An optimization method and device for a distributed photovoltaic system

Abstract

The application discloses an optimization method and device for a distributed photovoltaic system, determines a heat island intensity index through part of temperature data of a target city, calculates solar radiation intensity and reflected light distribution according to a three-dimensional building model, calculates photovoltaic panel temperature and system power generation efficiency of the distributed photovoltaic system through the temperature data and the solar radiation intensity, determines a photovoltaic panel installation strategy, constructs a photovoltaic panel heat balance model according to the installation strategy, optimizes the installation strategy according to key influencing factors determined by the heat balance model, adjusts the photovoltaic system according to the optimized strategy, reoptimizes the installation strategy according to system heat island intensity and reflected light distribution, and obtains an optimized photovoltaic system deployment strategy. The system optimization strategy is generated through the optimization method, the power generation efficiency of the photovoltaic system deployment strategy is improved, the photovoltaic panel temperature caused by the heat island effect and building reflected radiation is reduced, and intelligent management and efficient operation of the photovoltaic power generation system are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of photovoltaic system optimization, in particular to a distributed photovoltaic system optimization method and device. BACKGROUND

[0002] When deploying a distributed photovoltaic system in an urban environment, the urban heat island effect and the reflection of light by building walls are two key factors that jointly affect the power generation efficiency of photovoltaic panels. The urban heat island effect is caused by the absorption and storage of heat by artificial structures such as buildings and roads in cities, resulting in a generally higher temperature in the central urban area than in the surrounding rural areas. This temperature increase will have various effects on the photovoltaic system, including an increase in the operating temperature of the photovoltaic panels, a decrease in power generation efficiency, an increase in radiation intensity, or local overheating of the photovoltaic panels.

[0003] On the other hand, the walls of tall buildings in cities can reflect sunlight, which increases the radiation intensity on the surface of the photovoltaic panels. In theory, the increased radiation intensity should increase the power generation of the photovoltaic panels, but in reality, due to the non-direct nature of the reflected light, the light received by the photovoltaic panels may not be at the optimal angle, so it may not be effectively converted into electrical energy. At the same time, the reflected light can also cause local overheating of the photovoltaic panels, affecting their long-term stability and power generation efficiency.

[0004] Therefore, in order to solve the problems caused by the above two factors, the existing technology mainly uses photovoltaic power prediction technology to reduce the influence of the uncertainty of photovoltaic output power. However, as the prediction area increases and the number of photovoltaic power stations increases, the prediction calculation efficiency of the traditional prediction model gradually decreases, and the traditional prediction model does not take into account the influence of meteorological factors in the power station area, while the meteorological characteristics of photovoltaic power stations may differ greatly, which will also affect the accuracy of regional power prediction. SUMMARY

[0005] The present application provides a distributed photovoltaic system optimization method and device to improve the efficiency and stability of deploying photovoltaic systems, while also ensuring the efficient operation and long-term stability of the photovoltaic system.

[0006] In order to solve the above technical problems, the present application provides a distributed photovoltaic system optimization method, comprising the following steps:

[0007] Obtain temperature distribution data of a target city, and calculate the temperature distribution data by an interpolation analysis method to obtain a heat island intensity index;

[0008] Obtain a three-dimensional building model of the target city, and calculate the solar radiation intensity and reflected light distribution based on the three-dimensional building model;

[0009] Determine the photovoltaic panel temperature and system power generation efficiency of the distributed photovoltaic system according to the temperature distribution data and the solar radiation intensity, and output a first photovoltaic panel installation strategy;

[0010] Determine the photovoltaic panel radiation intensity based on the first photovoltaic panel installation strategy and the three-dimensional building model, and construct a photovoltaic panel heat balance model based on the photovoltaic panel radiation intensity;

[0011] Determine the key influencing factors according to the photovoltaic panel heat balance model, and optimize and adjust the first photovoltaic panel installation strategy according to the key influencing factors, output and optimize and adjust the distributed photovoltaic system according to the second photovoltaic panel installation strategy;

[0012] Obtain the actual operation data of the distributed photovoltaic system after optimization and adjustment, construct a multiple regression model according to the actual operation data, optimize and adjust the multiple regression model according to the heat island intensity index and the reflected light distribution, and output the optimized distributed photovoltaic system deployment strategy.

[0013] The optimization method provided by the application firstly performs spatial interpolation analysis on the temperature distribution data obtained from the target city by an interpolation analysis method to obtain the heat island intensity index of the city, so as to determine the heat island intensity change trend of each region of the target city at different times and seasons, and to determine the heat island effect degree of each region in the city, thereby providing a decision basis for city heat environment governance and providing reference data for subsequent output of the photovoltaic panel installation strategy of the city.

[0014] After determining the heat island intensity index of the city, the system obtains the three-dimensional building model of the city, and calculates the solar radiation intensity and the reflected light distribution of the city, thereby providing reference data for subsequent optimization and adjustment of the first photovoltaic panel installation strategy.

[0015] Through the temperature distribution data and the solar radiation intensity of the target city, the system can calculate and obtain the photovoltaic panel temperature and system power generation efficiency of the distributed photovoltaic system in the city, and determine the first photovoltaic panel installation strategy through the temperature distribution data and the solar radiation intensity, that is, the first photovoltaic panel installation strategy obtained after considering the system power generation efficiency and the photovoltaic panel installation environment and other factors, thereby providing a data basis for subsequent optimization.

[0016] After obtaining the first photovoltaic panel installation strategy, the system adjusts the installation position of the photovoltaic panel in the three-dimensional building model according to the strategy, and calculates and determines the radiation intensity of the photovoltaic panel according to the adjusted model, that is, determines the direct solar radiation and the reflected radiation of the building surface at different solar elevation angles and azimuth angles through model simulation, so as to determine the radiation intensity on the photovoltaic panel, and constructs a photovoltaic panel heat balance model according to the determined photovoltaic panel radiation intensity, thereby improving the accuracy and reliability of the model in predicting the temperature change and power generation performance of the photovoltaic panel.

[0017] The key factors affecting the temperature of the photovoltaic panel and the photovoltaic power generation efficiency can be further determined by the constructed photovoltaic panel heat balance model, that is, the key influencing factors, and the weight parameters of the first photovoltaic panel installation strategy are adjusted again according to the determined key influencing factors, and the strategy is adjusted again with the temperature change of the photovoltaic panel and the power generation efficiency as the optimization target, to obtain a second photovoltaic panel installation strategy.

[0018] After obtaining the second photovoltaic panel installation strategy, the distributed photovoltaic system can be adjusted through the strategy, and the strategy can be further optimized according to the actual operation data of the photovoltaic system, including the heat island intensity index and the distribution of reflected light, to obtain an optimized photovoltaic system optimization strategy, which improves the power generation efficiency of the optimized photovoltaic system deployment strategy, and also reduces the temperature of the photovoltaic panel caused by the urban heat island effect and the building reflected radiation, thereby improving the overall efficiency of the photovoltaic power generation system. At the same time, by identifying the power generation mode and efficiency characteristics of the photovoltaic system under different environmental conditions, and determining the correlation between the actual power generation efficiency and environmental factors, the deployment strategy of the photovoltaic system is optimized, and intelligent management and efficient operation of the photovoltaic power generation system are also realized.

[0019] As a preferred example, the temperature distribution data of the target city is obtained, and the temperature distribution data is calculated by an interpolation analysis method to obtain a heat island intensity index, including:

[0020] The initial temperature distribution data of the target city is obtained, and the initial temperature distribution data is subjected to outlier rejection processing and missing value supplementing processing to obtain the temperature distribution data;

[0021] The temperature distribution data is subjected to spatial interpolation analysis by a Kriging interpolation method to obtain a temperature distribution surface of the target city;

[0022] The heat island intensity index is calculated and obtained according to the temperature distribution surface, and the target city is divided into regions according to the heat island effect grade according to the heat island intensity index to obtain a regional heat island grade.

[0023] By rejecting outliers and supplementing missing values from the initial temperature distribution data, the quality and integrity of the temperature distribution data are improved, and by subjecting the temperature distribution data to spatial interpolation processing by the Kriging interpolation method, a temperature distribution surface, that is, a temperature distribution map, of different seasons in the city can be obtained, such as a temperature distribution comparison map of winter and summer, which more intuitively presents the heat island effect of each region in the target city. By calculating and determining the heat island intensity index of each region in the target city through the temperature distribution map, and dividing each region into a heat island effect grade, the degree of influence of the heat island effect on each region in the target city can be determined, and the user can also be prompted about the seriously affected regions, thereby providing a decision basis for urban heat environment management.

[0024] As a preferred example, the three-dimensional building model of the target city is obtained, and the solar radiation intensity and the reflection light distribution are calculated according to the three-dimensional building model, comprising:

[0025] The building point cloud data of the target city is obtained, and the building point cloud data is sequentially subjected to denoising, point cloud classification and three-dimensional reconstruction processing to obtain the three-dimensional building model;

[0026] The solar radiation data and the reflectivity data of the building surface material of the target city are obtained, the solar radiation data and the reflectivity data are input into the three-dimensional building model, and the solar radiation intensity and the reflection light distribution of the building surface are calculated by a Monte Carlo simulation algorithm.

[0027] The three-dimensional building model of the city is constructed according to the building point cloud data of the city, which provides a data basis for subsequent acquisition of the solar radiation intensity of the city and the reflection light distribution of the building surface of the city. Through the acquired solar radiation data and the reflectivity data of the building surface and the constructed three-dimensional building model, the system can simulate and determine the reflection and scattering process of the sunlight on the building surface of the city by a Monte Carlo simulation algorithm, so as to determine the radiation brightness and the radiation flux distribution of each building, and further determine the reflection light distribution of each building surface, and the solar radiation intensity obtained by calculating various radiation intensities, which provides reference data for subsequent calculation of the photovoltaic panel installation strategy.

[0028] As a preferred example, the photovoltaic panel temperature and the system power generation efficiency of the distributed photovoltaic system are calculated and determined according to the temperature distribution data and the solar radiation intensity, and a first photovoltaic panel installation strategy is output, specifically:

[0029] The temperature distribution data and the solar radiation intensity are input into a preset Sandia array performance model for calculation and processing to obtain the photovoltaic panel temperature and the system power generation efficiency;

[0030] The building density data and the green coverage data of the target city are obtained, and a photovoltaic array multi-objective optimization model is constructed based on the building density data, the green coverage data, and the photovoltaic panel temperature and the system power generation efficiency;

[0031] The photovoltaic array multi-objective optimization model is optimized and solved by a genetic algorithm, and the first photovoltaic panel installation strategy is output.

[0032] The temperature distribution data and the solar radiation intensity are processed by the Sandia array performance model, the spatial and temporal continuity and consistency of the temperature data are ensured, the environmental temperature boundary conditions are provided for subsequent photovoltaic array performance simulation, the material properties, electrical parameters and installation conditions of the photovoltaic panel are comprehensively considered through the solar radiation intensity data, and then the photovoltaic panel temperature and the power generation efficiency of the photovoltaic system are obtained, so that the accuracy and reliability of the obtained data are improved.

[0033] After the above data is obtained, the system also obtains the building density data and the greening coverage data of the city, so as to ensure that the photovoltaic panel installation strategy generated subsequently fully considers the shading effect of greening on the radiation of the photovoltaic panel, and the photovoltaic array multi-objective optimization model constructed through the above data not only comprehensively considers the system power generation, greening building shading and landscape coordination and other factors, but also is further optimized through the genetic algorithm, so that the practicality, reliability and accuracy of the output photovoltaic panel installation strategy are improved.

[0034] As a preferred example, the calculation and determination of the photovoltaic panel radiation intensity based on the first photovoltaic panel installation strategy and the three-dimensional building model, and the construction of the photovoltaic panel heat balance model based on the photovoltaic panel radiation intensity, include:

[0035] According to the first photovoltaic panel installation strategy, the parameters of the three-dimensional building model are adjusted, and the reflection and shading of sunlight are simulated through the Monte Carlo ray tracing method to obtain the radiation flux per unit area of the photovoltaic panel;

[0036] According to the radiation flux, a corresponding building surface radiation transmission mathematical model is constructed, and the photovoltaic panel radiation intensity is calculated and obtained through the building surface radiation transmission mathematical model;

[0037] According to the photovoltaic panel radiation intensity and the heat exchange process of the photovoltaic panel, the photovoltaic panel heat balance model is constructed.

[0038] After the three-dimensional building model is adjusted according to the output first photovoltaic panel installation strategy, the system will again simulate the reflection and shading of sunlight through the Monte Carlo ray tracing method, so as to determine the solar radiation intensity per unit area of each photovoltaic panel, i.e. the radiation flux, after the photovoltaic panel placement position is adjusted, and a corresponding building surface radiation transmission mathematical model is constructed through the determined radiation flux, so as to further clarify the propagation and distribution process of the radiation energy on the building surface.

[0039] The photovoltaic panel radiation intensity of the photovoltaic panel can be calculated through the constructed transmission mathematical model. According to the photovoltaic panel radiation intensity and the heat exchange process of the photovoltaic panel, a photovoltaic panel thermal balance model can be constructed. Considering the heat transfer mechanisms including solar radiation absorption, photoelectric conversion, convective heat transfer and thermal radiation, a mathematical relationship between the photovoltaic panel temperature and environmental conditions, material properties, structural parameters and other factors is established to construct the photovoltaic panel thermal balance model, so that the model can accurately predict the temperature change and power generation performance of the photovoltaic panel.

[0040] As a preferred example, the determining the key influencing factors according to the photovoltaic panel thermal balance model and the optimizing and adjusting the first photovoltaic panel installation strategy according to the key influencing factors include:

[0041] The photovoltaic panel temperature and the system power generation efficiency are simulated and analyzed through the photovoltaic panel thermal balance model to obtain the corresponding change curve;

[0042] The key influencing factors are obtained by screening the influencing factors of the change curve through a sensitivity analysis algorithm.

[0043] Then, the first photovoltaic panel installation strategy is optimized and adjusted based on the key influencing factors through a genetic algorithm.

[0044] The photovoltaic panel temperature and the power generation efficiency are simulated through the constructed thermal balance model to obtain the change curves of the photovoltaic panel temperature and the power generation efficiency with respect to time. By analyzing the above curves, factors that may affect the photovoltaic panel temperature and the power generation efficiency are screened and obtained. Through a sensitivity analysis algorithm, the most significant factors affecting the photovoltaic panel temperature and the efficiency, such as environmental temperature, wind speed or conversion efficiency, are screened out. After determining the key factors, the system optimizes and adjusts the installation strategy of the photovoltaic panel based on the key factors to further improve the power generation efficiency of the photovoltaic panel while reducing its temperature impact.

[0045] As a preferred example, the obtaining the actual operation data of the distributed photovoltaic system after the optimizing and adjusting, and constructing a multiple regression model according to the actual operation data include:

[0046] The actual operation data of the distributed photovoltaic system is obtained, and the actual operation data is processed by dimension reduction and feature extraction to obtain a photovoltaic feature data set.

[0047] The photovoltaic feature data set is subjected to cluster analysis, and the photovoltaic feature data set is divided into different cluster clusters according to a preset power generation index. The photovoltaic power generation influencing factors are determined according to the cluster clusters, and the multiple regression model is constructed according to the photovoltaic power generation influencing factors and the power generation efficiency.

[0048] The second adjustment photovoltaic panel installation strategy is determined, and the system adjusts the distributed photovoltaic system according to the second adjustment photovoltaic panel installation strategy to obtain actual operation data of the adjusted photovoltaic system. The actual operation data of the photovoltaic system is subjected to data dimension reduction and feature extraction to obtain a photovoltaic feature data set. Then, the photovoltaic feature data set is subjected to cluster analysis to mine power generation rules and efficiency characteristics of the photovoltaic panel under different environmental conditions, and a corresponding multiple regression model is constructed to represent the quantitative relationship between the power generation efficiency and the environmental factors.

[0049] As a preferred example, the multiple regression model is adjusted according to the heat island intensity index and the reflected light distribution, and an optimized distributed photovoltaic system deployment strategy is output.

[0050] The multiple regression model is adjusted according to the heat island intensity index and the reflected light distribution, and photovoltaic power generation efficiency is predicted by using the adjusted model to output photovoltaic prediction data.

[0051] The photovoltaic prediction data is compared with actual photovoltaic data, and a model prediction error is evaluated by using a bias analysis method on the comparison result, and the model parameters are adjusted according to the evaluation result.

[0052] The second photovoltaic panel installation strategy is optimized by using the model after the feedback adjustment to obtain the distributed photovoltaic system deployment strategy.

[0053] After the multiple regression model is obtained, the model is adjusted according to the heat island intensity index and the reflected light distribution, so that the prediction data output takes into account the factors such as the heat island intensity and the reflected light distribution of the city. The photovoltaic system power generation efficiency is predicted by using the adjusted model. The prediction data and actual photovoltaic data are compared to determine the error between the model and the actual photovoltaic system, and the error is analyzed and evaluated to determine the source of the error. Then, the model is adjusted according to the source of the error to further improve the practicability, reliability and accuracy of the model.

[0054] As a preferred example, the model prediction error is evaluated by using a bias analysis method on the comparison result, and the model parameters are adjusted according to the evaluation result.

[0055] The comparison result is attributed and decomposed by using the bias analysis method to obtain an error source analysis, and the model parameters are corrected according to the error source analysis.

[0056] The comparison result is subjected to uncertainty analysis to obtain a corresponding uncertainty source, and the model parameters are adjusted according to the uncertainty source.

[0057] The error source is determined by the bias analysis method, and the model is parameter corrected according to the error source, that is, the factors that have greater influence on the prediction error are determined, so as to realize the dynamic parameter adjustment of the model, so that the model can adapt to the changes of the actual operation state and environmental conditions of the photovoltaic system. Through the uncertainty analysis of the error, the uncertainty sources of the model parameters, input data and model structure are determined, the reliability and risk of the model prediction are evaluated, the model and algorithm are further optimized, the robustness and adaptability of the model prediction are improved, the continuous iteration and upgrading of the model are realized, and the scientificity and practicality of the photovoltaic power generation efficiency simulation prediction are improved.

[0058] Correspondingly, the embodiment also provides an optimization device of a distributed photovoltaic system, the optimization device comprising a heat island intensity determination module, a building model calculation module, a first strategy output module, a radiation intensity calculation module, a second strategy adjustment module and a photovoltaic system optimization module; wherein:

[0059] The heat island intensity determination module is configured to obtain temperature distribution data of a target city, and calculate the temperature distribution data by an interpolation analysis method to obtain a heat island intensity index;

[0060] The building model calculation module is configured to obtain a three-dimensional building model of the target city, and calculate solar radiation intensity and reflected light distribution according to the three-dimensional building model;

[0061] The first strategy output module is configured to determine photovoltaic panel temperature and system power generation efficiency of the distributed photovoltaic system according to the temperature distribution data and the solar radiation intensity, and output a first photovoltaic panel installation strategy;

[0062] The radiation intensity calculation module is configured to determine photovoltaic panel radiation intensity based on the first photovoltaic panel installation strategy and the three-dimensional building model, and construct a photovoltaic panel heat balance model based on the photovoltaic panel radiation intensity;

[0063] The second strategy adjustment module is configured to determine key influencing factors according to the photovoltaic panel heat balance model, and optimize and adjust the first photovoltaic panel installation strategy according to the key influencing factors, output and optimize and adjust the distributed photovoltaic system according to a second photovoltaic panel installation strategy;

[0064] The photovoltaic system optimization module is configured to obtain actual operation data of the distributed photovoltaic system after optimization and adjustment, construct a multiple regression model according to the actual operation data, optimize and adjust the multiple regression model according to the heat island intensity index and the reflected light distribution, and output an optimized distributed photovoltaic system optimization strategy. BRIEF DESCRIPTION OF DRAWINGS

[0065] Figure 1A flow chart of one embodiment of the optimization method of the distributed photovoltaic system provided by the present application;

[0066] Figure 2 A structure diagram of one embodiment of the optimization device of the distributed photovoltaic system provided by the present application. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the protection scope of the present application.

[0068] Embodiment one

[0069] Please refer to Figure 1 A flow chart of one embodiment of the optimization method of the distributed photovoltaic system provided by the present application, comprising steps 101 to 106, and each step is specifically as follows:

[0070] Step 101: Obtain temperature distribution data of a target city, and calculate the temperature distribution data by an interpolation analysis method to obtain a heat island intensity index.

[0071] The optimization method provided by the embodiments of the present application first performs spatial interpolation analysis on the temperature distribution data of the target city obtained by the interpolation analysis method to obtain the heat island intensity index of the city, so as to determine the heat island intensity change trend of each region of the target city at different times and seasons, to determine the heat island effect degree of each region in the city, to provide a decision basis for the city heat environment governance, and to provide reference data for the subsequent output of the photovoltaic panel installation strategy of the city.

[0072] In the present embodiment, the temperature distribution data of the target city is obtained, and the temperature distribution data is calculated by the interpolation analysis method to obtain the heat island intensity index, comprising:

[0073] Obtain the initial temperature distribution data of the target city, perform outlier rejection processing and missing value supplement processing on the initial temperature distribution data to obtain the temperature distribution data;

[0074] Perform spatial interpolation analysis on the temperature distribution data by the Kriging interpolation method to obtain the temperature distribution surface of the target city;

[0075] Calculate the heat island intensity index according to the temperature distribution surface, and divide the target city into regions according to the heat island effect grade according to the heat island intensity index to obtain the regional heat island grade.

[0076] By outlier rejection and missing value supplementing on the initial temperature distribution data, the quality and integrity of the temperature distribution data are improved, and by spatial interpolation of the temperature distribution data using the Kriging interpolation method, the temperature distribution surface in different seasons in the city, i.e. the temperature distribution map, such as the temperature distribution comparison map in winter and summer, can be obtained, which more intuitively shows the heat island effect of each region in the target city. By calculating the heat island intensity index of each region in the target city based on the temperature distribution map, and classifying the heat island effect of each region, the degree of influence of the heat island effect on each region in the target city can be determined, and the regions seriously affected can be prompted, thereby providing a decision basis for the urban heat environment management.

[0077] In this embodiment, the initial temperature distribution data obtained by the system includes temperature data in different time periods and seasons, and the obtained data needs to cover a large enough regional range and time span for subsequent comprehensive spatial interpolation analysis. After obtaining the initial temperature distribution data, the obtained temperature data is also preprocessed, including checking the integrity and accuracy of the data, and performing outlier rejection and missing value supplementing on the data, and preferably performing data interpolation and smoothing on the data to improve the data quality.

[0078] In this embodiment, when obtaining the temperature data of the target city, various observation means such as meteorological stations, automatic weather stations or mobile observation stations can be used to collect temperature data in different time and space scales. For example, 100 automatic weather stations are arranged in the central region of the target city, and each station records temperature data every 10 minutes, and continuous observation is performed for one year to obtain high temporal and spatial resolution temperature distribution data. When pre-processing the obtained temperature data, the box plot method can be used to identify outliers, and the data points exceeding 1.5 times the interquartile range of the upper and lower quartiles are regarded as outliers and are removed. For missing values, time series interpolation methods such as linear interpolation, spline interpolation, etc. can be used to estimate the missing values based on the temperature data before and after the missing values.

[0079] In this embodiment, when the system provided by the embodiment performs spatial interpolation analysis on the pre-processed temperature data using the Kriging interpolation method, the system will establish a best linear unbiased estimation model based on the spatial distribution and temperature value of the data points, specifically: selecting a suitable variogram model, such as an exponential model, a Gaussian model or a spherical model, etc., determining the model parameters through variogram fitting, calculating the spatial correlation and weight coefficient between the data points, and finally obtaining the continuous temperature distribution surface of the central region of the city. Based on the interpolation analysis results, the system can also generate the temperature distribution map of the central region of the city in different time periods and seasons, and intuitively present the spatio-temporal distribution characteristics of the urban heat island effect through visualization.

[0080] When the Kriging interpolation method is used for spatial interpolation analysis, an exponential variogram model can be selected, a variogram is fitted by a least square method, and parameters such as block gold value, base value and range are determined. According to the fitted variogram, a covariance matrix between data points is calculated, and then Kriging weight coefficients are calculated to obtain temperature estimation values at any position. For the interpolation analysis result, a temperature distribution map of the urban center area with a 1km*1km grid can be generated, and temperature distribution maps in different seasons, such as a temperature distribution comparison map in winter and summer, can be drawn.

[0081] To calculate the heat island intensity index, the embodiment quantifies the intensity of the heat island effect by calculating the average temperature difference between the urban center area and the suburb, or quantifies the calculation by using the calculation method of the heat island intensity index (HII), that is, HII=(Tu-Tr) / Tr, where Tu is the average temperature of the urban area, and Tr is the average temperature of the suburb. The change trend of the heat island intensity at different times and seasons can be analyzed by the above method. After determining the heat island intensity index of each area in the city, the system will also divide the degree of the heat island effect of each area in the city according to the grading standard of the heat island intensity index. The embodiment preferably divides the heat island intensity index into four levels of weak, medium, strong and extremely strong, to determine the high-temperature area seriously affected by the heat island effect and provide a decision basis for the urban heat environment management.

[0082] When calculating the heat island intensity index, 10 representative areas in the urban center area can be selected, the average temperature of each area is calculated, and then the average temperature of 10 reference areas in the suburb is compared to calculate the corresponding HII index. For example, when the average temperature of the urban center area is 35.5°C and the average temperature of the suburb is 32.1°C, HII=(35.5-32.1) / 32.1=0.106, indicating that the city has a strong heat island effect. According to the grading standard of the heat island intensity index, the area with HII>0.10 is divided into an extremely strong heat island area, which indicates that the area needs to take cooling measures to improve the efficiency of the cooling decision-making of the city.

[0083] Step 102: Obtain the three-dimensional building model of the target city, and calculate the solar radiation intensity and reflected light distribution according to the three-dimensional building model.

[0084] After determining the heat island intensity index of the city, the system obtains the three-dimensional building model of the city, and calculates the solar radiation intensity and reflected light distribution of the city to provide reference data for subsequent optimization and adjustment of the first photovoltaic panel installation strategy.

[0085] Specifically, the embodiment described obtaining the three-dimensional building model of the target city, and calculating the solar radiation intensity and the reflection light distribution according to the three-dimensional building model, comprising:

[0086] Obtain the building point cloud data of the target city, and sequentially perform denoising, point cloud classification and three-dimensional reconstruction processing on the building point cloud data to obtain the three-dimensional building model;

[0087] Obtain the solar radiation data and the reflectivity data of the building surface material of the target city, input the solar radiation data and the reflectivity data into the three-dimensional building model, and calculate the solar radiation intensity and the reflection light distribution of the building surface through the Monte Carlo simulation algorithm.

[0088] According to the building point cloud data of the city, the three-dimensional building model of the city is constructed, which provides a data basis for subsequent obtaining the solar radiation intensity of the city and the reflection light distribution of the city building surface. Through the obtained solar radiation data and the reflectivity data of the building surface and the constructed three-dimensional building model, the system can simulate and track the reflection and scattering process of sunlight on the city building surface through the Monte Carlo simulation algorithm, so as to determine the radiation brightness and the radiation flux distribution of each building, and further determine the reflection light distribution of each building surface, and the solar radiation intensity obtained by calculating various radiation intensities, which provides reference data for subsequent calculation of photovoltaic panel installation strategy.

[0089] In the embodiment, the building point cloud data of the city can be collected by laser radar scanning, unmanned aerial vehicle photogrammetry and other technologies to collect high-precision building point cloud data. Through point cloud data processing software, noise removal, point cloud classification and three-dimensional reconstruction are performed to generate a three-dimensional model of the city building, i.e. the three-dimensional building model described in the embodiment, including the geometric shape, spatial position and attribute information of the building. The system can extract the height, orientation and spacing of the building from the three-dimensional building model, calculate the absolute height and relative height of the building using three-dimensional space analysis method, determine the orientation of the building according to the normal vector of the outer wall surface of the building, and calculate the spacing between adjacent buildings by the shortest distance algorithm between buildings to form a building parameter database.

[0090] When obtaining the three-dimensional building model data of the city, a high-precision laser radar scanner such as LeicaScanStationP50 can be used to perform dense point cloud scanning on the city buildings, and the point cloud density can reach more than 1000 points per square meter. Then, point cloud processing software such as AutodeskReCap is used to remove noise points through statistical filtering algorithm, extract building point cloud using segmentation algorithm based on geometric features, and generate three-dimensional grid model of the building using Poisson surface reconstruction algorithm.

[0091] For the three-dimensional building model obtained by construction, the system can use the gridding method to calculate the building height, specifically: generate a building height grid layer with a spatial resolution of 1 meter, and use the MATLAB tool parameter ComputerVisionToolbox to calculate the main orientation of the building outer wall surface through the normal vector clustering algorithm to obtain the angle distribution of the building orientation. For the spacing between adjacent buildings, the Near tool of ArcGIS can be used to calculate the minimum Euclidean distance between each building and the adjacent building, and then generate a distance matrix of the building spacing.

[0092] After obtaining the three-dimensional building model of the city, the system will further obtain the solar radiation data of the region where the city is located, including the solar elevation angle, azimuth angle and direct radiation intensity, etc., and use the Perez model to calculate the solar radiation intensity at different times and positions, considering the influence of atmospheric transmittance, cloud cover and solar position, etc. Get the solar radiation intensity distribution at different positions and times in the city.

[0093] In calculating the solar radiation intensity, the system can use the gendaylit module of RADIANCE software, based on the Perez sky brightness distribution model, set the latitude and longitude coordinates, time zone and time parameters of the region where the city is located, and input the hourly meteorological parameters such as total cloud cover, low cloud cover, etc. The sky radiation brightness distribution is calculated by simulation. Then use the rtrace tool of RADIANCE to generate radiation sampling points in the city with a spatial step of 1 meter, calculate the direct solar radiation intensity and sky scattered radiation intensity received by each sampling point, and obtain the solar radiation intensity distribution diagram of the city at different positions and times.

[0094] For the collection of building surface material reflectivity data, spectral measurement will be performed on common building materials such as glass, concrete, paint, etc. to obtain the reflectivity curve of the material at different wavelengths, and establish a building material reflectivity database to provide material parameters for subsequent light tracing simulation.

[0095] When calculating the reflectivity of common building outer wall materials, ASD FieldSpec4 and other ground object spectrometers can be used to measure the spectral reflectivity curve of the material in the visible to near-infrared band (350-2500nm), and Beckman-Kirchhoff model is used to correct the measured data to obtain the standard reflectivity curve of the material.

[0096] After obtaining the two kinds of data including the solar radiation data and the reflectivity data of the building surface material, they are combined with the three-dimensional building model and input into the Monte Carlo ray tracing simulation software, i.e. the Monte Carlo simulation algorithm is used to calculate them in the embodiment. Specifically, the professional software such as Radiance and TracePro is used to set the parameters of the ray tracing such as the number of rays, the number of reflections and the energy threshold, and the propagation and reflection process of the sunlight in the urban building environment is simulated. By setting the parameters of the ray emission, intersection and reception, the reflection and scattering process of the light on the building surface is simulated, the radiation luminance and the radiation flux of the surface are calculated, and the reflected light intensity and the directional distribution of different positions of the building surface are obtained. The ray tracing simulation results are statistically analyzed, the reflected radiation data of the building wall are extracted, the average radiation intensity, the maximum radiation intensity and the total radiation energy under different time and direction are calculated, and the time sequence curve and the spatial distribution diagram of the reflected radiation are generated, i.e. the solar radiation intensity and the reflected light distribution in the embodiment.

[0097] In the Monte Carlo ray tracing simulation, the rcontrib tool of RADIANCE is preferably used in the embodiment, the number of rays is set to 10000000, the number of reflections is set to 5, the energy threshold is set to 0.001, the reflectivity curve of the building material is input as the material parameter, the reflection and scattering process of the sunlight on the building surface is simulated, and the radiation luminance and the radiation flux distribution of each position of the building surface are obtained. Then, the Statistics and Machine Learning Toolbox of MATLAB is used to statistically analyze the reflected radiation of the building wall, calculate the average radiation intensity, the maximum radiation intensity and the total radiation energy of the wall, and generate the space-time distribution diagram of the reflected radiation by using the interpolation algorithm.

[0098] Step 103: calculating the photovoltaic panel temperature and the system power generation efficiency of the distributed photovoltaic system according to the temperature distribution data and the solar radiation intensity, and outputting a first photovoltaic panel installation strategy.

[0099] Through the temperature distribution data and the solar radiation intensity of the target city, the system can calculate the photovoltaic panel temperature and the system power generation efficiency of the distributed photovoltaic system in the city, and determine the first photovoltaic panel installation strategy through the temperature distribution data and the solar radiation intensity, i.e. the first photovoltaic panel installation strategy obtained after considering the system power generation efficiency and the photovoltaic panel installation environment and other factors, which provides a data basis for subsequent optimization.

[0100] Specifically, the embodiment calculates the photovoltaic panel temperature and the system power generation efficiency of the distributed photovoltaic system according to the temperature distribution data and the solar radiation intensity, and outputs a first photovoltaic panel installation strategy, which specifically includes:

[0101] inputting the temperature distribution data and the solar radiation intensity into a preset Sandia array performance model for calculation and processing to obtain the photovoltaic panel temperature and the system power generation efficiency;

[0102] obtaining building density data and green coverage data of the target city, and constructing a photovoltaic array multi-objective optimization model based on the building density data, the green coverage data, and the photovoltaic panel temperature and the system power generation efficiency;

[0103] optimizing and solving the photovoltaic array multi-objective optimization model through a genetic algorithm to output the first photovoltaic panel installation strategy.

[0104] The temperature distribution data and the solar radiation intensity are processed through the Sandia array performance model, the spatiotemporal continuity and consistency of the temperature data are ensured, the environmental temperature boundary condition is provided for subsequent photovoltaic array performance simulation, the material properties, electrical parameters, and installation conditions of the photovoltaic panel are comprehensively considered through the solar radiation intensity data, and then the photovoltaic panel temperature and the power generation efficiency of the photovoltaic system are obtained, thereby improving the accuracy and reliability of the obtained data.

[0105] After obtaining the above data, the system also obtains the building density data and the green coverage data of the city to ensure that the subsequently generated photovoltaic panel installation strategy fully considers the shading effect of greenery on the radiation of the photovoltaic panel. The photovoltaic array multi-objective optimization model constructed through the above data not only comprehensively considers the system power generation, green building shading, and landscape coordination, but also is further optimized through a genetic algorithm, thereby improving the practicality, reliability, and accuracy of the output photovoltaic panel installation strategy.

[0106] As another example of obtaining temperature distribution data in the embodiment, the system can generate a temperature distribution grid data set of the three-dimensional space of the city through thermal infrared remote sensing, ground meteorological stations, and other multi-source data, through Kriging interpolation and Kalman filtering and other spatiotemporal interpolation and data assimilation methods, to ensure the spatiotemporal continuity and consistency of the temperature data and provide the environmental temperature boundary condition for subsequent photovoltaic array performance simulation, that is, the temperature distribution data obtained in the embodiment.

[0107] When obtaining the temperature distribution data of the city, the system can use Landsat8TIRS and other thermal infrared remote sensing images to extract the surface temperature information, the spatial resolution is 100 meters, and the temporal resolution is 16 days. At the same time, the hourly temperature observation data of the city meteorological station is used to obtain the temperature distribution of the 1000-meter grid through Kriging interpolation. The ensemble Kalman filtering algorithm is used to fuse the surface temperature inverted by remote sensing and the temperature interpolated by the meteorological station to obtain the spatiotemporal continuous three-dimensional temperature distribution data.

[0108] The temperature distribution data and the solar radiation intensity are processed by the Sandia array performance model. Specifically, the Sandia photovoltaic array performance model is used to calculate the working temperature and output power of the photovoltaic panel under different installation angles and positions by comprehensively considering factors such as material properties, electrical parameters and installation conditions of the photovoltaic panel, and the power generation efficiency curve of the photovoltaic array is obtained in combination with the inverter efficiency and system loss.

[0109] In this embodiment, the "PVLib" photovoltaic array performance calculation model proposed by Sandia National Laboratory is preferably used, the photovoltaic component is set as a single crystal silicon cell, the rated power is 320W, and the efficiency is 19.1%, and the photovoltaic panel temperature and output power curve under different inclination angles (0-90 degrees) and azimuth angles (0-360 degrees) are calculated.

[0110] After obtaining the building density data and green coverage data of the target city, the system will also calculate the available area and shading factor of the roof and wall of the building by using the area ratio method and the visual analysis method, extract the geometric information of the building, calculate the available area of the roof and wall, and consider the shading effect of the greenery on the radiation of the photovoltaic panel. In this embodiment, the green coverage rate of 40% is preferably considered to correct the effective radiation intensity of the photovoltaic array.

[0111] According to the above data, a multi-objective optimization model of the photovoltaic array is constructed, and a first photovoltaic panel installation strategy is output. Specifically, a multi-objective function for photovoltaic array layout optimization is constructed, factors such as maximum power generation, minimum building shading, and landscape coordination are considered, and a genetic algorithm is used for multi-objective optimization solution. The key elements such as the coding method of the decision variable, the construction of the fitness function, the design and parameter tuning of the genetic operator (selection, crossover, mutation), and the judgment of the convergence condition are determined, and the specific algorithm flow and pseudo code are given combined with the characteristics of photovoltaic layout optimization, and the optimization configuration scheme of the photovoltaic panel installation angle, orientation and density under different weight combinations is obtained, that is, the first photovoltaic panel installation strategy described in this embodiment.

[0112] In this embodiment, three objective functions for photovoltaic layout optimization are preferably constructed, which are annual power generation, building shading ratio and landscape coordination degree, and the NSGA-II multi-objective genetic algorithm is used, the population number is set to 100, the crossover probability is 0.8, the mutation probability is 0.1, and the iteration is 500 times, and the Pareto optimal solution set is obtained. A plurality of initial installation angle and position combinations are generated as the initial population, and the power generation efficiency and photovoltaic panel temperature of each combination are calculated, and then the fitness is evaluated according to the objective function, and the combinations with better performance are selected for crossover and mutation operation. A new generation of combinations is generated through crossover and mutation operation, and when the set number of iterations or the fitness is no longer significantly improved, the optimal installation angle and position are output.

[0113] Step 104: calculating the photovoltaic panel radiation intensity based on the first photovoltaic panel installation strategy and the three-dimensional building model, and constructing a photovoltaic panel heat balance model based on the photovoltaic panel radiation intensity.

[0114] After obtaining the first photovoltaic panel installation strategy, the system adjusts the installation position of the photovoltaic panel in the three-dimensional building model according to the strategy, and calculates the radiation intensity of the photovoltaic panel based on the adjusted model, that is, determines the direct solar radiation and building surface reflected radiation at different solar elevation angles and azimuth angles through model simulation to determine the radiation intensity on the photovoltaic panel, and constructs a photovoltaic panel heat balance model based on the determined photovoltaic panel radiation intensity, thereby improving the accuracy and reliability of the model in predicting the temperature change and power generation performance of the photovoltaic panel.

[0115] Specifically, the embodiment calculates the photovoltaic panel radiation intensity based on the first photovoltaic panel installation strategy and the three-dimensional building model, and constructs a photovoltaic panel heat balance model based on the photovoltaic panel radiation intensity, which includes:

[0116] According to the first photovoltaic panel installation strategy, the three-dimensional building model is adjusted in parameters, and the reflection and shielding of sunlight are simulated by the Monte Carlo ray tracing method to obtain the radiation flux per unit area of the photovoltaic panel;

[0117] According to the radiation flux, a corresponding building surface radiation transmission mathematical model is constructed, and the photovoltaic panel radiation intensity is calculated based on the building surface radiation transmission mathematical model;

[0118] According to the photovoltaic panel radiation intensity and the heat exchange process of the photovoltaic panel, the photovoltaic panel heat balance model is constructed.

[0119] After adjusting the three-dimensional building model in parameters by the output first photovoltaic panel installation strategy, the system will again simulate the reflection and shielding of sunlight by the Monte Carlo ray tracing method to determine the solar radiation intensity per unit area of each photovoltaic panel after adjusting the placement position of the photovoltaic panel, that is, the radiation flux, and construct a corresponding building surface radiation transmission mathematical model based on the determined radiation flux to further clarify the propagation and distribution process of radiation energy on the building surface.

[0120] The photovoltaic panel radiation intensity of the photovoltaic panel can be calculated based on the constructed transmission mathematical model, and the photovoltaic panel heat balance model can be constructed based on the photovoltaic panel radiation intensity and the heat exchange process of the photovoltaic panel, considering the heat transfer mechanisms including solar radiation absorption, photoelectric conversion, convective heat transfer, and thermal radiation, establishing the mathematical relationship between the photovoltaic panel temperature and environmental conditions, material properties, structural parameters, etc., to construct the heat balance model of the photovoltaic panel, so that the model can accurately predict the temperature change and power generation performance of the photovoltaic panel.

[0121] In this embodiment, when the system adjusts the three-dimensional building model according to the first photovoltaic panel installation strategy, it includes adjusting the three-dimensional building model according to the geographical coordinates of the building location and the time parameter, using the equatorial coordinate system model of the sun position, determining the position of the sun on the celestial sphere through the parameters of the sun declination and the sun declination, and then calculating the height angle and azimuth angle of the sun relative to the horizon according to the latitude and longitude of the building location and the time zone. The main calculation formulas include the solar hour angle, the declination angle, the height angle, and the azimuth angle, which need to consider the influence of the earth's revolution, introduce the correction terms of the mean time difference and the angle between the sun and the earth, and obtain the incident angle and the azimuth of the sun relative to the building surface at different times.

[0122] For the case of installing photovoltaic panels on the facade of a building, this embodiment first obtains a three-dimensional model of the building facade. When obtaining the three-dimensional model of the building facade, methods such as unmanned aerial vehicle photogrammetry or laser scanning can be used to collect point cloud data of the building surface with a spatial resolution of 0.1 meters. Through point cloud data processing software such as RealityCapture or CloudCompare, noise removal, point cloud segmentation, and triangular mesh reconstruction are performed to obtain a three-dimensional entity model of the building facade. For a building with a height of 50 meters, a width of 30 meters, and a length of 80 meters, a mesh model composed of 2 million triangular facets can be generated, with each triangular facet having a size of about 0.5-1 square meters. Using the Ladybug plug-in, based on the latitude and longitude coordinates of the building location (e.g., Beijing, East Longitude 116.3°, North Latitude 39.9°) and the UTC+8 time zone, the sun position at different times on June 22, 2022 is calculated. According to the WGS84 ellipsoid parameters and the Meeus algorithm, the sun declination, the sun declination, and the hour angle are calculated, and considering the atmospheric refraction correction of -0.8° and the sun correction time of ±8 minutes, the sun height angles at 9:00, 12:00, 15:00, and 18:00 are 28.3°, 73.2°, 52.1°, and 7.6°, respectively, and the azimuth angles are east-south 74.5°, south, west-south 63.8°, and west-north 86.4°, respectively.

[0123] The reflection and shading of sunlight are simulated using the Monte Carlo ray tracing method to obtain the radiation flux per unit area of the photovoltaic panel. Specifically, the Monte Carlo ray tracing method is used to simulate the reflection and shading of sunlight on the building surface. Starting from the sunlight source, a large number of rays are emitted towards the building surface according to the direction and intensity of the direct solar radiation. To balance the calculation accuracy and efficiency, methods such as hierarchical sampling or importance sampling are used to project more rays in areas with larger changes in radiation intensity and fewer rays in areas with smaller changes in radiation intensity. Parallel computing techniques such as GPU acceleration are also used to improve the calculation efficiency of ray tracing. When a ray intersects with the building surface, the reflection direction and intensity attenuation of the ray are calculated based on the optical parameters of the surface material such as reflectivity, absorptivity, and roughness. The next reflection is performed until the ray is absorbed or exits the building scene. During the ray tracing process, the radiation shading of the photovoltaic panel at different positions on the building facade is determined by the intersection test of the ray and the building surface. Algorithms such as ray-triangle intersection and octree spatial division are used to speed up the intersection test of the ray and the building surface.

[0124] In the Monte Carlo ray tracing method, the Importance Sampling algorithm is preferably used to generate 10^7 rays in the solid angle space according to the importance distribution of the BSDF reflectivity function. The Embree ray tracing kernel and GPU parallel computing are used to realize real-time intersection and multiple reflections of rays with the scene. For a photovoltaic panel with a size of 1m x 1.5m, 100 candidate installation positions are divided on the southern facade of the building from a height of 10m to 40m with a spacing of 2m. The octree algorithm is used to project 10^4 rays for each position to perform visibility analysis, and the cumulative values of direct solar radiation and sky scattered radiation during the period of 10:00-14:00 are calculated. The results show that the annual average radiation of position No. 12 is the highest, reaching 1280kWh / m^2, but there is a 20% and 35% shading rate during the periods of 9:00-10:00 and 16:00-17:00.

[0125] For each candidate installation position, the number and intensity of direct and reflected rays falling on the photovoltaic panel are counted, and the inclination and azimuth angles of the photovoltaic panel are considered to calculate the radiation flux per unit area of the photovoltaic panel. For the shaded photovoltaic panel positions, the cumulative shading time and shading ratio in a day are calculated as the constraint conditions for installation position optimization.

[0126] According to the radiation flux, a corresponding building surface radiation transmission mathematical model is constructed, which specifically includes considering multiple radiation sources such as direct solar radiation, sky scattered radiation and building surface reflected radiation, and using a radiation transmission equation to describe the propagation and distribution process of radiation energy on the building surface. Meanwhile, the embodiment will combine the statistical results of ray tracing to calculate the total radiation intensity variation curve of each photovoltaic panel installation position at different times of a day. Taking the maximum average radiation of the unit area of the photovoltaic panel as the objective function, and taking the geometric constraints and aesthetic requirements of the building facade as the constraint conditions, the genetic algorithm (GA) or the particle swarm optimization algorithm (PSO) is used to optimize the search of the installation angle and orientation of the photovoltaic panel.

[0127] Preferably, the embodiment adopts a radiation transmission equation and a finite element discretization method to establish a numerical model of building surface radiation transmission, and combines Radiance software to obtain the radiation intensity distribution of each photovoltaic panel position at different times.

[0128] Specifically, the inclination and azimuth of the photovoltaic panel are taken as the optimization variables, the annual average radiation is taken as the objective function, and the installation area, shading ratio, and aesthetic degree are taken as the constraint conditions to construct an optimization model. The GA algorithm constantly updates the population through selection, crossover, and mutation operations to search for the optimal solution; the PSO algorithm finds the optimal particle in the solution space through position updating and speed updating of the particle.

[0129] Preferably, the embodiment uses the NSGA-II multi-objective genetic algorithm to optimize the installation angle and orientation of the photovoltaic panel, takes the annual power generation, radiation uniformity, and shading rate as the optimization targets, takes the installation angle 0°-90° and the orientation angle -90°-90° as the constraint variables, sets the population size to 50, the crossover probability to 0.8, the mutation probability to 0.1, and iterates for 200 generations to obtain the Pareto optimal solution set. After balancing the three targets, the optimal installation angle is 30°, the optimal orientation angle is south by west 15°, the annual power generation is increased by 5%, and the shading rate is reduced by 10%.

[0130] In addition, the embodiment also sets reasonable algorithm parameters, such as population size, evolution generation, crossover probability, mutation probability, etc., and carries out parameter sensitivity analysis and algorithm performance evaluation, to obtain the optimal installation position and angle of the photovoltaic panel on the building facade. The optimized photovoltaic panel installation parameters are applied to the building photovoltaic integrated design to generate a three-dimensional visual model of the photovoltaic panel combined with the building facade, and light and shadow rendering and energy balance analysis are carried out to provide data support for subsequent construction of photovoltaic panel thermal balance model. According to the rated power and efficiency parameters of the photovoltaic panel, the power generation and benefit of the photovoltaic system under different seasons and weather conditions are estimated, to provide data support for the decision of building photovoltaic integrated scheme. At the same time, the sensitivity analysis of the installation position and angle of the photovoltaic panel is carried out, to evaluate the influence of the changes of building height-width ratio, spacing, surface material and other parameters on the photovoltaic power generation performance, to optimize the building design parameters and realize the maximization of the comprehensive benefit of building photovoltaic integration.

[0131] Preferably, the embodiment builds a parametric design model in Rhino platform, embeds the optimization results into the building facade, generates a three-dimensional model of photovoltaic panel integrated with the building, and introduces DIVA plug-in in Grasshopper to analyze the hourly power generation and daily power generation of photovoltaic system in different seasons. The peak power of the optimized photovoltaic system is 80kW, and the daily power generation of the system on the summer solstice day, the spring equinox day and the winter solstice day is 540kWh, 380kWh and 210kWh respectively, which is increased by 8%-12% compared with that before optimization. The analysis shows that the annual average radiation of the facade decreases by 1.5% when the height-width ratio of the building increases by 0.1; the shading rate of the photovoltaic panel increases by 2% when the building spacing decreases by 1 meter; the reflected radiation decreases by 30% when the facade material is changed from light color to dark color. Therefore, the introduction of photovoltaic optimization analysis in the building design stage can provide scientific and quantitative design basis for architects and promote the popularization and application of building photovoltaic integration.

[0132] According to the radiation intensity of the photovoltaic panel and the heat exchange process of the photovoltaic panel, a photovoltaic panel thermal balance model is constructed, which specifically includes: considering the heat exchange process between the photovoltaic panel and the surrounding environment, including solar radiation absorption, photoelectric conversion, convective heat transfer, thermal radiation and other heat transfer mechanisms, establishing the mathematical relationship between the temperature of the photovoltaic panel and the environmental conditions, material properties, structure parameters and other factors.

[0133] Meanwhile, the system will also collect typical meteorological year data of the location of the photovoltaic panel, including hourly environmental temperature, wind speed, solar radiation intensity and other meteorological parameters, as input conditions for energy simulation; obtain technical parameters of the photovoltaic panel, such as photoelectric conversion efficiency, surface roughness, heat capacity, thermal conductivity and the like, as boundary conditions and material attribute parameters of the thermal equilibrium model; and use energy simulation software to calibrate and verify the photovoltaic panel thermal equilibrium model, compare with the measured data, adjust the empirical coefficients and key parameters in the model, such as convective heat transfer coefficient, radiation absorption rate and the like, so that the model can accurately predict the temperature change and power generation performance of the photovoltaic panel.

[0134] Preferably, in the construction of the photovoltaic panel thermal equilibrium model, the Sandia photovoltaic array performance model and related components in the EnergyPlus software can be selected, the geometric size, orientation, inclination and the like of the photovoltaic panel are set, the photoelectric conversion efficiency curve, temperature coefficient and the like of the silicon cell are defined, the convective heat exchange process between the photovoltaic panel and the air, ground and the like environment is established, the hourly meteorological parameters of the target city typical meteorological year are input, such as dry bulb temperature, wind speed, total horizontal radiation intensity and the like, and the temperature change and power generation of the photovoltaic panel under different environmental conditions are simulated.

[0135] In addition, the system of the embodiment also uses root mean square error RMSE and mean absolute percentage error MAPE and the like to evaluate the accuracy of the model, and the smaller the RMSE and MAPE, the higher the accuracy of the model.

[0136] Preferably, the Hooke-Jeeves mode search algorithm can be used in the parameter estimation tool GenOpt in EnergyPlus, the measured photovoltaic panel temperature and output power are used as training data, the convective heat transfer coefficient, backboard infrared emissivity and the like key parameters in the model are optimized, the root mean square error RMSE between the model output and the measured data is less than 1.2℃, and the mean absolute percentage error MAPE is less than 5%.

[0137] Step 105: determining the key influencing factors according to the photovoltaic panel thermal equilibrium model, and optimizing and adjusting the first photovoltaic panel installation strategy according to the key influencing factors, and outputting and optimizing and adjusting the distributed photovoltaic system according to the second photovoltaic panel installation strategy.

[0138] The key factors, i.e. the key influencing factors, affecting the temperature and power generation efficiency of the photovoltaic panel can be further determined through the constructed photovoltaic panel thermal equilibrium model, the weight parameters of the first photovoltaic panel installation strategy are adjusted according to the determined key influencing factors, and the strategy is adjusted again to obtain the second photovoltaic panel installation strategy, with the temperature change and power generation efficiency of the photovoltaic panel as the optimization target.

[0139] Specifically, the method comprises the following steps:

[0140] The photovoltaic panel temperature and the system power generation efficiency are simulated and analyzed through the photovoltaic panel heat balance model to obtain corresponding change curves;

[0141] The key influencing factors are obtained through the sensitivity analysis algorithm to screen the change curves;

[0142] Then, the first photovoltaic panel installation strategy is optimized and adjusted based on the key influencing factors through the genetic algorithm.

[0143] The photovoltaic panel temperature and the power generation efficiency are simulated through the constructed heat balance model, and the change curves of the photovoltaic panel temperature and the power generation efficiency with time are obtained. The factors that may affect the photovoltaic panel temperature and the power generation efficiency are screened through the analysis of the change curves, and the most significant factors that affect the photovoltaic panel temperature and the efficiency, such as the environmental temperature, the wind speed or the conversion efficiency, are screened through the sensitivity analysis algorithm. After the key factors are determined, the installation strategy of the photovoltaic panel is secondarily optimized and adjusted according to the key factors, so that the power generation efficiency of the photovoltaic panel is further improved and the temperature influence is reduced.

[0144] In the embodiment, on the basis of the verified heat balance model, the system also carries out simulation analysis of the photovoltaic panel temperature and the power generation performance, sets different environmental temperature and radiation intensity conditions, simulates the dynamic temperature response and output power change of the photovoltaic panel, and draws the change curves of the temperature and the efficiency with time.

[0145] Preferably, on the basis of the verified heat balance model, the environmental temperature is set to -10℃, 0℃, 10℃, 25℃, 40℃, the radiation intensity is set to 200W / m 2 , 400W / m 2 , 600W / m 2 , 800W / m 2 , 1000W / m 2 , and a total of 25 working condition combinations are set. The hourly change curves of the photovoltaic panel temperature and the power generation efficiency under each working condition are simulated, and it is found that when the radiation intensity is 1000W / m 2 and the environmental temperature is 40℃, the maximum temperature of the photovoltaic panel can reach 78℃, and the power generation efficiency decreases to 8.5%.

[0146] The influence factor screening by sensitivity analysis algorithm is specifically as follows: the Morris global sensitivity analysis method is used to evaluate the influence significance of environmental factors, material properties and structure parameters on the photovoltaic panel temperature and power generation efficiency. The Morris method calculates the elementary effect value (EE) of each factor by factor perturbation and trajectory sampling. The EE is defined as the approximate value of the partial derivative of the model output with respect to a certain factor. The mean value μ of the EE is defined as the overall influence of the factor. The standard deviation σ of the EE is defined as the nonlinear influence of the factor or the interaction with other factors. In the Morris diagram, the greater the μ value, the stronger the main effect of the factor, and the greater the σ value, the stronger the nonlinear or interaction effect of the factor.

[0147] Preferably, the Morris sensitivity analysis method is used in the variation ranges of the initial temperature of the photovoltaic panel 25±5℃, the wind speed 2.5±0.5m / s, the radiation intensity 800±160W / m 2 , the silicon cell conversion efficiency 0.18±0.036, and the backboard roughness 0.9±0.18 to generate 50 Morris experimental samples. The EnergyPlus model is run to calculate the maximum temperature and average power generation efficiency of the photovoltaic panel, and the Morris indexes μ and σ of each factor are obtained. The above data show that the μ values of the radiation intensity, the silicon cell conversion efficiency and the wind speed are the largest, being 15.8, 12.6 and 9.4 respectively, which are the key factors affecting the temperature and efficiency of the photovoltaic panel. The σ values of the backboard roughness, the photovoltaic panel length and the silicon cell temperature coefficient are relatively large, being 4.2, 3.5 and 2.8 respectively, indicating that these factors have strong interaction effects with other factors.

[0148] Therefore, the sensitivity analysis of the influence factors can determine the factors to be analyzed and the variation ranges thereof. The perturbation vectors are randomly generated in the factor space, the Morris trajectory matrix is constructed, the trajectory matrix is taken as the input of the model, the model is run to calculate the output response, the EE value, μ value and σ value of each factor are calculated, the Morris diagram is drawn, and the key influence factors are screened. In the variation ranges, the initial temperature of the photovoltaic panel, the wind speed, the solar radiation intensity, the conversion efficiency, the surface roughness and other key parameters are perturbed, and the factors most significantly affecting the temperature and efficiency of the photovoltaic panel, such as the environmental temperature, the wind speed and the conversion efficiency, are screened.

[0149] According to the sensitivity analysis results, the system of the embodiment can determine the key influencing factors of the photovoltaic panel temperature and efficiency, and optimize the design of the heat dissipation structure and temperature control strategy of the photovoltaic panel by using a genetic algorithm, that is, the first photovoltaic panel installation strategy is adjusted according to the key influencing factors. The size, spacing, and material thermal conductivity of the photovoltaic panel heat dissipation fin are used as optimization variables, and the minimum maximum temperature, minimum temperature fluctuation, and maximum power generation efficiency of the photovoltaic panel are used as optimization objectives to establish a multi-objective optimization model.

[0150] Preferably, according to the sensitivity analysis results, the NSGA-II multi-objective genetic algorithm is used, the width, thickness, spacing, and material thermal conductivity of the heat dissipation fin are used as optimization parameters, the maximum temperature, temperature fluctuation, and power generation efficiency of the photovoltaic panel are used as optimization objectives, 50 initial individuals are generated, the crossover probability is 0.8, the mutation probability is 0.1, and the iteration is 500 generations, and 8 non-dominated solutions of the Pareto optimal front are obtained. After balancing the heat dissipation performance and cost, the scheme of heat dissipation fin width 0.08 m, thickness 0.002 m, spacing 0.04 m, and thermal conductivity 205 W / (m·K) is selected, which is applied to a 1 m×1.5 m, rated power 250 W polycrystalline photovoltaic panel.

[0151] Combined with the hourly weather forecast data and load prediction data, a temperature control strategy is designed, the upper limit of the photovoltaic panel surface temperature is set to 50℃, according to the predicted environmental temperature and radiation intensity, the heat dissipation fan is started 1 hour in advance, the fuzzy PID control algorithm is used, the speed of the heat dissipation fan is dynamically adjusted according to the deviation and deviation change rate of the photovoltaic panel surface temperature and the target temperature, so that the photovoltaic panel temperature is stabilized at 50±2℃, and the photovoltaic panel power generation performance is improved to the greatest extent. After optimization, under the summer sunny weather condition, the maximum temperature of the photovoltaic panel is reduced from 78℃ to 52℃, the temperature fluctuation is reduced from 30℃ to 5℃, the power generation efficiency is increased from 8.5% to 14.3%, the annual power generation capacity is increased by 10.2%, the annual power consumption of the heat dissipation fan is about 1.5% of the photovoltaic panel power generation capacity, and the operation and maintenance cost is equivalent to the annual power generation income of the photovoltaic panel.

[0152] Step 106: Obtain the actual operation data of the optimized and adjusted distributed photovoltaic system, construct a multiple regression model according to the actual operation data, optimize and adjust the multiple regression model according to the heat island intensity index and the reflection light distribution, and output the optimized distributed photovoltaic system deployment strategy.

[0153] After obtaining the second photovoltaic panel installation strategy, the distributed photovoltaic system can be adjusted through the strategy, and the strategy can be further optimized according to the actual operation data of the photovoltaic system, including the heat island intensity index and the reflected light distribution, to obtain an optimized photovoltaic system optimization strategy, thereby improving the power generation efficiency of the optimized photovoltaic system deployment strategy, and reducing the photovoltaic panel temperature caused by the urban heat island effect and the building reflected radiation, thereby improving the overall efficiency of the photovoltaic power generation system. At the same time, by identifying the power generation mode and efficiency characteristics of the photovoltaic system under different environmental conditions, and determining the correlation between the actual power generation efficiency and environmental factors, the deployment strategy of the photovoltaic system is optimized, and intelligent management and efficient operation of the photovoltaic power generation system are realized.

[0154] Specifically, the actual operation data of the distributed photovoltaic system after optimization and adjustment is obtained, and a multiple regression model is constructed according to the actual operation data, including:

[0155] The actual operation data of the distributed photovoltaic system is obtained, and the actual operation data is processed by dimension reduction and feature extraction to obtain a photovoltaic feature data set;

[0156] The photovoltaic feature data set is subjected to cluster analysis, and the photovoltaic feature data set is divided into different cluster clusters according to the preset power generation index, and the photovoltaic power generation influencing factors are determined according to the cluster clusters, and then the multiple regression model is constructed according to the photovoltaic power generation influencing factors and the power generation efficiency.

[0157] After determining the twice-adjusted photovoltaic panel installation strategy, the system can adjust the distributed photovoltaic system according to the strategy to obtain the actual operation data of the adjusted photovoltaic system, and obtain a photovoltaic feature data set by performing data dimension reduction and feature extraction on the actual operation data of the photovoltaic system. Then the photovoltaic feature data set is subjected to cluster analysis, so as to mine the power generation law and efficiency characteristics of the photovoltaic panel under different environmental conditions, and construct a corresponding multiple regression model for representing the quantitative relationship between power generation efficiency and environmental factors.

[0158] In this embodiment, the actual operation data of the photovoltaic panel is obtained through the photovoltaic power station monitoring system, including the voltage, current, power and other electrical parameters of the direct current side and alternating current side of the inverter, and the temperature data of the surface of the photovoltaic panel. The photovoltaic operation data is preprocessed to remove outliers and invalid values, and the missing data is interpolated to complete, and the data is normalized and standardized according to the statistical characteristics of the data, so as to eliminate the influence of different dimensions and orders of magnitude, and prepare for subsequent data mining analysis.

[0159] Preferably, in order to obtain actual operation data of the photovoltaic panel, the data acquisition device is used to collect data in multiple dimensions such as voltage, current, power and temperature of the photovoltaic panel in real time, and the sampling frequency can be set to once per minute. The collected data is cleaned and preprocessed, and abnormal data and noise data exceeding the normal range are removed, such as voltage exceeding rated value ± 5%, current exceeding rated value ± 10% and the like. Then the data is normalized by maximum and minimum value, and the data is mapped to the interval [0, 1].

[0160] Preferably, the principal component analysis (PCA) and independent component analysis (ICA) are used to extract features of the photovoltaic operation data, and the main feature vectors of the data are extracted. The PCA converts the original data set into a set of linearly independent principal components through orthogonal transformation, and extracts the main features of the data. The original data is centered, the covariance matrix of the data is calculated, the eigenvalue decomposition of the covariance matrix is performed, the eigenvectors corresponding to the largest k eigenvalues are selected, the principal component matrix is formed, and the original data is multiplied by the principal component matrix to obtain the principal component scores.

[0161] Specifically, the system extracts key feature parameters such as photovoltaic panel power generation efficiency, power generation power and temperature change according to the preprocessed data, and selects the first k principal components with cumulative variance contribution rate of 95% as feature vectors.

[0162] ICA separates independent source signals from mixed signals by maximizing statistical independence. Common ICA algorithms include FastICA, Infomax, etc. The data is centered and whitened, the demixing matrix is randomly initialized, the demixing matrix is iteratively updated to maximize the non-Gaussianity of the output signal, and the output signal is multiplied by the transpose of the demixing matrix to obtain the independent component. The extracted features include statistical indicators such as mean, variance and peak-to-peak value of voltage, current, power and temperature, as well as external factors such as ambient temperature, radiation intensity and wind speed, forming a photovoltaic power generation feature data set.

[0163] The clustering analysis of the photovoltaic feature data set is performed by using the K-means clustering algorithm and the hierarchical clustering algorithm, the data is divided into a plurality of clustering clusters according to the similarity of the voltage, the current, the power and the efficiency, and each cluster represents a typical power generation mode. K samples are randomly selected as initial clustering centers, the Euclidean distance of each sample to each clustering center is calculated, the sample is divided into the nearest cluster, the mean value of each cluster is recalculated as a new clustering center, the Euclidean distance and the cluster division are repeatedly calculated until the clustering center no longer changes. Each sample is initialized as a cluster by using the aggregation method, the distance matrix (such as the shortest distance, the longest distance or the average distance) between clusters is calculated, the two clusters with the nearest distance are merged, and the distance matrix is updated, the clusters are repeatedly merged until all samples are classified into one category or the preset cluster number is reached. The clustering process can be intuitively represented by a tree diagram.

[0164] Preferably, the K-means clustering algorithm is used to perform clustering analysis on the extracted feature parameters, the elbow rule is used to determine that the optimal clustering number is 3, and the photovoltaic panel power generation mode and efficiency feature set under three typical environmental conditions of sunny, cloudy and rainy days are obtained. Meanwhile, the environmental factor data of the region where the photovoltaic panel is located are obtained, including the solar radiation intensity, the air temperature, the humidity, the wind speed and the like, and data preprocessing and feature extraction are performed.

[0165] The multivariate regression model is constructed, specifically including: mining the power generation law and the efficiency feature of the photovoltaic panel under different environmental conditions, such as the high-temperature low-efficiency mode, the low-temperature high-efficiency mode and the like. For each power generation mode, the distribution of the environmental temperature, the radiation intensity, the wind speed, the photovoltaic panel temperature and the like is counted, the scatter plot and the box plot of the environmental factors and the power generation efficiency are drawn, the correlation and the influence trend between each factor and the power generation efficiency are analyzed, and the key environmental factors affecting the photovoltaic power generation are preliminarily judged. The power generation efficiency is selected as the dependent variable, and the environmental temperature, the radiation intensity, the wind speed, the photovoltaic panel temperature and the like are selected as the independent variables, a multivariate linear regression model is constructed, the least square method is used to estimate the model coefficients, and a quantitative relationship between the power generation efficiency and the environmental factors is obtained.

[0166] When constructing the regression model, the system provided in the embodiment also needs to verify whether there is a significant linear relationship between the independent variables and the dependent variable. F test can be used to compare the ratio of regression mean square and residual mean square under a given confidence level. If the ratio is greater than the critical value, it indicates that the regression model is significant. T test is performed on each independent variable. If the absolute value of the t statistic is greater than the critical value, it indicates that the independent variable has a significant impact on the dependent variable. According to the sign and size of the regression coefficient, the impact direction and impact strength of each independent variable on the dependent variable can be explained. At the same time, it is necessary to check whether there is multicollinearity between the independent variables. Further introduce the urban heat island intensity index and the building reflection radiation ratio and other factors to analyze the influence of urban microclimate environment on photovoltaic power generation efficiency and quantitatively evaluate the contribution rate of urban heat island effect and building reflection light.

[0167] The environmental factor feature set and the power generation efficiency feature set are correlated and analyzed, and a quantitative relationship model between the actual power generation efficiency and the environmental factors is established by using a multiple linear regression algorithm, and a regression equation is obtained: power generation efficiency = 78 x radiation intensity + 15 x air temperature - 03 x humidity - 02 x wind speed. Based on the model, the influence of the urban heat island effect on the photovoltaic panel power generation efficiency is evaluated. The urban heat island effect causes the temperature around the photovoltaic panel to rise by 2-3℃, resulting in an average decrease of about 5% in the photovoltaic panel power generation efficiency.

[0168] Moreover, the system applies the regression model to different urban areas and building types to predict the spatial distribution of photovoltaic power generation efficiency, draw the contour map and color spot map of photovoltaic power generation efficiency, and identify the high-efficiency power generation area and low-efficiency power generation area in the city. Combined with the spatial distribution data of the urban heat island intensity and the building density, the influence degree of the urban heat environment and the building reflection light on the photovoltaic power generation efficiency is quantitatively evaluated.

[0169] The reflection light intensity and reflection angle data of the building where the photovoltaic panel is located are obtained, which are collected by an optical sensor every 10 minutes and are preprocessed and feature extracted. The building reflection light feature set is correlated and analyzed with the actual power generation efficiency, and the influence of the building reflection light on the photovoltaic panel power generation efficiency is evaluated by using a partial least squares regression (PLSR) algorithm, and a regression equation is obtained: power generation efficiency = 82 x reflection light intensity + 12 x reflection angle. The analysis result shows that the photovoltaic panel power generation efficiency can be increased by about 2% when the building reflection light intensity is increased by 100 W / m 2 ; and the photovoltaic panel power generation efficiency can be increased by about 5% when the reflection angle is increased by 10°. Therefore, when the photovoltaic panel is laid out, the position with large building reflection light intensity and appropriate reflection angle should be selected as much as possible to improve the power generation efficiency.

[0170] Further, the multiple regression model is optimized and adjusted according to the heat island intensity index and the reflection light distribution, and an optimized distributed photovoltaic system optimization strategy is output, which includes:

[0171] According to the heat island intensity index and the reflected light distribution, the multiple regression model is adjusted in parameters, and the photovoltaic power generation efficiency is predicted through the adjusted model, and photovoltaic prediction data is output;

[0172] The photovoltaic prediction data is compared with the actual photovoltaic data, and the model prediction error is evaluated through the bias analysis method, and the model parameters are adjusted through the evaluation results;

[0173] The second photovoltaic panel installation strategy is optimized through the feedback adjusted model, and the distributed photovoltaic system deployment strategy is obtained.

[0174] After obtaining the multiple regression model, the system adjusts the model in parameters through the heat island intensity index and the reflected light distribution, so that the prediction data considers the factors such as the heat island intensity and the reflected light distribution of the city, and the photovoltaic system power generation efficiency is predicted through the adjusted model. According to the prediction data and the actual power generation efficiency data of the photovoltaic system, that is, the actual photovoltaic data, the error between the model and the actual photovoltaic system is determined, and the error is analyzed and evaluated to determine the source of the error. Then, according to the source of the error, the model is adjusted in feedback, and the practicality, reliability and accuracy of the model are further improved.

[0175] In this embodiment, it also includes collecting the historical data of the actual operation of the photovoltaic power station, including the key parameters such as the output power of the inverter, the conversion efficiency, the backboard temperature of the photovoltaic module, and the meteorological elements such as the environmental temperature, the radiation intensity and the wind speed, and constructing a multi-source heterogeneous operation data set. The operation data is analyzed and mined, the correlation coefficient of the photovoltaic module temperature and the power generation efficiency is calculated, the scatter plot and the regression curve are drawn, and the influence degree of the temperature on the efficiency is quantitatively evaluated.

[0176] The periodicity and trend of the temperature and efficiency time series are extracted by using wavelet transform and spectral analysis. Wavelet transform decomposes the time series by a mother wavelet function at multiple scales to extract features of different frequency components. Commonly used wavelet basis functions include Haar, Daubechies, Symlets, etc. Selecting an appropriate mother wavelet function and decomposition level, the wavelet transform is performed on the time series, the wavelet coefficients are thresholded to remove noise, and the denoised time series is reconstructed by the wavelet coefficients. The statistical characteristics of the wavelet coefficients, such as mean, variance, and energy, are extracted. Spectral analysis converts the time series to the frequency domain by Fourier transform to identify periodic components. Common spectral estimation methods include periodogram, BT method, MUSIC method, etc. The time series is detrended, the autocorrelation or cross-correlation function is calculated, and the Fourier transform of the correlation function is performed to obtain the power spectral density function. The peak frequency of the power spectral density function is identified to determine the periodic component.

[0177] In this embodiment, the passive thermal insulation scheme is optimized according to the structural characteristics and material properties of the photovoltaic module. Low thermal conductivity materials such as aerogel and vacuum insulation panels are filled between the module backsheet and the frame to reduce heat transfer from the backsheet to the cell. A low-emissivity selective coating is applied to the surface of the module glass cover plate to reduce the proportion of solar radiation absorption.

[0178] In this embodiment, different active cooling strategies are developed for different installation methods and climate conditions. For roof-mounted distributed photovoltaic systems, automatic adjustable louvers can be installed on the back of the module. According to the changes of temperature and radiation intensity, the opening angle of the ventilation opening is adjusted to enhance natural ventilation and heat exchange. For ground-mounted power stations, evaporative cooling materials can be laid under the modules to reduce the local environmental temperature by using the principle of heat absorption by water evaporation.

[0179] The temperature control effects of active cooling and passive insulation measures are analyzed comprehensively, and the maximum working temperature, temperature fluctuation range, and temperature uniformity of different schemes are compared. According to the climate characteristics of the photovoltaic power station location, the definitions of high-temperature and low-temperature working conditions are given. In the evaluation of the temperature control scheme, the temperature range and time scale of the evaluation need to be set according to the high-temperature and low-temperature characteristics of different climate zones to improve the applicability and comparability of the evaluation results. Select typical high-temperature and low-temperature weather conditions to simulate the power generation performance of the photovoltaic array, calculate the annual average power generation efficiency improvement and annual power generation increase. In addition, extreme weather conditions such as sustained high temperature and typhoon need to be considered to evaluate the reliability and safety of the temperature control scheme under extreme conditions.

[0180] Furthermore, the comparative results are evaluated by the bias analysis method in this embodiment, and the model parameters are adjusted by the evaluation results, including:

[0181] The error source analysis is obtained by attributing and decomposing the comparison result by the bias analysis method, and the model is parameter corrected according to the error source analysis;

[0182] The uncertainty analysis is performed on the comparison result to obtain the corresponding uncertainty source, and then the model is parameter adjusted according to the uncertainty source.

[0183] The error source is determined by the bias analysis method, and the model is parameter corrected according to the error source, that is, the factors that have greater influence on the prediction error are determined, so as to realize the dynamic parameter adjustment of the model, so that the model can adapt to the changes of the actual operation state and environmental conditions of the photovoltaic system. Through the uncertainty analysis of the error, the uncertainty sources of the model parameters, input data and model structure are determined, the reliability and risk of the model prediction are evaluated, the model and algorithm are further optimized, the robustness and adaptability of the model prediction are improved, the continuous iteration and upgrading of the model are realized, and the scientificity and practicality of the photovoltaic power generation efficiency simulation prediction are improved.

[0184] In this embodiment, the actual power generation efficiency data is compared with the simulated and predicted power generation efficiency data, the error statistics of the two groups of data at different time scales (such as hour by hour, day by day, month by month) are calculated, including mean absolute error MAE, root mean square error RMSE, mean relative error MAPE, etc., to quantitatively evaluate the precision and bias of the model prediction. The bias analysis method is used to attribute and decompose the model prediction error, to distinguish between systematic bias and random bias, to analyze the time trend, spatial distribution and influencing factors of the error, such as decomposing the MSE of the hourly error into three parts of mean bias, variance bias and covariance bias, to determine the main source of the error.

[0185] Firstly, the structure, parameters and input data of the model are diagnosed and corrected based on the bias analysis result in this embodiment, and the sensitivity analysis method such as Morris screening or Sobol index is used to determine the factors that have greater influence on the prediction error.

[0186] If the Morris method is used, the basic influence value μ and σ of each input parameter are calculated by perturbing each input parameter, where μ represents the overall influence of the parameter, and σ represents the nonlinear influence of the parameter or the interaction with other parameters. The value range of each parameter is divided into several levels, a reference point is randomly selected in the parameter space, each parameter is perturbed in turn, a group of Morris trajectories is obtained, the basic influence value of the output response is calculated for each trajectory, the Morris trajectory and the calculation of the basic influence value are repeated multiple times, the distribution of μ and σ of each parameter is obtained, and the importance of the parameters is sorted according to the size of μ and σ.

[0187] If Sobol index is used, the total variance of the model output is decomposed into the variance contribution of each input parameter by variance decomposition, including the first-order index and global index of the parameter. The value range of the parameter is converted into a uniform distribution between 01, Latin hypercube sampling is used to generate two sets of parameter sample matrix A and B, the model output vectors YA and YB of A and B are calculated respectively, the i-th parameter in A is replaced by the corresponding value in B to obtain a new sample matrix Ci, the output vector YCi is calculated, the variances of YA, YB and YCi are calculated to obtain the first-order index and global index of the i-th parameter. Repeat the calculation of the output vector YCi and the first-order index and global index of the i-th parameter until all parameters are calculated.

[0188] In addition, the embodiment also uses automatic machine learning algorithms such as RandomForest or XGBoost to optimize the hyperparameters of the model, improve the stability and robustness of the model. Taking random forest as an example, the hyperparameters that need to be optimized include the number of decision trees, the maximum depth of each tree, the minimum number of samples for each node, the maximum number of features for feature selection, etc. Using grid search or random search, a set of hyperparameter combinations is randomly sampled within the value range of the hyperparameters. For each set of hyperparameters, use k-fold cross-validation to randomly divide the dataset into k subsets, select k-1 subsets as the training set and the remaining 1 subset as the validation set each time, train the model and evaluate the performance of the model on the validation set, such as mean square error MSE, decision coefficient R 2 , etc. Repeat k times to get k sets of performance indicators, and take their average as the performance score of this set of hyperparameters. Select the set of hyperparameters with the best performance score as the final model parameters.

[0189] The uncertainty analysis of the comparison results is described in the embodiment, which is specifically: considering the uncertainty sources of model parameters, input data and model structure, etc., using Monte Carlo simulation or Bayesian inference method to estimate the confidence interval or probability distribution of the prediction result, to evaluate the reliability and risk of model prediction, and to provide reference for decision making. Based on the uncertainty analysis results, further optimize the model and algorithm, improve the robustness and adaptability of the prediction through model integration or Bayesian model averaging, realize the continuous iteration and upgrading of the model, establish the closed-loop optimization mechanism of model prediction, error analysis, parameter correction and uncertainty evaluation, and improve the scientificity and practicality of photovoltaic power generation efficiency simulation and prediction.

[0190] Preferably, the embodiment carries out the uncertainty analysis of the model prediction, considers the measurement errors of the input parameters such as environmental temperature and radiation, and the uncertainty of the model structure and parameters, extracts 1000 groups of input samples by using the Monte Carlo method, and calculates the mean value and confidence interval of the model output. The data shows that the 95% confidence interval of the model prediction efficiency is [11.2%, 13.5%], and the uncertainty level is controllable. Through a series of measures such as model error analysis, parameter correction, and uncertainty evaluation, the accuracy and reliability of the photovoltaic power generation efficiency prediction model are significantly improved, which provides important data support and decision basis for the optimized operation of the photovoltaic power station.

[0191] In order to better illustrate the working principle and step flow of the optimization method and device of the distributed photovoltaic system, reference can be made to the related description in the foregoing, but is not limited thereto.

[0192] Correspondingly, reference can be made to Figure 2 , Figure 2 The structure diagram of one embodiment of the optimization device of the distributed photovoltaic system provided by the present application is shown in the figure. Figure 2 As shown in the figure, the optimization device comprises a heat island intensity determination module 201, a building model calculation module 202, a first strategy output module 203, a radiation intensity calculation module 204, a second strategy adjustment module 205, and a photovoltaic system optimization module 206; wherein:

[0193] The heat island intensity determination module 201 is used for acquiring temperature distribution data of a target city, and calculating the temperature distribution data by an interpolation analysis method to obtain a heat island intensity index;

[0194] The building model calculation module 202 is used for acquiring a three-dimensional building model of the target city, and calculating the solar radiation intensity and the reflected light distribution according to the three-dimensional building model;

[0195] The first strategy output module 203 is used for determining the photovoltaic panel temperature and the system power generation efficiency of the distributed photovoltaic system according to the temperature distribution data and the solar radiation intensity calculation, and outputting a first photovoltaic panel installation strategy;

[0196] The radiation intensity calculation module 204 is used for determining the photovoltaic panel radiation intensity based on the first photovoltaic panel installation strategy and the three-dimensional building model calculation, and constructing a photovoltaic panel heat balance model based on the photovoltaic panel radiation intensity;

[0197] The second strategy adjustment module 205 is used for determining key influencing factors according to the photovoltaic panel heat balance model, and optimizing and adjusting the first photovoltaic panel installation strategy according to the key influencing factors, and outputting and optimizing and adjusting the distributed photovoltaic system according to a second photovoltaic panel installation strategy;

[0198] The photovoltaic system optimization module 206 is configured to acquire actual operation data of the distributed photovoltaic system after optimization adjustment, construct a multiple regression model according to the actual operation data, perform optimization adjustment on the multiple regression model according to the heat island intensity index and the reflected light distribution, and output an optimized distributed photovoltaic system optimization strategy.

[0199] In summary, the embodiment of the present application provides a kind of distributed photovoltaic system optimization method and device, the heat island intensity index is determined by the temperature part data of target city, solar radiation intensity and reflected light distribution are calculated according to three-dimensional building model, the photovoltaic panel temperature and system power generation efficiency of distributed photovoltaic system are calculated by temperature data and solar radiation intensity, photovoltaic panel installation strategy is determined, photovoltaic panel heat balance model is constructed according to installation strategy, key influencing factors are determined by heat balance model, installation strategy is optimized, and photovoltaic system is adjusted according to optimized strategy, installation strategy is re-optimized according to system heat island intensity and reflected light distribution, and the optimized photovoltaic system deployment strategy is obtained. System optimization strategy is generated by the above optimization method, the power generation efficiency of photovoltaic system deployment strategy is improved, the photovoltaic panel temperature caused by heat island effect and building reflection radiation is reduced, and the intelligent management and efficient operation of photovoltaic power generation system are realized.

[0200] The above specific embodiments further illustrate the purpose, technical solutions and advantages of the present application, and it should be understood that the above only describes specific embodiments of the present application and is not intended to limit the protection scope of the present application. It should be particularly pointed out that, for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for optimizing a distributed photovoltaic system, characterized in that, The method comprises the following steps: obtain temperature distribution data of a target city, and calculate the temperature distribution data by an interpolation analysis method to obtain a heat island intensity index; obtain a three-dimensional building model of the target city, and calculate solar radiation intensity and reflected light distribution based on the three-dimensional building model; determine the temperature of photovoltaic panels and the power generation efficiency of a distributed photovoltaic system based on the temperature distribution data and the solar radiation intensity, and output a first photovoltaic panel installation strategy, specifically: obtain building density data and green coverage data of the target city, and construct a multi-objective optimization model of photovoltaic arrays based on the building density data, the green coverage data, and the temperature of photovoltaic panels and the power generation efficiency, optimize and solve the multi-objective optimization model of photovoltaic arrays by a genetic algorithm, and output the first photovoltaic panel installation strategy; determine the radiation intensity of photovoltaic panels based on the first photovoltaic panel installation strategy and the three-dimensional building model, and construct a photovoltaic panel heat balance model based on the radiation intensity of photovoltaic panels; determine key influencing factors based on the photovoltaic panel heat balance model, specifically: simulate and analyze the temperature of photovoltaic panels and the power generation efficiency of the distributed photovoltaic system by the photovoltaic panel heat balance model to obtain corresponding change curves, screen influencing factors from the change curves by a sensitivity analysis algorithm to obtain the key influencing factors, optimize and adjust the first photovoltaic panel installation strategy based on the key influencing factors, and output and optimize and adjust the distributed photovoltaic system based on a second photovoltaic panel installation strategy; obtain actual operation data of the distributed photovoltaic system after optimization and adjustment, construct a multiple regression model based on the actual operation data, optimize and adjust the multiple regression model based on the heat island intensity index and the reflected light distribution, and output an optimized distributed photovoltaic system optimization strategy.

2. The method of Claim 1, wherein, The method of obtaining temperature distribution data of a target city and calculating the temperature distribution data by an interpolation analysis method to obtain a heat island intensity index comprises: obtain initial temperature distribution data of the target city, perform outlier rejection processing and missing value supplement processing on the initial temperature distribution data to obtain the temperature distribution data; perform spatial interpolation analysis on the temperature distribution data by a Kriging interpolation method to obtain a temperature distribution surface of the target city; calculate the heat island intensity index based on the temperature distribution surface, and divide the target city into regions according to the heat island intensity index to obtain a regional heat island level.

3. The method of optimizing a distributed photovoltaic system of claim 1, wherein, The method of obtaining a three-dimensional building model of the target city and calculating solar radiation intensity and reflected light distribution based on the three-dimensional building model comprises: obtain building point cloud data of the target city, and sequentially perform denoising, point cloud classification, and three-dimensional reconstruction processing on the building point cloud data to obtain the three-dimensional building model; Obtaining solar radiation data and reflectivity data of building surface materials of the target city, inputting the solar radiation data and the reflectivity data into the three-dimensional building model, and calculating the solar radiation intensity and the reflected light distribution of the building surface by a Monte Carlo simulation algorithm.

4. The method of Claim 1, wherein, The photovoltaic panel temperature and system power generation efficiency of the distributed photovoltaic system are calculated according to the temperature distribution data and the solar radiation intensity, specifically: The temperature distribution data and the solar radiation intensity are input into a preset Sandia array performance model for calculation and processing to obtain the photovoltaic panel temperature and the system power generation efficiency.

5. The method of optimizing a distributed photovoltaic system of claim 1, wherein, The photovoltaic panel radiation intensity is calculated based on the first photovoltaic panel installation strategy and the three-dimensional building model, and a photovoltaic panel heat balance model is constructed based on the photovoltaic panel radiation intensity, including: The three-dimensional building model is parameter-adjusted according to the first photovoltaic panel installation strategy, and the reflection and shielding of sunlight are simulated by a Monte Carlo ray tracing method to obtain the radiation flux per unit area of the photovoltaic panel; A corresponding building surface radiation transmission mathematical model is constructed according to the radiation flux, and the photovoltaic panel radiation intensity of the photovoltaic panel is calculated by the building surface radiation transmission mathematical model; The photovoltaic panel heat balance model is constructed according to the photovoltaic panel radiation intensity and the heat exchange process of the photovoltaic panel.

6. The method of optimizing a distributed photovoltaic system of claim 1, wherein, The first photovoltaic panel installation strategy is optimized and adjusted according to the key influencing factors, including: The first photovoltaic panel installation strategy is parameter-optimized and adjusted based on the key influencing factors by a genetic algorithm.

7. The method of optimizing a distributed photovoltaic system of claim 1, wherein, The actual operation data of the distributed photovoltaic system after optimization and adjustment are obtained, and a multiple regression model is constructed according to the actual operation data, including: The actual operation data of the distributed photovoltaic system are obtained, and the actual operation data are processed by dimension reduction and feature extraction to obtain a photovoltaic feature data set; The photovoltaic feature data set is subjected to cluster analysis, the photovoltaic feature data set is divided into different cluster clusters according to a preset power generation index, and photovoltaic power generation influencing factors are determined according to the cluster clusters, and then a multiple regression model is constructed according to the photovoltaic power generation influencing factors and power generation efficiency.

8. The method of optimizing a distributed photovoltaic system of claim 1, wherein, The multiple regression model is optimized and adjusted according to the heat island intensity index and the reflected light distribution, and an optimized distributed photovoltaic system optimization strategy is output, including: The multiple regression model is parameter-adjusted according to the heat island intensity index and the reflected light distribution, and the photovoltaic power generation efficiency is predicted by the adjusted model to output photovoltaic prediction data; The photovoltaic prediction data are compared with actual photovoltaic data, and model prediction error evaluation is performed on the comparison results by a bias analysis method, and model parameters are feedback-adjusted according to the evaluation results; The second photovoltaic panel installation strategy is optimized by the model after feedback adjustment to obtain the distributed photovoltaic system optimization strategy.

9. The method of optimizing a distributed photovoltaic system of claim 8, wherein, The model prediction error evaluation is performed on the comparison results by a bias analysis method, and the model parameters are feedback-adjusted according to the evaluation results, including: Attribution and decomposition of the comparison results are performed by the bias analysis method to obtain error source analysis, and parameter correction of the model is performed according to the error source analysis; Uncertainty analysis is performed on the comparison results to obtain corresponding uncertainty sources, and then parameter adjustment of the model is performed according to the uncertainty sources.

10. An optimization apparatus of a distributed photovoltaic system, characterized by, The optimization device comprises a heat island intensity determination module, a building model calculation module, a first strategy output module, a radiation intensity calculation module, a second strategy adjustment module and a photovoltaic system optimization module; wherein: The heat island intensity determination module is configured to obtain temperature distribution data of a target city, and calculate the temperature distribution data by an interpolation analysis method to obtain a heat island intensity index; The building model calculation module is configured to obtain a three-dimensional building model of the target city, and calculate solar radiation intensity and reflected light distribution based on the three-dimensional building model; The first strategy output module is configured to determine photovoltaic panel temperature and system power generation efficiency of a distributed photovoltaic system based on the temperature distribution data and the solar radiation intensity, and output a first photovoltaic panel installation strategy; specifically, building density data and greening coverage data of the target city are obtained, and a photovoltaic array multi-objective optimization model is constructed based on the building density data, the greening coverage data, the photovoltaic panel temperature and the system power generation efficiency; the photovoltaic array multi-objective optimization model is optimized and solved by a genetic algorithm, and the first photovoltaic panel installation strategy is outputted; The radiation intensity calculation module is configured to determine photovoltaic panel radiation intensity based on the first photovoltaic panel installation strategy and the three-dimensional building model, and construct a photovoltaic panel heat balance model based on the photovoltaic panel radiation intensity; The second strategy adjustment module is configured to determine key influencing factors based on the photovoltaic panel heat balance model; specifically, the photovoltaic panel temperature and the system power generation efficiency are simulated and analyzed by the photovoltaic panel heat balance model to obtain a corresponding change curve, the change curve is screened for influencing factors by a sensitivity analysis algorithm to obtain the key influencing factors, the first photovoltaic panel installation strategy is optimized and adjusted according to the key influencing factors, and the distributed photovoltaic system is optimized and adjusted according to a second photovoltaic panel installation strategy; The photovoltaic system optimization module is configured to obtain actual operation data of the distributed photovoltaic system after optimization and adjustment, construct a multiple regression model based on the actual operation data, optimize and adjust the multiple regression model based on the heat island intensity index and the reflected light distribution, and output an optimized distributed photovoltaic system optimization strategy.

Images