Coordinated optimization design method of gymnasium wind environment based on gan and rf-nsga integrated algorithm

Abstract

The present application relates to the field of wind and light storage cooperation technology, especially to a gymnasium wind and light energy cooperation optimization design method based on GAN and RF-NSGA integrated algorithm.The method comprises the following steps: determining skylight design parameters, the skylight design parameters including skylight and roof area ratio, skylight quantity, skylight length-width ratio and skylight change rate;based on the skylight design parameters, obtaining building performance simulation data through building performance simulation, the building performance simulation data including effective daylight utilization rate, thermal comfort percentage and photovoltaic power generation capacity;generating generative data enhancement on the building performance simulation data to generate an expanded performance data set.The present application can fundamentally solve the problem of light-generating trade-off caused by traditional single-objective optimization, and realize the maximization of roof resource utilization and the minimization of building operation carbon emission.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of wind-solar-storage coordination technology, and particularly relates to a gymnasium wind-solar-energy coordination optimization design method based on a GAN and RF-NSGA integrated algorithm. BACKGROUND

[0002] As an important part of the gymnasium building, the design of the roof not only affects natural lighting, thermal comfort and ventilation performance, but also has great potential for integrating building photovoltaic systems (Building-Integrated Photovoltaics, BIPV). By reasonably designing the roof skylight system, the indoor light environment quality and natural ventilation performance can be effectively improved, and the energy consumption of air conditioning and lighting can be reduced; at the same time, arranging the BIPV system in the remaining area of the roof helps to realize on-site power generation of renewable energy and reduce building operation carbon emissions.

[0003] However, there is a clear spatial conflict and performance coupling relationship between skylight design and BIPV system arrangement.

[0004] On the one hand, the increase in the number of skylights and the decentralization of the layout help to improve lighting uniformity and thermal comfort, but it will occupy the effective area of the roof, reduce the arrangement density of photovoltaic panels, and cause the power generation to decrease; on the other hand, the efficient arrangement of the BIPV system requires the roof to have a large continuous available area, and is extremely sensitive to shading, and the existence of skylights may cause the skylight diffusion effect (Skylight Diffusion Effect, SDE) between photovoltaic arrays, further reducing the power generation efficiency of the system.

[0005] At present, the research on the gymnasium roof system mainly focuses on the optimization of a single performance target. For example, some research focuses on improving lighting and thermal comfort through skylight optimization, and others focus on the power generation efficiency and arrangement strategy of the roof photovoltaic system. However, few studies include lighting, thermal comfort and photovoltaic power generation in a unified multi-objective optimization framework, and lack a systematic parameter control and performance trade-off mechanism. SUMMARY

[0006] Therefore, it is necessary to provide a gymnasium wind-solar-energy coordination optimization design method based on a GAN and RF-NSGA integrated algorithm to solve at least one of the above technical problems.

[0007] To achieve the above purpose, a gymnasium wind-solar-energy coordination optimization design method based on a GAN and RF-NSGA integrated algorithm includes the following steps:

[0008] Step S1: Determine the skylight design parameters, including the skylight-to-roof area ratio, the number of skylights, the skylight length-width ratio and the skylight change rate;

[0009] Step S2: obtaining building performance simulation data based on the skylight design parameters through building performance simulation, the building performance simulation data including effective daylight utilization, thermal comfort percentage and photovoltaic power generation;

[0010] Step S3: generating extended performance data set by generative data augmentation on the building performance simulation data;

[0011] Step S4: establishing a prediction relationship between the skylight design parameters and the effective daylight utilization, thermal comfort percentage and photovoltaic power generation through regression analysis based on the extended performance data set;

[0012] Step S5: performing collaborative optimization on the effective daylight utilization, thermal comfort percentage and photovoltaic power generation through a multi-objective optimization method based on the prediction relationship, to generate a first Pareto optimal solution set;

[0013] Step S6: determining an optimal skylight design parameter range based on the first Pareto optimal solution set.

[0014] The beneficial effects of the present application are:

[0015] On the one hand, the GAN generates a high-fidelity extended data set by high-dimensional interpolation of a small number of real simulation samples in the latent space, completely covers the skylight-photovoltaic coupling performance surface in a data-driven manner, significantly relieves the simulation resource pressure caused by the roof scheme combination explosion, provides sufficient and diverse training samples for subsequent agent modeling, and thus improves the modeling accuracy and robustness.

[0016] On the other hand, the random forest regression is used to quickly fit the high-dimensional nonlinear mapping and quantify the feature importance, and an interpretable agent model is established between the skylight geometric parameters and the daylight utilization, thermal comfort and photovoltaic power generation, which provides parameter sensitivity information while ensuring prediction accuracy, and provides a stable, differentiable and low-computing-cost evaluation engine for multi-objective optimization.

[0017] On the other hand, the RF-NSGA dynamically adjusts the search pressure in the target space through a reference point mechanism, balances the convergence and uniformity of the Pareto front, and outputs a balanced solution set of high daylighting, high thermal comfort and high power generation at one time, so that the designer can directly lock the optimal balance area under the conflict between the skylight and the photovoltaic panel without repeated trial calculation, fundamentally solves the problem of trade-off between daylighting and power generation caused by traditional single-objective optimization, and realizes the comprehensive benefits of maximizing roof resource utilization, minimizing building operation carbon emissions and shortening design cycle. BRIEF DESCRIPTION OF DRAWINGS

[0018] Other features, objects and advantages of the present application will become more apparent through reading the following detailed description made with reference to the accompanying drawings:

[0019] Fig. 1 A schematic diagram of the step flow of the gym wind and light energy collaborative optimization design method based on the GAN and RF-NSGA integrated algorithm of an embodiment is shown.

[0020] Fig. 2 A detailed schematic diagram of the step S6 of an embodiment is shown.

[0021] Fig. 3 A gym roof map of an embodiment is shown. DETAILED DESCRIPTION

[0022] The technical method of the present application will be described clearly and completely below in conjunction with the drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0023] In addition, the drawings are only schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated descriptions thereof will be omitted. Some block diagrams shown in the drawings are functional entities, which do not necessarily have to correspond to physically or logically independent entities. The functional entities can be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0024] It should be understood that although the terms "first", "second" and the like can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of the exemplary embodiments, a first element can be called a second element, and similarly a second element can be called a first element. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0025] To achieve the above-mentioned purpose, please refer to Figs. 1 to 3 The present application provides a gym wind and light energy collaborative optimization design method based on GAN and RF-NSGA integrated algorithm, comprising the following steps:

[0026] Step S1: determining the skylight design parameters, including the skylight to roof area ratio, the number of skylights, the skylight length-width ratio and the skylight change rate;

[0027] Step S2: Based on the skylight design parameters, obtain building performance simulation data through building performance simulation. The building performance simulation data includes effective solar utilization rate, thermal comfort percentage, and photovoltaic power generation.

[0028] Step S3: Perform generative data augmentation on the building performance simulation data to generate an expanded performance dataset;

[0029] Step S4: Based on the extended performance dataset, establish the predictive relationship between skylight design parameters and effective solar utilization rate, thermal comfort percentage and photovoltaic power generation through regression analysis;

[0030] Step S5: Based on the predicted relationship, the effective solar utilization rate, thermal comfort percentage and photovoltaic power generation are synergistically optimized using a multi-objective optimization method to generate the first Pareto optimal solution set;

[0031] Step S6: Determine the optimal range of sunroof design parameters based on the first Pareto optimal solution set.

[0032] It should be noted that in step S2, the effective solar utilization rate is obtained through solar simulation calculation, the thermal comfort percentage is obtained through thermal comfort simulation calculation, and the photovoltaic power generation is obtained through photovoltaic power generation simulation calculation.

[0033] The specific operation is as follows: Based on the skylight design parameters (area ratio, number, aspect ratio, rate of change) and the architectural characteristics of the target stadium (orientation, roof structure, usage mode), a 3D model of the stadium is generated using Building Information Modeling (BIM) software. Energy Plus or Design Builder software is then used in conjunction with the BIM model to set specific physical parameters, including solar radiation, optical properties of glass and frame materials, and indoor heat load, thus providing basic data for building performance simulation. Sunlight simulation calculates the illuminance distribution on the working surface of each room throughout the year, statistically analyzing the percentage of areas meeting the illuminance standard (e.g., 300 lux), to obtain the effective sunlight utilization rate. Thermal comfort simulation, based on the ISO 7730 standard and combined with parameters such as indoor temperature, humidity, and airflow speed, calculates the predicted average vote (PMV) value and statistically analyzes the percentage of time when the thermal comfort standard (PMV between -0.5 and +0.5) is met. Photovoltaic power generation simulation combines the installation angle of the photovoltaic panels, the radiation of the tilted surface, and system efficiency to calculate the total annual power generation.

[0034] Of particular importance, the following is included before step S1:

[0035] Collect architectural characteristic parameters of the target stadium, including building orientation, roof type, usage function, and climate zone.

[0036] In the embodiments of this invention, please refer to Fig. 3Before establishing any skylight optimization model, the target gymnasium needs to be digitized by laser scanning and BIM model linkage to obtain four architectural characteristic parameters of building orientation, roof form, use function and climate zone; the building orientation is recorded as 0° south, 360° clockwise, the roof form is coded as four types of double slope, single slope, dome and flat roof, the use function is divided into four enumerated values of competition, training, performance and comprehensive, and the climate zone directly quotes the thermal zoning number of GB 50178-93 standard.

[0037] In an implementation manner of the embodiment of the application, it is assumed that the target gymnasium is located in a certain place in the northern hemisphere, the BIM model shows that the building orientation is 15° east of south, the roof is a double slope structure, the main use function is competition, and the climate zone belongs to a cold region (zoning number 2); after on-site measurement and cross verification of drawings, the generated characteristic vector is [15, 1, 0, 2], wherein the 1 in the second position represents the double slope roof code.

[0038] Based on the architectural characteristic parameters, a building type characteristic library is established, and the target gymnasium is matched with typical building types in the characteristic library;

[0039] In the embodiment of the application, the as-built drawings and operation data of 300 completed gymnasiums at home and abroad are collected and cleaned in advance on the cloud server, the K-means++ algorithm is used for clustering of the 8-bit characteristic vector, 12 typical architectural prototypes are obtained, the centroid vector, sample quantity and skylight design parameter statistical value of each prototype are saved, and a building type characteristic library is formed; when the target gymnasium characteristic vector is uploaded, the Euclidean distance between the target gymnasium characteristic vector and the 12 centroids is calculated, and a type with the smallest distance and less than a set threshold value 0.15 is selected as the matching result.

[0040] In an implementation manner of the embodiment of the application, the Euclidean distance between the target gymnasium characteristic vector [15, 1, 0, 2] and the centroid [18, 1, 0, 2] of the 7th prototype is 3, which is lower than the threshold value 0.15 (the distance after Z-score normalization), so it is classified into the 7th type; the 7th type includes 32 similar double slope roof competition gymnasiums, the average value of the historical skylight and roof area ratio is 8.5%, the average value of the skylight quantity is 24, the average value of the length-width ratio is 1.6, and the average value of the skylight change rate is 1.

[0041] According to the matching result, the initial value range of the skylight design parameter is adjusted to form a skylight design parameter benchmark range suitable for a specific building type;

[0042] In the embodiment of the application, after the matching is completed, the parameter quartile value saved by the 7th type prototype is called to automatically generate the initial value interval of the skylight design parameter by using the mean value ± 0.5 times the standard deviation strategy: the area ratio range is 6%-11%, the skylight number range is 18-30, the length-width ratio range is 1.2-2.0, and the change rate range is 0.6-1.2; the interval is narrowed by 42% compared with the industry general specification, which not only ensures that the initial solution of the genetic algorithm falls in the high potential area, but also avoids non-feasible solutions caused by blind search.

[0043] In an implementation manner of the embodiment of the application, if the project party proposes special requirements of the Winter Olympics event hall, the system allows secondary manual correction on the locked interval: the lower limit of the area ratio is increased by 1% and the upper limit is reduced by 1% in the XML to reserve a larger continuous roof area for arranging BIPV; the new interval after correction is 7%-10%, and the remaining parameters remain unchanged, the version is marked as 7-Winter subclass and stored in the feature library to realize knowledge self-accumulation.

[0044] Based on the building type feature library, a skylight design parameter recommendation value table of different types of gymnasiums is established to provide an initial parameter setting basis for step S1.

[0045] In the embodiment of the application, based on the statistical results of the 12 types of prototypes, a skylight design parameter recommendation value table of the gymnasium is automatically generated, and the table structure includes 10 columns of building type ID, typical orientation, roof form, use function, climate zone, recommended area ratio, recommended number, recommended length-width ratio, recommended change rate and confidence.

[0046] In an implementation manner of the embodiment of the application, the designer inputs the project number BJ-2025-01 in the front-end interface, the background retrieves SQLite to obtain the 7th type record, and returns the recommended values: area ratio 8.5%, number 24, length-width ratio 1.6, change rate 1.0, and confidence 92%; the interface synchronously displays the three-dimensional effect diagram of the same case, and the designer confirms the values by one key, which are automatically filled into the initial population individuals of step S1.

[0047] Preferably, step S3 comprises:

[0048] The generator of the preset generative adversarial network extracts features from the building performance simulation data, wherein the generator adopts a U-Net architecture and includes a preset number of down-sampling layers and a preset number of up-sampling layers.

[0049] In the embodiment of the application, a generative adversarial network is selected as a data enhancement engine, a generator of which adopts a U-Net architecture, four levels are respectively arranged in a down-sampling layer and an up-sampling layer, each level of down-sampling is multiplied by a channel number and halved in spatial size through 3*3 convolution + BN + Leaky ReLU, until the size of a latent vector is compressed to 8*8*512; a corresponding up-sampling layer uses a skip connection, after the same level of encoding features and decoding features are spliced in a channel dimension, 3*3 transpose convolution + BN + ReLU is used to gradually restore to the original input size 64*64*3.

[0050] In an implementation manner of the embodiment of the application, the input is a 64*64 pixel three-channel effective daylight utilization-thermal comfort-photovoltaic power generation combined heat map, the batch size is set to 32, the generator is first compressed to 8*8*512 through 4 times of down-sampling, then the latent space is cascaded with a 128-dimensional Gaussian noise, and the spatial resolution is restored through 4 times of up-sampling and a skip connection; in the training stage, an Adam optimizer is used, the learning rate of the generator is , the learning rate of the discriminator is , the loss function is a Wasserstein loss with gradient penalty, and after 200 epochs of training, the SSIM of the generated image is greater than or equal to 0.92, so as to meet the subsequent synthesis requirements.

[0051] The synthetic performance data is generated in the latent space, and the noise vector dimension and the batch size are set in the synthesis process.

[0052] In the embodiment of the application, after the generator completes encoding, a 512*8*8 tensor is flattened into 32768-dimensional latent features, and then the 32768-dimensional latent features are spliced with 128-dimensional random noise to form a 32896-dimensional mixed vector; the vector is mapped back to the decoding entrance of 8*8*256 through two full connections (node number 4096->2048), and a 64*64*3 synthetic performance heat map is output through the up-sampling network, so as to realize end-to-end generation of the latent vector-performance distribution; the noise vector dimension and the batch size are fixed in the configuration file.

[0053] In an implementation manner of the embodiment of the application, the noise vector dimension is set to 128, and the batch size is set to 64; before each training iteration, a 64*128-dimensional noise matrix is sampled from N(0, 1), and then the noise matrix is spliced with 64 pieces of latent features corresponding to the real samples and sent to the decoding network to generate 64 pieces of synthetic performance images; in order to avoid mode collapse, the FID index is used to monitor the distribution offset every 20 epochs, when the FID is greater than 30, the learning rate of the generator is automatically reduced by 10%, until the FID is stably below 25, so as to ensure that the synthetic data and the real data are highly overlapped in distribution.

[0054] The synthetic performance data and the building performance simulation data are merged according to a preset proportion to form an initial expanded data set.

[0055] In the embodiment of the present application, the synthetic data qualified by FID is mixed with the building performance simulation data at a ratio of 3:7 to form an initial expanded data set; the same normalization is performed on the two types of data before merging, i.e., the minimum value is 0 and the maximum value is 1, to prevent model bias caused by scale difference; and the total amount of the data set after merging is expanded to 1.43 times of the original real sample.

[0056] In one implementation manner of the embodiment of the present application, if the original real sample is 1000, 429 synthetic data verified by FID are selected to splice, to obtain 1429 initial expanded sets; SQLite records the source label of each sample (0=real, 1=synthetic), and the prediction error of the real and synthetic subsets is respectively counted in subsequent cross-validation, to ensure that the synthetic data does not introduce significant deviation, and if the prediction error is greater than 5%, the GAN is triggered for retraining.

[0057] The Jensen-Shannon divergence of the synthetic performance data and the building performance simulation data is calculated, and when the Jensen-Shannon divergence exceeds a preset divergence threshold, the corresponding synthetic data sample is removed, so as to determine the expanded performance data set.

[0058] In the embodiment of the present application, for each synthetic sample in the initial expanded data set, the Jensen-Shannon divergence (JSD) between the synthetic sample and the real sample set is calculated: the histogram distribution is estimated by flattening the 64x64x3 vector, the number of buckets is 512, and then the JSD value of the real distribution P and the synthetic distribution Q is calculated; if the JSD of a single synthetic sample is greater than 0.025, it is determined that the distribution drift is too large and is automatically removed; the loop is filtered until the average JSD of the remaining synthetic samples is less than or equal to 0.020, so as to lock the final expanded performance data set.

[0059] In one implementation manner of the embodiment of the present application, multi-thread parallel computing JSD is enabled, and each thread processes 50 synthetic samples; in this round, 87 high-diversity samples are removed, and the remaining 342 synthetic data and 1000 real data jointly constitute an expanded performance data set of 1342, the average JSD of which is reduced to 0.018, and the determination coefficient of the subsequent random forest training is 0.91 is improved to 0.94, and the verification screening mechanism is effective.

[0060] Preferably, the regression analysis in step S4 includes:

[0061] Based on the expanded performance data set, a random forest algorithm is used to establish a mapping relationship between the design parameters of the window and the preset performance indicators, the number of decision trees is set to H, the maximum tree depth is set to F, and the determination coefficient and the root mean square error are calculated as evaluation indexes, wherein the value range of H is 50 to 200, and the value range of F is 5 to 15;

[0062] In this embodiment of the invention, the 1342 extended performance datasets obtained in step S3 are divided into training and testing sets in an 8:2 ratio. The input variables are 4-dimensional skylight design parameters (area ratio, number, aspect ratio, and rate of change), and the output variables are 3-dimensional performance indicators (effective solar utilization rate, thermal comfort percentage, and photovoltaic power generation). A multi-output regression model is constructed using scikit-learn's RandomForest Regressor to predict the three-dimensional indicators.

[0063] In one implementation of this invention, the number of decision trees is set to H=150, the maximum depth F=12, the minimum number of leaf node samples=5, the maximum number of features=sqrt(4)=2, and bootstrap sampling is used; after training, the model's coefficient of determination on the training set is... =0.94, test set =0.91, Root Mean Square Error (RMSE) = (2.1%, 1.8%, 0.05 kWh / All meet the preset accuracy threshold. ≥0.90 and RMSE≤ (3%, 3%, 0.1kWh / Therefore, the mapping relationship is deemed to meet the standard and is locked as the prediction relationship for subsequent optimization.

[0064] When the coefficient of determination reaches or exceeds the preset accuracy threshold and the root mean square error is lower than the preset error threshold, the mapping relationship is considered to meet the preset requirements.

[0065] Select the mapping relationship that meets the preset requirements as the prediction relationship.

[0066] In this embodiment of the invention, the training set is further divided into 5 parts, and 4 parts are used for training and 1 part for validation in turn, recording the results of each fold. With RMSE; only when 50% average ≥0.90 and average RMSE ≤ (3%, 3%, 0.1kWh / Only when the condition is met is the model deemed robust; otherwise, H and F are automatically adjusted using a grid search, with H step size of 25 and F step size of 2, until the condition is met.

[0067] In one implementation of this invention, the initial combination H=100 and F=8 is a 5-fold average. =0.88 was not met, so grid search was automatically initiated; after 3 rounds of iteration, when H=150 and F=12, the 50% average was achieved. It rose to 0.905, and the average RMSE decreased to (2.3%, 2.0%, 0.048kWh / If the dual threshold requirements are met, the search stops; this set of hyperparameters is written to config.json as the sole predictive relation model for subsequent multi-objective optimization stages.

[0068] Preferably, the multi-objective optimization method in step S5 comprises:

[0069] a multi-objective optimization problem is constructed based on the prediction relationship, wherein the optimization objectives include maximizing the effective daylight utilization, maximizing the percentage of thermal comfort, and maximizing the photovoltaic power generation;

[0070] In the embodiment of the present application, the random forest surrogate model obtained in step S4 is used as a fast evaluator to construct a three-objective optimization problem of maximizing the effective daylight utilization, maximizing the percentage of thermal comfort, and maximizing the photovoltaic power generation; the decision variables follow the 4-dimensional window design parameters, and boundary constraints (area ratio 6%-11%, number 18-30, length-width ratio 1.2-2.0, and change rate 0.6-1.2) are applied to the input layer of the surrogate model to ensure that the individuals generated by the genetic algorithm fall within the physically feasible domain.

[0071] In one implementation manner of the embodiment of the present application, the three objectives are written in vector form , and the negative sign indicates that maximizing is converted into minimizing fitness; the NSGA-III framework of the pymoo library is called, real number coding is performed on the decision variables , and the surrogate model is called once to return three-dimensional target values, and the time consumption of a single evaluation is about 2 ms, which is more than 4000 times faster than the traditional Energy Plus call, making it possible to iterate a large population.

[0072] The solving parameters of the multi-objective optimization problem are set, and the solving parameters include the population size, the iteration number, and the number of reference points;

[0073] In the embodiment of the present application, the population size N=120, the iteration number T=150, and the number of reference points are preset according to the problem complexity, and the 3-dimensional combination of p=12 is set according to the Das-Dennis rule, a total of C(12+3-1, 3-1)=91 reference points are generated, and the reference points are uniformly distributed on the unit hyperplane ; each reference point corresponds to a preferred direction to guide the algorithm to form a uniform grid in the target space.

[0074] In one implementation manner of the embodiment of the present application, if it is monitored during running that the front distribution is too sparse, the system can dynamically insert additional reference points: when the minimum neighborhood distance is greater than 1.5 times the average distance, one reference point is added at the center of the neighborhood, and the total number does not exceed 150.

[0075] The non-dominated sorting genetic algorithm based on reference point distribution is used to solve the multi-objective optimization problem;

[0076] In the embodiment of the present application, the algorithm flow follows the standard NSGA-III: first, the initial parent is generated by simulating binary crossover (SBX, =30) and polynomial mutation ( =20) to obtain offspring , merge After performing non-dominated sorting, the next generation is selected according to the reference point association and niche count. The whole process is replaced by a proxy model instead of real simulation.

[0077] In an implementation manner of the embodiment of the application, the crossover probability =0.9, the mutation probability =1 / 4=0.25, and rebound repair is performed on the genes exceeding the boundary after mutation, that is, if the area ratio is greater than 11%, 11%-(x-11%) is taken, so that the search space is continuous; after 150 generations of evolution, 87 of the 91 reference points are occupied by at least one individual, and the occupation rate is 95.6%, indicating that the algorithm successfully drives the population to cover all the preferred directions.

[0078] In the solving optimization process, a preset reference point adjustment mechanism is introduced, and the position and number of the reference points are dynamically adjusted according to the distribution density of the solution set in the target space.

[0079] In the embodiment of the application, the reference point health degree is checked once every 30 generations: the number of individuals associated with each reference point is counted, if the association number of a reference point is zero for two generations in succession, it is determined that the reference point deviates from the front, and then the reference point is moved by a distance of 5% in the direction of the centroid of the target space, and is normalized to the unit hyperplane again.

[0080] In an implementation manner of the embodiment of the application, at the 90th generation, it is found that reference points 17 and 42 have no associated individuals, after the system performs migration, at the 91st generation, three new individuals fall into the neighborhood of 17, and the association is successful; before and after migration, the front hyper-volume (HV) index increases from 0.847 to 0.851.

[0081] The distribution uniformity and convergence index of the intermediate solution set of the solving optimization process are calculated, and when the distribution uniformity and convergence index are both lower than the preset standard, the optimization strategy is automatically adjusted.

[0082] In the embodiment of the application, IGD (Inverted Generational Distance) and Spacing double indexes are selected as process monitoring: the indexes are calculated once every 10 generations, if IGD>0.015 and Spacing>0.020, it is considered that the uniformity and convergence are both lower than the preset standard, and the system automatically activates the intensive search mode: the crossover distribution index η is reduced from 30 to 15 within the next 20 generations, the search range is improved, and the algorithm is prompted to jump out of the local.

[0083] In one implementation manner of the embodiment of the application, in the 100th generation, IGD=0.018 and Spacing=0.023 are measured, and the reinforcement mode is triggered; the system automatically reduces η and introduces a large mutation probability of 0.4, and in the 120th generation, IGD is reduced to 0.012 and Spacing is reduced to 0.018, which meets the double thresholds, so that the normal parameters are restored; in this case, the feedback closed loop ensures that the entire evolution process is always in a high-quality exploration state.

[0084] After a preset number of iterations of optimization, a first Pareto optimal solution set containing a preset number of non-dominated solutions is output, wherein each solution in the first Pareto optimal solution set represents a sunroof design scheme and a corresponding performance index value.

[0085] In the embodiment of the application, when the iteration count reaches 150 generations and the HV increment of two consecutive generations is less than 0.1%, the evolution is terminated, the individuals most adjacent to the 91 reference points are screened from the last generation of non-dominated layer Level 0, and a first Pareto optimal solution set containing 87 non-dominated solutions is formed; each solution corresponds to a set of sunroof parameters (area ratio, number, length-width ratio, and change rate) and three-objective performance values predicted by the proxy model.

[0086] Preferably, step S6 comprises:

[0087] Step S61: Extract the sunroof and roof area ratio, the number of sunroofs, the length-width ratio of the sunroof, and the change rate of the sunroof from the first Pareto optimal solution set respectively, and calculate the mean value, the standard deviation, and the quantile to obtain the distribution characteristics of each sunroof design parameter;

[0088] In the embodiment of the application, the sunroof design variables are analyzed from the 87 non-dominated solutions obtained in step S5, and four one-dimensional arrays of area ratio, number, length-width ratio, and change rate are established respectively; the mean value , the standard deviation , and the [10%, 25%, 50%, 75%, 90%] quantile of each set of data are calculated by using Numpy to form a five-number summary table for describing the actual distribution form of each parameter on the Pareto frontier.

[0089] In one implementation manner of the embodiment of the application, the statistical area ratio array mean value is 8.7%, the standard deviation is 1.2%, the 50% quantile is 8.5%, and the 75% quantile is 9.6%; the number array mean value is 24.3, the standard deviation is 2.1; the length-width ratio mean value is 1.58, the standard deviation is 0.18; the change rate mean value is 17.8°, and the standard deviation is 1.4°; all the coefficients of variation are less than 0.15, indicating that the parameter distribution in the frontier solution set is concentrated, and the preferred interval can be selected based on ± range.

[0090] Step S62: Determine the preferred interval of each sunroof design parameter based on the distribution characteristics.

[0091] In the embodiment of the present application, the initial selection interval is [ - , + ], and the intersection of the initial selection interval and the 10%-90% quantile interval is obtained to ensure that the preferred interval covers the statistical main body and the extreme good solution; if the lower limit of the intersection is lower than the initial boundary of step S1, the boundary value is taken as a hard constraint, and finally the preferred interval with an area ratio of 7.5%-10.0%, a number of 22-27, a length-width ratio of 1.4-1.8, and a change rate of 0.9-1.1 is obtained.

[0092] In an implementation manner of the embodiment of the present application, if a certain parameter - is less than the initial lower limit, 25% quantile is used instead: for example, the length-width ratio - =1.40, which is higher than the boundary 1.2, and remains unchanged.

[0093] Step S63: The preferred interval is modified according to the preset engineering actual constraint to determine the modified preferred interval, and the modification factors include the structural safety constraint and the construction feasibility constraint.

[0094] In the embodiment of the present application, the structural safety and the construction feasibility are quantified as calculable constraints:

[0095] 1) Structural safety: area ratio ≤10% to ensure that the roof continuous purlin span is ≤4.2m;

[0096] 2) Construction feasibility: single window width ≤1.8m and weight ≤200kg, so that the single window area should not be >2.5 when the number is ≥22, and the upper limit of the length-width ratio is 1.8; only when both conditions are met, the modified preferred interval can be entered, otherwise the boundary is clipped.

[0097] In an implementation manner of the embodiment of the present application, the original preferred area ratio upper limit 10.0% is equal to the structural limit value, and remains unchanged; the upper limit of the number 27 corresponds to the average area of a single window 2.4 , which meets the hoisting requirements after rechecking; the length-width ratio 1.8 is 1.68m×3.02m after window type library comparison, and the weight 190kg is less than 200kg, which is qualified.

[0098] Step S64: The parameter range is adjusted based on the modified preferred interval to obtain the optimal skylight design parameter range.

[0099] In the embodiment of the present application, the modified interval is packaged into an optimal parameter range table, which includes the field {variable, lower limit, upper limit, unit, source}.

[0100] Preferably, the step S5 is followed by a step of calculating a performance balance factor:

[0101] Based on the first set of Pareto optimal solutions, the change rate ratio values between the effective daylight utilization rate, the percentage of thermal comfort and the photovoltaic power generation capacity are calculated two by two;

[0102] The change rate ratio values are calculated by the performance index difference ratio of adjacent solutions on the Pareto frontier;

[0103] The geometric mean of the three change rate ratio values is defined as the performance balance factor.

[0104] In the embodiment of the application, for the 87 non-dominated solutions obtained in step S5, the adjacent solution change rate ratio values on two targets are calculated in turn after the target space is normalized and the Pareto frontier is sorted: , , Wherein is the difference value of adjacent solutions in the ith dimension target; the geometric mean of the three ratio values obtained for each pair of adjacent solutions is taken as the local balance factor of the edge, and the global performance balance factor is finally obtained by averaging the entire frontier .

[0105] In one implementation manner of the embodiment of the application, taking the sorted solutions 21 and 22 as an example, the normalized target difference is =0.018, =0.012, =0.009, then =1.50, =1.33, =0.75, and the geometric mean ; after traversing all 86 edges, the global =1.23, The closer to 1 indicates that the frontier trade-off is more balanced.

[0106] Preferably, the application of the performance balance factor after step S6 includes:

[0107] Based on the performance balance factor, the influence degree of the skylight-to-roof area ratio, the number of skylights, the skylight length-width ratio and the skylight change rate on the performance balance factor is calculated respectively, wherein the influence degree is quantified by a sensitivity analysis method;

[0108] In the embodiment of the application, the global performance balance factor is taken as the response value, and Sobol sensitivity analysis based on variance decomposition is performed on the 4-dimensional skylight design parameters: N=1024 groups of samples are generated by using Saltelli sampling within the optimal parameter range locked in step S6, and a random forest proxy model is called to quickly calculate the corresponding , and then the first-order and total-order sensitivity indexes are estimated.

[0109] In an implementation manner of the embodiment of the application, the calculation result shows that the area ratio is 0.72, the number is 0.18, the length-width ratio is 0.06, and the change rate is 0.9; the influence threshold is set to 0.15, so that the area ratio and the number are determined as the key skylight design parameters, and subsequent simplification optimization is only performed around the two dimensions, and the decision space can be reduced from 4 dimensions to 2 dimensions.

[0110] When the influence degree of a certain skylight design parameter on the performance balance factor exceeds the preset influence threshold, the skylight design parameter is defined as a key skylight design parameter;

[0111] A simplified optimization model is established based on the key skylight design parameters;

[0112] In the embodiment of the application, the screened key parameters (the area ratio and the number) are used as new decision vectors, the length-width ratio and the change rate are fixed at the median values 1.6 and 1.0 in the optimal interval in step S6, and a simplified surrogate model is constructed: the random forest is retrained, only 2 dimensions are input, and the number of trees is reduced to 100 to further speed up; the optimization target is still set to maximize 、 、 , but the constraint is degenerated from a 4-dimensional hyper-rectangular body to a 2-dimensional plane, so that the time consumption of a single evaluation is reduced from 2 ms to 0.3 ms.

[0113] A preset number of solutions are randomly selected from the first Pareto optimal solution set as an initial scheme set;

[0114] In the embodiment of the application, 20 solutions are randomly selected from the 87 schemes in the first Pareto optimal solution set as the initial scheme set, and a fixed random seed is used in the selection process to ensure reproducibility; only the key parameter values are retained after the selection, and the length-width ratio and the change rate dimensions are removed, so as to form a 20x2 initial matrix, which is used for subsequent rapid re-optimization and screening in a 2-dimensional space.

[0115] The skylight design schemes in the initial scheme set are rapidly screened through the simplified optimization model, and the scheme evaluation time in the screening process is set to be not more than 10% of the original method evaluation time, and an optimized scheme list after screening is output.

[0116] In the embodiment of the application, the simplified surrogate model is used as an evaluator, and a 2-dimensional greedy local search is performed on the initial scheme set: 8 neighborhood solutions are generated in each generation, and solutions not worse than parent's are selected into the next generation, and the process is terminated if there is no improvement for 5 consecutive generations; the number of calls is limited to ≤200 throughout the process, and the total evaluation time is about 0.06 s, which is only 8.6% of the original 4-dimensional NSGA-III evaluation time (≈0.7 s), and meets the preset requirement of not more than 10%.

[0117] Preferably, after step S5, it further comprises:

[0118] generating a photovoltaic panel arrangement scheme based on the photovoltaic power generation simulation result in the building performance simulation;

[0119] In the embodiment of the present application, after the photovoltaic power generation module of the building performance simulation is completed, the available area of the roof and its radiation distribution are extracted, and the continuous area with irradiation ≥1200 kWh / m2 is defined as the panel arrangement area; the rectangular layout algorithm is used to arrange the photovoltaic panel 1.65m×0.99m as a unit in the panel arrangement area along the roof slope direction, the row spacing is 0.05m, the panel edge distance from the skylight contour is 0.3m, and the initial photovoltaic panel arrangement scheme without overlapping is automatically generated and the center coordinates of each panel are output.

[0120] Based on the skylight design scheme and the photovoltaic panel arrangement scheme, the Euclidean distance from each skylight edge point to the nearest photovoltaic panel center is calculated;

[0121] In the embodiment of the present application, the skylight polygon is uniformly dispersed into a boundary point cloud with a side length of 0.1m, and the three-dimensional Euclidean distance from each boundary point to all photovoltaic panel centers is calculated =‖ - ‖2, and min( ) is taken as the minimum distance of the point; after traversing all the boundary points, the distance array D is formed, and the length is equal to the total number of boundary points.

[0122] In one implementation manner of the embodiment of the present application, the perimeter of a certain skylight contour is 28m, and after dispersion, there are 280 points, and the coordinates of one of the points are (12.4, 7.2, 13.1)m, and the nearest panel center (13.1, 7.8, 13.4)m is calculated, =0.92m; the minimum distance range of all 280 points is 0.31-1.05m, and the average value is 0.62m.

[0123] The reciprocal of the Euclidean distance is taken, and the weighted sum is taken according to the skylight area to obtain the skylight diffusion effect index;

[0124] In the embodiment of the present application, the reciprocal of the array D is taken element by element to obtain the local diffusion coefficient 1 / , and the weighted sum is taken with the skylight area A as the weight to define the skylight diffusion effect index SDE= , the unit ; the larger the SDE is, the more serious the skylight to the photovoltaic array is.

[0125] According to the preset threshold range and the sunroof diffusion effect index, the space conflict severity level is determined.

[0126] In the embodiment of the application, the preset SDE threshold interval is: ≤0.8 is mild, >0.8 and ≤1.4 is moderate, >1.4 is severe; after reading each sunroof SDE, a grade label is automatically assigned, and the pareto solution set metadata is written, so that the designer can quickly identify high conflict schemes without manual comparison.

[0127] According to the space conflict severity level, a hierarchical conflict resolution strategy is formulated.

[0128] In the embodiment of the application, differentiated strategies are formulated for three levels of conflict: mild, maintain the original scheme; moderate, move the photovoltaic panels outside by 0.2m within 0.3m on both sides of the sunroof and restring; severe, first move the panels outside, then reduce the sunroof area by 5%, and update the agent model input simultaneously, reevaluate the performance to ensure that it is still near the pareto frontier after resolution.

[0129] Preferably, after step S6, it further comprises:

[0130] Obtaining the building use mode of the target gymnasium, the building use mode being any one of a competition mode, a training mode and a daily mode;

[0131] In the embodiment of the application, the owner end app sends an electronic questionnaire, the venue operator selects one of the competition / training / daily options, and the system writes the reply into the project table after receiving the reply; if there is no feedback within 3 days, the daily mode is defaulted and a reminder email is sent, ensuring that subsequent threshold adjustments have clear basis.

[0132] In one implementation manner of the embodiment of the application, the target gymnasium is determined to be the 2025 Winter Olympics test venue, the operator selects the competition mode, encodes the label as 2 and stores it in the mode field of SQLite, and triggers the threshold adjustment sub-process to prepare for subsequent regeneration of the pareto frontier.

[0133] Collecting the local climate conditions of the target gymnasium;

[0134] In the embodiment of the application, the Meteonorm API is used to automatically download the hourly typical meteorological year data of the target venue according to the latitude and longitude, and the average outdoor temperature, the scattering radiation ratio and the average wind speed in winter (November-March) are extracted as the cold-high scattering-low wind climate label; the label together with the use mode determines the correction coefficient of the satisfaction threshold.

[0135] Adjust the satisfaction threshold of the effective daylight utilization rate and the thermal comfort percentage according to the local climate conditions, wherein the satisfaction threshold of the competition mode is increased by a preset percentage compared with the daily mode;

[0136] In the embodiment of the application, the preset daily mode reference threshold is: effective daylight utilization rate ≥ 60%, thermal comfort percentage ≥ 70%; the competition mode is increased by 10% on the basis of the reference, that is, ≥ 66% and ≥ 77%; after encoding the reading mode, the threshold is automatically written into the multi-objective optimization constraint layer to replace the original constraint value, so that the front of the re-search moves as a whole in the direction of high lighting and high comfort.

[0137] Regenerate the second Pareto optimal solution set based on the adjusted satisfaction threshold.

[0138] In the embodiment of the application, NSGA-III is called with the same population size N = 120 and the number of generations T = 150, but the constraint boundary is replaced by the adjusted threshold, and the proxy model remains unchanged; after evolution, the second Pareto optimal solution set is output, wherein all solutions meet the higher lighting and comfort requirements of the competition mode + local climate, so that the owner can select the preferred skylight-photovoltaic scheme during the event period.

[0139] Preferably, after step S6, it further comprises:

[0140] The Latin hypercube sampling method is used to generate N verification schemes within the optimal skylight design parameter range, wherein N is an integer between 50 and 200;

[0141] In the embodiment of the application, the Latin Hypercube method of scipy-stats is used to generate N = 100 verification schemes within the optimal skylight parameter range (area ratio 7.5%-10.0%, number 22-27, length-width ratio 1.4-1.8, change rate 0.9-1.1); before sampling, the 4-dimensional variables are normalized to [0, 1], and after sampling, the boundary is linearly inverse transformed to ensure that each dimension only appears once in the 100 equal interval, and a uniform and well space-filling verification data set is obtained.

[0142] In one implementation manner of the embodiment of the application, the random seed is set to 42, the generation time is 0.8s, and a 100x4 array is output; the first sample is decoded as an area ratio of 7.6%, a number of 23, a length-width ratio of 1.45, and a change rate of 1.06, and the last sample is decoded as an area ratio of 9.8%, a number of 26, a length-width ratio of 1.76, and a change rate of 1.08, which covers the range and boundary, without out-of-bound phenomenon, and can be directly sent to building performance simulation.

[0143] Calculate the effective daylight utilization rate, the thermal comfort percentage and the photovoltaic power generation capacity of each verification scheme through building performance simulation;

[0144] In the embodiment of the present application, the above-mentioned 100 schemes are simulated in batches through the Rhino / GH+Energy Plus automatic process: the indoor illumination, PMV and photovoltaic power generation for 8760 hours per year are output each time, and the effective daylight utilization rate, the percentage of thermal comfort and the annual power generation are obtained after post-processing.

[0145] The standard deviation and the coefficient of variation of the effective daylight utilization rate, the percentage of thermal comfort and the photovoltaic power generation of each verification scheme are calculated respectively;

[0146] In the embodiment of the present application, the sample standard deviation of the three performance indicators of the 100 groups is calculated respectively and the coefficient of variation CV= / ; wherein is the average of each indicator, and CV is dimensionless and can be compared horizontally in the fluctuation amplitude; the CV threshold values of daylight, comfort and power generation are set to be less than or equal to 5%, 6% and 4% respectively as the high robustness criterion, and if all the three meet the criterion, the scheme is marked as a high robustness scheme, otherwise it is listed as a common scheme.

[0147] The high robustness scheme in the N verification schemes is determined according to the standard deviation and the coefficient of variation;

[0148] In the embodiment of the present application, the CV normalized scores are weighted and summed: Score=0.4×CV_daylight+0.4×CV_comfort+0.2×CV_power generation, and the lower the score, the higher the robustness; the top 30% (i.e. 30) schemes are taken as the high robustness schemes.

[0149] Based on the high robustness scheme, the optimal shading design parameter range is divided into a core recommended area and an extended applicable area.

[0150] In the embodiment of the present application, the minimum-maximum envelope of the 4-dimensional parameters of the high robustness scheme is taken to form the core recommended area; and the envelope of the remaining 70 common schemes is subtracted from the core area to obtain the extended applicable area.

[0151] Especially important is that after step S6, it further includes:

[0152] Based on the monitoring performance data collected in the actual building operation process, the actual effective daylight utilization rate, the actual percentage of thermal comfort and the actual photovoltaic power generation are calculated;

[0153] In the embodiment of the present application, the BAS system continuously collects the illumination, indoor temperature and photovoltaic direct current metering signals from the first year after the roof is put into operation: the illumination is recorded by 16 roof light sensors every minute, and the daily average value is taken; the thermal comfort is calculated according to ISO 7730 to obtain PMV, and the integral point output is obtained; the photovoltaic power generation is uploaded through the RS485 inverter to obtain the daily power generation.

[0154] The monitoring performance data is compared with the expected performance index corresponding to the optimal range of shading design parameters, and a performance deviation index is calculated.

[0155] In the embodiment of the application, the normalized deviation is defined as , wherein is the expected value, is the actual and expected difference; the preset deviation threshold is = 5%, if > it is determined that the model drifts, and the agent model needs to be retrained and the optimal parameter range is updated.

[0156] In one implementation manner of the embodiment of the application, the above-mentioned monitoring data from January 2026 to July 2026 = 4.2%, which does not exceed the threshold; but by July 2026, the dust accumulation and the shadow of the newly built tower around the building cause to rise to 5.8%, which exceeds the threshold, and the system automatically starts the recalibration process and calls steps S4-S6 for online updating.

[0157] When the performance deviation index exceeds the preset deviation threshold, steps S4 to S6 are re-executed based on the monitoring performance data, and the optimal shading design parameter range is updated;

[0158] In the embodiment of the application, the 12-month monitoring data is added to the original expanded performance data set as a new real sample to form an enhanced training set; the GAN-RF-NSGA process is kept unchanged, the agent model is re-established, and a new Pareto front is evolved, and finally the corrected optimal shading parameter range is output.

[0159] A parameter range optimization record database is established to store key parameters and performance indexes of the previous parameter range optimization process.

[0160] In the embodiment of the application, the range_update.db is established, and the table structure includes {version ID, update time, trigger reason, old range JSON, new range JSON, old , new , value}; each time the re-optimization is completed, a record is written.

[0161] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, the scope of the application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the application file are intended to be included in the application.

[0162] The foregoing is considered as illustrative only of the principles of the application. Numerous modifications and changes will readily occur to those skilled in the art, and it is intended to embrace all such modifications and changes that fall within the scope of the application. Accordingly, the application is not to be restricted in scope to the specific embodiments disclosed herein but is to be accorded the full scope that the principles and novel features request appropriately granted.

Claims

1. A method for coordinated optimization design of wind and solar energy in stadiums based on a fusion algorithm of GAN and RF-NSGA, characterized in that, Includes the following steps: Step S1: Determine the skylight design parameters, including the skylight-to-roof area ratio, the number of skylights, the skylight length-to-width ratio, and the skylight variation rate; Step S2: Based on the skylight design parameters, obtain building performance simulation data through building performance simulation. The building performance simulation data includes effective solar utilization rate, thermal comfort percentage, and photovoltaic power generation. Step S3: Perform generative data augmentation on the building performance simulation data to generate an expanded performance dataset; Step S4: Based on the extended performance dataset, establish the predictive relationship between skylight design parameters and effective solar utilization rate, thermal comfort percentage and photovoltaic power generation through regression analysis; Step S5: Based on the predicted relationship, the effective solar utilization rate, thermal comfort percentage and photovoltaic power generation are synergistically optimized using a multi-objective optimization method to generate the first Pareto optimal solution set; Step S6: Determine the optimal range of sunroof design parameters based on the first Pareto optimal solution set.

2. The method for coordinated optimization design of wind and solar energy in stadiums based on the integrated algorithm of GAN and RF-NSGA as described in claim 1, characterized in that, Step S3 includes: Feature extraction is performed on building performance simulation data using a pre-defined generative adversarial network generator, which adopts a U-Net architecture and includes a pre-defined number of downsampling layers and a pre-defined number of upsampling layers. Generate synthetic performance data in the latent space, and set the noise vector dimension and batch size during the synthesis process; The synthetic performance data and the building performance simulation data are merged according to a preset ratio to form an initial expanded dataset; The Jensen-Shannon divergence between the synthetic performance data and the building performance simulation data is calculated. When the Jensen-Shannon divergence exceeds a preset divergence threshold, the corresponding synthetic data sample is removed, thereby determining the expanded performance dataset.

3. The method for coordinated optimization design of wind and solar energy in stadiums based on the integrated algorithm of GAN and RF-NSGA as described in claim 1, characterized in that, The regression analysis in step S4 includes: Based on the extended performance dataset, the random forest algorithm is used to establish the mapping relationship between the window design parameters and the preset performance indicators. The number of decision trees is set to H, the maximum tree depth is F, and the coefficient of determination and root mean square error are calculated as evaluation indicators. The value of H ranges from 50 to 200, and the value of F ranges from 5 to 15. When the coefficient of determination reaches or exceeds the preset accuracy threshold and the root mean square error is lower than the preset error threshold, the mapping relationship is considered to meet the preset requirements. Select the mapping relationship that meets the preset requirements as the prediction relationship.

4. The method for coordinated optimization design of wind and solar energy in a stadium based on the integrated algorithm of GAN and RF-NSGA as described in claim 1, characterized in that, The multi-objective optimization methods in step S5 include: A multi-objective optimization problem is constructed based on the predictive relationship, where the optimization objectives include maximizing the effective solar utilization rate, maximizing the thermal comfort percentage, and maximizing photovoltaic power generation. Set the solution parameters for the multi-objective optimization problem. The solution parameters include population size, number of iterations, and number of reference points. A non-dominated sorting genetic algorithm based on the distribution of reference points is used to solve the multi-objective optimization problem. In the optimization process of solving the problem, a preset reference point adjustment mechanism is introduced to dynamically adjust the position and number of reference points according to the distribution density of the solution set in the target space. The algorithm calculates the uniformity of distribution and convergence index of intermediate solution set during the optimization process. When both the uniformity of distribution and convergence index are lower than the preset standard, the optimization strategy is automatically adjusted. After a preset number of iterations, the output is a first Pareto optimal solution set containing a preset number of non-dominated solutions, where each solution in the first Pareto optimal solution set represents a sunroof design scheme and its corresponding performance index value.

5. The method for coordinated optimization design of wind and solar energy in a stadium based on the integrated algorithm of GAN and RF-NSGA as described in claim 1, characterized in that, Step S6 includes: Step S61: Extract the ratio of skylight to roof area, number of skylights, length-to-width ratio of skylights, and skylight change rate from the first Pareto optimal solution set, and calculate their mean, standard deviation, and quantiles to obtain the distribution characteristics of each skylight design parameter; Step S62: Determine the optimal range of design parameters for each skylight based on distribution characteristics; Step S63: Modify the preferred range according to the preset actual constraints of the project, and determine the modified preferred range. The modification factors include structural safety constraints and construction feasibility constraints. Step S64: Adjust the parameter range based on the modified preferred range to obtain the optimal sunroof design parameter range.

6. The method for coordinated optimization design of wind and solar energy in a stadium based on the integrated algorithm of GAN and RF-NSGA as described in claim 1, characterized in that, Step S5 is followed by a step to calculate the performance balance factor: Based on the first Pareto optimal solution set, calculate the ratio of the rate of change between each pair of effective solar utilization, thermal comfort percentage, and photovoltaic power generation; The ratio of the rate of change is calculated by the ratio of the performance index differences between adjacent solutions on the Pareto front; The geometric mean of the ratios of the three rates of change is defined as the performance balance factor.

7. The method for coordinated optimization design of wind and solar energy in stadiums based on the integrated algorithm of GAN and RF-NSGA as described in claim 1, characterized in that, The application of the performance balance factor after step S6 includes: Based on the performance balance factor, the influence of the ratio of skylight to roof area, the number of skylights, the length-to-width ratio of skylights, and the rate of change of skylights on the performance balance factor were calculated, and the degree of influence was quantified by the sensitivity analysis method. When the influence of a certain sunroof design parameter on the performance balance factor exceeds the preset influence threshold, it is defined as a key sunroof design parameter. A simplified optimization model was established based on key sunroof design parameters; A predetermined number of solutions are randomly selected from the first Pareto optimal solution set as the initial solution set; The simplified optimization model is used to quickly screen the skylight design schemes in the initial scheme set. During the screening process, the scheme evaluation time is set to not exceed 10% of the evaluation time of the original method, and a list of the preferred schemes after screening is output.

8. The method for coordinated optimization design of wind and solar energy in a stadium based on the integrated algorithm of GAN and RF-NSGA as described in claim 1, characterized in that, The process after step S5 also includes: A photovoltaic panel layout scheme is generated based on the photovoltaic power generation simulation results in building performance simulation. Based on the skylight design scheme and photovoltaic panel layout scheme, calculate the Euclidean distance from each skylight edge point to the nearest photovoltaic panel center; The reciprocal of the Euclidean distance is taken, and the sum is weighted according to the skylight area to obtain the skylight diffusion effect index; The severity level of spatial conflict is determined based on the preset threshold range and the skylight diffusion effect index. Develop tiered conflict resolution strategies based on the severity of spatial conflicts.

9. The method for coordinated optimization design of wind and solar energy in stadiums based on the integrated algorithm of GAN and RF-NSGA as described in claim 1, characterized in that, The process after step S6 also includes: Obtain the building usage mode of the target stadium. The building usage mode can be any one of the following: competition mode, training mode, and daily mode. Collect data on the climate conditions of the target stadium's location; The satisfaction thresholds for effective sunlight utilization and thermal comfort percentage are adjusted according to local climate conditions, with the satisfaction threshold for competition mode being increased by a preset percentage compared to daily mode. The second Pareto optimal solution set is regenerated based on the adjusted satisfaction threshold.

10. The method for coordinated optimization design of wind and solar energy in a stadium based on the integrated algorithm of GAN and RF-NSGA as described in claim 1, characterized in that, The process after step S6 also includes: Within the optimal sunroof design parameter range, N verification schemes are generated using the Latin hypercube sampling method, where N is an integer between 50 and 200; The effective solar utilization rate, thermal comfort percentage, and photovoltaic power generation of each verification scheme were calculated through building performance simulation. Calculate the standard deviation and coefficient of variation of the effective solar utilization rate, thermal comfort percentage, and photovoltaic power generation for each verification scheme; The most robust scheme among N validation schemes is determined based on the standard deviation and coefficient of variation; Based on a highly robust approach, the optimal sunroof design parameter range is divided into a core recommended area and an extended applicable area.

Images