Highway engineering photovoltaic equipment layout optimization method based on solar energy conversion efficiency

Abstract

The invention relates to a highway engineering photovoltaic equipment layout optimization method based on solar energy conversion efficiency, and relates to the field of photovoltaic equipment layout optimization, and the method comprises the steps: carrying out the random layout of a preset photovoltaic module in a constraint region, and obtaining two groups of layout information and corresponding position and angle parameters; and comparing the two groups of positions to obtain a difference irradiation prediction model, and analyzing to obtain two groups of predicted irradiance. And sorting the two groups of layout information according to irradiance, and updating a sorting result. And when the convergence condition is met, configuring a layout scheme according to the sorting result, and managing the layout of the road photovoltaic equipment. The technical problem of low optimization efficiency caused by complex irradiance analysis in the layout optimization of the highway engineering photovoltaic equipment in the prior art is solved, the photovoltaic modules in different layout modes are compared in pairs, only different irradiation types are analyzed, and the optimization efficiency of the highway engineering photovoltaic equipment is improved on the premise of ensuring the layout optimization effect of the photovoltaic equipment. The calculation complexity is simplified, and the technical effect of improving the layout optimization efficiency of the highway engineering photovoltaic equipment is achieved.

Description

Technical Field

[0001] The invention relates to the field of photovoltaic equipment layout optimization, and in particular to a highway engineering photovoltaic equipment layout optimization method based on solar energy conversion efficiency. Background Art

[0002] In the prior art, the optimization of photovoltaic equipment layout for highway projects usually requires comprehensive irradiance analysis of the entire photovoltaic equipment group to evaluate its solar energy conversion efficiency. However, due to the strong nonlinear characteristics of irradiance analysis, the calculation process is complex and requires high computing power. Especially in the optimization of photovoltaic equipment layout for large-scale highway projects, traditional methods often lead to low processing efficiency and the optimization speed is difficult to meet the actual application requirements.

[0003] In view of the above problems, the existing technology has proposed some improvement schemes. For example, a simplified irradiance model is adopted to improve the computational efficiency by sacrificing a certain degree of accuracy; or parallel computing technology is used to perform irradiance analysis through multiple processing units at the same time to shorten the overall optimization time. However, these schemes are insufficient in optimization effect or have limitations in implementation cost and complexity.

[0004] Therefore, how to improve the optimization efficiency and simplify the calculation complexity while ensuring the optimization effect of photovoltaic equipment layout has become an urgent problem to be solved in the field of photovoltaic equipment layout optimization in highway engineering. Summary of the invention

[0005] The present invention aims to solve the technical problem of low optimization efficiency due to complex irradiance analysis in the existing highway engineering photovoltaic equipment layout optimization, and provides a highway engineering photovoltaic equipment layout optimization method based on solar energy conversion efficiency.

[0006] The technical solution of the present invention to solve the above technical problems is as follows:

[0007] The present invention provides a method for optimizing the layout of photovoltaic equipment for highway engineering based on solar energy conversion efficiency, comprising: randomly arranging photovoltaic modules of preset models based on the horizontal layout constraint area and the vertical layout constraint area of ​​the photovoltaic equipment layout constraint area for highway engineering, obtaining first photovoltaic module layout information and second photovoltaic module layout information; obtaining a first layout position, a first layout inclination angle, and a first layout azimuth of the first photovoltaic module layout information, and obtaining a second layout position, a second layout inclination angle, and a second layout azimuth of the second photovoltaic module layout information; performing differential irradiation type configuration according to the first layout position and the second layout position, obtaining a differential irradiance prediction model; and configuring a differential irradiance prediction model according to the differential irradiance. An illumination prediction model is used to perform an irradiance analysis based on the first layout position, the first layout inclination angle, and the first layout azimuth to obtain a first predicted irradiance; according to the differential irradiance prediction model, an irradiance analysis is performed based on the second layout position, the second layout inclination angle, and the second layout azimuth to obtain a second predicted irradiance; according to the first predicted irradiance and the second predicted irradiance, the first photovoltaic component layout information and the second photovoltaic component layout information are updated from large to small to sort the layout information; when the photovoltaic component layout information meets the preset convergence conditions, a photovoltaic layout plan is configured based on the layout information sorting result to perform photovoltaic equipment layout management for highway projects.

[0008] The beneficial effects of the present invention are as follows: based on the horizontal layout constraint area and the vertical layout constraint area of ​​the photovoltaic equipment layout constraint area of ​​the highway project, the preset model photovoltaic components are randomly laid out, the first photovoltaic component layout information and the second photovoltaic component layout information are obtained, and two layout schemes of single photovoltaic components are obtained, which can be two photovoltaic components in different positions, or two component layout methods with different layout angles in the same position, providing a basis for subsequent comparison and optimization. The first layout position, the first layout inclination angle, and the first layout azimuth of the first photovoltaic component layout information are obtained, and the second layout position, the second layout inclination angle, and the second layout azimuth of the second photovoltaic component layout information are obtained to prepare for the subsequent irradiance analysis. Differential irradiation type configuration is performed according to the first layout position and the second layout position to obtain a differential irradiance prediction model, and by comparing the position difference of the two layout schemes, the differentiated area that needs to be analyzed for irradiance is determined, and a corresponding prediction model is established, thereby reducing unnecessary calculations. According to the differential irradiance prediction model, an irradiance analysis is performed based on the first layout position, the first layout inclination angle, and the first layout azimuth to obtain the first predicted irradiance. The differential irradiance prediction model is used to predict the irradiance of the first photovoltaic module layout information to obtain the corresponding irradiance estimation value. According to the differential irradiance prediction model, an irradiance analysis is performed based on the second layout position, the second layout inclination angle, and the second layout azimuth to obtain the second predicted irradiance. Similarly, an irradiance prediction is performed on the second photovoltaic module layout information to obtain the corresponding estimation value. According to the first predicted irradiance and the second predicted irradiance, the layout information of the first photovoltaic module layout information and the second photovoltaic module layout information are updated from large to small to sort the layout information. By comparing the irradiance prediction results of the two layout schemes, they are sorted to select a layout scheme with larger irradiance and higher solar energy conversion efficiency. When the layout information of the photovoltaic module meets the preset convergence conditions, the photovoltaic layout scheme is configured based on the layout information sorting results to carry out the layout management of photovoltaic equipment in highway engineering. By comparing photovoltaic modules with different layouts in pairs and analyzing only the different irradiation types, the calculation complexity is significantly reduced and the optimization efficiency is improved while ensuring the optimization effect of photovoltaic equipment layout. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic diagram of the process of optimizing the layout of photovoltaic equipment for highway projects based on solar energy conversion efficiency provided by the present invention;

[0010] Figure 2 A schematic diagram of the structure of an electronic device provided by the present invention;

[0011] Figure 3 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0012] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0013] Electronic device 100 , memory 110 , processor 120 , first computer program 111 , computer-readable storage medium 200 , second computer program 211 . DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0015] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0016] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0017] Embodiment 1:

[0018] like Figure 1 As shown, the embodiment of the present invention provides a method for optimizing the layout of photovoltaic equipment in highway engineering based on solar energy conversion efficiency, including:

[0019] S100: Based on the horizontal layout constraint area and the vertical layout constraint area of ​​the highway engineering photovoltaic equipment layout constraint area, randomly layout the preset model photovoltaic modules to obtain first photovoltaic module layout information and second photovoltaic module layout information.

[0020] Specifically, the layout constraint area of ​​PV equipment in highway projects is a three-dimensional space area delineated according to the actual situation of highway projects, and PV modules need to be reasonably arranged within this area. First, based on the layout constraint area of ​​PV equipment in highway projects, the horizontal layout constraint area and the vertical layout constraint area are divided as optional installation spaces for optimizing the layout of PV modules. Among them, the horizontal layout constraint area and the vertical layout constraint area are determined according to the actual situation of highway projects. They can be areas suitable for installing PV modules, such as both sides of the highway, roadbed slopes, and interchanges. By clarifying the layout boundaries in the horizontal and vertical directions, the layout constraints can be more specific and quantified.

[0021] After determining the horizontal layout constraint area and the vertical layout constraint area, a preset model of photovoltaic modules is selected as the object to be laid out. The preset model of photovoltaic modules has standard parameters such as dimensions, rated power, and conversion efficiency. By selecting a specific model of modules as the layout object, the advantages and disadvantages of different layout methods can be evaluated under the same specifications.

[0022] Then, the preset photovoltaic modules are randomly arranged in the constraint area, and two different photovoltaic module layouts are automatically generated, which can be two photovoltaic modules in different positions, or two module layouts in the same position with different layout angles. For example, a random number generation function is used to randomly generate the installation position coordinates, orientation angles (azimuths), inclinations and other layout parameters of two groups of photovoltaic modules within the horizontal and vertical layout constraint areas, thereby forming the first photovoltaic module layout information and the second photovoltaic module layout information.

[0023] By pre-delineating the layout constraint areas in the horizontal and vertical directions and randomly laying out specific types of photovoltaic modules in them, two sets of photovoltaic module layout information are automatically generated, providing a variety of alternative solutions for subsequent comparative optimization, which is the basis for achieving high-efficiency photovoltaic array layout.

[0024] S200: Obtain a first layout position, a first layout inclination angle, and a first layout azimuth angle of the first photovoltaic assembly layout information, and obtain a second layout position, a second layout inclination angle, and a second layout azimuth angle of the second photovoltaic assembly layout information.

[0025] Specifically, after obtaining the first photovoltaic component layout information and the second photovoltaic component layout information, first, extract the first layout position coordinates, the first layout inclination angle and the first layout azimuth angle data of the photovoltaic component under the layout mode from the first photovoltaic component layout information. Among them, the first layout position refers to the spatial coordinates of the photovoltaic component within the three-dimensional constraint area, expressed in the form of longitude and latitude, elevation or relative coordinate system, and is used to determine the horizontal and vertical position of the component. The first layout inclination angle refers to the angle between the photovoltaic component and the horizontal plane. During actual installation, the inclination angle can be optimized according to local latitude, terrain and other factors so that the component can receive more solar radiation. The first layout azimuth angle refers to the deflection angle of the projection of the photovoltaic component on the horizontal plane, indicating the orientation of the component. Generally, the south direction is 0°, and the clockwise direction is positive.

[0026] Similarly, from the second photovoltaic module layout information, the second layout position, second layout inclination angle and second layout azimuth of the photovoltaic module under the layout mode are also extracted. Through information extraction, the two sets of random layout information are further parsed into a series of specific position and angle parameters, which describe the spatial state of the photovoltaic module in the three-dimensional layout constraint area.

[0027] By extracting the specific position and angle parameters of PV modules from the PV module layout information, the spatial properties of PV modules are quantitatively described, and two groups of alternative random layout schemes are represented in a structured data form, providing the necessary data basis for subsequent steps such as irradiance prediction and layout optimization.

[0028] S300: Perform differential irradiance type configuration according to the first layout position and the second layout position to obtain a differential irradiance prediction model.

[0029] Specifically, the first layout position and the second layout position are key parameters for describing the spatial distribution of photovoltaic modules in the first photovoltaic module layout information and the second photovoltaic module layout information. By comparing the position coordinates of the photovoltaic modules in the two sets of layouts, the differences in the spatial distribution of the two sets of layouts can be found. In actual photovoltaic power generation application scenarios, the solar radiation received by photovoltaic modules at different positions may be different in type and intensity, mainly reflected in direct radiation, scattered radiation and reflected radiation. Among them, direct radiation refers to the direct radiation of sunlight at a certain incident angle directly hitting the surface of the photovoltaic module. Photovoltaic modules at different positions and angles will receive different direct radiation intensities; scattered radiation refers to the scattering of sunlight in the atmosphere and clouds, and the scattered light in all directions eventually hits the surface of the photovoltaic module. The spatial distribution of scattered radiation is relatively uniform, but there will still be certain differences at different positions; reflected radiation refers to the reflection of sunlight after it hits the ground or other objects. The intensity distribution of reflected radiation may be different for photovoltaic modules at different positions due to differences in the surrounding environment and terrain.

[0030] Therefore, according to the difference between the first layout position and the second layout position, the differences between the two groups of photovoltaic modules in direct irradiation, scattered irradiation, and reflected irradiation are judged, and the irradiance difference type that has a greater impact on the efficiency of the two groups of layouts is identified to form a configuration result of the differential irradiation type. After clarifying the irradiance difference type of the two groups of layouts, the corresponding differential irradiance prediction model is selected. The so-called differential irradiance prediction model refers to a pre-established parameterized mathematical model for a specific irradiance difference type. By inputting parameters such as the position and angle of the photovoltaic module, the irradiance distribution characteristics of the module can be quickly predicted.

[0031] By utilizing the differences in spatial distribution of the two groups of random layouts, the main types of irradiance differences are identified, and a targeted irradiance prediction model is called to simplify the subsequent irradiance analysis process. While ensuring the prediction accuracy, redundant calculation operations are avoided, and the evaluation efficiency of the layout scheme is improved.

[0032] S400: Performing irradiance analysis based on the differential irradiance prediction model and the first layout position, the first layout inclination angle, and the first layout azimuth angle to obtain a first predicted irradiance.

[0033] Specifically, the three parameters of the first layout position, the first layout tilt angle, and the first layout azimuth fully describe the spatial properties of the photovoltaic modules in the first group of random layouts. Among them, the first layout position determines the installation position coordinates of the photovoltaic module in the three-dimensional constraint area; the first layout tilt angle represents the angle between the photovoltaic module and the horizontal plane, which affects the effective receiving area of ​​solar radiation; the first layout azimuth represents the orientation of the photovoltaic module on the horizontal plane projection, which is related to the radiation amount at different time periods.

[0034] These parameters of the first layout group (first layout position, first layout inclination angle, first layout azimuth angle) are input into the differential irradiance prediction model. For the photovoltaic modules of this layout, quantitative analysis and calculation are performed from three aspects: direct irradiation, scattered irradiation, and reflected irradiation. The irradiance intensity that the photovoltaic modules can receive under this layout condition is predicted to obtain the first predicted irradiance. Among them, the differential irradiance prediction model is selected based on the difference in the two layout positions. Since the model fully considers the differences in irradiance distribution of layouts at different positions, it can predict the key irradiance influencing factors in a targeted manner, so it can efficiently complete the irradiance analysis task of the first layout group with high accuracy.

[0035] By utilizing the differential irradiance prediction model, based on the specific layout parameters of the first group of random layouts, such as position, inclination, azimuth, etc., the irradiance prediction value of the photovoltaic modules under this layout is obtained, which provides an important basis for subsequent layout evaluation and screening.

[0036] S500: Performing irradiance analysis based on the second layout position, the second layout inclination angle, and the second layout azimuth angle according to the differential irradiance prediction model to obtain a second predicted irradiance.

[0037] Specifically, the differential irradiance prediction model will derive the irradiance distribution prediction of the photovoltaic components based on the position coordinates, inclination angle, azimuth orientation and other parameters of the photovoltaic components in the second layout (i.e., the second layout position, the second layout inclination angle, and the second layout azimuth), and obtain the second predicted irradiance.

[0038] Since the two groups of random layouts differ in spatial distribution characteristics, the specific parameters of the second group of layouts are used as input, and the irradiance prediction results obtained will also have a certain deviation from the first predicted irradiance, reflecting the impact of different layout methods on photovoltaic power generation efficiency, and providing a reference for subsequent comparison and optimization of layout plans. In the subsequent stages, based on the two quantitative indicators of the first predicted irradiance and the second predicted irradiance, it can be determined which group of layout plans can achieve better photovoltaic power generation efficiency, thereby guiding the optimization and screening of layout plans.

[0039] Predicting two different groups of random layouts through the differential irradiance prediction model can better adapt to different layout conditions, improve the accuracy of irradiance prediction, and provide key data support for the optimized layout of photovoltaic arrays.

[0040] S600: updating a layout information sorting result of the first photovoltaic assembly layout information and the second photovoltaic assembly layout information from large to small according to the first predicted irradiance and the second predicted irradiance.

[0041] Specifically, the first predicted irradiance and the second predicted irradiance reflect the photovoltaic power generation efficiency corresponding to the two groups of layout schemes. Therefore, next, the two groups of random layouts are ranked according to the predicted irradiance, and a relatively better layout scheme is selected.

[0042] First, the order of merit of the two groups of layouts is determined according to the numerical values ​​of the first predicted irradiance and the second predicted irradiance. If the first predicted irradiance is greater than the second predicted irradiance, it indicates that the first group of random layout schemes can obtain higher photovoltaic power generation efficiency, and thus has a higher priority; otherwise, the second group of layout schemes has a higher priority. According to the above comparison results, the first photovoltaic module layout information and the second photovoltaic module layout information are sorted in descending order of predicted irradiance. The layout information corresponding to the larger predicted irradiance is ranked first, and the layout information corresponding to the smaller predicted irradiance is ranked later. Through the sorting process, the order of merit of the two groups of layout schemes is quantified into an ordered sequence, which is recorded as the layout information sorting result.

[0043] By comparing the two quantitative indicators of the first predicted irradiance and the second predicted irradiance, the pros and cons of the two groups of random layout schemes were established, and the layout information sorting results were updated. This intuitively reflected the differences in photovoltaic power generation efficiency obtained by using different layout methods of photovoltaic components, laying the foundation for ultimately determining the optimal layout scheme for actual engineering.

[0044] S700: When the layout information of the photovoltaic components meets the preset convergence condition, a photovoltaic layout plan is configured based on the sorting result of the layout information to perform layout management of photovoltaic equipment in the highway project.

[0045] Specifically, first, a preset convergence condition is set as a standard for judging whether the alternative layout scheme has reached the optimal level. Only when the photovoltaic module layout information meets the preset convergence condition (such as the photovoltaic module layout information has covered all layout possibilities of the photovoltaic equipment layout constraint area of ​​the highway project), the scheme is considered to be sufficiently optimized and can be used as the final layout selection. Among them, the photovoltaic module layout information refers to all photovoltaic module layout information generated by randomly laying out the preset model photovoltaic modules.

[0046] After determining that the layout scheme of the photovoltaic module layout information meets the preset convergence conditions, the overall photovoltaic layout scheme is further optimized in combination with the layout information sorting results. Since the layout information sorting results already contain the quality level information of different individual photovoltaic module layouts, this sorting can be used as a reference to determine the photovoltaic layout scheme with the best comprehensive evaluation. After obtaining the photovoltaic layout scheme, it is applied to the actual layout management of photovoltaic equipment in highway projects. Specifically, according to the key parameter information such as position and angle provided by the photovoltaic layout scheme, the actual installation tasks of each photovoltaic module are planned and arranged, so as to achieve efficient optimization of photovoltaic equipment layout.

[0047] Furthermore, the embodiment of the present application also includes:

[0048] S310: Obtaining a first direct radiation influencing factor, a first scattered radiation influencing factor, and a first reflected radiation influencing factor of the first layout position;

[0049] S320: Obtaining a second direct radiation influencing factor, a second scattered radiation influencing factor, and a second reflected radiation influencing factor of the second layout position;

[0050] S330: Compare the first direct radiation influencing factor and the second direct radiation influencing factor to obtain a direct radiation factor deviation;

[0051] S340: Compare the first scattered radiation influencing factor and the second scattered radiation influencing factor to obtain a scattered radiation factor deviation;

[0052] S350: Compare the first reflected radiation influencing factor and the second reflected radiation influencing factor to obtain a reflected radiation factor deviation;

[0053] S360: When the direct radiation factor deviation is greater than or equal to the direct radiation factor deviation threshold, add the direct radiation to the differential radiation type; when the scattered radiation factor deviation is greater than or equal to the scattered radiation factor deviation threshold, add the scattered radiation to the differential radiation type; when the reflected radiation factor deviation is greater than or equal to the reflected radiation factor deviation threshold, add the reflected radiation to the differential radiation type;

[0054] S370: According to the differential irradiance type, retrieve the differential irradiance prediction model.

[0055] In a preferred embodiment, first, the influencing factors of direct irradiation, scattered irradiation and reflected irradiation at the first layout position and the second layout position are obtained respectively, that is, the first direct irradiation influencing factor, the first scattered irradiation influencing factor and the first reflected irradiation influencing factor at the first layout position, and the second direct irradiation influencing factor, the second scattered irradiation influencing factor and the second reflected irradiation influencing factor at the second layout position. These influencing factors comprehensively reflect the lighting conditions and radiation characteristics of a specific layout position. For the influencing factors of direct irradiation, the parameters such as the position of the sun (including azimuth and altitude), atmospheric transparency, photovoltaic module installation angle (tilt angle and azimuth), solar constant, accumulated day and solar altitude angle are mainly considered, which jointly determine the incident intensity and angular distribution of direct sunlight at different layout positions. For the influencing factors of scattered irradiation, it is necessary to focus on atmospheric composition parameters (such as aerosol and water vapor content), cloud amount and cloud type, solar altitude angle, surface albedo and the specific installation position and angle of photovoltaic modules. These factors work together to affect the intensity distribution and receiving efficiency of scattered radiation at different layout positions. The factors affecting reflected radiation mainly include the reflectivity of the surrounding environment (such as the ground, buildings, water bodies, etc.), the installation angle of photovoltaic modules, the distribution of surrounding terrain and objects, and the altitude and azimuth of the sun, which together affect the directionality, uniformity and reception of reflected radiation at different layout locations. By obtaining the above three types of radiation influencing factors, the differences in radiation conditions at different layout locations can be described more comprehensively.

[0056] Then, the differences in the three types of irradiation influencing factors between the first layout position and the second layout position were compared respectively, and the deviation of irradiation conditions between the two positions was quantitatively evaluated to obtain the three key parameters of direct irradiation factor deviation, scattered irradiation factor deviation and reflected irradiation factor deviation, thus realizing the quantitative characterization and comparison of layout position differences and providing a basis for the subsequent determination of differential irradiation types. Then, by setting the deviation threshold (direct irradiation factor deviation threshold, scattered irradiation factor deviation threshold and reflected irradiation factor deviation threshold), it was determined whether the deviation of each type of irradiation influencing factor was significant. When the deviation of a certain type of irradiation factor exceeds the threshold, it indicates that there is a large difference between the two layout positions in this type of irradiation, which is included in the differential irradiation type as the focus of subsequent differential analysis, thereby identifying the factors that contribute most to the irradiation difference between the two layout positions, laying the foundation for the targeted invocation of the prediction model. Specifically, when the direct radiation factor deviation is greater than or equal to the direct radiation factor deviation threshold, the direct radiation is added to the differential radiation type; when the scattered radiation factor deviation is greater than or equal to the scattered radiation factor deviation threshold, the scattered radiation is added to the differential radiation type; when the reflected radiation factor deviation is greater than or equal to the reflected radiation factor deviation threshold, the reflected radiation is added to the differential radiation type. Afterwards, according to the determined differential radiation type, the corresponding differential irradiance prediction model is specifically called to provide customized calculation tools for subsequent irradiance analysis and layout optimization, thereby avoiding comprehensive prediction of all radiation types, reducing unnecessary calculations, and improving overall solution efficiency.

[0057] By accurately identifying the key radiation difference factors between different layout locations and selecting matching prediction models, the foundation is laid for improving the targetedness and computational efficiency of irradiance prediction and layout optimization.

[0058] Furthermore, the process of obtaining the first reflected radiation influencing factor includes:

[0059] S311: The first layout position includes a first grounding position of a first photovoltaic device support, and a first ground feature is obtained with the first grounding position as the center and a preset length as the radius;

[0060] S312: Setting the first ground feature as the first reflected radiation influencing factor.

[0061] In a preferred embodiment, first, determine the first grounding position of the first photovoltaic device support corresponding to the first layout position. The support may be a photovoltaic module mounting frame, a pile foundation, etc., and its grounding position is the connection point between the support and the ground, reflecting the spatial installation position of the photovoltaic module. With the first grounding position as the center and a preset length as the radius, a circular area is delineated, called the first ground feature area. This area characterizes the ground environment characteristics within a certain range around the photovoltaic module, and has a direct impact on the reflected radiation incident on the photovoltaic module.

[0062] Then, the first ground feature obtained is directly set as the first reflected irradiation influencing factor. This is because the physical properties of the ground environment, such as material, roughness, and color, determine the reflectivity and reflection direction distribution of sunlight after it hits the ground, which in turn affects the reflected irradiation intensity received by the photovoltaic module. The first ground feature area centered on the first grounding position comprehensively reflects the reflected irradiation characteristics of the surrounding surface and can be used as an important parameter for calculating the reflected irradiation intensity.

[0063] By establishing a direct connection between the local layout characteristics of photovoltaic modules and the reflected radiation intensity, a convenient and efficient scheme for obtaining the factors affecting reflected radiation is proposed. Compared with traditional methods, it can more finely characterize the differences in reflected radiation under different layout modes, providing support for improving the overall power generation efficiency of photovoltaic arrays.

[0064] Furthermore, the differential irradiance prediction model includes a direct irradiance prediction model, a scattered irradiance prediction model and a reflected irradiance prediction model, and the training methods of the direct irradiance prediction model, the scattered irradiance prediction model and the reflected irradiance prediction model are the same, wherein the direct irradiance prediction model training step includes:

[0065] S371: Based on the rated interval of the radiation influencing factors, randomly configure the recorded data of the direct radiation influencing factors;

[0066] S372: Recording data of the direct radiation influencing factors, collecting radiation samples for the photovoltaic module models, and obtaining a set of direct radiation recorded values;

[0067] S373: Performing a central tendency evaluation on the direct irradiance record value set to obtain direct irradiance identification data;

[0068] S374: adding the direct radiation influencing factor record data into the direct radiation influencing factor record data set, and adding the direct radiation irradiance identification data into the direct radiation irradiance identification data set;

[0069] S375: Training the direct irradiance prediction model according to the direct irradiance identification data set and the direct irradiance influencing factor record data set.

[0070] In a preferred embodiment, the differential irradiance prediction model includes a direct irradiance prediction model, a diffuse irradiance prediction model and a reflected irradiance prediction model, and the three sub-models adopt the same training steps.

[0071] Taking the training of the direct irradiance prediction model as an example, first, based on the known rated interval of irradiance influencing factors, a set of recorded data of direct irradiance influencing factors is randomly generated. These influencing factors include the position of the sun, atmospheric transparency, the tilt angle and azimuth of the photovoltaic module, etc. By randomly sampling within their rated intervals, a series of representative combinations of influencing factors can be obtained for subsequent irradiation sample collection and model training. Next, the generated recorded data of direct irradiation influencing factors are used to collect actual irradiation samples of the specified model of photovoltaic modules. For example, this is achieved through physical measurement or simulation, with the aim of obtaining the direct irradiation intensity data actually received by the photovoltaic module under different combinations of influencing factors, forming a set of direct irradiance recorded values.

[0072] Subsequently, the collected direct irradiance record value set is statistically analyzed to evaluate the central tendency of its data distribution, and the comprehensive direct irradiance identification data is obtained accordingly. The identification data can be the average, median or other central tendency index of the irradiance record value, which is used to characterize the overall level of direct irradiance under the current combination of influencing factors. By summarizing a set of irradiance record values ​​into a representative identification value, it is convenient for subsequent model training and application. Then, the generated direct irradiation influencing factor record data and the obtained direct irradiance identification data are added to the corresponding data sets, namely the direct irradiation influencing factor record data set and the direct irradiance identification data set. These two sets are used to store the input feature data and target output data required for model training, respectively. By continuously accumulating more sample records, the coverage and diversity of training data can be expanded, laying a data foundation for improving the generalization ability of the model. Afterwards, the obtained direct irradiation influencing factor record data set is used as input, and the direct irradiance identification data set is used as a supervisory signal to train a direct irradiance prediction model through a machine learning algorithm. The model can predict the direct irradiance identification value under corresponding conditions according to the combination of input influencing factors. Among them, machine learning algorithms such as neural networks, support vector machines, decision trees, etc. can be used for training the model.

[0073] Through the above-mentioned differential irradiance prediction model training process, the irradiation influencing factors and measured irradiance data are fully utilized to build an efficient and accurate prediction model, which can quantitatively analyze the irradiance differences of photovoltaic modules under different layout methods, and provide important basis for subsequent layout optimization decisions.

[0074] Furthermore, the embodiment of the present application also includes:

[0075] S410: extracting a first difference irradiance prediction model according to the difference irradiance prediction model, wherein the first difference irradiance prediction model has a first difference irradiance type label, and the first difference irradiance type label has a first weight;

[0076] S420: collecting first irradiation influencing factor characteristic data of the first layout position according to the first differential irradiation type label, processing the first irradiation influencing factor characteristic data by using the first differential irradiance prediction model, and generating a first type of predicted irradiance;

[0077] S430: until an Nth difference irradiance prediction model is extracted according to the difference irradiance prediction model, wherein the Nth difference irradiance prediction model has an Nth difference irradiance type label, and the Nth difference irradiance type label has an Nth weight;

[0078] S440: According to the Nth difference irradiation type label, collect the Nth irradiation influencing factor characteristic data of the first layout position, process the Nth irradiation influencing factor characteristic data by the Nth difference irradiance prediction model, and generate the Nth type predicted irradiance, wherein 3≥N≥0, and N is an integer;

[0079] S450: weighting the first type predicted irradiance normalized value to the Nth type predicted irradiance normalized value according to the first weight to the Nth weight to obtain an N-element irradiance feature array;

[0080] S460: Processing the N-element irradiance feature array through an irradiance fusion analysis model to generate the first predicted irradiance.

[0081] In a preferred embodiment, first, according to the constructed differential irradiance prediction model, the first differential irradiance prediction model is extracted for subsequent analysis. The model is specially modeled for a specific type of irradiance difference (such as direct irradiance difference, scattered irradiance difference, etc.), so it has a corresponding irradiance type label, i.e., the first differential irradiance prediction model. At the same time, a weight value is assigned to the type label of the model to characterize the relative importance of the contribution of the irradiance difference type to the total irradiance. Next, according to the first differential irradiance type label of the first differential irradiance prediction model, the characteristic data of the irradiance influencing factors of the first layout position matching it are collected, i.e., the characteristic data of the first irradiance influencing factors. These characteristic data may include various information such as the position of the sun, meteorological conditions, topography, etc., and are obtained through various sensors or databases. Then, the collected characteristic data of the first irradiance influencing factors are input into the first differential irradiance prediction model for processing, so as to obtain the irradiance prediction value for a specific type of irradiance difference under the layout conditions, i.e., the first type of predicted irradiance.

[0082] Repeat the above process until all difference irradiance prediction models are traversed. Among them, the total number of difference irradiance prediction models is N (3≥N≥0, N is an integer). For the Nth difference irradiance prediction model, its irradiance type label and corresponding weight are also obtained, the relevant feature data of the first layout position is collected, and the Nth type of predicted irradiance is generated through the model. After obtaining all types of predicted irradiances, these predicted values ​​are weighted fused. First, the predicted irradiances from the first type to the Nth type are normalized so that their numerical range is unified to the interval [0, 1], which is convenient for subsequent weight addition. Then, using the obtained weights of each type of label, the normalized predicted irradiance is weighted summed, and finally an irradiance feature array containing N elements is obtained. This array integrates the prediction results of different irradiance difference types and reflects the relative contribution of each type of irradiance in the total irradiance. After that, the obtained N-element irradiance feature array is input into the pre-trained irradiance fusion analysis model for processing. This model is a machine learning model (such as neural network, decision tree, etc.), which has mastered the law of how to map the feature combination of different types of irradiance to the total irradiance prediction value by learning a large amount of historical data. After calculation by the fusion analysis model, the total irradiance prediction value of the first layout mode under the current parameter setting is obtained, that is, the first predicted irradiance.

[0083] By carrying out modeling prediction and weight addition for different types of irradiance differences, the irradiance distribution characteristics in complex environments can be more precisely characterized. The introduction of normalization and weighted fusion allows the prediction results of different types of irradiance to be comprehensively evaluated on a unified scale, reflecting the relative importance of each type of irradiance. At the same time, the irradiance fusion analysis model is used to perform secondary processing on the weighted features, further improving the accuracy of the total irradiance prediction.

[0084] Furthermore, the steps for constructing the irradiance fusion analysis model include:

[0085] S461: According to the photovoltaic module model, configure an M-element irradiance array record data set and an irradiance detection true value data set;

[0086] S462: using the irradiance detection true value dataset as supervision and the M-element irradiance array record dataset as input, training a first-level irradiance fusion analysis model;

[0087] S463: extracting the output deviation vector set of the first-level irradiance fusion analysis model;

[0088] S464: performing system error vector analysis on the output deviation vector set to obtain a primary system error vector;

[0089] S465: When the modulus of the primary system error vector is greater than or equal to the modulus threshold, setting the opposite number of the primary system error vector as the secondary irradiance identification data set;

[0090] S466: Using the secondary irradiance identification data set as supervision and the M-element irradiance array record data set as input, training a secondary irradiance fusion analysis model;

[0091] S467: until the modulus value of the Q-level system error vector is less than the modulus value threshold, the outputs of the first-level irradiance fusion analysis model, the second-level irradiance fusion analysis model, and the Q-level irradiance fusion analysis model are added and fully connected to obtain the irradiance fusion analysis model.

[0092] In a preferred embodiment, first, two basic data sets are configured according to the photovoltaic module model to be analyzed. One is an M-element irradiance array record data set, which contains a large number of irradiance feature samples under different conditions, and each sample is represented by an irradiance feature vector composed of M components. The other is an irradiance detection true value data set, which records the actual irradiance measurement value corresponding to each irradiance feature sample as label data for model training. The configuration of these two data sets provides the necessary data basis for subsequent model training. Next, an initial irradiance fusion analysis model is trained using the configured data set, which is called a first-level irradiance fusion analysis model. Specifically, the M-element irradiance array data set is used as the input of the model, and the irradiance detection true value data set is used as the supervisory signal, and parameter optimization and model training are performed through machine learning algorithms such as neural networks and decision trees. The trained first-level irradiance fusion analysis model can preliminarily realize the mapping relationship from irradiance features to actual irradiance.

[0093] In order to further improve the prediction accuracy of the model, an iterative optimization process is introduced. First, the prediction results of the first-level irradiance fusion analysis model on the training data set are compared with the true labels to obtain a series of output deviation vectors, that is, a set of output deviation vectors, which reflects the prediction error distribution of the current model. Then, a systematic error analysis is performed on these output deviation vectors, and the overall deviation characteristics of the model output are evaluated by indicators such as mean value and variance to obtain a comprehensive first-level systematic error vector. This vector characterizes the average prediction deviation of the first-level model in the entire sample space. Subsequently, it is determined whether the modulus of the first-level systematic error vector exceeds the preset modulus threshold. If it exceeds the threshold, it means that the prediction error of the current model is large and further optimization is required. At this time, the first-level systematic error vector is inverted as a new irradiance identification data set, called the second-level irradiance identification data set. This new identification data set actually reflects the prediction deviation distribution of the first-level irradiance fusion analysis model, which can be used to guide the training optimization of the next-level model.

[0094] Subsequently, the M-element irradiance array record data set is used as input, and the secondary irradiance identification data set is used as the supervision signal to train the secondary irradiance fusion analysis model. This new model is similar to the primary irradiance fusion analysis model in structure, but the training goal is no longer to directly predict the true value of irradiance, but to fit the prediction deviation of the primary irradiance fusion analysis model. In this way, the secondary irradiance fusion analysis model can capture the law of the prediction error of the primary irradiance fusion analysis model, and make compensation corrections on this basis. Repeat the execution until the Q-level system error vector modulus of the trained Q-level irradiance fusion analysis model is less than the modulus threshold. This iterative optimization process can gradually reduce the prediction deviation of the model and improve the accuracy of irradiance prediction. Afterwards, all irradiance fusion analysis models from level 1 to level Q are added and fully connected to obtain the final irradiance fusion analysis model. Specifically, the outputs of each level of the model are weighted and summed, and the weights can be optimized by methods such as cross-validation. Through the combined integration of this multi-level model, the predictive ability of each level of model can be fully utilized, and complementary advantages can be achieved under different error distributions, thus obtaining an irradiance fusion analysis model with stronger robustness and better generalization ability.

[0095] Through the irradiance fusion analysis model construction process, the complexity and nonlinear characteristics of the photovoltaic irradiance prediction problem are fully considered. By introducing multi-level iterative optimization and error compensation mechanisms, the prediction accuracy and adaptability of the model can be continuously improved. Compared with the traditional single model method, the multi-level integrated model used in the present invention can better capture the inherent laws of irradiance data, show stronger robustness under noise interference and abnormal deviations, and provide a reliable decision-making basis for the layout of photovoltaic modules.

[0096] Furthermore, the embodiment of the present application also includes:

[0097] S710: configuring, through the user terminal, a layout distance constraint variance, a layout boundary constraint distance, and a layout constraint quantity for the layout constraint area of ​​the highway project photovoltaic equipment;

[0098] S720: constructing a fitness function, wherein the fitness function is a sum of the sequence numbers of the layout information sorting results;

[0099] S730: taking the layout distance constraint variance, the layout boundary constraint distance and the layout constraint quantity as constraints, performing a number of random combinations based on the layout information sorting results, and configuring a photovoltaic device layout solution set;

[0100] S740: performing particle swarm optimization on the photovoltaic equipment layout solution set according to the fitness function to obtain a recommended photovoltaic equipment layout solution;

[0101] S750: Performing photovoltaic equipment layout management for highway projects according to the recommended photovoltaic equipment layout plan.

[0102] In a preferred embodiment, first, a series of constraint parameters are configured for the layout constraint area of ​​the highway engineering photovoltaic equipment through the user end, including the layout distance constraint variance, the layout boundary constraint distance and the layout constraint number. Among them, the layout distance constraint variance is used to limit the distance variation range between adjacent photovoltaic components, requiring that the variance of the distance between each photovoltaic component in the layout scheme is greater than the constraint value; the layout boundary constraint distance defines the minimum distance between the photovoltaic component and the layout area boundary to ensure that the component does not exceed the restricted area; the layout constraint number specifies the total number of photovoltaic components that need to be laid out. The introduction of these constraints provides the necessary boundary restrictions for the generation of subsequent layout schemes. Next, a fitness function is constructed to evaluate the pros and cons of candidate layout schemes. For example, the fitness function is defined as the sum of the serial numbers of the layout information sorting results. The layout information sorting result refers to the sequence obtained by sorting the candidate single photovoltaic components from best to worst according to the predicted irradiance. The smaller the sum of the serial numbers, the more high-quality photovoltaic component layouts are in the front, and the higher the overall fitness.

[0103] Subsequently, based on the obtained layout information sorting results, several candidate photovoltaic equipment layout schemes are generated by random combination with the set constraints as the restriction, forming a set of photovoltaic equipment layout schemes. Among them, random combination refers to randomly selecting several photovoltaic module layouts in the sorting results for combination to explore new layout possibilities. At the same time, it is ensured that the randomly generated schemes meet the requirements of layout distance constraint variance, layout boundary constraint distance and layout constraint quantity to ensure the feasibility of the scheme. Then, the particle swarm optimization algorithm is used to further optimize the obtained photovoltaic equipment layout scheme set. Particle swarm optimization is a heuristic search algorithm based on swarm intelligence. It simulates the foraging behavior of bird flocks to find the optimal solution in the solution space. Each candidate photovoltaic module layout is regarded as a particle, and the value of the fitness function is used as the fitness evaluation indicator of the particle. By iteratively updating the position and velocity of the particle, it continuously moves in the direction of higher fitness, and finally converges to a global optimal or approximately optimal layout scheme as the recommended photovoltaic equipment layout scheme. Afterwards, the recommended photovoltaic equipment layout plan will be applied to the actual photovoltaic equipment layout management of highway projects to ensure that the photovoltaic power generation system can operate efficiently and stably according to the recommended photovoltaic equipment layout plan, so as to achieve the goal of improving solar energy conversion efficiency and power generation.

[0104] Furthermore, the embodiment of the present application also includes:

[0105] S761: The preset convergence conditions include a threshold value of the volume proportion of the laid-out area, a threshold value of the proportion of the laid-out tilt angle interval, and a threshold value of the proportion of the laid-out azimuth angle interval.

[0106] S762: When the volume proportion of the layout area of ​​the layout information of the photovoltaic components is greater than or equal to the volume proportion threshold of the layout area, and the layout inclination angle interval of any layout position is greater than or equal to the layout inclination angle interval proportion threshold, and the layout azimuth angle interval of any layout position is greater than or equal to the layout azimuth angle interval proportion threshold, it is deemed that the preset convergence condition is met.

[0107] In a preferred embodiment, the preset convergence conditions are defined to include a threshold value for the volume proportion of the laid-out area, a threshold value for the proportion of the laid-out inclination angle interval, and a threshold value for the proportion of the laid-out azimuth angle interval. These three thresholds quantitatively evaluate the convergence state of the photovoltaic module layout from three aspects: layout coverage, degree of inclination angle optimization, and degree of azimuth angle optimization. Among them, the proportion of the volume of the laid-out area refers to the ratio of the volume of the area where the photovoltaic modules are currently randomly laid out to the volume of the entire layout constraint area. The two indicators, the proportion of the laid-out inclination angle interval and the proportion of the laid-out azimuth angle interval, judge the layout from the angle. Both the inclination angle and the azimuth angle affect the efficiency of the photovoltaic module in receiving solar radiation, and different angle combinations may lead to significant differences in power generation.

[0108] Taking the above three convergence conditions into consideration, a standard is given to determine whether the layout information of photovoltaic modules meets the preset convergence conditions. Specifically, only when the volume proportion of the layout area in the layout information of photovoltaic modules is greater than or equal to the corresponding threshold, and the proportion of the layout inclination angle interval and the proportion of the azimuth angle interval reach or exceed the corresponding threshold, the current photovoltaic module layout information is considered to meet the preset convergence conditions, so that the overall photovoltaic module layout planning can be started.

[0109] The method for optimizing the layout of photovoltaic equipment in highway engineering based on solar energy conversion efficiency provided by the embodiment of the present invention has at least the following technical effects:

[0110] Based on the horizontal layout constraint area and vertical layout constraint area of ​​the photovoltaic equipment layout constraint area of ​​the highway project, the preset model photovoltaic modules are randomly laid out to obtain the first photovoltaic module layout information and the second photovoltaic module layout information, and different single photovoltaic module layouts are generated in the constraint area to provide a variety of candidate solutions for subsequent comparison and optimization. The first layout position, the first layout inclination angle, and the first layout azimuth of the first photovoltaic module layout information are obtained, and the second layout position, the second layout inclination angle, and the second layout azimuth of the second photovoltaic module layout information are obtained to obtain the key factors affecting the irradiance of the photovoltaic module, and provide the necessary input parameters for the subsequent irradiance analysis. According to the first layout position and the second layout position, the differential irradiation type configuration is performed to obtain the differential irradiance prediction model. By comparing the layout differences, the areas that need to be analyzed are identified, and a targeted irradiance prediction model is established to reduce unnecessary calculations. According to the differential irradiance prediction model, the irradiance analysis is performed based on the first layout position, the first layout inclination angle, and the first layout azimuth to obtain the first predicted irradiance, and the irradiance level of the photovoltaic module under the first layout scheme is evaluated to provide a basis for the subsequent scheme optimization. According to the differential irradiance prediction model, irradiance analysis is performed based on the second layout position, the second layout inclination angle, and the second layout azimuth to obtain the second predicted irradiance, and the irradiance level of the photovoltaic module under the second layout mode is evaluated to provide a basis for the subsequent scheme optimization. According to the first predicted irradiance and the second predicted irradiance, the first photovoltaic module layout information and the second photovoltaic module layout information are updated from large to small, and the layout information sorting result is updated. Based on the irradiance level, a single photovoltaic module layout mode with higher solar energy conversion efficiency is selected to provide a reference for the final layout optimization. When the layout information of the photovoltaic module meets the preset convergence conditions, the photovoltaic layout plan is configured based on the layout information sorting result to carry out the layout management of photovoltaic equipment in highway projects. Through iterative optimization, the layout plan is continuously updated and screened, and finally the optimal layout that meets the requirements is obtained to guide the actual deployment of photovoltaic equipment, while ensuring the optimization effect and improving the optimization efficiency.

[0111] Embodiment 2:

[0112] See also Figure 2 , Figure 2 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 2 As shown, an electronic device 100 provided by an embodiment of the present invention includes a memory 110, a processor 120, and a first computer program 111 stored in the memory 110 and executable on the processor 120. When the processor 120 executes the first computer program 111, a method for optimizing the layout of photovoltaic equipment for highway engineering projects based on solar energy conversion efficiency is implemented.

[0113] Embodiment three:

[0114] See also Figure 3 , Figure 3 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 3 As shown, this embodiment provides a computer-readable storage medium 200 on which a second computer program 211 is stored. When the second computer program 211 is executed by a processor, a method for optimizing the layout of photovoltaic equipment in highway engineering based on solar energy conversion efficiency is implemented.

[0115] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0116] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0118] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0120] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0121] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technology, the present invention is also intended to include these changes and variations.

Claims

1. A method for optimizing the layout of photovoltaic equipment for highway engineering projects based on solar energy conversion efficiency, characterized in that: include: Based on the horizontal layout constraint area and the vertical layout constraint area of ​​the highway engineering photovoltaic equipment layout constraint area, randomly layout the preset model photovoltaic components to obtain the first photovoltaic component layout information and the second photovoltaic component layout information; Obtaining a first layout position, a first layout inclination angle, and a first layout azimuth angle of the first photovoltaic assembly layout information, and obtaining a second layout position, a second layout inclination angle, and a second layout azimuth angle of the second photovoltaic assembly layout information; Perform differential irradiance type configuration according to the first layout position and the second layout position to obtain a differential irradiance prediction model; According to the differential irradiance prediction model, performing irradiance analysis based on the first layout position, the first layout inclination angle, and the first layout azimuth angle to obtain a first predicted irradiance; According to the differential irradiance prediction model, performing irradiance analysis based on the second layout position, the second layout inclination angle, and the second layout azimuth angle to obtain a second predicted irradiance; According to the first predicted irradiance and the second predicted irradiance, the first photovoltaic assembly layout information and the second photovoltaic assembly layout information are sorted from large to small to update the layout information sorting result; When the layout information of the photovoltaic components meets the preset convergence condition, a photovoltaic layout plan is configured based on the sorting result of the layout information to perform layout management of photovoltaic equipment in highway engineering.

2. The method according to claim 1, characterized in that Performing differential irradiance type configuration according to the first layout position and the second layout position to obtain a differential irradiance prediction model includes: Obtaining a first direct radiation influencing factor, a first scattered radiation influencing factor, and a first reflected radiation influencing factor of the first layout position; Obtaining a second direct radiation influencing factor, a second scattered radiation influencing factor, and a second reflected radiation influencing factor of the second layout position; Comparing the first direct radiation influencing factor with the second direct radiation influencing factor to obtain a direct radiation factor deviation; comparing the first scattered radiation influencing factor and the second scattered radiation influencing factor to obtain a scattered radiation factor deviation; Comparing the first reflected radiation influencing factor and the second reflected radiation influencing factor to obtain a reflected radiation factor deviation; When the direct radiation factor deviation is greater than or equal to the direct radiation factor deviation threshold, direct radiation is added to the differential radiation type; when the scattered radiation factor deviation is greater than or equal to the scattered radiation factor deviation threshold, scattered radiation is added to the differential radiation type; when the reflected radiation factor deviation is greater than or equal to the reflected radiation factor deviation threshold, reflected radiation is added to the differential radiation type; According to the differential irradiance type, the differential irradiance prediction model is retrieved.

3. The method according to claim 2, characterized in that The process of obtaining the first reflected radiation influencing factor includes: The first layout position includes a first grounding position of a first photovoltaic device support, and a first ground feature is obtained with the first grounding position as the center and a preset length as the radius; The first ground feature is set as the first reflected radiation influencing factor.

4. The method according to claim 1, characterized in that: The differential irradiance prediction model includes a direct irradiance prediction model, a scattered irradiance prediction model and a reflected irradiance prediction model. The training methods of the direct irradiance prediction model, the scattered irradiance prediction model and the reflected irradiance prediction model are the same, wherein the direct irradiance prediction model training step includes: Based on the rated interval of radiation influencing factors, the data of direct radiation influencing factors are randomly configured; Recording data based on the direct radiation influencing factors, collecting radiation samples for photovoltaic module models, and obtaining a set of direct radiation recorded values; Performing a central tendency assessment on the direct irradiance record value set to obtain direct irradiance identification data; Adding the direct radiation influencing factor record data into the direct radiation influencing factor record data set, and adding the direct radiation irradiance identification data into the direct radiation irradiance identification data set; The direct irradiance prediction model is trained according to the direct irradiance identification data set and the direct irradiance influencing factor record data set.

5. The method according to claim 4, characterized in that According to the differential irradiance prediction model, irradiance analysis is performed based on the first layout position, the first layout inclination angle, and the first layout azimuth angle to obtain a first predicted irradiance, including: Extracting a first difference irradiance prediction model according to the difference irradiance prediction model, wherein the first difference irradiance prediction model has a first difference irradiance type label, and the first difference irradiance type label has a first weight; According to the first differential irradiation type label, first irradiation influencing factor characteristic data of the first layout position is collected, and the first irradiation influencing factor characteristic data is processed by the first differential irradiance prediction model to generate a first type of predicted irradiance; Until an Nth difference irradiance prediction model is extracted according to the difference irradiance prediction model, wherein the Nth difference irradiance prediction model has an Nth difference irradiance type label, and the Nth difference irradiance type label has an Nth weight; According to the Nth difference irradiation type label, collecting the Nth irradiation influencing factor characteristic data of the first layout position, processing the Nth irradiation influencing factor characteristic data by the Nth difference irradiance prediction model, and generating the Nth type predicted irradiance, wherein 3≥N≥0, and N is an integer; According to the first weight to the Nth weight, weighting the first type predicted irradiance normalized value to the Nth type predicted irradiance normalized value to obtain an N-element irradiance feature array; The N-element irradiance feature array is processed through an irradiance fusion analysis model to generate the first predicted irradiance.

6. The method according to claim 5, characterized in that The steps of constructing the irradiance fusion analysis model include: According to the PV module model, configure the M-element irradiance array record data set and the irradiance detection true value data set; Taking the irradiance detection true value data set as supervision and the M-element irradiance array record data set as input, training a first-level irradiance fusion analysis model; Extracting a set of output deviation vectors of the first-level irradiance fusion analysis model; Performing system error vector analysis on the output deviation vector set to obtain a primary system error vector; When the modulus of the primary system error vector is greater than or equal to the modulus threshold, setting the opposite number of the primary system error vector as the secondary irradiance identification data set; Using the secondary irradiance identification data set as supervision and the M-element irradiance array record data set as input, training a secondary irradiance fusion analysis model; Until the modulus value of the Q-level system error vector is less than the modulus value threshold, the outputs of the first-level irradiance fusion analysis model, the second-level irradiance fusion analysis model, and the Q-level irradiance fusion analysis model are added and fully connected to obtain the irradiance fusion analysis model.

7. The method according to claim 1, characterized in that When the layout information of the photovoltaic components meets the preset convergence condition, a photovoltaic layout plan is configured based on the sorting result of the layout information to perform layout management of photovoltaic equipment for highway engineering, including: By means of a user terminal, for the layout constraint area of ​​the highway project photovoltaic equipment, a layout distance constraint variance, a layout boundary constraint distance and a layout constraint quantity are configured; Constructing a fitness function, wherein the fitness function is a sum of the sequence numbers of the layout information sorting results; Taking the layout distance constraint variance, the layout boundary constraint distance and the layout constraint quantity as constraints, performing several random combinations based on the layout information sorting results to configure a photovoltaic device layout solution set; According to the fitness function, performing particle swarm optimization on the photovoltaic equipment layout solution set to obtain a recommended photovoltaic equipment layout solution; The photovoltaic equipment layout management of the highway project is carried out according to the recommended photovoltaic equipment layout plan.

8. The method according to claim 7, characterized in that When the PV panel layout information meets the preset convergence conditions, including: The preset convergence conditions include a threshold value of the volume proportion of the laid-out area, a threshold value of the proportion of the laid-out inclination angle interval, and a threshold value of the proportion of the laid-out azimuth angle interval. When the volume proportion of the layout area of ​​the layout information of the photovoltaic components is greater than or equal to the volume proportion threshold of the layout area, and the layout inclination angle interval of any layout position is greater than or equal to the layout inclination angle interval proportion threshold, and the layout azimuth angle interval of any layout position is greater than or equal to the layout azimuth angle interval proportion threshold, it is deemed that the preset convergence condition is met.

Images