CN-121980892-A - Multi-objective optimization method for BIPV (building integrated photovoltaic) structure setting

CN121980892ACN 121980892 ACN121980892 ACN 121980892ACN-121980892-A

Abstract

The invention discloses a multi-objective optimization method for BIPV structure setting, which relates to the technical field of building integrated photovoltaics, and aims to solve the BIPV into a plurality of modules and perform attribute coding on each module, so that the calculation of the BIPV in building energy consumption is converted into the calculation of module energy consumption, the energy consumption calculation amount of a complex building is greatly reduced, meanwhile, the energy consumption of the module can be calculated through the geometric features and boundary conditions of the module and is restrained through the structure setting of the building, namely, the overall design of the BIPV can be decomposed into the modules with different attribute codes and the required quantity of each attribute coded module, and the optimal optimization objective in the maximum generating capacity, the minimum building energy consumption and the optimal life cycle cost is determined according to the actual requirement, and then the optimal geometric features, boundary conditions and structure setting proportion are obtained through a multi-objective optimization model.

Inventors

Shen Pengyuan
ZHANG YI

Assignees

清华大学深圳国际研究生院

Dates

Publication Date: 20260505
Application Date: 20250929

Claims (10)

1. A multi-objective optimization method for BIPV construction setup, comprising the steps of: S100, building decomposition, namely decomposing the BIPV into a plurality of modules and carrying out attribute coding on the modules, wherein the attribute coding at least comprises geometric characteristics, boundary conditions and constructional settings; s200, acquiring data, namely acquiring building scheme information and building economic information of the BIPV, and establishing a multi-objective optimization model taking generating capacity, building energy consumption and life cycle cost as optimization objectives; S300, determining a target, wherein the multi-target optimization model determines an optimal optimization target according to actual requirements, and the optimal optimization target is one or more of maximum power generation, minimum building energy consumption and optimal life cycle cost; S400, target optimization, wherein the multi-target optimization model calculates the attribute codes of the modules and the quantity required by each attribute code according to the optimal optimization targets, so that optimal geometric features, boundary conditions and configuration setting proportions are obtained based on the optimal optimization targets in a design stage.
2. The multi-objective optimization method of BIPV construction setup according to claim 1, wherein step S400 comprises the steps of: s401, classifying the modules according to the geometric features, thermal boundary conditions and structural settings of the modules; S402, clustering the modules into clusters through a K-means clustering algorithm, so that the calculation complexity is reduced; S403, performing representative optimization, namely performing multi-objective optimization on the modules included in each cluster, and determining optimal geometric features, boundary conditions and configuration setting proportions; s404, solution propagation, wherein the multi-objective optimization result is applied to the modules in the same cluster.
3. The multi-objective optimization method of BIPV configuration setting according to claim 1, further comprising the steps of: S101, establishing a parameter model, taking the building energy consumption of the BIPV as the sum of the energy consumption of a plurality of modules, and correcting through thermal interaction between the modules so as to establish a function of the building energy consumption and the modules; s102, establishing feature engineering, and typing the attribute codes of the modules into a parameter modeling platform so as to generate feature data readable by a machine learning algorithm; S103, training the model, and training the characteristic data through a machine learning algorithm to realize prediction of building energy consumption.
4. The multi-objective optimization method of BIPV construction set according to claim 1, wherein the geometric features include the surface type and aspect ratio and the window-to-wall ratio of the BIPV.
5. The multi-objective optimization method of BIPV construction set according to claim 1, wherein the boundary conditions include outdoor, ground, heat insulation surface and air wall.
6. The multi-objective optimization method of BIPV construction set-up according to claim 1, wherein the construction set-up comprises wall construction, photovoltaic construction, roof and floor.
7. The multi-objective optimization method of BIPV construction setup according to claim 1, wherein the lifecycle costs include capital costs and operation and maintenance costs; Wherein the capital costs include BIPV assembly costs, system cost balances, installation costs, and material offset savings; the operation and maintenance costs include routine maintenance, component replacement and performance monitoring.
8. The multi-objective optimization method of BIPV structure setup according to claim 1, wherein in step S101, the parametric modeling platform is Grasshopper platform.
9. The multi-objective optimization method of BIPV construction setup according to claim 1, wherein the multi-objective optimization model is based on the strength pareto evolution algorithm 2.
10. The multi-objective optimization method of BIPV structure according to claim 1, wherein the machine learning predictive model is a model trained based on XGBoost algorithm.

Description

Multi-objective optimization method for BIPV (building integrated photovoltaic) structure setting Technical Field The invention relates to the technical field of building integrated photovoltaics, in particular to a multi-objective optimization method for BIPV structure setting. Background The multi-objective nature of BIPV optimization requires simultaneous consideration of power generation maximization, building energy consumption minimization, economic feasibility and building integration constraints. Traditional design methods rely on sequential analysis and the intuition of the designer, often resulting in suboptimal solutions that do not fully exploit the potential of integrated photovoltaic systems. When considering the different module configurations possible in a modular structure, the complexity grows exponentially, wherein the different module types and assembly modes create a unique optimized landscape, requiring a systematic evaluation method. Optimization of modular building BIPV systems presents significant design challenges that are difficult to effectively address by conventional methods. The early design phase is the most critical phase of BIPV optimization, and the basic decisions of the geometric features, boundary conditions and construction setting design of the modules of the modular building BIPV determine the performance potential of the whole building lifecycle. However, the existing design tools lack comprehensive optimization capability, and cannot systematically evaluate complex interactions among photovoltaic power generation, building energy consumption and building life cycle cost, so that optimal geometric features, boundary conditions and configuration setting proportions of modules cannot be obtained based on optimal optimization targets among photovoltaic power generation, building energy consumption and building life cycle cost in the early stage of design. Disclosure of Invention The invention mainly aims to provide a multi-objective optimization method for BIPV (building integrated photovoltaic) structure setting, and aims to solve the technical problems that the prior art cannot systematically evaluate complex interactions among photovoltaic power generation capacity, building energy consumption and building life cycle cost, and optimal geometric characteristics, boundary conditions and structure setting proportion of modules are obtained. The multi-objective optimization method for BIPV construction setting comprises the following steps of S100, building decomposition, decomposing the BIPV into a plurality of modules and carrying out attribute coding on the modules, wherein the attribute coding at least comprises geometric features, boundary conditions and construction setting, S200, data acquisition, construction scheme information and building economic information of the BIPV, and establishment of a multi-objective optimization model taking generating capacity, building energy consumption and life cycle cost as optimization targets, S300, target determination, the multi-objective optimization model determining an optimal optimization target according to actual requirements, wherein the optimal optimization target is one or more of maximum generating capacity, minimum building energy consumption and optimal life cycle cost, S400, target optimization, and the multi-objective optimization model calculates the attribute coding of the modules and the quantity required by each attribute coding according to the optimal optimization target, so that optimal geometric features, boundary conditions and construction setting proportions are obtained based on the optimal optimization target in a design stage. Preferably, the step S400 comprises the steps of classifying the modules according to the geometric features, the thermal boundary conditions and the structural arrangement of the modules, classifying the modules by S401, clustering the modules into clusters through a K-means clustering algorithm to reduce the computational complexity, performing multi-objective optimization on the modules included in each cluster by S403 and representative optimization to determine optimal geometric features, boundary conditions and structural arrangement proportion, and spreading the solutions by S404 and applying the multi-objective optimization results to the modules in the same cluster. Preferably, the method further comprises the steps of S101, establishing a parameter model, taking building energy consumption of BIPV as the sum of energy consumption of a plurality of modules, correcting through thermal interaction among the modules so as to establish a function of the building energy consumption and the modules, S102, establishing a feature engineering, typing attribute codes of the modules into a parameter modeling platform so as to generate feature data readable by a machine learning algorithm, S103, training the model, and training the feature data through the machine learning alg