Distributed photovoltaic array arrangement method and device, electronic equipment and storage medium

Abstract

The embodiment of the present disclosure relates to the technical field of photovoltaic array arrangement, and provides a distributed photovoltaic array arrangement method and device, electronic equipment and storage medium, the method comprises: establishing a three-dimensional roof model, determining an unobstructed roof available area in combination with illumination conditions; determining a final roof available area from the unobstructed roof available area based on roof obstacle and eave distance and ridge spacing constraint conditions; arranging a distributed photovoltaic array in the final roof available area according to a preset arrangement rule, to obtain a corresponding initial arrangement scheme; and optimizing the initial arrangement scheme by using a preset optimization algorithm, to obtain a final arrangement scheme. The embodiment of the present disclosure can significantly improve the accuracy and efficiency of roof photovoltaic array arrangement, and is especially suitable for complex distributed scenarios.

Description

Technical Field

[0001] This disclosure relates to the field of photovoltaic array arrangement technology, and in particular to a method and apparatus for arranging distributed photovoltaic arrays, electronic equipment, and storage medium. Background Technology

[0002] The arrangement of photovoltaic (PV) arrays is a core aspect of PV power generation system design, directly impacting PV power generation efficiency, investment costs, and ease of operation and maintenance. With the rapid development of distributed PV, rooftop power stations, due to their limited space, variable shading, and complex building structures, face higher demands on PV array arrangement methods.

[0003] Traditional photovoltaic array deployment methods often rely on human experience and manual operation, which is not only inefficient and prone to errors, but also difficult to adapt to complex scenarios and meet the actual needs of complex scenarios as the scale and complexity of photovoltaic power plants increase.

[0004] With the rapid development of automation and intelligent technologies, automatic arrangement methods for photovoltaic arrays have gradually become a research hotspot. These automatic arrangement methods, by introducing advanced algorithms and technologies, can achieve efficient and accurate arrangement of photovoltaic arrays, thereby improving the overall performance of photovoltaic power generation systems.

[0005] For example, existing automatic layout methods for photovoltaic arrays include rule-based layout methods, intelligent optimization methods, building information modeling (BIM) based layout methods, and layout methods for specific scenarios.

[0006] Rule-based placement methods typically guide the arrangement of photovoltaic arrays by pre-setting a series of rules. While this method can improve placement efficiency to some extent, its pre-set rules are often too simple and fixed, such as only pre-setting fixed rules about spacing, orientation, etc., lacking dynamic adaptability and making it difficult to cope with complex roof structures and dynamic shadow changes, thus failing to adapt to complex and ever-changing application scenarios.

[0007] Intelligent optimization methods have been widely used in the field of photovoltaic array layout in recent years. They can automatically search for the optimal layout scheme based on the actual needs and constraints of the photovoltaic array. Common intelligent optimization methods typically employ genetic algorithms, particle swarm optimization algorithms, and ant colony optimization algorithms. These algorithms have advantages such as strong global search capabilities and good adaptability, and can find high-quality solutions in complex and ever-changing application scenarios. However, they have high computational complexity, are difficult to generate schemes in real time, and have insufficient support for three-dimensional spatial modeling.

[0008] With the popularization of BIM technology, some researchers have begun to explore its application in the automated layout of photovoltaic arrays, leading to BIM-based layout methods. This method, by acquiring the BIM model of the building, can extract its geometric information and spatial relationships, thus providing precise data support for the layout of the photovoltaic array and achieving accurate matching and efficient integration between the array and the building. However, this method relies on Building Information Modeling (BIM), but BIM data acquisition is costly and has poor compatibility with unstructured roofs (such as older buildings).

[0009] For specific scenarios (such as rooftop solar PV and mountain solar PV), some researchers have developed specialized deployment algorithms, resulting in deployment methods tailored to these scenarios. For example, for rooftop solar PV scenarios, researchers have proposed an automatic optimization method and system for rooftop solar array layout. This method achieves efficient deployment of rooftop solar arrays by collecting rooftop point cloud data, simulating shadow occlusion, and automatically setting the orientation and tilt angle of solar panels. However, most of these rooftop solar PV-specific methods are limited to two-dimensional planar analysis and lack three-dimensional spatial avoidance capabilities, leading to problems such as shadow occlusion and component overlap.

[0010] In summary, although existing technologies provide some methods for arranging photovoltaic arrays, there are still some industry pain points in photovoltaic array arrangement, such as low efficiency of manual design, easy to overlook local shading, difficulty in dynamically integrating three-dimensional terrain, building structure and lighting data, and lack of rapid and accurate arrangement tools for distributed rooftop power stations. Summary of the Invention

[0011] This disclosure aims to address at least one of the problems existing in the prior art by providing a method and apparatus for arranging distributed photovoltaic arrays, electronic equipment, and storage media.

[0012] One aspect of this disclosure provides a method for arranging a distributed photovoltaic array, the method comprising:

[0013] Create a 3D roof model and, based on lighting conditions, determine the unobstructed usable area of ​​the roof.

[0014] Based on the constraints of roof obstacles, eaves distance, and ridge spacing, the final usable area of ​​the roof is determined from the unobstructed roof usable area;

[0015] According to the preset layout rules, a distributed photovoltaic array is arranged in the final usable area of ​​the roof to obtain the corresponding initial layout scheme;

[0016] The initial layout scheme is optimized using a preset optimization algorithm to obtain the final layout scheme.

[0017] Optionally, the step of establishing a three-dimensional roof model and determining the unobstructed usable area of ​​the roof, in conjunction with lighting conditions, includes:

[0018] Based on any one or more of the UAV point cloud data, building CAD model, and roof input parameters, establish the three-dimensional roof model and mark the usable roof area.

[0019] Based on the available roof area, the dynamic changes of shadows under different lighting conditions are simulated by three-dimensional ray tracing to generate a light occlusion map for a specified time period.

[0020] The unobstructed roof usable area is obtained by removing the corresponding range of the light occlusion map within a specified time period from the usable roof area.

[0021] Optionally, determining the final usable area of ​​the roof from the unobstructed roof usable area based on roof obstacles and constraints such as eaves distance and ridge spacing includes:

[0022] The roof obstacles in the three-dimensional roof model are labeled to obtain the roof obstacle labeling results;

[0023] The roof obstacle labeling results are input into a convolutional neural network for obstacle boundary recognition to obtain the corresponding obstacle boundary recognition results;

[0024] The boundaries of the layout area are determined based on the constraints of the eaves distance and the ridge spacing.

[0025] Based on the obstacle boundary identification results and the layout area boundary, unusable areas are removed from the unobstructed roof usable area to obtain the final usable area of ​​the roof.

[0026] Optionally, the preset arrangement rules include starting direction selection rules, array unit and electrical matching rules, multi-pattern component adaptation and optimization rules, and gap compensation and secondary filling rules;

[0027] The starting direction selection rules include: using any one of the following to determine the starting direction of the arrangement: unilateral starting mode, symmetrical starting mode, and dynamic selection logic mode;

[0028] The array unit and electrical matching rules include: prioritizing the arrangement of photovoltaic strings as array units, ensuring that each photovoltaic module in the same photovoltaic string has the same orientation and tilt angle, and if the remaining space in the final usable area of ​​the roof is insufficient to arrange the entire photovoltaic string, then adjusting the length of the photovoltaic string or arranging the photovoltaic strings in parallel.

[0029] The multi-module adaptation and optimization rules include: for the currently available area in the final available area of ​​the roof, calculating the densest number and coverage of each module, and using a multi-objective optimization algorithm combined with economic parameters to optimize based on the densest number and coverage, and selecting the comprehensive optimal module scheme.

[0030] The gap compensation and secondary filling rules include: when the photovoltaic modules that have been arranged in the final usable area of ​​the roof are deleted, the corresponding gap boundary is detected, and an attempt is made to fill the empty area corresponding to the gap boundary by reducing the spacing between adjacent photovoltaic modules, while ensuring that the spacing between adjacent photovoltaic modules is not lower than the minimum safety value. If the empty area cannot be filled, the empty area is marked as an area to be optimized; for the remaining narrow space at the edge of the roof in the final usable area of ​​the roof, different arrangement patterns are used for arrangement.

[0031] Optionally, the single-sided starting mode includes: starting from one side edge of the area with the highest roof daylighting efficiency, arranging a distributed photovoltaic array in the final usable area of ​​the roof in a serpentine path;

[0032] The symmetrical starting pattern includes: arranging the roof ridge line or roof center line as the axis of symmetry, and simultaneously arranging the roof in the final usable area from both sides of the axis of symmetry to maximize the use of the symmetrical space of the final usable area of ​​the roof.

[0033] The dynamic selection logic mode includes: selecting the optimal starting mode from the single-sided starting mode and the symmetrical starting mode to arrange the distributed photovoltaic array according to the roof length-to-width ratio and the shape of the final usable area of ​​the roof.

[0034] Optionally, optimizing the initial layout scheme using a preset optimization algorithm to obtain the final layout scheme includes:

[0035] With the goals of maximizing the number of photovoltaic modules, minimizing shading loss, and minimizing cable cost, the particle swarm optimization algorithm is used to adjust the spacing, layout combination, and starting direction of the photovoltaic modules in the initial arrangement scheme to obtain the corresponding solution set.

[0036] According to the Pareto principle, frontier screening is performed to retain the non-dominated solution set in the solution set;

[0037] The layout effect and corresponding indicators of at least one alternative layout scheme corresponding to the non-dominated solution set are displayed to the user, and the alternative layout scheme selected by the user is taken as the final layout scheme.

[0038] Another aspect of this disclosure provides a distributed photovoltaic array arrangement device, the distributed photovoltaic array arrangement device comprising:

[0039] A module is created to build a 3D roof model and, based on lighting conditions, determine the unobstructed usable area of ​​the roof.

[0040] The determination module is used to determine the final usable area of ​​the roof from the unobstructed roof usable area based on roof obstacles and constraints such as eaves distance and ridge spacing;

[0041] The initial layout module is used to arrange the distributed photovoltaic array in the finally available area of ​​the roof according to the preset layout rules, so as to obtain the corresponding initial layout scheme.

[0042] The optimization module is used to optimize the initial layout scheme using a preset optimization algorithm to obtain the final layout scheme.

[0043] Another aspect of this disclosure provides an electronic device comprising:

[0044] At least one processor; and,

[0045] A memory that is communicatively connected to at least one processor; wherein,

[0046] The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform the distributed photovoltaic array arrangement method described above.

[0047] Another aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the distributed photovoltaic array arrangement method described above.

[0048] Another aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the distributed photovoltaic array arrangement method described above.

[0049] Compared with the prior art, this disclosure can achieve adaptive switching of multiple layouts by pre-setting layout rules, and combined with multi-objective dynamic optimization, which can significantly improve the accuracy and efficiency of rooftop photovoltaic array layout, especially suitable for complex distributed scenarios. Attached Figure Description

[0050] One or more embodiments are illustrated by way of example with the corresponding pictures in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0051] Figure 1 A flowchart illustrating a distributed photovoltaic array arrangement method provided in one embodiment of this disclosure;

[0052] Figure 2 A schematic diagram of starting direction selection in a unilateral starting mode provided for another embodiment of this disclosure;

[0053] Figure 3 A schematic diagram of starting direction selection in a symmetrical starting mode provided for another embodiment of this disclosure;

[0054] Figure 4 A schematic diagram of a distributed photovoltaic array arrangement device provided for another embodiment of this disclosure;

[0055] Figure 5 A schematic diagram of the structure of an electronic device provided in another embodiment of this disclosure. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the various embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details have been provided in the various embodiments of this disclosure to facilitate a better understanding of the disclosure. However, the technical solutions claimed in this disclosure can be implemented even without these technical details and with various variations and modifications based on the following embodiments. The division of the various embodiments below is for ease of description and should not constitute any limitation on the specific implementation of this disclosure. The various embodiments can be combined with and referenced by each other without contradiction.

[0057] One embodiment of this disclosure relates to a method for arranging a distributed photovoltaic array, the process of which is as follows: Figure 1 As shown, it includes steps S110 to S140.

[0058] Step S110: Establish a three-dimensional roof model and determine the unobstructed usable area of ​​the roof based on the lighting conditions.

[0059] Specifically, step S110 mainly involves creating a three-dimensional model of the roof used to arrange the distributed photovoltaic array, performing a statistical analysis of the available areas, and determining the areas that are not shaded under sunlight.

[0060] For example, step S110 includes: establishing a three-dimensional roof model based on any one or more of the UAV point cloud data, building CAD model, and roof input parameters, and marking the usable roof area; generating a light occlusion map for a specified time period by simulating the dynamic changes of shadows under different lighting conditions through three-dimensional ray tracing based on the usable roof area; and removing the corresponding area of ​​the light occlusion map for the specified time period from the usable roof area to obtain the unoccupied usable roof area.

[0061] Specifically, after obtaining the three-dimensional roof model, the usable roof area can be marked to determine the unobstructed roof area.

[0062] Step S120: Based on the constraints of roof obstacles, eaves distance, and ridge spacing, determine the final usable area of ​​the roof from the unobstructed usable area of ​​the roof.

[0063] Specifically, step S120 mainly involves intelligently identifying unusable areas and combining this with the unobstructed roof usable areas determined in step S110 to determine the final usable area of ​​the roof.

[0064] For example, step S120 includes: annotating the roof obstacles in the three-dimensional roof model to obtain the roof obstacle annotation results; inputting the roof obstacle annotation results into a convolutional neural network to perform obstacle boundary recognition to obtain the corresponding obstacle boundary recognition results; determining the layout area boundary based on the eaves distance and ridge spacing constraints; and removing unusable areas from the unobstructed roof usable area based on the obstacle boundary recognition results and the layout area boundary to obtain the final usable roof area.

[0065] Specifically, when intelligently identifying unusable areas, the input data includes roof obstacle labeling results, eaves distance, and ridge spacing constraints. The roof obstacle labeling results are input into a convolutional neural network (CNN), which identifies obstacle boundaries and outputs the obstacle boundary identification results. The eaves distance and ridge spacing constraints are used to determine the boundaries of the layout area. The ridge spacing constraints can be obtained through an interactive interface based on user input. After obtaining the obstacle boundary identification results and the layout area boundaries, the areas containing the obstacles and the layout area boundaries are removed from the unobstructed roof usable areas as unusable areas, thus obtaining the final usable roof area.

[0066] Step S130: According to the preset layout rules, the distributed photovoltaic array is arranged in the final usable area of ​​the roof to obtain the corresponding initial layout scheme.

[0067] Specifically, the preset layout rules can be set according to actual needs.

[0068] For example, the preset layout rules include starting direction selection rules, array unit and electrical compatibility rules, multi-pattern component adaptation and optimization rules, and gap compensation and secondary filling rules.

[0069] The starting direction selection rules include: using any one of the following to determine the starting direction of the arrangement: unilateral starting mode, symmetrical starting mode, or dynamic selection logic mode.

[0070] One-sided initiation mode can include starting from one edge of the area with the highest daylighting efficiency on the roof and arranging distributed photovoltaic arrays along a serpentine path throughout the ultimately usable area of ​​the roof. For example, it can be combined with... Figure 2 When the eaves are located on the south side of the ridge, the area with the highest roof lighting efficiency is usually the south-facing slope of the roof. In this case, the single-sided starting mode can be applied from one edge of the south-facing slope of the roof, such as... Figure 2 The edge of the roof or Figure 2 Starting from the eaves, a distributed photovoltaic array is filled into the final usable area of ​​the roof following a serpentine path in the direction of the arrow.

[0071] Symmetrical starting patterns include: arranging elements synchronously on both sides of the ridgeline or roof centerline as an axis of symmetry within the final usable area of ​​the roof, maximizing the use of the symmetrical space within that area. For example, combining... Figure 3 A symmetrical starting pattern can be arranged synchronously on both sides of the roof centerline, with the roof centerline as the axis of symmetry. For example, ... Figure 3 As shown, the symmetrical start-up mode can arrange distributed photovoltaic arrays simultaneously from the roof edges on both sides of the roof centerline towards the roof centerline in the ultimately usable area of ​​the roof, along the direction of the arrow. Alternatively, the symmetrical start-up mode can also arrange distributed photovoltaic arrays simultaneously from the roof centerline towards the roof edges on both sides in the ultimately usable area of ​​the roof; those skilled in the art can choose according to actual needs.

[0072] The dynamic selection logic mode includes: choosing the optimal starting mode from single-sided starting mode and symmetrical starting mode for the arrangement of distributed photovoltaic arrays based on the roof's aspect ratio and the shape of the final usable area of ​​the roof. Users can also choose to use either the single-sided starting mode or the symmetrical starting mode themselves.

[0073] The array unit and electrical matching rules include: prioritizing the arrangement of photovoltaic (PV) strings as array units, ensuring that all PV modules within the same PV string face the same direction and tilt angle to reduce circuit losses. If the remaining space in the ultimately usable roof area is insufficient to accommodate the entire PV string, the length of the PV string is adjusted or the PV strings are arranged in parallel. Each PV string typically contains several PV modules. The number of PV modules contained in a PV string is the length of that PV string. For example, a PV string can contain 20 PV modules; in this case, the length of the PV string is 20. Specifically, areas where the length of the PV strings is adjusted or where PV strings are arranged in parallel can be marked as non-standard areas to distinguish them from areas with normal arrangement.

[0074] The multi-module adaptation and optimization rules include: for the currently available area within the final usable area of ​​the rooftop, calculating the densest arrangement quantity and coverage rate of each module type; and optimizing the selection based on the densest arrangement quantity and coverage rate using a multi-objective optimization algorithm combined with economic parameters to choose the overall optimal module scheme. Existing module types, including module dimensions and efficiency parameters, can be stored in a pre-set module type database, while also supporting user-defined additions. Different module types can have different dimensions. For example, module dimensions for different types may include, but are not limited to, 2.382m × 1.134m and 2.278m × 1.134m. Economic parameters may include, but are not limited to, module cost, power generation efficiency, and cable length. For instance, the multi-objective optimization algorithm can employ the Non-dominated Sorting Genetic Algorithm II (NSGA-II). Of course, those skilled in the art can also choose other types of multi-objective optimization algorithms, and this implementation is not limited in this regard.

[0075] The gap compensation and secondary filling rules include: when photovoltaic modules already arranged in the final usable area of ​​the roof are deleted, the corresponding gap boundary is detected, and an attempt is made to fill the empty area corresponding to the gap boundary by reducing the spacing between adjacent photovoltaic modules, while ensuring that the spacing between adjacent photovoltaic modules is not lower than the minimum safety value. If the empty area cannot be filled, the empty area is marked as an area to be optimized. For the remaining narrow space at the edge of the roof in the final usable area of ​​the roof, different arrangement modes are used. Among them, the arrangement of photovoltaic arrays in the area to be optimized can be manually intervened or the module layout can be adjusted. Different arrangement modes include, but are not limited to, vertical and horizontal arrangement modes. For example, for the remaining narrow space at the edge of the roof in the final usable area of ​​the roof, the initial vertical arrangement mode can be changed to a horizontal arrangement mode to improve the utilization rate of the remaining narrow space.

[0076] After the above arrangement rules are determined, step S130 can complete the arrangement of the distributed photovoltaic array according to these arrangement rules, obtain the corresponding initial arrangement scheme, and also perform three-dimensional visualization display of the initial arrangement scheme and count the number of photovoltaic modules involved.

[0077] By pre-setting layout rules, safety logic such as window avoidance and edge constraints can be implemented through rule-driven automation. Flexible adaptation can be achieved through deep collaboration between symmetrical / asymmetrical layout strategies and photovoltaic string design.

[0078] Step S140: Optimize the initial layout scheme using a preset optimization algorithm to obtain the final layout scheme.

[0079] For example, step S140 may include: adjusting the spacing, layout combination, and starting direction of the photovoltaic modules in the initial layout scheme with the goal of maximizing the number of photovoltaic modules, minimizing shading loss, and minimizing cable cost through a particle swarm optimization algorithm to obtain the corresponding solution set; performing frontier screening according to the Pareto principle to retain the non-dominated solution set; displaying the layout effect and corresponding indicators of at least one alternative layout scheme corresponding to the non-dominated solution set to the user, and using the alternative layout scheme selected by the user as the final layout scheme.

[0080] Specifically, maximizing the number of photovoltaic (PV) modules represents the total number of PV modules covering the final usable area of ​​the roof, denoted as N. Minimizing shading loss represents the proportion of power generation efficiency reduction caused by shading under winter solstice sunlight, denoted as L. Minimizing cable cost represents the total length of cables required to connect each PV string, denoted as C. When optimizing the initial layout, the values ​​of N, L, and C are first calculated. Then, a neighborhood search is performed, and the spacing, panel combination, and starting direction of the PV modules are adjusted using a particle swarm optimization algorithm to obtain the corresponding solution set. Subsequently, the Pareto principle is used for frontier screening, retaining the non-dominated solution set obtained from the particle swarm optimization algorithm. This achieves intelligent optimization from "single coverage" to "multi-objective balance." Users can select the final layout scheme from the alternative layout schemes corresponding to the non-dominated solution set based on their preferences.

[0081] In particular, after each adjustment to the layout plan, the layout effect and layout indicators can be updated in real time using the 3D platform, allowing users to optimize the layout plan through interactive means.

[0082] The distributed photovoltaic array arrangement method provided in this disclosure, compared with the prior art, can achieve adaptive switching of multiple layouts by pre-setting arrangement rules, and combined with multi-objective dynamic optimization, can significantly improve the accuracy and efficiency of rooftop photovoltaic array arrangement, and is especially suitable for complex distributed scenarios.

[0083] Another embodiment of this disclosure relates to a distributed photovoltaic array arrangement device, such as Figure 4 As shown, it includes a setup module 410, a determination module 420, an initial layout module 430, and an optimization module 440.

[0084] Module 410 is used to create a three-dimensional roof model and, in conjunction with lighting conditions, determine the unobstructed usable area of ​​the roof.

[0085] The determination module 420 is used to determine the final usable area of ​​the roof from the unobstructed usable area of ​​the roof based on roof obstacles and constraints such as eaves distance and ridge spacing.

[0086] The initial layout module 430 is used to arrange the distributed photovoltaic array in the final usable area of ​​the roof according to the preset layout rules, so as to obtain the corresponding initial layout scheme.

[0087] The optimization module 440 is used to optimize the initial layout scheme using a preset optimization algorithm to obtain the final layout scheme.

[0088] For a detailed implementation method of the distributed photovoltaic array arrangement device provided in this disclosure, please refer to the distributed photovoltaic array arrangement method provided in this disclosure, which will not be repeated here.

[0089] The distributed photovoltaic array arrangement device provided in this disclosure, compared with the prior art, can achieve adaptive switching of multiple layouts by pre-setting arrangement rules, and combined with multi-objective dynamic optimization, can significantly improve the accuracy and efficiency of rooftop photovoltaic array arrangement, and is especially suitable for complex distributed scenarios.

[0090] Another embodiment of this disclosure relates to an electronic device, such as Figure 5 As shown, it includes:

[0091] At least one processor 501; and,

[0092] Memory 502 is communicatively connected to at least one processor 501; wherein,

[0093] The memory 502 stores instructions that can be executed by at least one processor 501, which enables the at least one processor 501 to perform the distributed photovoltaic array arrangement method described in the above embodiments.

[0094] The memory and processor are connected via a bus, which can include any number of interconnecting buses and bridges, connecting various circuits of one or more processors and memories. The bus can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and will not be described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over the wireless medium via an antenna, which further receives data and transmits it to the processor.

[0095] The processor manages the bus and general processing, and also provides various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory is used to store data used by the processor during operation.

[0096] Another embodiment of this disclosure relates to a computer-readable storage medium storing a computer program that, when executed by a processor, implements the distributed photovoltaic array arrangement method described in the above embodiments.

[0097] That is, those skilled in the art will understand that all or part of the steps in the methods described in the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0098] Another embodiment of this disclosure relates to a computer program product, including a computer program that, when executed by a processor, implements the distributed photovoltaic array arrangement method described in the above embodiments.

[0099] Those skilled in the art will understand that the above embodiments are specific implementations of this disclosure, and in practical applications, various changes can be made to them in form and detail without departing from the spirit and scope of this disclosure.

Claims

1. A method for arranging a distributed photovoltaic array, characterized in that, The distributed photovoltaic array arrangement method includes: Create a 3D roof model and, based on lighting conditions, determine the unobstructed usable area of ​​the roof. Based on the constraints of roof obstacles, eaves distance, and ridge spacing, the final usable area of ​​the roof is determined from the unobstructed roof usable area; According to the preset layout rules, a distributed photovoltaic array is arranged in the final usable area of ​​the roof to obtain the corresponding initial layout scheme; The initial layout scheme is optimized using a preset optimization algorithm to obtain the final layout scheme; The preset layout rules include starting direction selection rules, array unit and electrical matching rules, multi-pattern component adaptation and optimization rules, and gap compensation and secondary filling rules. The starting direction selection rules include: using any one of the following to determine the starting direction of the arrangement: unilateral starting mode, symmetrical starting mode, and dynamic selection logic mode; The array unit and electrical matching rules include: prioritizing the arrangement of photovoltaic strings as array units, ensuring that each photovoltaic module in the same photovoltaic string has the same orientation and tilt angle, and if the remaining space in the final usable area of ​​the roof is insufficient to arrange the entire photovoltaic string, then adjusting the length of the photovoltaic string or arranging the photovoltaic strings in parallel. The multi-module adaptation and optimization rules include: for the currently available area in the final available area of ​​the roof, calculating the densest number and coverage of each module, and using a multi-objective optimization algorithm combined with economic parameters to optimize based on the densest number and coverage, and selecting the comprehensive optimal module scheme. The gap compensation and secondary filling rules include: when the photovoltaic modules that have been arranged in the final usable area of ​​the roof are deleted, the corresponding gap boundary is detected, and an attempt is made to fill the empty area corresponding to the gap boundary by reducing the spacing between adjacent photovoltaic modules, while ensuring that the spacing between adjacent photovoltaic modules is not lower than the minimum safety value. If the empty area cannot be filled, the empty area is marked as an area to be optimized; for the remaining narrow space at the edge of the roof in the final usable area of ​​the roof, different arrangement patterns are used for arrangement. The step of optimizing the initial layout scheme using a preset optimization algorithm to obtain the final layout scheme includes: With the goals of maximizing the number of photovoltaic modules, minimizing shading loss, and minimizing cable cost, the particle swarm optimization algorithm is used to adjust the spacing, layout combination, and starting direction of the photovoltaic modules in the initial arrangement scheme to obtain the corresponding solution set. According to the Pareto principle, frontier screening is performed to retain the non-dominated solution set in the solution set; The layout effect and corresponding indicators of at least one alternative layout scheme corresponding to the non-dominated solution set are displayed to the user, and the alternative layout scheme selected by the user is taken as the final layout scheme.

2. The distributed photovoltaic array arrangement method according to claim 1, characterized in that, The process of establishing a three-dimensional roof model and determining the unobstructed usable area of ​​the roof, based on lighting conditions, includes: Based on any one or more of the UAV point cloud data, building CAD model, and roof input parameters, establish the three-dimensional roof model and mark the usable roof area. Based on the available roof area, the dynamic changes of shadows under different lighting conditions are simulated by three-dimensional ray tracing to generate a light occlusion map for a specified time period. The unobstructed roof usable area is obtained by removing the corresponding range of the light occlusion map within a specified time period from the usable roof area.

3. The distributed photovoltaic array arrangement method according to claim 1, characterized in that, The determination of the final usable area of ​​the roof from the unobstructed roof usable area, based on constraints such as roof obstacles, eaves distance, and ridge spacing, includes: The roof obstacles in the three-dimensional roof model are labeled to obtain the roof obstacle labeling results; The roof obstacle labeling results are input into a convolutional neural network for obstacle boundary recognition to obtain the corresponding obstacle boundary recognition results; The boundaries of the layout area are determined based on the constraints of the eaves distance and the ridge spacing. Based on the obstacle boundary identification results and the layout area boundary, unusable areas are removed from the unobstructed roof usable area to obtain the final usable area of ​​the roof.

4. The distributed photovoltaic array arrangement method according to claim 1, characterized in that, The single-sided initiation mode includes: starting from the single edge of the area with the highest roof light-gathering efficiency, and arranging the distributed photovoltaic array in the final usable area of ​​the roof in a serpentine path; The symmetrical starting pattern includes: arranging the roof ridge line or roof center line as the axis of symmetry, and simultaneously arranging the roof in the final usable area from both sides of the axis of symmetry to maximize the use of the symmetrical space of the final usable area of ​​the roof. The dynamic selection logic mode includes: selecting the optimal starting mode from the single-sided starting mode and the symmetrical starting mode to arrange the distributed photovoltaic array according to the roof length-to-width ratio and the shape of the final usable area of ​​the roof.

5. A distributed photovoltaic array arrangement device, characterized in that, The distributed photovoltaic array arrangement device includes: A module is created to build a 3D roof model and, based on lighting conditions, determine the unobstructed usable area of ​​the roof. The determination module is used to determine the final usable area of ​​the roof from the unobstructed roof usable area based on roof obstacles and constraints such as eaves distance and ridge spacing; The initial layout module is used to arrange the distributed photovoltaic array in the finally available area of ​​the roof according to the preset layout rules, so as to obtain the corresponding initial layout scheme. An optimization module is used to optimize the initial layout scheme using a preset optimization algorithm to obtain the final layout scheme; The preset layout rules include starting direction selection rules, array unit and electrical matching rules, multi-pattern component adaptation and optimization rules, and gap compensation and secondary filling rules. The starting direction selection rules include: using any one of the following to determine the starting direction of the arrangement: unilateral starting mode, symmetrical starting mode, and dynamic selection logic mode; The array unit and electrical matching rules include: prioritizing the arrangement of photovoltaic strings as array units, ensuring that each photovoltaic module in the same photovoltaic string has the same orientation and tilt angle, and if the remaining space in the final usable area of ​​the roof is insufficient to arrange the entire photovoltaic string, then adjusting the length of the photovoltaic string or arranging the photovoltaic strings in parallel. The multi-module adaptation and optimization rules include: for the currently available area in the final available area of ​​the roof, calculating the densest number and coverage of each module, and using a multi-objective optimization algorithm combined with economic parameters to optimize based on the densest number and coverage, and selecting the comprehensive optimal module scheme. The gap compensation and secondary filling rules include: when the photovoltaic modules that have been arranged in the final usable area of ​​the roof are deleted, the corresponding gap boundary is detected, and an attempt is made to fill the empty area corresponding to the gap boundary by reducing the spacing between adjacent photovoltaic modules, while ensuring that the spacing between adjacent photovoltaic modules is not lower than the minimum safety value. If the empty area cannot be filled, the empty area is marked as an area to be optimized; for the remaining narrow space at the edge of the roof in the final usable area of ​​the roof, different arrangement patterns are used for arrangement. The step of optimizing the initial layout scheme using a preset optimization algorithm to obtain the final layout scheme includes: With the goals of maximizing the number of photovoltaic modules, minimizing shading loss, and minimizing cable cost, the particle swarm optimization algorithm is used to adjust the spacing, layout combination, and starting direction of the photovoltaic modules in the initial arrangement scheme to obtain the corresponding solution set. According to the Pareto principle, frontier screening is performed to retain the non-dominated solution set in the solution set; The layout effect and corresponding indicators of at least one alternative layout scheme corresponding to the non-dominated solution set are displayed to the user, and the alternative layout scheme selected by the user is taken as the final layout scheme.

6. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the distributed photovoltaic array arrangement method according to any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the distributed photovoltaic array arrangement method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the distributed photovoltaic array arrangement method according to any one of claims 1 to 4.

Images