Photovoltaic module arrangement scheme generation method and system, and storage medium

Abstract

The embodiment of the invention provides a photovoltaic module arrangement scheme generation method and system and a storage medium. The method comprises the steps of obtaining multi-source data of a target installation area; determining a ventilation coefficient and an irrigation coefficient of the target installation area according to building data, historical weather data and landscape greening data in the multi-source data; acquiring lighting demand data and an indoor target heat gain rate of the target installation area; generating a first arrangement scheme according to the multi-source data, the lighting demand data, the indoor target heat gain rate, the ventilation coefficient and the irrigation coefficient; and simulating the first arrangement scheme and the multi-source data collaborative digital twin model, and correcting the first arrangement scheme to obtain a target arrangement scheme. The corresponding first arrangement scheme is generated according to the multi-source data of the target installation area, and the generation efficiency of the arrangement scheme is high; the first arrangement scheme is corrected through simulation of the digital twinborn model to obtain the target arrangement scheme, and the completeness of the photovoltaic module arrangement scheme is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a photovoltaic module arrangement scheme generation method and system and a storage medium. BACKGROUND

[0002] With the development of photovoltaic industry and technology, the installation environment of photovoltaic modules is increasingly diversified.

[0003] Before installation, the photovoltaic modules need to determine the corresponding arrangement scheme, and the existing technology determines the arrangement scheme through manual analysis, and the generation efficiency of the arrangement scheme is low, and the data of all aspects need to be analyzed, which can easily lead to an imperfect arrangement scheme. SUMMARY

[0004] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0005] The main purpose of the embodiment of the present application is to provide a photovoltaic module arrangement scheme generation method and system and a storage medium, which can improve the generation efficiency and perfection of the photovoltaic module arrangement scheme.

[0006] In a first aspect, the embodiment of the present application provides a photovoltaic module arrangement scheme generation method, comprising: obtaining multi-source data of a target installation area, wherein the multi-source data comprises building data, historical weather data, cultural data and landscape greening data; determining a ventilation coefficient of the target installation area according to the building data, the historical weather data and the landscape greening data; determining an irrigation coefficient of the target installation area according to the historical weather data and the landscape greening data; obtaining lighting demand data and indoor target heat gain rate of the target installation area; generating a first arrangement scheme according to the multi-source data, the lighting demand data, the indoor target heat gain rate, the ventilation coefficient and the irrigation coefficient; constructing a digital twin model of the first arrangement scheme and the multi-source data; obtaining a simulation result after simulating the digital twin model; correcting the first arrangement scheme to obtain a target arrangement scheme according to the simulation result.

[0007] In some optional embodiments, the determining the ventilation coefficient of the target installation area according to the building data, the historical weather data and the landscape greening data comprises: constructing a first model according to the building data and the landscape greening data; simulate the first model according to the historical weather data to obtain a first ventilation quantity; determine a first coefficient according to the first ventilation quantity and a maximum ventilation quantity, the maximum ventilation quantity representing a ventilation quantity without shielding; determine a seasonal correction coefficient according to the historical weather data; determine a green growth correction coefficient according to the landscape greening data; correct the first coefficient according to the seasonal correction coefficient and the green growth correction coefficient to obtain the ventilation coefficient.

[0008] In some optional embodiments, the determining the irrigation coefficient of the target installation area according to the historical weather data and the landscape greening data comprises: obtaining rainfall and evaporation in the historical weather data; obtaining green area and green water demand in the landscape greening data; determining basic water demand according to the green area and the green water demand; determining irrigation water according to the rainfall and the evaporation; determining the irrigation coefficient according to the irrigation water and the basic water demand.

[0009] In some optional embodiments, the generating a first arrangement scheme according to the multi-source data, the daylighting demand data, the indoor target heat gain rate, the ventilation coefficient and the irrigation coefficient comprises: constructing a neural network fusion model of a multi-objective optimization algorithm and a reinforcement learning framework; inputting the multi-source data, the daylighting demand data, the indoor target heat gain rate, the ventilation coefficient and the irrigation coefficient into the neural network fusion model; configuring an optimization objective of the neural network fusion model as maximizing photovoltaic power generation, maximizing indoor daylighting satisfaction rate, maximizing indoor heat gain rate compliance rate, minimizing ventilation coefficient loss and maximizing irrigation coefficient matching degree; constructing a target function corresponding to the optimization objective; configuring design variables of the neural network fusion model as photovoltaic component installation inclination, photovoltaic array spacing, photovoltaic component installation position, photovoltaic component orientation, photovoltaic component light transmittance and water collection tank coverage rate; configuring constraint conditions of the neural network fusion model as structural load constraint, sunshine spacing constraint, cultural landscape constraint and greenery coordination constraint; iterating the design variables based on the constraint conditions, the target function and the optimization objective to obtain a Pareto optimal solution set; The first arrangement scheme is obtained after selecting a target solution from the set of Pareto optimal solutions according to comprehensive benefit requirements.

[0010] In some optional embodiments, the set of Pareto optimal solutions is obtained after iteratively adjusting the design variables based on the constraint conditions, the target function, and the optimization target. A preset number of initial design variable combinations are randomly generated, and the initial design variable combinations meet the constraint conditions. The initial design variable combinations are substituted into the target function to calculate the fitness value of the optimization target, and the fitness value represents the matching degree with the optimization target. The initial design variable combinations are non-dominantly sorted according to the fitness value to obtain non-dominant solutions. New iteration design variable combinations are generated after gene recombination and random variation of the non-dominant solutions, and the iteration number is incremented by one. In the case where the iteration number is less than or equal to a preset number, the iteration design variable combinations are configured as the initial design variable combinations for iterative calculation, and the iterative calculation represents the step of generating the iteration design variable combinations. In the case where the iteration number is greater than the preset number, the non-dominant solutions are configured as the set of Pareto optimal solutions.

[0011] In some optional embodiments, the first arrangement scheme and the digital twin model cooperated with the multi-source data are constructed, including: The building data is converted into a BIM model. The first arrangement scheme is superimposed on the BIM model to obtain a first model. The historical weather data is associated with the first model to obtain a second model. The cultural data and the landscape greening data are superimposed on the second model to obtain a third model. A first coupling model capable of calculating the hourly power generation, indoor heat gain rate, ventilation volume, daylighting rate, and water collection volume of each location is generated according to the first arrangement scheme, the historical weather data, the landscape greening data, the cultural data, and the building data, and the first coupling model is superimposed on the third model to obtain the digital twin model.

[0012] In some optional embodiments, after the simulation of the digital twin model obtains a simulation result, including: generate a simulation atlas according to the simulation result, the simulation atlas being used to indicate a difference between multi-dimensional simulation data and target data at each position of the target installation area, the multi-dimensional simulation data representing simulated hourly power generation, indoor heat gain rate, daylighting rate, ventilation volume and water collection volume; obtain a preprocessed image by sequentially performing grayscale processing, filtering processing and denoising processing on the simulation atlas; segment the preprocessed image into a plurality of spatial image sub-regions; obtain abnormal region information according to a similarity between the plurality of spatial image sub-regions, the abnormal region information representing contour information and spatial position information of a target region having a significant difference from an adjacent region.

[0013] In some optional embodiments, the obtaining of the abnormal region information according to the similarity between the plurality of spatial image sub-regions comprises: perform a similarity comparison on a first similarity between a first image sub-region and a third image sub-region and a second similarity between a second image sub-region and the third image sub-region to obtain a comparison result, the third image sub-region being any one of the spatial image sub-regions, the first image sub-region being located at a first side of the third image sub-region, the second image sub-region being located at a second side of the third image sub-region, and the first image sub-region, the second image sub-region and the third image sub-region all representing the spatial image sub-region; in a case where the comparison result represents that the first similarity is greater than the second similarity, sequentially performing unit distance adjustment and unit scale scaling on the third image sub-region to a position where the second image sub-region is located, and configuring contour information and spatial information of the third image sub-region having a maximum difference value between the first similarity and the second similarity as the abnormal region information; in a case where the comparison result represents that the first similarity is less than the second similarity, sequentially performing unit distance adjustment and unit scale scaling on the third image sub-region to a position where the first image sub-region is located, and configuring contour information and spatial information of the third image sub-region having a maximum difference value between the first similarity and the second similarity as the abnormal region information; in a case where the comparison result represents that the first similarity is equal to the second similarity, synchronously moving the first image sub-region and the second image sub-region by a unit distance and performing unit scale scaling until the first similarity is not equal to the second similarity.

[0014] In a second aspect, an embodiment of the present application provides a controller, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the photovoltaic module arrangement scheme generation method of the first aspect when executing the computer program.

[0015] In a third aspect, an embodiment of the present application provides a photovoltaic module arrangement scheme generation system, comprising the controller of the second aspect.

[0016] In a fourth aspect, a computer storage medium stores computer executable instructions, and the computer executable instructions are used to execute the photovoltaic module arrangement scheme generation method of the first aspect.

[0017] The beneficial effects of the present application include: obtaining multi-source data of a target installation area, the multi-source data including building data, historical weather data, cultural data, and landscape greening data; determining a ventilation coefficient of the target installation area according to the building data, the historical weather data, and the landscape greening data; determining an irrigation coefficient of the target installation area according to the historical weather data and the landscape greening data; obtaining daylighting demand data and an indoor target heat gain rate of the target installation area; generating a first arrangement scheme according to the multi-source data, the daylighting demand data, the indoor target heat gain rate, the ventilation coefficient, and the irrigation coefficient; constructing a digital twin model of the first arrangement scheme and the multi-source data; obtaining simulation results after simulating the digital twin model; and correcting the first arrangement scheme to obtain a target arrangement scheme according to the simulation results. The first arrangement scheme corresponding to the multi-source data of the target installation area is automatically generated, and the generation efficiency of the arrangement scheme is high; the digital twin model corresponding to the first arrangement scheme and the multi-source data is generated, and simulation is performed, so that the first arrangement scheme is corrected to obtain the target arrangement scheme, and the perfection of the photovoltaic module arrangement scheme is improved.

[0018] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application can be achieved and obtained by the structure particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 is a step flow block diagram of a photovoltaic module arrangement scheme generation method provided by an embodiment of the present application; Figure 2 is a schematic diagram of a controller provided by an embodiment of the present application.

[0020] Reference signs: controller 1000, processor 1100, memory 1200. DETAILED DESCRIPTION

[0021] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0022] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical sequence is shown in the flowchart, in some cases, the steps shown or described can be executed in a manner different from the module division in the device or the sequence in the flowchart. The terms "first", "second", etc. in the specification, claims or above-described drawings are used to distinguish similar objects, and do not necessarily describe a specific sequence or order.

[0023] In the present application, a photovoltaic module arrangement scheme generation method, system and storage medium are provided, which are described in detail one by one in the following embodiments.

[0024] As shown in Figure 1 The present application provides a photovoltaic module arrangement scheme generation method, which includes steps S100, S200, S300, S400, S500, S600, S700 and S800: Step S100, acquiring multi-source data of a target installation area, the multi-source data including building data, historical weather data, cultural data and landscape greening data.

[0025] Specifically, the multi-source data of the present application can be data stored in a background server or a corresponding storage space in advance, can be data obtained by accessing a corresponding data storage system or platform, or can be obtained by detecting the target installation area. The specific acquisition method is not limited herein.

[0026] The building data covers geometric shape, structural performance and thermal property. The geometric shape obtains the three-dimensional contour, slope and peripheral obstacle size of the installation area (roof, facade, etc.) through three-dimensional laser scanning, and supplements the internal structural details in combination with the BIM model; the structural performance obtains the load limit value by referring to the design drawings, and the concrete strength and steel structure welding quality of old buildings need to be detected on site; the thermal property determines the thermal conductivity coefficient, solar radiation absorption rate and other parameters of the external envelope structure through material sampling detection or table lookup.

[0027] The historical weather data collects the hourly temperature and humidity, total solar radiation, rainfall and typhoon data in the past 30 years, establishes a climate parameter database, and draws the corresponding atlas in combination with the GIS system.

[0028] The human data includes crowd activities, landscape culture, and management specifications. By obtaining the corresponding human data, it is ensured that the installation of the photovoltaic module is in line with the corresponding human characteristics.

[0029] The landscape greening data covers plant attributes, soil topography, and irrigation systems. The plant attributes include species, plant height, crown width, daily water consumption, and growth cycle; the soil topography is obtained by sampling and detecting the permeability and pH value, and the slope and slope direction are obtained by unmanned aerial vehicle mapping; the irrigation system checks the existing mode, pipeline direction, and sprinkler state, and counts the annual water consumption and peak period demand.

[0030] In step S200, a ventilation coefficient of the target installation area is determined according to the building data, the historical weather data, and the landscape greening data.

[0031] Specifically, the three-dimensional contour of the target installation area, the position and size of the ventilation opening, the height and distance of the surrounding obstacles are obtained from the building data, and the coordinate accuracy is ensured by means of three-dimensional laser scanning and BIM model; the hourly wind speed and direction in the past 5 years are selected from the historical weather data, the seasonal dominant wind direction frequency and maximum wind speed, and the turbulence intensity are counted, and the abnormal data are eliminated; the plant type, crown width, height, planting density, and relative position with the target area are obtained from the landscape greening data, and the resistance coefficient of different plants is determined.

[0032] A wind field simulation model is constructed, the main building is simplified, the ventilation opening is retained, the green area is set as a porous medium with corresponding resistance coefficient, and the target area is set as a monitoring surface; the boundary conditions are set, the inlet adopts a logarithmic wind speed profile to input the historical wind speed and direction, the outlet is set as standard atmospheric pressure, and the ground and building surface take corresponding roughness according to the material. Then, the ventilation volume is simulated in different scenes; in the non-interference scene, the ideal wind field without buildings and greenery is simulated, and the theoretical maximum ventilation volume is calculated; in the actual basic scene, the influence of building shielding and green resistance is simulated, and the actual basic ventilation volume is calculated, so that the ventilation coefficient is calculated according to the actual basic ventilation volume and the theoretical maximum ventilation volume.

[0033] In some optional embodiments, the ventilation coefficient of the target installation area is determined according to the building data, the historical weather data, and the landscape greening data, including: S210, a first model is constructed according to the building data and the landscape greening data; Specifically, the geometric model is constructed in the CFD software by combining the building data (the three-dimensional contour of the target area, the size of the ventilation opening, the position of the surrounding obstacles, etc.) and the landscape greening data (plant type, resistance coefficient, planting distribution, etc.), the building is simplified, the ventilation opening is retained, the green area is set as a porous medium with corresponding resistance coefficient, and the target installation area is set as a monitoring surface.

[0034] S220, performing a ventilation simulation on the first model according to the historical weather data to obtain a first ventilation amount; Specifically, the historical weather data (hourly wind speed and dominant wind direction in the past 5 years) is taken as a boundary condition (the inlet is provided with a logarithmic wind speed profile, and the outlet is provided with standard atmospheric pressure), the RNG k-ε turbulence model is used to simulate the ventilation of the first model, and the actual basic ventilation amount under the combined action of building shielding and greening resistance, i.e., the first ventilation amount, is output.

[0035] S230, determining a first coefficient according to the first ventilation amount and a maximum ventilation amount, the maximum ventilation amount representing a ventilation amount without shielding; Specifically, an ideal wind field without buildings and greening shielding is simulated to obtain a maximum ventilation amount representing maximum ventilation potential; the first coefficient is a ratio of the first ventilation amount to the maximum ventilation amount, reflecting the static influence of buildings and greening on ventilation.

[0036] S240, determining a seasonal correction coefficient according to the historical weather data; Specifically, the seasonal correction coefficient is determined based on a ratio of average wind speed in each season to average wind speed in a year, for example, the coefficient is greater than 1 when the wind speed in summer is higher than the average, and the coefficient is less than 1 when the wind speed in winter is lower than the average.

[0037] S250, determining a greening growth correction coefficient according to the landscape greening data; Specifically, the greening growth correction coefficient is determined according to the seasonal growth state of plants in the landscape greening data, for example, the resistance of deciduous trees is reduced when there is no leaf in winter, and the coefficient is taken as 1.2-1.3; the resistance is higher when there is full leaf in summer, and the coefficient is taken as 1.0.

[0038] S260, correcting the first coefficient according to the seasonal correction coefficient and the greening growth correction coefficient to obtain the ventilation coefficient.

[0039] Specifically, the first coefficient is multiplied by the seasonal correction coefficient and the greening growth correction coefficient to finally obtain the ventilation coefficient reflecting the dynamic ventilation potential (the value is 0-1, and the greater the value, the stronger the ventilation capacity).

[0040] Step S300, determining an irrigation coefficient of the target installation area according to the historical weather data and the landscape greening data.

[0041] Specifically, the monthly rainfall, monthly evaporation and rainfall distribution in the past 5 years are screened from the historical weather data; the total area of green areas (distinguished as arbor area, shrub area and lawn area), daily water consumption of various plants, critical period of plant water demand (such as 30% increase in water demand in summer high temperature) and efficiency of existing irrigation facilities are obtained from the landscape greening data. The monthly average green water demand is calculated, and the total basic water demand is obtained. Combined with the seasonal evaporation difference in the historical weather data, the seasonal correction coefficient (the seasonal correction coefficient is equal to the ratio between the seasonal average evaporation and the annual average evaporation) is introduced, and the irrigation facility efficiency (the actual water supply amount needs to be greater than the plant absorption amount, and needs to be divided by the irrigation efficiency) is considered. Finally, the monthly average green water demand is obtained. Then, the irrigation coefficient is calculated; the irrigation coefficient is the ratio of the monthly average green water demand to the monthly average rainwater availability. If the ratio is ≤1, it means that the rainwater can meet the green irrigation demand; if the ratio is >1, it means that the rainwater has a gap and needs to be supplemented with additional water source.

[0042] In some optional embodiments, the irrigation coefficient of the target installation area is determined according to the historical weather data and the landscape greening data, comprising: S310, obtaining rainfall and evaporation in the historical weather data; S320, obtaining green area and green water demand in the landscape greening data; S330, determining basic water demand according to the green area and the green water demand; S340, determining irrigation water according to the rainfall and the evaporation; S350, determining the irrigation coefficient according to the irrigation water and the basic water demand.

[0043] Specifically, the monthly rainfall and monthly evaporation of the target area in the past 5 years are obtained from the historical weather data; the total area of green areas (distinguished as arbor, shrub, lawn and other types) and the daily water consumption of various green plants are obtained from the landscape greening data.

[0044] The basic water demand is the total water consumption of the green area for maintaining healthy growth each month, which needs to be calculated in combination with the green area and the plant water demand. First, the single-class water demand is calculated according to the green type, and then the basic water demand of the target area each month is obtained by summarizing the water demand of various types.

[0045] The irrigation water quantity is the effective rainwater quantity for greening irrigation based on historical weather data, which needs to be corrected in combination with rainfall and evaporation: first, calculate the monthly average rainwater collection potential; then deduct the water loss caused by evaporation, and finally obtain the actual water quantity available for irrigation. The irrigation coefficient is the ratio of the basic water demand to the irrigation water quantity. If the coefficient ≤ 1, it means that rainwater can meet the greening irrigation demand; if the coefficient > 1, it means that there is a gap in rainwater, and the larger the coefficient, the larger the gap. For example, the basic water demand is 150 m³, the irrigation water quantity is 100 m³, and the irrigation coefficient is 1.5, which means that 50% of the irrigation water needs to be supplemented.

[0046] Step S400, obtaining the daylighting demand data and indoor target heat gain rate of the target installation area.

[0047] Specifically, the daylighting demand of each building in the target installation area is determined according to the function of the building; for example, the minimum value of the daylighting coefficient of an office (side daylighting) ≥ 3%, a bedroom (side daylighting) ≥ 2%, and a garage passage ≥ 0.5%.

[0048] The indoor target heat gain rate is determined according to the building energy-saving design standard, combined with the local climate division (such as severe cold area, hot summer and cold winter area), to determine the indoor target heat gain rate in different seasons. For example, in hot summer and cold winter area, the indoor target heat gain rate in summer ≤ 40% (reduce solar radiation heat gain), and in winter ≥ 60% (increase solar radiation heat gain), the target value is determined after calculating the baseline heat gain rate by building energy consumption simulation software (such as EnergyPlus).

[0049] Step S500, generating a first arrangement scheme according to the multi-source data, the daylighting demand data, the indoor target heat gain rate, the ventilation coefficient and the irrigation coefficient.

[0050] Specifically, a multi-objective optimization algorithm is used to generate the first arrangement scheme. The environmental data, ventilation coefficient, irrigation coefficient, daylighting demand data, and indoor target heat gain rate are used as input parameters for iterative calculation, and the Pareto optimal solution set is output, and the scheme with the best comprehensive performance is selected as the first arrangement scheme.

[0051] In some optional embodiments, the first arrangement scheme is generated according to the multi-source data, the daylighting demand data, the indoor target heat gain rate, the ventilation coefficient and the irrigation coefficient, comprising: S510, constructing a neural network fusion model of a multi-objective optimization algorithm and a reinforcement learning framework; Specifically, a fusion model of multi-objective optimization algorithm (such as improved NSGA-III) and reinforcement learning framework (such as DQN) is built; the reinforcement learning framework is used to quickly locate the potential optimal design variable interval; the multi-objective optimization algorithm is used to perform fine search in the interval screened by the reinforcement learning, so as to balance the exploration efficiency and the accuracy of the solution. Meanwhile, a full connection neural network is used to build the mapping relationship between the objective function and the design variable, and the model is pre-trained by using historical photovoltaic arrangement case data (performance parameters such as power generation and light transmittance), so as to improve the optimization convergence speed.

[0052] S520, inputting the multi-source data, the daylighting demand data, the indoor target heat gain rate, the ventilation coefficient and the irrigation coefficient into the neural network fusion model; Specifically, the multi-source data (load limit value in building data, irradiance / wind speed in historical weather data, landscape requirement in human data, plant water requirement in landscape greening data, etc.), the daylighting demand data (standard value of daylighting coefficient of each space, sunshine duration), the indoor target heat gain rate (heat gain rate range by season), the ventilation coefficient (ventilation potential value by region), and the irrigation coefficient (rainwater supply-demand matching degree) are standardized according to the format of space ID-time dimension-attribute parameter, and then input into the neural network fusion model as the basic input matrix of optimization solution.

[0053] S530, configuring the optimization target of the neural network fusion model as maximum photovoltaic power generation, maximum indoor daylighting satisfaction rate, maximum indoor heat gain rate compliance rate, minimum ventilation coefficient loss and maximum irrigation coefficient matching degree; S540, constructing a target function corresponding to the optimization target; Specifically, the target function of the maximum photovoltaic power generation is:

[0054] wherein, is the total area of the photovoltaic module, is the hourly irradiance, is the power generation efficiency of the photovoltaic module, is the hourly ambient temperature, is the installation inclination angle of the photovoltaic module, is the shading coefficient related to the photovoltaic array spacing.

[0055] The target function of the maximum indoor daylighting satisfaction rate is:

[0056] wherein, is the actual daylighting value of room i, is the standard daylighting value of room i, m is the total number of rooms, and sing() is a sign function (taking 1 when satisfied, and 0 when not satisfied).

[0057] The objective function for maximizing the indoor heat gain rate compliance rate is:

[0058] wherein, is the indoor target minimum heat gain rate of season S, is the indoor target maximum heat gain rate of season S.

[0059] The objective function for minimizing the ventilation coefficient loss is:

[0060] wherein, is the ventilation coefficient after installation of the photovoltaic component, is the ventilation coefficient before installation of the photovoltaic component.

[0061] The objective function for maximizing the irrigation coefficient matching degree is:

[0062] wherein, is the water collection amount of the photovoltaic component, is the water requirement amount of the greenery.

[0063] S550, configure the design variables of the neural network fusion model as photovoltaic component installation inclination, photovoltaic array spacing, photovoltaic component installation position, photovoltaic component orientation, photovoltaic component light transmittance, and water collection tank coverage rate; Specifically, set the photovoltaic component installation inclination, photovoltaic array spacing, photovoltaic component installation position, photovoltaic component orientation, photovoltaic component light transmittance, and water collection tank coverage rate as adjustable parameters for model iterative optimization.

[0064] S560, configure the constraint conditions of the neural network fusion model as structural load constraint, sunshine spacing constraint, cultural landscape constraint, and greenery coordination constraint; Specifically, the structural load constraint is that the total weight of the photovoltaic component and the support is less than or equal to the building load limit value. The sunshine spacing constraint is that the shadow length of the photovoltaic component at noon on the winter solstice is less than or equal to one-third of the spacing between surrounding buildings. The cultural landscape constraint is that the light transmittance of the facade photovoltaic component is greater than or equal to 60% (for historical buildings surrounding), and the color of the photovoltaic component matches the main tone of the building. The greenery coordination constraint is that the support height is greater than or equal to the plant height plus 0.5 m to avoid blocking plant growth.

[0065] S570, obtain a Pareto optimal solution set by iterating the design variables based on the constraint conditions, the objective function, and the optimization target; Specifically, the model initializes a population of design variables (100 in size, only as an example) based on the constraint conditions, explores variable combinations through reinforcement learning (preferentially selects variable intervals with good performance in historical interactions), calculates the objective function value of each variable combination using a multi-objective optimization algorithm, performs non-dominated sorting (filters non-dominated solutions that are not inferior to other solutions in a single objective), and outputs a Pareto optimal solution set (containing 20-30 solution sets) after 1000 iterations (the specific number of iterations is set according to requirements and is not limited here).

[0066] S580, after selecting a target solution from the Pareto optimal solution set according to the comprehensive benefit requirement, the first arrangement scheme is obtained.

[0067] Specifically, according to the comprehensive benefit requirement (such as prioritizing power generation by selecting the top 20% of solutions in terms of power generation, or prioritizing state coordination by selecting solutions with high matching degrees of ventilation and irrigation), one best solution is selected as the first arrangement scheme.

[0068] In some optional embodiments, the Pareto optimal solution set obtained after iterating the design variables based on the constraint conditions, the objective function, and the optimization target includes: S571, a predetermined number of initial design variable combinations are randomly generated, and the initial design variable combinations meet the constraint conditions; Specifically, a predetermined number (100-200 groups, balancing calculation efficiency and solution diversity) of design variable combinations (including photovoltaic component inclination, array spacing, installation position, and all adjustable parameters) are randomly generated. During the generation process, it is necessary to verify in real time whether the constraint conditions are met: for example, the total weight of the components and the support should be ≤ the building load limit value (structural load constraint), the shadow length of the components on the winter solstice should be ≤ one third of the spacing between surrounding buildings (daylight spacing constraint), and the light transmittance of the facade components should meet the requirements of the human landscape. For combinations that do not meet the constraints, they are directly eliminated and regenerated until a predetermined number of valid initial design variable combinations are obtained, forming an initial population.

[0069] S572, the initial design variable combinations are substituted into the objective function to calculate the fitness value of the optimization target, and the fitness value represents the matching degree with the optimization target; Specifically, each group of initial design variables is combined into the objective functions corresponding to the five optimization objectives, and the fitness values of each objective are calculated respectively. The fitness value is used to quantify the matching degree of the variable combination and the optimization objective. For example, in the photovoltaic power generation capacity objective, the fitness value is equal to the ratio between the actual calculated power generation capacity and the theoretical maximum power generation capacity (the theoretical maximum power generation capacity is calculated based on the condition of no obstruction and optimal inclination angle). The closer the ratio is to 1, the higher the fitness value is. In the ventilation coefficient loss objective, the fitness value = 1-actual ventilation loss rate. The fitness value calculation logic of the daylighting satisfaction rate, heat gain rate compliance rate, and irrigation matching degree objectives is similar, and finally a five-dimensional fitness value vector of each group of variable combinations is formed (such as [0.92, 0.88, 0.95, 0.91, 0.86]).

[0070] S573, non-dominated sorting the initial design variable combinations according to the fitness values to obtain non-dominated solutions; Specifically, the design variable combinations in the initial population are classified using the non-dominated sorting method (such as the sorting logic in the NSGA-II algorithm). If all the fitness values of a certain variable combination are not lower than those of another combination, and at least one fitness value is higher than that of the combination, the former dominates the latter, and the latter is eliminated. All variable combinations that are not dominated by other combinations are retained, which are the non-dominated solutions (the first front solution). At the same time, the crowding distance of the non-dominated solutions is calculated (quantifying the dispersion of the solution in the objective space) to ensure the diversity of the solutions. The larger the crowding distance, the more unique the solution in the objective space, which can avoid the aggregation of solutions.

[0071] S574, generating new iteration design variable combinations by gene recombination and random variation of the non-dominated solutions, and adding 1 to the iteration number; Specifically, the gene recombination adopts a two-point crossover method, randomly selects two non-dominated solutions (parents), selects two crossover points in the design variable sequence, and exchanges the variable fragments between the crossover points (such as crossing "inclination angle 35°, spacing 2.5H" of parent 1 with "inclination angle 40°, spacing 2.0H" of parent 2 to generate "inclination angle 35°, spacing 2.0H" of offspring), and the offspring needs to be checked for constraint satisfaction after recombination, and if not, it needs to be re-crossed.

[0072] Random variation is to randomly adjust a certain design variable according to a preset variation probability (5%-10%) for the recombined offspring variables (such as varying "transmittance 40%" to "transmittance 45%" and "installation position R1" to "installation position R2"). Similarly, the constraint satisfaction needs to be checked to ensure the effectiveness of the offspring. Repeat the above operations to generate new iteration design variable combinations consistent with the initial population size, and add 1 to the iteration number (the initial iteration number is 0).

[0073] S575, in the case of the number of iterations is less than or equal to the preset number of times, the iterative design variable combination is configured as the initial design variable combination, and iterative calculation is performed, which represents the step of generating the iterative design variable combination; Specifically, the current number of iterations is compared with the preset number of times (1000-2000 times, which needs to be set according to the calculation resources and the accuracy requirement, and is not limited here); if the number of iterations is less than or equal to the preset number of times, the newly generated iterative design variable combination is used as the “initial design variable combination” again, and the steps S572-S574 are repeated to perform iterative calculation, so as to continuously optimize the quality and diversity of the non-dominated solution.

[0074] S576, in the case of the number of iterations is greater than the preset number of times, the non-dominated solution is configured as the Pareto optimal solution set.

[0075] Specifically, if the number of iterations is greater than the preset number of times, the iteration is stopped, and the finally obtained non-dominated solution (20-30 groups are reserved after multiple rounds of screening) is formally configured as the Pareto optimal solution set. The solution set covers the optimal trade-off scheme between multiple objectives (for example, a solution has the highest power generation but the lighting satisfaction rate is moderate, and a solution has high matching degrees of lighting and irrigation but low power generation).

[0076] Step S600, constructing a digital twin model of the first arrangement scheme and the multi-source data.

[0077] Specifically, the multi-source data is fused with the first arrangement scheme to obtain a fused BIM model. The fused BIM model and the first arrangement scheme are imported, and the building, the photovoltaic component, the green area, and the cultural activity path are restored according to a preset proportion. The visualization layer of the multi-physical field simulation result (such as wind speed vector arrow, lighting coefficient thermal map, and rainwater collection path animation) is superimposed to obtain the corresponding digital twin model. The digital twin model supports scene scaling, translation, and rotation. By clicking any component, real-time parameters such as power generation and temperature of the component and associated multi-source data (such as the water demand of the green area below the component) can be viewed. Historical weather replay (such as replaying the scheme running state on an extreme high-temperature day) and parameter adjustment preview (dragging a slider to modify the inclination angle of the component, and the platform displays the change trend of the power generation and the ventilation coefficient in real time) functions are provided. Performance charts are generated to display the current values and target values of the power generation, the lighting satisfaction rate, the heat gain rate, the ventilation coefficient, and the irrigation matching degree in real time. A simulation report (including a key parameter cloud map, a time series curve, and a constraint satisfaction condition description) is automatically generated.

[0078] In some optional embodiments, the construction of the digital twin model of the first arrangement scheme and the multi-source data includes: S610, converting the building data into a BIM model; Specifically, building data is extracted from multi-source data, and a model is constructed through BIM software; the main structure of the roof, facade, floor, etc. is restored according to the actual building layout, the positions and parameters of key components such as load-bearing beams, ventilation openings, doors and windows are labeled, and the structural performance parameters in the building data are associated with the corresponding BIM components.

[0079] S620, superimpose the first arrangement scheme to the BIM model to obtain a first model; Specifically, the core parameters (installation area, number, inclination, spacing, light transmittance, and water collection tank coverage rate of photovoltaic modules) in the first arrangement scheme are extracted, a photovoltaic module family (including component size, self-weight, electrical parameters, and other attributes) is created in the BIM software, the module family is accurately superimposed on the corresponding area (such as the southeast area of the roof and the south side of the facade) of the BIM model according to the position coordinates labeled in the scheme: spatial collision detection is performed during the superimposition process to ensure that there is no positional conflict between the module and the building component, and the total weight of the module and the support load does not exceed the building load limit; at the same time, the performance parameters (such as the power of a single module and the temperature coefficient) of the module are bound to the module family in the BIM model to form a first model containing building structure and photovoltaic module arrangement.

[0080] S630, associate the historical weather data with the first model to obtain a second model; Specifically, historical weather data is selected from multi-source data and associated with the first model according to the logic of time stamp and spatial position: meteorological parameters (such as hourly wind speed at a height of 15m for the roof area and solar radiation at a height of 8m for the facade area) are bound to different areas in the BIM model, historical weather data is embedded in the components of the first model in the form of attribute parameters through an API interface, and data association rules (such as automatically calling the component efficiency attenuation coefficient at the corresponding temperature during the summer high-temperature period) are set to form a second model that integrates building, photovoltaic, and meteorological data.

[0081] S640, superimpose the humanistic data and the landscape greening data to the second model to obtain a third model; Specifically, the landscape requirements (such as the building facade component color needs to match the main color tone), the activity path (such as the roof maintenance passage width is greater than or equal to 1.2 m), and the management specification (such as the distance between the component and the fire passage is greater than or equal to 0.5 m) in the human data are extracted, the constraint area is marked in the BIM model by using a marking layer (such as the maintenance passage is marked by a red line, and the component coverage is prohibited), and the human constraint parameters (such as the component color RGB value range) are associated with the corresponding area component family. The plant type, height, crown width, planting position, and soil parameters in the landscape greening data are extracted, the greening plant family (such as the tree family and the shrub family) is created in the BIM model, and is superimposed to the greening area of the model according to the actual planting distribution, and the plant water requirement, resistance coefficient and other parameters are embedded into the plant family, forming a third model including the building, photovoltaic, meteorological, human and greening.

[0082] S650, generating a first coupling model capable of calculating the hourly power generation, indoor heat gain rate, ventilation volume, daylighting rate and water collection volume of each position according to the first arrangement scheme, the historical weather data, the landscape greening data, the human data and the building data, and superimposing the first coupling model to the third model to obtain the digital twin model.

[0083] Specifically, based on the first arrangement scheme, the historical weather data, the landscape greening data, the human data and the building data, the first coupling model is developed by coupling the software such as EnergyPlus, Fluent and Radiance, to realize the hourly calculation of the key performance.

[0084] Hourly power generation calculation: combined with the component inclination, light transmittance (from the first arrangement scheme) and hourly irradiance, temperature (from the historical weather data), the hourly power generation of each component is calculated by using the PVsyst algorithm.

[0085] Indoor heat gain rate calculation: based on the building envelope thermal parameter (from the building data), the component shading rate (from the first arrangement scheme) and the hourly solar radiation (from the historical weather data), the indoor hourly heat gain rate is calculated by EnergyPlus to match the indoor target heat gain rate.

[0086] Ventilation volume calculation: combined with the building ventilation port position (from the building data), the component array spacing (from the first arrangement scheme), the plant resistance coefficient (from the landscape greening data) and the hourly wind speed (from the historical weather data), the indoor and outdoor hourly ventilation volume is calculated by using the RNG k-ε model of Fluent.

[0087] Daylighting rate calculation: according to the component light transmittance (from the first arrangement scheme), the window position (from the building data) and the solar altitude angle (from the historical weather data), the indoor hourly daylighting rate is calculated by the Radiance ray tracing algorithm to match the daylighting demand data.

[0088] The water collection calculation: combined with the assembly water collection area, the water collection tank coverage rate (from the first arrangement scheme) and the hourly rainfall (from the historical weather data), the hourly water collection of each water collection tank is calculated, and the green water demand (from the landscape data) is associated. Finally, through the data interface, the performance calculation function of the first coupling model is associated with the geometric space of the third model to realize the function of viewing the hourly power generation, heat gain rate, ventilation, lighting and water collection of the region by clicking any position of the model, forming a digital twin model with geometric visualization and performance simulation functions.

[0089] Step S700, after simulating the digital twin model, a simulation result is obtained.

[0090] Specifically, the digital twin model is simulated, the core performance target of the first arrangement scheme is combined with the multi-source data driven model operation, and the simulation result of quantitative and scenario combination is output through multi-dimensional calculation.

[0091] In the power generation dimension, the hourly irradiance and environmental temperature are input, the solar incidence correction coefficient is calculated combined with the assembly inclination orientation, the assembly efficiency is corrected according to the temperature coefficient, and the hourly power generation of the single assembly, the partition and the whole is output, and the daily / weekly / seasonal total power generation is accumulated; in the lighting and heat gain dimension, the influence of assembly shielding on indoor illuminance is simulated by ray tracing algorithm, the hourly lighting ratio and lighting satisfaction rate of each room are calculated, and whether it meets the indoor target heat gain rate is verified based on the thermal calculation module, inputting the envelope structure parameters and assembly light transmittance, and outputting the hourly heat gain rate; in the ventilation dimension, the wind field distribution is simulated combined with the building contour, assembly spacing and plant resistance coefficient, the indoor and outdoor hourly ventilation volume is calculated, and the actual ventilation coefficient and ventilation loss rate are output; in the irrigation dimension, the hourly rainwater collection amount is calculated according to the hourly rainfall, assembly water collection area and water collection tank coverage rate, and the evaporation loss is deducted, the irrigation matching degree is obtained combined with the plant water demand, and the irrigation satisfaction rate and rainwater gap are counted.

[0092] Finally, the simulation result is output, including quantitative report and visual content. The quantitative report covers the core data of power generation (partition power generation, efficiency, loss rate), lighting and heat gain (room lighting ratio satisfaction rate, heat gain rate compliance rate), ventilation (ventilation volume, ventilation coefficient, loss rate), irrigation (water collection, matching degree, gap amount) and the like; the visual content superimposes the performance parameter space distribution (such as power generation heat map, lighting ratio cloud map), time sequence curve (hourly power generation, heat gain rate change) and scene dynamic simulation (wind field streamline animation, rainwater collection path) in the BIM scene, and intuitively presents the performance of the scheme in different scenes.

[0093] In some optional embodiments, after the simulation of the digital twin model, the simulation result is obtained, which comprises: S710, generate a simulation atlas according to the simulation result, the simulation atlas being used to indicate a difference between multi-dimensional simulation data and target data at each position of the target installation area, the multi-dimensional simulation data representing simulated hourly power generation, indoor heat gain rate, daylighting rate, ventilation volume, and water collection volume; Specifically, based on the multi-dimensional simulation data (hourly power generation, indoor heat gain rate, daylighting rate, ventilation volume, and water collection volume) output by the digital twin model and the preset target data (such as a power generation target value, an indoor heat gain rate standard range, a daylighting rate standard value, etc.), a simulation atlas is generated according to a spatial position and performance difference value correspondence.

[0094] First, the spatial coordinate system of the atlas is determined (consistent with the BIM coordinate system of the digital twin model), the target installation area is divided into 1m x 1m grid cells, and each cell corresponds to a spatial position; for each grid cell, the difference between the multi-dimensional simulation data and the target data is calculated (for example, the simulation power generation of a certain cell is 200W, the target power generation is 250W, the difference is -50W; the simulation daylighting rate of a certain cell is 2.8%, the target daylighting rate is 3%, the difference is -0.2%).

[0095] The difference value is visualized using a color coding rule: for example, red represents an out-of-standard difference value (such as a power generation difference value < -50W and a daylighting rate difference value < -0.3%), yellow represents a difference value close to a critical value (such as a power generation difference value -50W ~ -20W and a daylighting rate difference value -0.3% ~ -0.1%), and green represents a difference value that meets the standard (such as a power generation difference value ≥ -20W and a daylighting rate difference value ≥ -0.1%), and finally a simulation atlas covering the entire area and containing multi-dimensional performance difference value information is generated.

[0096] S720, sequentially perform grayscale processing, filtering processing, and denoising processing on the simulation atlas to obtain a preprocessed image; Specifically, the color simulation atlas is converted into a grayscale image, the performance difference value is quantified by the grayscale value (such as a grayscale value of 0 corresponding to a maximum negative difference value and a grayscale value of 255 corresponding to a maximum positive difference value, a difference value and grayscale value mapping relationship is established), the color information is eliminated to interfere with subsequent processing, and the data dimension is simplified.

[0097] The filtering processing uses a Gaussian filtering algorithm to perform smoothing processing on the grayscale image, removes subtle noise (such as a grayscale value jump of adjacent grid cells due to calculation errors) generated during atlas generation due to grid division and data calculation, makes the grayscale change of the image more gentle, and retains the overall performance difference value distribution trend.

[0098] The de-noising processing further eliminates the isolated noise points (such as grid cells with abnormal single gray value) remaining after the filtering by a median filtering algorithm, ensures that the change in the gray value in the image is caused only by the real performance difference, and finally obtains a pre-processed image with uniform gray distribution and small noise interference.

[0099] S730, segmenting the pre-processed image into a plurality of spatial image sub-regions; Specifically, the region growing algorithm is used to spatially segment the pre-processed image to obtain a plurality of spatial image sub-regions: first, select grid cells with similar gray values in the image as initial seed points (such as cells with gray values of 180-200 as seed points of the power generation standard area, and cells with gray values of 50-70 as seed points of the abnormal power generation area); take the seed point as the center, and gradually combine the adjacent grid cells with a gray value difference of ≤5 (a threshold value set according to the image gray range) to form a continuous spatial region.

[0100] The above process is repeated until all grid cells in the image are classified into corresponding regions, and finally the pre-processed image is segmented into a plurality of spatial image sub-regions with clear boundaries and high internal gray value similarity (such as power generation standard sub-regions, abnormal lighting ratio sub-regions, etc.).

[0101] S740, obtaining abnormal region information according to the similarity between a plurality of spatial image sub-regions, the abnormal region information representing the contour information and spatial position information of a target region that has obvious differences with adjacent regions.

[0102] Specifically, the gray value similarity (calculated by the structural similarity index SSIM, with a value range of 0-1, and the closer the value to 1, the higher the similarity) between each spatial image sub-region and the adjacent sub-region is calculated, the abnormal region is identified, and the information is extracted.

[0103] In some optional embodiments, the abnormal region information is obtained according to the similarity between a plurality of spatial image sub-regions, including: S741, comparing the first similarity between the first image sub-region and the third image sub-region and the second similarity between the second image sub-region and the third image sub-region to obtain a comparison result, the third image sub-region being any one of the spatial image sub-regions, the first image sub-region being located on a first side of the third image sub-region, the second image sub-region being located on a second side of the third image sub-region, and the first image sub-region, the second image sub-region and the third image sub-region all representing the spatial image sub-region. Specifically, any sub-region is selected from the segmented spatial image sub-regions as a third image sub-region (a core region to be judged whether abnormal), and two adjacent sub-regions of the third image sub-region are determined: a first image sub-region located on the first side (for example, the left side) of the third image sub-region, and a second image sub-region located on the second side (for example, the right side) of the third image sub-region. A first similarity between the third image sub-region and the first image sub-region and a second similarity between the third image sub-region and the second image sub-region are calculated by a structural similarity index (SSIM). The closer the SSIM value is to 1, the more similar the gray scale distribution (corresponding to the performance difference distribution) of the two sub-regions is. The closer the value is to 0, the more significant the difference is.

[0104] S742, in the case where the comparison result represents that the first similarity is greater than the second similarity, sequentially performing unit distance adjustment and unit scale scaling on the third image sub-region to the position where the second image sub-region is located, and configuring the contour information and the spatial information of the third image sub-region with the maximum difference value of the first similarity and the second similarity as the abnormal region information; Specifically, the first similarity and the second similarity are compared, and the third image sub-region is dynamically adjusted according to the comparison result.

[0105] If the comparison result shows that the first similarity is greater than the second similarity (indicating that the third sub-region is more similar to the first sub-region on the left side and more different from the second sub-region on the right side): sequentially performing unit distance adjustment (for example, moving 1 grid unit to the right along the horizontal direction each time, corresponding to 0.5 m in actual space) and unit scale scaling (for example, reducing the scale by 5% along the axis perpendicular to the moving direction each time, maintaining the integrity of the sub-region) on the third image sub-region to the side (the right side) where the second image sub-region is located, and recalculating the similarity of the current third sub-region with the first and second sub-regions each time the adjustment is performed. During the dynamic adjustment of the third image sub-region, the difference value of the first similarity and the second similarity after each adjustment is continuously recorded. When the difference value reaches the maximum value (indicating that the third sub-region is extremely similar to one side sub-region and the difference with the other side sub-region reaches the peak value, which meets the feature that “the abnormal region and the adjacent region have obvious difference”), the adjustment is stopped. The contour information (for example, the polygon boundary after scaling) and the spatial position information (for example, the coordinate range based on the coordinate system of the digital twin model) of the third image sub-region at this time are extracted and configured as the abnormal region information; the abnormal region information accurately reflects the region range with the most significant performance difference from the surrounding region, and can be directly corresponded to the actual position of the target installation region, facilitating subsequent rapid analysis of photovoltaic arrangement problems.

[0106] S743、in the case that the comparison result represents that the first similarity is less than the second similarity, sequentially performing unit distance adjustment and unit scale scaling on the third image sub-region to the position where the first image sub-region is located, and configuring the contour information and the spatial information of the third image sub-region with the maximum difference between the first similarity and the second similarity as the abnormal region information; Specifically, if the comparison result shows that the first similarity is less than the second similarity (indicating that the third sub-region is more similar to the right second sub-region and more different from the left first sub-region): sequentially performing unit distance adjustment and unit scale scaling on the third image sub-region to the side (left side) where the first image sub-region is located, and similarly, recalculating the two sets of similarities each time the adjustment is performed, and configuring the contour information and the spatial information of the third image sub-region as the abnormal region information when the difference between the first similarity and the second similarity is the largest.

[0107] S744、in the case that the comparison result represents that the first similarity is equal to the second similarity, synchronously moving the first image sub-region and the second image sub-region by a unit distance and performing unit scale scaling until the first similarity is not equal to the second similarity.

[0108] Specifically, if the comparison result shows that the first similarity is equal to the second similarity (indicating that the third sub-region is balancedly different from the two sub-regions on the left and right sides, and it is temporarily impossible to determine the abnormality): synchronously performing unit distance adjustment (such as moving 1 grid unit towards the third sub-region) and unit scale scaling (such as reducing by 5%) on the first image sub-region and the second image sub-region, recalculating the similarities of the third sub-region with the two sub-regions each time the adjustment is performed, and then performing subsequent adjustment according to the above two cases until the two sets of similarities are not equal.

[0109] In some optional embodiments, after obtaining the abnormal region information according to the similarities between the plurality of spatial image sub-regions, the method further includes: S745、obtaining target data corresponding to the spatial position indicated by the abnormal region information, the target data belonging to simulation data; Specifically, according to the determined abnormal position information, extracting the simulation data corresponding to the spatial position from the simulation atlas, i.e., the target data.

[0110] S746、determining a target abnormal type of a target region according to the target data and a preset analysis rule; Specifically, the preset analysis rule is a corresponding rule of a parameter threshold and an abnormal type prepared in advance; the corresponding abnormal type can be determined by analyzing the characteristics of the target data through the preset analysis rule; the extracted target data is compared with the parameter threshold in the preset analysis rule one by one, to determine the parameter exceeding the normal range and the corresponding abnormal type; if there are multiple parameters exceeding the standard in the target data, the main abnormal type is determined according to the influence priority, and finally the target abnormal type of the target area is obtained.

[0111] S747, in the case where the target abnormal type does not belong to the abnormal type table, performing manual review analysis processing on the target area to obtain a review abnormal type; Specifically, the abnormal type table is a standardized abnormal type set formed by previous practice and historical data accumulation, and the determined target abnormal type is matched with the abnormal type table. If the target abnormal type is not in the abnormal type table, it means that the abnormality may be a new abnormality caused by special installation environment or installation position, and the accuracy needs to be verified through review analysis processing.

[0112] S748, in the case where the review abnormal type is equal to the target abnormal type, the target abnormal type is added to the abnormal type table; Specifically, if the review abnormal type is consistent with the target abnormal type determined in the previous stage, it means that the target abnormal type is accurate, and the target abnormal type is supplemented to the abnormal type table, and the corresponding analysis rule is improved.

[0113] S749, in the case where the review abnormal type is not equal to the target abnormal type, the target abnormal type is replaced by the review abnormal type, and the review abnormal type is added to the abnormal type table.

[0114] Specifically, if the review abnormal type is not consistent with the target abnormal type, it means that there is a model prediction deviation in the previous target data, the target abnormal type is replaced by the review abnormal type, and the review abnormal type is added to the abnormal type table.

[0115] S800, correcting the first arrangement scheme according to the simulation result to obtain a target arrangement scheme.

[0116] Specifically, based on the abnormal area information (contour and spatial position) in the simulation results, the corresponding physical area (such as the northwest area of the roof and the 2nd floor of the south facade) is located in the digital twin model, and the multi-dimensional performance difference of the area in the simulation results is matched. For different performance problems, combined with the constraint conditions in the multi-source data (such as building load and cultural landscape requirements), parameter adjustment strategies are formulated. The corrected parameters (new inclination, spacing, light transmittance, etc.) are updated to the first arrangement scheme, a corrected scheme is generated and imported into the digital twin model for secondary simulation, and the simulation results meet the arrangement requirements. The corrected scheme can be used as the target arrangement scheme so as to install the photovoltaic modules according to the target arrangement scheme.

[0117] In some optional embodiments, after the target arrangement scheme is obtained by correcting the first arrangement scheme according to the simulation results, the method further includes: S810, determining a first priority of each arrangement sub-area according to simulation data corresponding to the arrangement sub-area in the target arrangement scheme.

[0118] Specifically, the arrangement sub-area (such as a residential sub-area, a commercial sub-area, and a municipal road sub-area) divided by the target arrangement scheme is taken as a unit, the simulation data corresponding to each arrangement sub-area is extracted, the priority evaluation index and the weight are set, the first priority score of each arrangement sub-area is calculated, and the higher the score, the higher the first priority.

[0119] S820, determining the relevance between each arrangement sub-area by a network analysis method; Specifically, the network analysis method is used to identify the mutual correlation of each arrangement sub-area in terms of construction resources, process connection, and environmental impact, construct a correlation matrix, and quantify the correlation strength.

[0120] S830, obtaining a second priority by correcting the first priority according to the relevance, so that each arrangement sub-area installs the photovoltaic modules according to the second priority in turn.

[0121] Specifically, the correlation weight is used as a correction coefficient to adjust the first priority score to obtain the second priority, so as to ensure that the installation order of the photovoltaic modules takes into account the characteristics of the arrangement sub-area and the overall relevance. The photovoltaic modules are installed according to the corrected second priority, so as to ensure the optimization of resources, efficiency, and economic benefits.

[0122] The beneficial effects of this invention include: acquiring multi-source data of the target installation area, including building data, historical weather data, human data, and landscape greening data; determining the ventilation coefficient of the target installation area based on the building data, historical weather data, and landscape greening data; determining the irrigation coefficient of the target installation area based on the historical weather data and landscape greening data; acquiring the light requirement data and indoor target heat gain rate of the target installation area; generating a first layout scheme based on the multi-source data, the light requirement data, the indoor target heat gain rate, the ventilation coefficient, and the irrigation coefficient; constructing a digital twin model of the first layout scheme and the multi-source data; simulating the digital twin model to obtain simulation results; and correcting the first layout scheme based on the simulation results to obtain the target layout scheme. The invention automatically generates the corresponding first layout scheme based on the multi-source data of the target installation area, resulting in high generation efficiency. By combining the first layout scheme and the multi-source data to generate a corresponding digital twin model and performing simulation, the first layout scheme is corrected to obtain the target layout scheme, thus improving the completeness of the photovoltaic module layout scheme.

[0123] like Figure 2 As shown, Figure 2 A structural block diagram of a controller 1000 according to an embodiment of this application is shown. The components of the controller 1000 include, but are not limited to, a memory 1200 and a processor 1100. The processor 1100 is connected to the memory 1200 via a bus, and the memory 1200 is used to store data.

[0124] The controller 1000 also includes an access device that enables the controller 1000 to communicate via one or more networks. Examples of such networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device may include one or more of any type of wired or wireless network interface (e.g., a Network Interface Card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Global System for Microwave Access (GSM) interface, or a Wi-Fi interface. Interfaces include MAX, Ethernet, USB, cellular, Bluetooth, NFC, and more.

[0125] The controller 1000 can be any type of stationary or mobile electronic device, including a mobile computer or mobile electronic device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smartphone), a wearable electronic device (e.g., a smart watch, smart glasses, etc.), or other type of mobile device, or a stationary electronic device such as a desktop computer or PC. The controller 1000 can also be a mobile or stationary server.

[0126] The processor 1100 is configured to execute computer-executable instructions of the photovoltaic module arrangement scheme generation method.

[0127] The above is a schematic scheme of the controller of the embodiment. It should be noted that the technical scheme of the controller belongs to the same concept as the technical scheme of the photovoltaic module arrangement scheme generation method described above, and the details of the technical scheme of the controller that are not described in detail can be referred to the description of the technical scheme of the photovoltaic module arrangement scheme generation method.

[0128] According to an embodiment of the present application, a photovoltaic module arrangement scheme generation system is also provided. The photovoltaic module arrangement scheme generation system includes a controller 1000, and the automatic generation of the construction scheme is realized through the controller 1000. It should be noted that the technical scheme of the photovoltaic module arrangement scheme generation system belongs to the same concept as the technical scheme of the photovoltaic module arrangement scheme generation method described above, and the details of the technical scheme of the computing device that are not described in detail can be referred to the description of the technical scheme of the photovoltaic module arrangement scheme generation method.

[0129] The embodiment of the present application also provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program. When the computer program is executed by a processor, the photovoltaic module arrangement scheme generation method described above is realized.

[0130] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include a high-speed random access memory and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can include memory that is remotely located with respect to the processor, which can be connected to the processor through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The above-described device embodiments are only illustrative, and units described as separate components can or can not be physically separated, implemented in one place, or can also be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment.

[0131] Those of ordinary skill in the art can understand that all or some steps in the above disclosed method and system can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all physical components can be implemented as software executed by a processor, such as a central processor, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software can be distributed on a computer readable medium, which can include computer storage media (or non-transitory media) and communication media (or transitory media). As known to those of ordinary skill in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. In addition, as known to those of ordinary skill in the art, communication media generally includes computer readable instructions, data structures, program modules or other data in modulated data signals such as carrier waves or other transport mechanisms, and can include any information delivery medium.

[0132] The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the present application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the present application.

Claims

1. A method for generating a photovoltaic module layout scheme, characterized in that, include: Acquire multi-source data of the target installation area, including building data, historical weather data, human data, and landscape greening data; The ventilation coefficient of the target installation area is determined based on the building data, the historical weather data, and the landscape greening data; The irrigation coefficient for the target installation area is determined based on the historical weather data and the landscape greening data. Obtain the lighting requirements data and indoor target heat gain rate of the target installation area; A first layout scheme is generated based on the multi-source data, the lighting demand data, the indoor target heat gain rate, the ventilation coefficient, and the irrigation coefficient; Construct a digital twin model of the first layout scheme and the multi-source data collaboration; The simulation results were obtained after simulating the digital twin model. The target layout scheme is obtained by correcting the first layout scheme based on the simulation results.

2. The method for generating a photovoltaic module layout scheme according to claim 1, characterized in that, Determining the ventilation coefficient of the target installation area based on the building data, the historical weather data, and the landscape greening data includes: A first model is constructed based on the building data and the landscape greening data; The first ventilation volume is obtained by performing ventilation simulation on the first model based on the historical weather data. A first coefficient is determined based on the first ventilation volume and the maximum ventilation volume, wherein the maximum ventilation volume represents the ventilation volume when there is no obstruction. The seasonal correction factor is determined based on the historical weather data. Determine the greening growth correction coefficient based on the aforementioned landscape greening data; The ventilation coefficient is obtained by correcting the first coefficient based on the seasonal correction coefficient and the greening growth correction coefficient.

3. The method for generating a photovoltaic module layout scheme according to claim 1, characterized in that, The step of determining the irrigation coefficient of the target installation area based on the historical weather data and the landscape greening data includes: Obtain the rainfall and evaporation from the historical weather data; Obtain the green area and water requirement for greening from the landscape greening data; The basic water requirement is determined based on the green area and the water demand of the green area; The amount of irrigation water is determined based on the rainfall and evaporation. The irrigation coefficient is determined based on the irrigation water volume and the basic water requirement.

4. The method for generating a photovoltaic module layout scheme according to claim 1, characterized in that, The step of generating a first layout scheme based on the multi-source data, the lighting demand data, the indoor target heat gain rate, the ventilation coefficient, and the irrigation coefficient includes: Construct a neural network fusion model combining multi-objective optimization algorithms and reinforcement learning frameworks; The multi-source data, the lighting demand data, the indoor target heat gain rate, the ventilation coefficient, and the irrigation coefficient are input into the neural network fusion model; The optimization objectives of the neural network fusion model are configured as maximizing photovoltaic power generation, maximizing indoor lighting satisfaction rate, maximizing indoor heat gain rate compliance rate, minimizing ventilation coefficient loss, and maximizing irrigation coefficient matching degree. Construct the objective function corresponding to the optimization objective; The design variables of the neural network fusion model are configured as photovoltaic module installation tilt angle, photovoltaic array spacing, photovoltaic module installation position, photovoltaic module orientation, photovoltaic module transmittance, and water collection tank coverage. The constraints of the neural network fusion model are configured as structural load constraints, solar spacing constraints, human landscape constraints, and greening synergy constraints. Based on the constraints, the objective function, and the optimization objective, the Pareto optimal solution set is obtained by iterating the design variables. The first layout scheme is obtained by selecting the target solution from the Pareto optimal solution set based on the overall benefit requirements.

5. The method for generating a photovoltaic module layout scheme according to claim 4, characterized in that, The process of obtaining the Pareto optimal solution set by iterating the design variables based on the constraints, the objective function, and the optimization objective includes: A preset number of initial design variable combinations are randomly generated, and the initial design variable combinations satisfy the constraints. The initial design variables are substituted into the objective function to calculate the fitness value of the optimization objective, and the fitness value represents the degree of matching with the optimization objective. The non-dominated solution is obtained by performing a non-dominated sorting of the initial design variable combination based on the fitness value. After performing gene recombination and random mutation on the non-dominated solution, a new combination of iterative design variables is generated, and the iteration number is incremented by one. When the number of iterations is less than or equal to the preset number of iterations, the iterative design variable combination is configured as the initial design variable combination and then iterative calculation is performed. The iterative calculation represents the steps described above for generating the iterative design variable combination. If the number of iterations is greater than a preset number, the non-dominated solution is configured as the Pareto optimal solution set.

6. The method for generating a photovoltaic module layout scheme according to claim 4, characterized in that, The construction of the first layout scheme and the digital twin model of multi-source data collaboration includes: Convert the building data into a BIM model; The first layout scheme is superimposed onto the BIM model to obtain the first model; The historical weather data is correlated with the first model to obtain the second model; The third model is obtained by overlaying the humanistic data and the landscape greening data onto the second model. Based on the first layout scheme, the historical weather data, the landscape greening data, the human data, and the building data, a first coupled model is generated that can calculate the hourly power generation, indoor heat gain rate, ventilation volume, daylighting rate, and water collection volume at each location. The first coupled model is then superimposed on the third model to obtain the digital twin model.

7. The method for generating a photovoltaic module layout scheme according to claim 1, characterized in that, After obtaining the simulation results by simulating the digital twin model, the process includes: A simulation map is generated based on the simulation results. The simulation map is used to indicate the difference between the multi-dimensional simulation data and the target data at each location of the target installation area. The multi-dimensional simulation data characterizes the simulated hourly power generation, indoor heat gain rate, daylighting rate, ventilation volume, and water collection volume. The simulated image is then subjected to grayscale conversion, filtering, and denoising processes in sequence to obtain a preprocessed image. The preprocessed image is divided into multiple spatial image sub-regions; Abnormal region information is obtained based on the similarity between multiple spatial image sub-regions. The abnormal region information represents the contour information and spatial location information of the target region that is significantly different from the adjacent regions.

8. The method for generating a photovoltaic module layout scheme according to claim 7, characterized in that, The step of obtaining abnormal region information based on the similarity between multiple spatial image sub-regions includes: The comparison result is obtained by comparing the first similarity between the first image sub-region and the third image sub-region and the second similarity between the second image sub-region and the third image sub-region. The third image sub-region is any of the spatial image sub-regions. The first image sub-region is located on the first side of the third image sub-region, and the second image sub-region is located on the second side of the third image sub-region. The first image sub-region, the second image sub-region, and the third image sub-region all represent the spatial image sub-region. If the comparison result indicates that the first similarity is greater than the second similarity, the third image sub-region is adjusted by unit distance and scaled by unit scale sequentially towards the location of the second image sub-region, and the contour information and spatial information of the third image sub-region with the largest difference between the first similarity and the second similarity are configured as the abnormal region information; If the comparison result indicates that the first similarity is less than the second similarity, the third image sub-region is adjusted by unit distance and scaled by unit scale sequentially towards the location of the first image sub-region, and the contour information and spatial information of the third image sub-region with the largest difference between the first similarity and the second similarity are configured as the abnormal region information; If the comparison result indicates that the first similarity is equal to the second similarity, the first image sub-region and the second image sub-region are simultaneously moved by a unit distance and scaled by a unit until the first similarity is not equal to the second similarity.

9. A photovoltaic module layout scheme generation system, characterized in that, The system includes a controller, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the photovoltaic module layout scheme generation method according to any one of claims 1-8.

10. A computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, which are used to execute the photovoltaic module layout scheme generation method according to any one of claims 1-8.

Images