heatmaps, establish a quantitative model of the visual impact of photovoltaic morphological parameters and visual interference, and perform cross-validation by coupling with visual saliency maps to optimize model parameters. The appearance of the building surface was determined by on-site measurement using a spectrometer, with reflectance referenced to the conventional constant of the wall. Based on the visibility assessment in step S2, the viewing angle setting selects the building viewing angle that is most likely to be observed by outdoor pedestrians and indoor users, and adopts a cloudy sky model that conforms to the International Commission on Illumination (ICI) standards. To ensure accurate quantitative assessment of visual impact, three key evaluation factors—color, brightness, and line direction—are considered, and different weights are assigned to them in the model. Simultaneously, based on different Gaussian smoothing parameters, renderings and corresponding visual saliency maps of various building-integrated photovoltaic (BIPV) design schemes are generated. An eye-tracking experiment was used to record dynamic gaze point heatmaps, saccade paths, and pupil diameter changes of the observer. Segmentation and clustering algorithms were employed to extract the first gaze duration, gaze duration, and visual interference values ​​of the photovoltaic modules on the building surface.

2. The building-integrated photovoltaics spatial deployment method under dual constraints of vision and performance as described in claim 1, characterized in that, In step S1, the grid density is dynamically adjusted according to the curvature of the building surface. A finer grid is used in areas with greater curvature, a coarser grid is used in flat areas, and a uniform grid is used for regular surfaces. In step S2, the visibility of the building surface is determined by the unobstructed connectivity between the target point and the observation point. If there are no obstacles between the target point and the observation point on the building surface, it means that the surface is visible to the observation point.

3. The building-integrated photovoltaics spatial deployment method under dual constraints of vision and performance as described in claim 1, characterized in that, In step S4, building vector data and road vector data are collected, and data cleaning and organization work is carried out in the geographic information system software for spatial topology checking, coordinate transformation, and building outline transformation.

4. The building-integrated photovoltaics spatial deployment method under dual constraints of vision and performance as described in claim 1, characterized in that, Step S5, which involves a comprehensive assessment of the solar energy potential and visual impact of building-integrated photovoltaics (BIPV), specifically includes the following steps: S501: Using the three-dimensional spatial data from step S4, and through image acquisition and sky visibility factors, determine the photovoltaic usable area on the building surface; S502: Obtain local solar altitude angle, azimuth angle, and incident angle data. Based on these data, calculate the effective proportion of the direct sunlight area and the effective radiation intensity of the building surface using a real-time dynamic shading calculation method, and analyze the photovoltaic potential of the building surface. The method for calculating photovoltaic solar radiation in real-time dynamic shading is as follows: （1） （2） （3） （4） （5） in Represents the total radiation from photovoltaic systems; The amount of direct solar radiation received by the photovoltaic system; This refers to the amount of solar diffuse radiation received by the photovoltaic system. The amount of solar radiation received by a photovoltaic system; This refers to direct, horizontal solar radiation. Impact factor; The angle of incidence of the sun; The solar zenith angle; This refers to the horizontal scattered radiation from the sun. The tilt angle of the photovoltaic system; The solar luminance coefficient; Horizontal brightness coefficient; Total horizontal solar radiation; Ground albedo; The ratio of photovoltaic shading area; Sky visibility factor; S503: Combining the visual impact quantification model in Visual S3, this study comprehensively assesses the solar energy potential and visual impact of the entire surface of buildings in the research area by integrating multiple simulation platforms and programming tools such as Grasshopper-Rhino, LadybugTools, and Python.

5. The building-integrated photovoltaics spatial deployment method under dual constraints of vision and performance as described in claim 1, characterized in that, In step S6, under the constraints of photovoltaic power generation and solar radiation, photovoltaic performance benefits and visual impact are simultaneously used as optimization objectives to maximize photovoltaic performance and minimize visual salience. The NSGA-II algorithm is used to generate Pareto optimal solution set curves to determine the best installation location of building photovoltaics in the study area. Two ranking methods based on total energy priority and energy intensity priority are compared and analyzed to verify the optimization effect of the multi-objective optimization method.

6. A building-integrated photovoltaic (BIPV) spatial deployment system under dual constraints of vision and performance, used to implement the building-integrated photovoltaic spatial deployment method under dual constraints of vision and performance as described in any one of claims 1-5, characterized in that, The building-integrated photovoltaics spatial deployment system under both visual and performance constraints includes: The target point extraction module is used to perform mesh generation and target point extraction on the building surface of building photovoltaic integration for the scene model under study. The visibility assessment module is used to employ visibility algorithms to count the frequency of visibility of the building surface, including the roof and facade, from the observation points of pedestrians and indoor users, thereby calculating the cumulative visibility of the building surface and quantifying the visibility assessment of the building appearance. The characterization model construction module is used to acquire photovoltaic morphology parameters and building surface data, and combine the cumulative visibility of building surfaces to construct a visual impact quantification model of building photovoltaic integration. The 3D model building module is used to collect key GIS data of the research scene and process it in geographic information system software to build a 3D model of the research area. The calculation module is used to calculate the effective radiation intensity of the building surface based on the regional spatial data in S4 and the local meteorological data, and to comprehensively evaluate the solar energy potential and visual impact of the building surface in combination with the visual impact quantification model in S3. The optimization module is used to simultaneously consider the visual impact and performance benefits of photovoltaics as optimization objectives using a multi-objective optimization method, and obtain the optimal three-dimensional deployment strategy for photovoltaics on building surfaces through comparative analysis.

7. A computer device, characterized in that, The computer device includes a memory and a processor. The memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the building-integrated photovoltaic spatial deployment method under dual constraints of vision and performance as described in any one of claims 1-5.

8. A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the building-integrated photovoltaic spatial deployment method under dual constraints of vision and performance as described in any one of claims 1-5.

9. An information data processing terminal, characterized in that, The information data processing terminal is used to realize the building-integrated photovoltaic spatial deployment system under the dual constraints of vision and performance as described in claim 6.

Images