Intelligent decision support method and device for existing building additional photovoltaic system design

Abstract

The invention relates to the technical field of building photovoltaic, in particular to an intelligent decision support method and device for existing building additional photovoltaic system design, and the method comprises the steps: considering the complex decision features and demands of an existing building additional photovoltaic system, so as to construct a design decision element framework; constructing an existing building additional photovoltaic system design intelligent decision support model supporting multi-decision variable-multi-target simulation optimization under multi-condition attribute constraints; and based on the design decision element framework and the intelligent decision support model, obtaining, extracting, converting and integrating multi-source heterogeneous decision information data of the target existing building so as to carry out multi-target optimization, iterative evaluation and multi-criterion evaluation on the photovoltaic system design of the target building to obtain a final design scheme. Therefore, the complex semi-structured decision problem that the existing building additional photovoltaic system not only relates to multi-condition attribute constraints and multi-decision variables, but also relates to a multi-target system of technology, economy, environment and the like is difficult to effectively solve in related design.

Description

Technical Field

[0001] The present invention relates to the technical field of building photovoltaics, and particularly relates to an intelligent decision support method and device for the design of an additional photovoltaic system for existing buildings. Background Art

[0002] The decision-making information presented in the design of an additional photovoltaic system for existing buildings is characterized by rich sources, diverse types, and complex structures. The current research on the collection of decision-making information often shows fragmented and selective characteristics, and fails to comprehensively and systematically sort out and integrate all decision-making elements. Some may focus on the analysis of spatial data such as three-dimensional building modeling, while ignoring the importance of unstructured data such as policy documents and design standards; or only focus on quantitative data such as building area and solar radiation intensity, while ignoring the comprehensive impact of qualitative factors such as building structure and the surrounding environment of the building. It is difficult to comprehensively capture the complexity and diversity of the design of an additional photovoltaic system for existing buildings, which may lead to limitations and insufficient practicality of the design scheme.

[0003] Facing the three core elements of decision variables, decision-making objectives, and constraints in the design decision of an additional photovoltaic system for existing buildings, many current studies often fail to fully clarify the intricate relationships and logical mapping expressions among them, ignoring the depth and breadth of the mutual influence among the elements. Specifically, although it is recognized that the solar radiation level in a given area, as a key constraint condition, has a direct impact on decision variables such as the selection of photovoltaic module materials and the determination of installed capacity, most studies have not delved deeply into how this condition further indirectly affects decision-making objectives such as system economic benefits, power generation, and emission reduction effects through complex physical mechanisms and economic models. At the same time, the interaction between decision variables, such as the combined effect of the distance between photovoltaic modules and the installation inclination on power generation efficiency, is also often simplified or ignored.

[0004] Therefore, it is necessary to comprehensively and systematically sort out decision-making elements, clarify the complex relationships among decision-making elements, conduct scientific and accurate relationship mapping and expression among decision-making elements, and build a systematic decision-making element framework for the design of an additional photovoltaic system for existing buildings.

[0005] Current research on decision support for the design of an additional photovoltaic system for existing buildings mostly relies on single technical means such as light simulation and building information models, or uses existing photovoltaic system simulation software to directly evaluate the layout, performance, and safety of the photovoltaic system, that is, abstracting it into simple mathematical optimization or engineering design problems, and over-simplifying the problems. However, it often only focuses on the performance of the system itself, while ignoring multi-dimensional information such as its interaction with the existing building structure, system integration complexity, and economy. Therefore, it is necessary to systematically analyze the decision-making mechanism process, deeply explore the characteristics of the decision-making process and the scientific attributes of multi-objective semi-structured for the design of the photovoltaic system, and deepen and expand the decision-making theory for the application of photovoltaics in existing buildings.

[0006] The scenario complexity of the attached photovoltaic system for existing buildings is reflected in the diversity of building structures, the regional differences in climate conditions, the individualization of decision-makers' needs, etc. However, the existing research has a relatively weak understanding of the scenario complexity of the design decision-making of the attached photovoltaic system for existing buildings, ignoring the above factors, resulting in the difficulty of the decision-making design scheme to adapt to the changing decision-making scenarios and limited decision-making support. In addition, the existing decision-making support models for building attached photovoltaic systems often ignore the influence of key dynamic factors such as the performance degradation of photovoltaic modules and future climate change, and there are obvious gaps in the long-term performance evaluation of the system. There is a lack of a comprehensive evaluation framework that can predict long-term power generation efficiency, economic feasibility, and environmental benefits. Therefore, it is necessary to build an intelligent decision-making support model for the design of photovoltaic systems that can effectively respond to the diversity of decision-making scenarios from the perspective of a long time scale, providing data support and theoretical basis for the comprehensive design and scientific decision-making of the attached photovoltaic system for existing buildings. Summary of the Invention

[0007] The present invention provides an intelligent decision-making support method and device for the design of an attached photovoltaic system for existing buildings to solve the complex semi-structured decision-making problem in related designs that it is difficult to effectively solve the attached photovoltaic system for existing buildings, which involves multi-condition attribute constraints, multi-decision variables, and multi-objective systems such as technology, economy, and environment.

[0008] The first aspect embodiment of the present invention provides an intelligent decision-making support method for the design of an attached photovoltaic system for existing buildings, including the following steps:

[0009] Construct a decision-making element framework for the design of an attached photovoltaic system for existing buildings;

[0010] Construct an intelligent decision-making support model for the design of an attached photovoltaic system for existing buildings;

[0011] Based on the decision-making element framework for the design of the attached photovoltaic system for existing buildings and the intelligent decision-making support model for the design of the attached photovoltaic system for existing buildings, obtain, extract, transform, and integrate multi-source heterogeneous decision-making information data of the target existing building to perform multi-objective simulation optimization, iterative evaluation, and multi-criteria evaluation on the design of the attached photovoltaic system of the target existing building to obtain the final design scheme of the attached photovoltaic system.

[0012] Optionally, the construction of the decision-making element framework for the design of the attached photovoltaic system for existing buildings includes:

[0013] Obtain and analyze the historical design cases, literature research, and standard specifications of the attached photovoltaic system for existing buildings to obtain a set of decision variables;

[0014] Obtain and sort out the literature research and policy guidance of the attached photovoltaic system for existing buildings to obtain decision-making objectives, where the decision-making objectives include economic benefit indicators, energy revenue indicators, and carbon reduction potential indicators;

[0015] Obtain building structure information, surrounding environment information, climate change data, decision-maker preferences, and the standard specifications as decision-making constraints;

[0016] Construct the design decision-making element framework of the attached photovoltaic system for existing buildings according to the decision variable set, the decision-making objectives, and the decision-making constraints.

[0017] Optionally, the intelligent decision-making support model for the design of the attached photovoltaic system for existing buildings includes a decision information data input sub-model, a photovoltaic system performance simulation sub-model, a multi-objective optimization sub-model, and a multi-criterion scheme evaluation and ranking sub-model.

[0018] Optionally, based on the design decision-making element framework of the attached photovoltaic system for existing buildings and the intelligent decision-making support model for the design of the attached photovoltaic system for existing buildings, obtain, extract, transform, and integrate multi-source heterogeneous decision information data of the target existing building to perform multi-objective simulation optimization, iterative evaluation, and multi-criterion evaluation on the design of the attached photovoltaic system for the target existing building to obtain the final attached photovoltaic system design scheme, including:

[0019] Based on the design decision-making element framework of the attached photovoltaic system for existing buildings, obtain the multi-source heterogeneous decision information data of the target existing building, and input the multi-source heterogeneous decision information data into the decision information data input sub-model for extraction, transformation, and collation to obtain decision-making elements;

[0020] Input the decision-making elements into the multi-objective optimization sub-model to randomly generate multiple initial design schemes;

[0021] Transmit the multiple initial design schemes to the photovoltaic system performance simulation sub-model to generate decision-making objective simulation results of the economic benefits, energy revenue, and carbon reduction potential of the multiple initial design schemes;

[0022] Feed back the decision-making objective simulation results to the multi-objective optimization sub-model to perform multi-objective optimization using the multi-objective optimization intelligent algorithm to obtain the offspring design scheme, and iterate the above photovoltaic system performance simulation and multi-objective optimization process until the preset number of iterations is reached to obtain the Pareto optimal design scheme solution set;

[0023] Input the Pareto optimal design scheme solution set into the multi-criterion scheme evaluation and ranking sub-model to obtain the final attached photovoltaic system design scheme of the target existing building.

[0024] Optionally, inputting the multi-source heterogeneous decision information data into the decision information data input sub-model for extraction, transformation, and collation to obtain decision elements, including:

[0025] Based on the existing building additional photovoltaic system design decision element framework, identifying the multi-source heterogeneous decision information data to classify the multi-source heterogeneous decision information data into the decision variable set, the decision objective, and the decision constraints to obtain the decision elements. Among them, information extraction and structured transformation are required for the unstructured source data in the decision variable set, the decision objective, and the decision constraints to obtain operable structured data.

[0026] Optionally, transmitting the multiple initial design schemes to the photovoltaic system performance simulation sub-model to generate decision objective simulation results of the economic benefits, energy benefits, and carbon reduction potential of the multiple initial design schemes, including:

[0027] Using the multiple initial design schemes for irradiance simulation to evaluate the irradiance and surface shadow conditions of the target existing building skin;

[0028] Simulating the life cycle power generation according to the irradiance and surface shadow conditions of the target existing building skin, and taking the life cycle power generation as the energy benefit index;

[0029] Simulating the initial investment cost and internal rate of return according to the multiple initial design schemes and the life cycle power generation, and taking the initial investment cost and the internal rate of return as the economic benefit indexes;

[0030] Simulating the carbon payback period according to the multiple initial design schemes and the life cycle power generation, and taking the carbon payback period as the carbon reduction potential index;

[0031] Taking the life cycle power generation, the internal rate of return, and the carbon payback period as the decision objective simulation results.

[0032] Optionally, feeding back the decision objective simulation results to the multi-objective optimization sub-model to perform multi-objective optimization using a multi-objective optimization intelligent algorithm to obtain offspring design schemes, including:

[0033] Feeding back the decision objective simulation results to the multi-objective optimization sub-model to perform non-dominated sorting on the multiple initial design schemes to obtain a non-dominated sorting result;

[0034] Selecting the schemes with the top sorting levels and large crowding degrees in the same level from the non-dominated sorting results to obtain multiple initial design schemes after screening;

[0035] Perform crossover and mutation operations on the multiple initial design schemes after screening to obtain the offspring design schemes.

[0036] Optionally, inputting the Pareto optimal design scheme solution set into the multi-criteria scheme evaluation and ranking sub-model to obtain the final additional photovoltaic system design scheme of the target existing building includes:

[0037] Normalize the simulation results of the decision-making objectives of economic benefits, energy benefits, and carbon reduction potential for each alternative design scheme in the Pareto optimal design scheme solution set to obtain each alternative design scheme after normalizing the decision-making objectives;

[0038] Determine the positive ideal solution and the negative ideal solution according to the normalized alternative design schemes;

[0039] Calculate the Euclidean distances between the normalized alternative design schemes and the positive ideal solution and the negative ideal solution;

[0040] Combined with the weight distribution of the decision-making objectives by the decision maker, calculate the relative closeness of the normalized alternative design schemes to the positive ideal solution as the evaluation score;

[0041] Arrange the normalized alternative design schemes in descending order according to the evaluation score to obtain the descending result;

[0042] Select the first design scheme in the descending result as the final additional photovoltaic system design scheme of the target existing building.

[0043] An embodiment of the second aspect of the present invention provides an intelligent decision-making support device for the design of an additional photovoltaic system for an existing building, including:

[0044] The first construction module is used to construct a decision-making element framework for the design of an additional photovoltaic system for an existing building;

[0045] The second construction module is used to construct an intelligent decision-making support model for the design of an additional photovoltaic system for an existing building;

[0046] The simulation and optimization module is used to obtain, extract, transform, and integrate multi-source heterogeneous decision information data of the target existing building based on the decision-making element framework for the design of an additional photovoltaic system for an existing building and the intelligent decision-making support model for the design of an additional photovoltaic system for an existing building, so as to perform multi-objective simulation optimization, iterative evaluation, and multi-criteria evaluation on the design of the additional photovoltaic system for the target existing building to obtain the final additional photovoltaic system design scheme.

[0047] In a third aspect embodiment of the present invention, an electronic device is provided, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the intelligent decision support method for the design of the additional photovoltaic system for existing buildings as described in the above embodiments.

[0048] In a fourth aspect embodiment of the present invention, a computer program product is provided, and when the computer program / instructions are executed by a processor, the intelligent decision support method for the design of the additional photovoltaic system for existing buildings as described above is implemented.

[0049] In a fifth aspect embodiment of the present invention, a computer-readable storage medium is provided, and the computer-readable storage medium stores a computer program, and when the program is executed by a processor, the intelligent decision support method for the design of the additional photovoltaic system for existing buildings as described above is implemented.

[0050] The intelligent decision support method and device for the design of the additional photovoltaic system for existing buildings proposed in the embodiments of the present invention consider the complex decision-making characteristics and requirements of the additional photovoltaic system for existing buildings, comprehensively and systematically sort out multi-source heterogeneous decision-making elements, clarify the complex correlation relationships and logical mapping expressions among them, and construct a design decision-making element framework including three elements: decision variables, constraint conditions, and decision-making objectives, providing a framework support for systematic data collection and integration in the research of intelligent decision support model methods; comprehensively applying multi-objective optimization intelligent algorithms and multi-criterion evaluation and ranking methods, constructing an intelligent decision support method for the design of the additional photovoltaic system for existing buildings that can support the simulation and optimization of multiple decision variables under a multi-dimensional target system, providing support conditions for photovoltaic design decisions considering economic feasibility, energy supply and demand, emission reduction potential, etc. for the photovoltaic system; carrying out an example application research of the decision support model, and verifying to a large extent the scientific rationality of the intelligent decision support model method for the additional photovoltaic system for existing buildings from three dimensions: the effectiveness of the decision result, the adaptability of the decision scenario, and the long-term performance evaluation of the decision plan.

[0051] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The above and / or additional aspects and advantages of the present invention will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, where:

[0053] Figure 1 is a flowchart of an intelligent decision support method for the design of an additional photovoltaic system for existing buildings provided by an embodiment of the present invention;

[0054] Figure 2 is an execution schematic diagram of an intelligent decision support method for the design of an additional photovoltaic system for existing buildings provided by an embodiment of the present invention;

[0055] Figure 3 Schematic diagram of the design decision element framework for the attached photovoltaic system of existing buildings provided by the embodiments of the present invention;

[0056] Figure 4 Schematic diagram of the intelligent decision-making support model for the design of the attached photovoltaic system of existing buildings provided by the embodiments of the present invention;

[0057] Figure 5 Schematic diagram of the multi-objective optimization intelligent algorithm provided by the embodiments of the present invention;

[0058] Figure 6 Schematic diagram of the multi-criterion scheme evaluation and ranking provided by the embodiments of the present invention;

[0059] Figure 7 Schematic diagram of the block diagram of an intelligent decision-making support device for the design of the attached photovoltaic system of existing buildings provided by the embodiments of the present invention;

[0060] Figure 8 Schematic diagram of the structure of the electronic device provided by the embodiments of the present invention. Detailed implementation manners

[0061] The embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, in which the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present invention, but should not be construed as limiting the present invention.

[0062] The intelligent decision-making support method and device for the design of the attached photovoltaic system of existing buildings according to the embodiments of the present invention will be described below with reference to the accompanying drawings.

[0063] Figure 1 Schematic diagram of the flow of an intelligent decision-making support method for the design of the attached photovoltaic system of existing buildings provided by the embodiments of the present invention.

[0064] As Figure 1 shown, the intelligent decision-making support method for the design of the attached photovoltaic system of existing buildings includes the following steps:

[0065] In step S101, a design decision element framework for the attached photovoltaic system of existing buildings is constructed.

[0066] In some embodiments, historical design cases, literature research, and standards and specifications of the attached photovoltaic system of existing buildings are obtained and analyzed to obtain a decision variable set;

[0067] Obtain and sort out the literature research and policy guidance of the attached photovoltaic system for existing buildings to obtain decision-making objectives, where the decision-making objectives include economic benefit indicators, energy revenue indicators, and carbon reduction potential indicators;

[0068] Obtain building structure information, surrounding environment information, climate change data, decision-maker preferences, and standards and specifications as decision-making constraints;

[0069] Construct a design decision-making element framework for the attached photovoltaic system of existing buildings based on the decision variable set, decision-making objectives, and decision-making constraints.

[0070] During the actual implementation process, as Figure 2 and 3 shown, the embodiment of the present invention is based on the comprehensive analysis of historical literature cases, policy standards, and expert interviews related to the design of the attached photovoltaic system for existing buildings. The decision variable set is comprehensively determined to include photovoltaic module types, installation angles (installation inclination and azimuth angle), distance between modules, installation quantity, and location, and a decision variable set is established. This set includes the scientific basis for parameter selection, the rigorous determination method of parameter types and their value ranges, and deeply considers the mutual correlation between decision variables. For example, the minimum non-occlusion distance between modules is restricted by the installation inclination angle, and the calculation formula is:

[0071]

[0072] where L represents the length of the inclined plane of the photovoltaic array, θ represents the photovoltaic installation inclination angle, and λ represents the local latitude.

[0073] At the same time, a dynamic update mechanism is added to ensure that the decision variable set can be adjusted according to technological progress, policy changes, and environmental conditions to maintain the adaptability and forefront of the system.

[0074] Furthermore, through literature research and policy standard sorting, a multi-level decision-making objective function including three dimensions of economic benefit, energy revenue, and carbon reduction potential is proposed, and the evaluation indicators of each dimension are further refined to provide guidance for the design decision-making behavior of the attached photovoltaic system for existing buildings under the background of complex multi-objective coordination. Among them, the economic benefit mainly measures the cost-benefit situation of the system, including the initial investment and the internal rate of return of the project. Among them, the calculation formula of the internal rate of return (IRR) of the project is:

[0075]

[0076] where represents the total power generation of the photovoltaic system in the t-th year, represents the electricity price in the t-th year, represents the annual operation and maintenance cost of the i-th type of photovoltaic module, represents the installation quantity of the i-th type of photovoltaic module, and replace i with PV in the decision variable parameter tabler and represents the type of photovoltaic modules on the roof and the k-th facade, C total represents the total initial investment cost of installing the photovoltaic system, T represents the lifespan of the photovoltaic system, and t represents the number of years.

[0077] The energy revenue mainly examines the life-cycle power output of the photovoltaic system. The calculation formula for the power generation of the project during its life cycle is:

[0078]

[0079] Among them, represents the total power generation of the photovoltaic system in the t-th year, and represent the total area of the roof photovoltaic modules and the total area of the facade photovoltaic modules respectively, and represent the power generation per square meter of the roof and facade photovoltaic modules. T represents the lifespan of the photovoltaic system, and t represents the number of years. 2

[0080] Among them, the calculation formula for E PV is:

[0081] E PV =I×η PV ×K

[0082] Among them, I represents the solar radiation amount (W / m 2 ) on each square meter of the photovoltaic module, η PV represents the efficiency of the photovoltaic module, and this efficiency is affected by meteorological conditions. K is the system loss correction coefficient, which takes into account factors such as inverter efficiency, line correction, and attenuation during the long-term operation of the components. The calculation formula for the parameter η PV is:

[0083] η PV =η Panel +(1 + γ×(T panel -T STC ))

[0084] Among them, η Panel represents the panel efficiency under standard conditions, γ represents the typical efficiency response of the monocrystalline silicon solar panel, T STC represents the panel temperature under standard conditions (25 °C), T panel is the panel temperature corrected by temperature, radiation, and wind speed, and its calculation formula is:

[0085] T panel =c 1 +c 2 ×T + c 3 ×I + c 4 ×V​

[0086] Among them, c 1 is 4.3 °C, c 2 is 0.943, T represents the ambient temperature (°C), I represents the solar radiation on the photovoltaic module (Wm -2 ), c 3 is 0.028 °C -1 W 2 ), c 4 is -1.528 °Csm -1 ), V represents the surface wind speed of the component (ms -1 ).

[0087] The carbon emission reduction potential is defined by the evaluation indicators of carbon emission reduction amount and environmental benefits, and its calculation formula is:

[0088]

[0089] Among them, EF grid represents the carbon dioxide emission factor of electricity, represents the total power generation of the photovoltaic system in the t-th year, EM i represents the total carbon emissions in the life cycle of the i-th type of photovoltaic system, represents the installation quantity of the i-th type of photovoltaic module, and t represents the number of years.

[0090] Furthermore, based on design constraints and environmental adaptation requirements, a complete constraint network covering building characteristic data, standards and specifications, and decision-maker preferences is constructed. Among them, the building characteristic data includes structural characteristics, surrounding environment, and future climate prediction data to ensure that the design scheme of the photovoltaic system can meet physical constraints such as building structure load-bearing, surrounding shadow effects, and wind loads while adapting to possible future climate change scenarios. The standards and specifications define the legal boundaries of system design according to current industry regulations, technical standards, and safety codes, ensuring that the system meets policy requirements and is operable. For example, when the building has a flat roof structure, the installation height of the roof photovoltaic module needs to be lower than 1.8 m, and the parametric expression is:

[0091]

[0092] Among them, represents the length of the inclined plane of the roof photovoltaic array, and θ r represents the installation inclination angle of the roof photovoltaic array.

[0093] The decision-maker preferences take into account the needs, financial status, and risk preferences of different users or stakeholders, supporting the optimization of the photovoltaic system design based on meeting personalized needs.

[0094] Finally, systematically clarify the complex relationships among multiple elements in the design of the attached photovoltaic system for existing buildings, construct a complete framework of decision-making elements for the design of the attached photovoltaic system for existing buildings, and clarify the interaction relationships, constraints, and constituent elements among the three major elements (decision variables, decision-making objectives, and decision-making constraint conditions), providing systematic theoretical support and structured guidance for the construction of an intelligent decision-making support model for the attached photovoltaic system for existing buildings.

[0095] In step S102, construct an intelligent decision-making support model for the design of the attached photovoltaic system for existing buildings.

[0096] In some embodiments, the intelligent decision-making support model for the design of the attached photovoltaic system for existing buildings includes a decision information data input sub-model, a photovoltaic system performance simulation sub-model, a multi-objective optimization sub-model, and a multi-criteria scheme evaluation and ranking sub-model.

[0097] During the actual execution process, as Figure 2 and 4 shown, based on the LCA theory and LCC method, use software simulation to establish a photovoltaic system performance simulation sub-model to support the simulation of decision-making objectives for the attached photovoltaic design scheme; construct a multi-objective optimization sub-model based on the genetic algorithm in the multi-objective optimization intelligent algorithm and the multi-objective - multi-variable optimization decision theory to perform multi-objective optimization of the design scheme and obtain the Pareto optimal design scheme solution set; establish a multi-criteria scheme evaluation and ranking sub-model based on the TOPSIS method or the FTOPSIS method to obtain the final attached photovoltaic system design scheme for the target existing building.

[0098] In step S103, based on the decision-making element framework for the design of the attached photovoltaic system for existing buildings and the intelligent decision-making support model for the design of the attached photovoltaic system for existing buildings, obtain, extract, transform, and integrate the multi-source heterogeneous decision information data of the target existing building, so as to perform multi-objective simulation optimization, iterative evaluation, and multi-criteria evaluation on the design of the attached photovoltaic system for the target existing building, and obtain the final attached photovoltaic system design scheme.

[0099] In some embodiments, based on the decision-making element framework for the design of the attached photovoltaic system for existing buildings and the intelligent decision-making support model for the design of the attached photovoltaic system for existing buildings, obtain, extract, transform, and integrate the multi-source heterogeneous decision information data of the target existing building, so as to perform multi-objective simulation optimization, iterative evaluation, and multi-criteria evaluation on the design of the attached photovoltaic system for the target existing building, and obtain the final attached photovoltaic system design scheme, including:

[0100] Based on the decision-making element framework for the design of the attached photovoltaic system for existing buildings, obtain the multi-source heterogeneous decision information data of the target existing building, and input the multi-source heterogeneous decision information data into the decision information data input sub-model for extraction, transformation, and collation to obtain decision-making elements;

[0101] Input decision-making elements into the multi-objective optimization sub-model to randomly generate multiple initial design schemes;

[0102] Transmit multiple initial design schemes to the photovoltaic system performance simulation sub-model to generate simulation results of decision-making objectives such as economic benefits, energy benefits, and carbon reduction potential for multiple initial design schemes;

[0103] Feed back the simulation results of decision-making objectives to the multi-objective optimization sub-model to perform multi-objective optimization using the multi-objective optimization intelligent algorithm to obtain offspring design schemes, and iterate the above photovoltaic system performance simulation and multi-objective optimization processes until the preset number of iterations is reached to obtain the Pareto optimal design scheme solution set;

[0104] Input the Pareto optimal design scheme solution set into the multi-criteria scheme evaluation and ranking sub-model to obtain the final additional photovoltaic system design scheme for the target existing building.

[0105] In some embodiments, input multi-source heterogeneous decision-making information data into the decision-making information data input sub-model for extraction, transformation, and collation to obtain decision-making elements, including:

[0106] Based on the decision-making element framework for the additional photovoltaic system design of existing buildings, identify the multi-source heterogeneous decision-making information data to classify the multi-source heterogeneous decision-making information data into the decision variable set, decision-making objectives, and decision-making constraints to obtain decision-making elements. Among them, information extraction and structured transformation of the unstructured source data in the decision variable set, decision-making objectives, and decision-making constraints are required to obtain operable structured data.

[0107] In some embodiments, transmit multiple initial design schemes to the photovoltaic system performance simulation sub-model to generate simulation results of decision-making objectives such as economic benefits, energy benefits, and carbon reduction potential for multiple initial design schemes, including:

[0108] Use multiple initial design schemes to perform irradiance simulation to evaluate the irradiance situation and surface shadow situation of the target existing building skin;

[0109] Simulate the life cycle power generation based on the irradiance situation and surface shadow situation of the target existing building skin, and use the life cycle power generation as an energy benefit index;

[0110] Simulate the initial investment cost and internal rate of return based on multiple initial design schemes and life cycle power generation, and use the initial investment cost and internal rate of return as economic benefit indexes;

[0111] Simulate the carbon payback period based on multiple initial design schemes and life cycle power generation, and use the carbon payback period as a carbon reduction potential index;

[0112] Life cycle energy production, internal rate of return and carbon payback period are used as decision-making objectives for simulation results.

[0113] In some embodiments, the decision target simulation results are fed back to the multi-objective optimization sub-model to perform multi-objective optimization using a multi-objective optimization intelligent algorithm to obtain a sub-generation design solution, including:

[0114] Feeding the decision-making target simulation results back to the multi-objective optimization sub-model to perform non-dominated sorting on multiple initial design schemes to obtain non-dominated sorting results;

[0115] In the non-dominated sorting results, the schemes with the highest order and the highest degree of congestion in the same order are selected, and multiple initial design schemes are obtained;

[0116] The multiple initial design schemes after screening are subjected to crossover and mutation operations to obtain offspring design schemes.

[0117] In some embodiments, the Pareto optimal design solution set is input into the multi-criteria solution evaluation and ranking sub-model to obtain the final additional photovoltaic system design solution for the target existing building, including:

[0118] Normalize the decision-making target simulation results of the economic benefits, energy benefits, and carbon reduction potential of each alternative design solution in the Pareto optimal design solution set to obtain each alternative design solution after the normalized decision-making target;

[0119] Determine positive ideal solutions and negative ideal solutions according to the normalized alternative design solutions;

[0120] Calculate the normalized Euclidean distances between each alternative design solution and the positive ideal solution and the negative ideal solution;

[0121] Combined with the decision maker's weight allocation to each decision goal, the relative closeness of each normalized alternative design scheme to the positive ideal solution is calculated as the evaluation score;

[0122] Arrange the normalized alternative design solutions in descending order according to the evaluation scores to obtain a descending result;

[0123] The first design scheme is selected in the descending results as the final additional photovoltaic system design scheme for the target existing building.

[0124] In the actual implementation process, Figure 4As shown, based on the design decision-making element framework of the attached photovoltaic system for existing buildings, the multi-source heterogeneous decision-making information data of the target attached photovoltaic system for existing buildings to be obtained is clarified, and the required data is input into the decision-making information data input sub-model in the intelligent decision-making support model for the design of the attached photovoltaic system for existing buildings to preprocess the multi-source heterogeneous decision-making information data, and decision-making elements to support the subsequent operation of the sub-model can be obtained.

[0125] Among them, the specific process of preprocessing is as follows: First, identify and classify multi-source heterogeneous structured data such as photovoltaic products, building body characteristics, building environment parameters, and energy prices, and use data classification technology to reasonably file various types of information into the decision variable set, decision-making objectives, and decision-making constraint conditions to provide a comprehensive information basis for subsequent decision-making. For unstructured data sources of decision-making information data, such as text descriptions or original measurement data, they are converted into operable structured data through information extraction and structured conversion technology to ensure the standardization and processability of the data. At the same time, for future climate data, a refined resolution operation needs to be adopted, and the hourly irradiance data under clear sky conditions is proportionally corrected using the predicted data of future daily average irradiance, and then the future hourly irradiance data is obtained. This process takes into account the impact of climate change, can simulate the irradiance fluctuations in the same future time period, and provides input data support for the performance simulation calculation of the photovoltaic system.

[0126] Furthermore, as Figure 4 and 5 shown, the decision-making elements are input into the multi-objective optimization sub-model. Based on the NSGA-II algorithm in the multi-objective optimization intelligent algorithm, an initial design scheme is randomly generated within the value range of the decision variables. It should be noted that in the initial design scheme, the position of the photovoltaic modules on the building roof is modeled in the form of an array, and on the building facade is modeled through grid processing, and all decision variables are expressed using real number coding. The specific parametric expression form of the multi-objective problem optimized by the algorithm is as follows:

[0127] minimize / maxmize f m (x), m = 1, 2, 3;

[0128] subject to g j (x) ≤ 0, j = 1, 2, … J;

[0129] h k (x) = 0, k = 1, 2, … K;

[0130]

[0131] Among them, f m (x) represents three decision-making objectives of economic benefits, energy benefits, and carbon reduction potential, g j(x) represents inequality constraints, h k (x) represents equality constraints, x represents a vector of decision variables including the type of photovoltaic module, installation angle (tilt angle and azimuth angle), distance between modules, number of installations, and location, x = (x 1 , x 2 … x n ) T , represents the lower bound of the decision variable value, represents the upper bound of the decision variable value.

[0132] Meanwhile, as shown in Figure 4 , the above design scheme is input into the photovoltaic system performance simulation sub-model. Based on the geometric projection-based occlusion shadow simulation method, the surrounding environment data of the building is used to evaluate the possible shadow conditions generated by the building skin under different times and weather conditions. On this basis, based on the LCA theory and LCC method, the simulation results of decision-making objectives such as the plane irradiance of photovoltaic array components, the life-cycle electricity output of the photovoltaic system, the carbon payback period, the internal rate of return of the project, and the initial investment cost in each design scheme under different layouts and configurations (i.e., energy benefit indicators, carbon reduction potential indicators, and economic benefit indicators) are obtained, and the simulation results of the decision-making objectives are fed back into the multi-objective optimization sub-model to assist the multi-objective optimization intelligent algorithm in subsequent selection operations.

[0133] Furthermore, as shown in Figure 4 and 5 , the simulation results of the decision-making objectives are used as the fitness values of each design scheme for evaluation. Based on the non-dominated sorting, the schemes with higher ranking levels and larger crowding degrees in the same level are selected and retained, and the offspring design schemes are obtained through crossover and mutation operations. Then, the design scheme is input into the photovoltaic system performance simulation sub-model to calculate the simulation results of the decision-making objectives.

[0134] Through the data interaction between the photovoltaic system performance simulation sub-model and the multi-objective optimization sub-model, the above-mentioned performance simulation, selection, crossover, and mutation operations are repeatedly executed to iteratively update the design scheme until the preset number of iterations is reached, so that the solution set gradually approaches the Pareto optimal front, and finally a Pareto optimal design scheme solution set containing multiple alternative design schemes that meet the constraint conditions and balance multiple objectives is generated.

[0135] Finally, as shown in Figure 4 and 6As shown, the Pareto optimal design solution set is input into the multi-criteria evaluation and ranking sub-model. Based on the TOPSIS method (Technique for Order Preference by Similarity to an Ideal Solution) in multi-criteria evaluation and ranking, the decision objective values of multiple alternative design solutions in the Pareto solution set are normalized to obtain the normalized Pareto solution set; the positive ideal solution and the negative ideal solution are determined according to the normalized Pareto solution set; the Euclidean distances between each alternative solution in the normalized Pareto solution set and the positive and negative ideal solutions are calculated. Furthermore, in combination with the decision maker's weight assignment for each decision objective, the relative closeness of each normalized alternative design solution to the positive ideal solution is calculated as the evaluation score; the relative closeness of multiple alternative design solutions to the positive ideal solution is ranked in descending order according to the evaluation score to obtain the descending result, and the first design solution in the descending result is selected as the optimal design solution provided by the decision maker (i.e., the final additional photovoltaic system design solution for the target existing building). Among them, the TOPSIS method can also be extended to FTOPSIS (Fuzzy Technique for Order Preference by Similarity to an Ideal Solution) to handle the situation where the decision maker's description of the decision objective weights is relatively fuzzy. Finally, the optimal design solution will be visually outputted.

[0136] Among them, the TOPSIS method can also be extended to FTOPSIS (Fuzzy Technique for Order Preference by Similarity to an Ideal Solution) to handle fuzzy data and uncertainties, especially suitable for the situation where the decision maker's description of the importance of indicators is relatively fuzzy. Finally, the optimal design solution will be visually outputted.

[0137] This step is based on the NSGA-II algorithm in the multi-objective optimization intelligent algorithm to effectively handle multi-objective problems in the potential solution space, ensuring an optimal balance between conflicting objectives. In addition, combining the semi-structured characteristics of the decision-making and the decision maker's preferences, the TOPSIS method (Technique for Order Preference by Similarity to an Ideal Solution) is used to rank the optimal solutions in the Pareto solution set to quantify the decision maker's preference for the balance between objectives and give a design solution that meets the decision maker's needs.

[0138] In addition, the embodiment of the present invention also conducts a functional verification study on the intelligent decision support method for the additional photovoltaic system design of existing buildings, mainly including the verification of the effectiveness of decision results, the verification of the adaptability of decision scenarios, and the long-term performance evaluation of decision solutions.

[0139] The verification of the effectiveness of decision results is based on the installation experience of ordinary photovoltaic projects, the intuitive solution of the designer, and the comparison with the optimal design solution given by the decision support model for the additional photovoltaic system design of existing buildings. Observe the differences in the values of decision variables and the performance of decision objective evaluation indicators to verify the effectiveness and advantages of this model in decision optimization and objective balance.

[0140] Specifically, taking a single target building as an example, the embodiments of the present invention demonstrate the design optimization and evaluation process of the intelligent decision-making support method for the design of the additional photovoltaic system for existing buildings, and conduct quality assessment, comparing the decision-making objective evaluation index values of the output scheme of the model with those of the empirical design scheme of the target building, so as to verify the scientific validity of the intelligent decision-making support model from two aspects: better decision-making results and reasonable scheme design.

[0141] In the building facade design, the results show that the values of each target evaluation index of the facade optimization design scheme are only about 25%-40% of those of the roof design scheme, and the internal rate of return of the project is lower than the investment and construction standard, which conforms to the empirical intuitive judgment.

[0142] In the building roof design, the results show that the evaluation score of the optimal design scheme given by the model is 9% higher than that of the empirical scheme in the multi-criteria evaluation ranking, and the energy benefit evaluation index is 12% higher than that of the empirical scheme. Analyzing the source of the difference, the results show that the intelligent decision-making support model is more accurate than manual in the balance control between the installation tilt angle and the distance between components. The model not only focuses on the optimal solution of a single variable, but comprehensively gives a multi-objective balanced design scheme by weighing the complex relationships between different decision variables.

[0143] The verification of the decision-making scenario adaptability is to introduce key constraint conditions such as the initial investment cost and the maximum electricity demand of the building to simulate various limiting factors in actual applications. At the same time, by adjusting the geographical location of the project, covering different climate conditions, sunshine resources and electricity demands and other variables, the performance of the model in different decision-making scenarios is further investigated. By analyzing the adaptability of the model under changing conditions, its flexibility and robustness in coping with diverse decision-making demands and environmental changes are evaluated, and its optimization ability in dynamic and complex scenarios is revealed.

[0144] Specifically, the embodiments of the present invention conduct the verification of the decision-making scenario adaptability by adding the constraint of the initial investment cost. The results show that compared with the scheme variables obtained without constraint conditions, the number of installed photovoltaic modules is significantly reduced. At the same time, the installation tilt angle and azimuth angle are both concentrated at the optimal values in the project location, the distance between components is larger, and the installation positions are more concentrated at the southwest corner of the building roof. Analyzing the reasons: the cost limits the number of installed photovoltaic modules. In order to increase the power generation, the installation tilt angle and azimuth angle both tend to the optimal independent values. At the same time, increasing the distance between components avoids mutual shading and improves the utilization and conversion of solar irradiance. In addition, the percentage of the northeast corner of the building roof being shaded is the largest, so the area with lower light intensity is avoided for installation.

[0145] In the embodiment of the present invention, the decision-making scenario adaptability verification is carried out by adding the constraint of the maximum electricity demand of the building. The results show that: the life-cycle power generation of most design schemes is concentrated near the maximum electricity demand. Because when the power generation exceeds the electricity demand of the building, the photovoltaic power generation income is only the feed-in subsidy, and the internal rate of return of the project will decrease significantly. The diminishing marginal effect makes the model tend to design reasonable power generation to meet the demand; the selected photovoltaic modules in the optimized scheme tend to be of the type with the same power generation efficiency but smaller area, which is more suitable for the situation with power generation restrictions.

[0146] In the embodiment of the present invention, the decision-making scenario adaptability verification is carried out by adjusting the geographical location of the target building. The results show that: the economic benefits and the evaluation index values of the carbon reduction potential of the design scheme have deteriorated, but the energy benefit index has increased by more than 40%. Analyzing the source of the difference, the results show that: the latitude of the current project location is relatively low, and the solar radiation intensity is greater than that of the original project location. However, the high temperature at the same time leads to a decrease in the power generation efficiency, and generally the installation effect is weaker; but the optimized scheme adjusts the installation inclination according to the low-latitude position, reduces the minimum non-shading distance between the photovoltaic modules, and increases the number of installed photovoltaic panels, resulting in an increase in the life-cycle power generation, indicating that the intelligent decision-making support model has good scenario adaptability and has the ability of dynamic adjustment.

[0147] The long-term performance evaluation of the decision-making scheme is to compare the efficiency and effect of the model to obtain the design decision-making scheme in two scenarios of using future climate change data and using historical climate data, verify the long-term adaptability and operation efficiency of the design scheme under the background of possible climate change, and prove the necessity of incorporating climate change factors into the decision-making process.

[0148] Specifically, in the embodiment of the present invention, under the background of climate change in the next 25 years, the impact of climate fluctuations on the design scheme of the attached photovoltaic system of existing buildings is analyzed to carry out the long-term performance evaluation of the decision-making scheme. The results show that: under the annual electricity demand limit, the Pareto optimal frontier solution considering climate change is 2%-4% better than that without considering climate change in terms of economic benefits and carbon reduction potential, and the design scheme considering climate change is more stable to adapt to the changing climate conditions, resulting in the decision variables being more concentrated in the stable configuration rather than relying on the compensation effect of short-term decision variables. Analyzing the reason for the difference shows that: within the next 25 years, the increase in irradiance caused by climate change will make up for the negative impact of the rising temperature on the photovoltaic power generation efficiency, and overall improve the power generation efficiency of the system. At the same time, the rising irradiance significantly affects the selection tendency of the photovoltaic modules. The small-size photovoltaic module type helps to optimize the layout, reduce the shading effect, and improve the economic efficiency and space utilization efficiency of the system. It shows that incorporating climate change into the photovoltaic design decision-making can achieve a more adaptable long-term solution and improve the energy efficiency and economic return of the photovoltaic system.

[0149] In summary, the intelligent decision-making support method for the design of the attached photovoltaic system for existing buildings proposed according to the embodiments of the present invention has the following beneficial effects:

[0150] (1) Considering the complex decision-making characteristics and requirements of the attached photovoltaic system for existing buildings, comprehensively and systematically sorting out multi-source heterogeneous decision-making elements, clarifying the complex correlation relationships and logical mapping expressions among them, and forming a design decision-making element framework including three elements: decision variables, constraint conditions, and decision-making objectives, providing a framework support for systematic data collection and integration for the research on the intelligent decision-making support model method of the attached photovoltaic system for existing buildings;

[0151] (2) Comprehensively applying multi-objective optimization intelligent algorithms and multi-criterion evaluation and ranking methods, forming an intelligent decision-making support method for the design of the attached photovoltaic system for existing buildings that can support the simulation and optimization of multiple decision variables under a multi-dimensional target system, providing support conditions for the design decision-making of photovoltaic systems considering economic feasibility, energy supply and demand, carbon reduction potential, etc.;

[0152] (3) Conducting an evaluation study on the decision-making support model, in order to verify to a greater extent the scientific rationality of the intelligent decision-making support model method for the attached photovoltaic system for existing buildings from three dimensions: the effectiveness of decision-making results, the adaptability of decision-making scenarios, and the long-term performance evaluation of decision-making schemes.

[0153] Next, an intelligent decision-making support device for the design of the attached photovoltaic system for existing buildings proposed according to the embodiments of the present invention will be described with reference to the accompanying drawings.

[0154] Figure 7 It is a block diagram of the intelligent decision-making support device for the design of the attached photovoltaic system for existing buildings according to the embodiments of the present invention.

[0155] As Figure 7 shown, the intelligent decision-making support device 70 for the design of the attached photovoltaic system for existing buildings includes: a first construction module 701, a second construction module 702, and a simulation and optimization module 703.

[0156] Among them, the construction module 701 is used to construct a design decision-making element framework for the attached photovoltaic system for existing buildings. The simulation module 702 is used to construct an intelligent decision-making support model for the design of the attached photovoltaic system for existing buildings. The optimization module 703 is used to obtain multi-source heterogeneous decision-making information data of the target existing building based on the design decision-making element framework for the attached photovoltaic system for existing buildings and the intelligent decision-making support model for the design of the attached photovoltaic system for existing buildings, and perform multi-objective simulation and optimization on the multi-source heterogeneous decision-making information data to obtain the final attached photovoltaic system design scheme of the target existing building.

[0157] In some embodiments, the first construction module 701 includes:

[0158] An analysis unit that obtains and analyzes historical design cases, literature studies, and standards and specifications of the attached photovoltaic system for existing buildings to obtain a set of decision variables;

[0159] A sorting unit for obtaining and sorting literature studies and policy guidance of the attached photovoltaic system for existing buildings to obtain decision-making objectives, where the decision-making objectives include economic benefit indicators, energy benefit indicators, and carbon reduction potential indicators;

[0160] A determination unit for obtaining building structure information, surrounding environment information, climate change data, decision-maker preferences, and standards and specifications to obtain decision-making constraints;

[0161] A construction unit for constructing a decision-making element framework for the design of the attached photovoltaic system for existing buildings according to the set of decision variables, decision-making objectives, and decision-making constraints.

[0162] In some embodiments, the intelligent decision-making support model for the design of the attached photovoltaic system for existing buildings includes a decision-making information data input sub-model, a photovoltaic system performance simulation sub-model, a multi-objective optimization sub-model, and a multi-criterion scheme evaluation and ranking sub-model.

[0163] In some embodiments, the simulation and optimization module 703 includes:

[0164] A processing unit for obtaining multi-source heterogeneous decision-making information data of the target existing building based on the decision-making element framework for the design of the attached photovoltaic system for existing buildings, and inputting the multi-source heterogeneous decision-making information data into the decision-making information data input sub-model for extraction, transformation, and sorting to obtain decision-making elements;

[0165] A first generation unit for inputting the decision-making elements into the multi-objective optimization sub-model to randomly generate multiple initial design schemes;

[0166] A second generation unit for transmitting the multiple initial design schemes to the photovoltaic system performance simulation sub-model to generate simulation results of decision-making objectives for the economic benefits, energy benefits, and carbon reduction potential of the multiple initial design schemes;

[0167] An iteration unit for feeding back the simulation results of the decision-making objectives to the multi-objective optimization sub-model to perform multi-objective optimization using a multi-objective optimization intelligent algorithm to obtain offspring design schemes, and iterating the above photovoltaic system performance simulation and multi-objective optimization processes until a preset number of iterations is reached to obtain a Pareto optimal design scheme solution set;

[0168] A queuing unit for inputting the Pareto optimal design scheme solution set into the multi-criterion scheme evaluation and ranking sub-model to obtain the final attached photovoltaic system design scheme for the target existing building.

[0169] In some implementations, the processing unit includes:

[0170] Based on the design decision element framework of the attached photovoltaic system for existing buildings, identify multi-source heterogeneous decision information data, so as to classify the multi-source heterogeneous decision information data into the decision variable set, decision objectives, and decision constraints, in order to obtain decision elements. Among them, it is necessary to extract information and perform structured transformation on the unstructured source data in the decision variable set, decision objectives, and decision constraints to obtain operable structured data.

[0171] In some embodiments, the second generation unit includes:

[0172] Use multiple initial design schemes to perform irradiance simulation to evaluate the irradiance situation and surface shadow situation of the target existing building skin;

[0173] Simulate the life cycle power generation based on the irradiance situation and surface shadow situation of the target existing building skin, and use the life cycle power generation as an energy benefit index;

[0174] Simulate the initial investment cost and internal rate of return based on multiple initial design schemes and life cycle power generation, and use the initial investment cost and internal rate of return as economic benefit indicators;

[0175] Simulate the carbon payback period based on multiple initial design schemes and life cycle power generation, and use the carbon payback period as a carbon reduction potential indicator;

[0176] Use the life cycle power generation, internal rate of return, and carbon payback period as the simulation results of decision objectives.

[0177] In some embodiments, the iteration unit includes:

[0178] Feed back the simulation results of the decision objectives to the multi-objective optimization sub-model to perform non-dominated sorting on multiple initial design schemes to obtain non-dominated sorting results;

[0179] Select the schemes with the top sorting levels and large crowding degrees in the same level from the non-dominated sorting results to obtain multiple initial design schemes after screening;

[0180] Perform crossover and mutation operations on the multiple initial design schemes after screening to obtain offspring design schemes.

[0181] In some embodiments, the sorting unit includes:

[0182] Normalize the simulation results of the decision objectives of economic benefits, energy benefits, and carbon reduction potential for each alternative design scheme in the Pareto optimal design solution set to obtain each alternative design scheme after normalizing the decision objectives;

[0183] Determine the positive ideal solution and negative ideal solution according to each alternative design scheme after normalization;

[0184] Calculate the Euclidean distances between each normalized alternative design solution and the positive ideal solution and the negative ideal solution;

[0185] Combined with the weight distribution of each decision-making objective by the decision maker, calculate the relative closeness of each normalized alternative design solution to the positive ideal solution as the evaluation score;

[0186] Arrange each normalized alternative design solution in descending order according to the evaluation score to obtain the descending result;

[0187] Select the first design solution in the descending result as the final additional photovoltaic system design solution for the target existing building.

[0188] It should be noted that the foregoing explanation of the intelligent decision-making support method embodiment for the design of the additional photovoltaic system for existing buildings is also applicable to the intelligent decision-making support device for the design of the additional photovoltaic system for existing buildings in this embodiment, and will not be elaborated here.

[0189] The intelligent decision-making support device for the design of the additional photovoltaic system for existing buildings proposed according to the embodiment of the present invention has the following

[0190] Beneficial effects:

[0191] (1) Considering the complex decision-making characteristics and requirements of the additional photovoltaic system for existing buildings, comprehensively and systematically sorting out multi-source heterogeneous decision-making elements and clarifying the complex correlation relationships and logical mapping expressions among them, forming a design decision-making element framework including three elements: decision variables, constraint conditions, and decision-making objectives, providing a framework support for systematic data collection and integration in the research of intelligent decision-making support model methods for the additional photovoltaic system for existing buildings;

[0192] (2) Comprehensively applying multi-objective optimization intelligent algorithms and multi-criterion evaluation and ranking methods, forming an intelligent decision-making support method for the design of the additional photovoltaic system for existing buildings that can support the simulation and optimization of multiple decision variables under a multi-dimensional target system, providing support conditions for photovoltaic system design decisions considering economic feasibility, energy supply and demand, carbon reduction potential, etc.;

[0193] (3) Conducting an evaluation study on the decision-making support model, aiming to verify to a large extent the scientific rationality of the intelligent decision-making support model method for the additional photovoltaic system for existing buildings from three dimensions: the effectiveness of decision-making results, the adaptability of decision-making scenarios, and the long-term performance evaluation of decision-making solutions.

[0194] Figure 8 It is a schematic structural diagram of the electronic device provided by the embodiment of the present invention. The electronic device may include:

[0195] A memory 801, a processor 802, and a computer program stored on the memory 801 and executable on the processor 802.

[0196] When the processor 802 executes the program, it implements the intelligent decision-making support method for the design of the additional photovoltaic system for existing buildings provided in the above embodiments.

[0197] Furthermore, the electronic device further includes:

[0198] A communication interface 803 for communication between the memory 801 and the processor 802.

[0199] A memory 801 for storing a computer program that can run on the processor 802.

[0200] The memory 801 may include a high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0201] If the memory 801, the processor 802, and the communication interface 803 are implemented independently, the communication interface 803, the memory 801, and the processor 802 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 only a thick line is shown in the figure, but it does not mean that there is only one bus or one type of bus.

[0202] Optionally, in a specific implementation, if the memory 801, the processor 802, and the communication interface 803 are integrated on a chip, the memory 801, the processor 802, and the communication interface 803 can communicate with each other through an internal interface.

[0203] The processor 802 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0204] The embodiments of the present invention also provide a computer program product, and when the computer program / instructions are executed by a processor, they implement the above intelligent decision-making support method for the design of the additional photovoltaic system for existing buildings.

[0205] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the intelligent decision-making support method for the design of the additional photovoltaic system for existing buildings as described above.

[0206] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0207] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0208] Any process or method description in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or N executable instructions for implementing a customized logic function or process. The scope of the preferred embodiments of the present invention includes additional implementations, where the functions may be executed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0209] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part (electronic device) having one or N wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0210] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0211] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0212] In addition, in each embodiment of the present invention, each functional unit can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0213] The above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disc, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. An intelligent decision support method for designing an additional photovoltaic system for an existing building, characterized in that: The following steps are involved: Construct a framework of design decision factors for additional photovoltaic systems on existing buildings; Construct an intelligent decision support model for the design of additional photovoltaic systems for existing buildings; Based on the design decision factor framework of the additional photovoltaic system for existing buildings and the intelligent decision support model for the design of the additional photovoltaic system for existing buildings, the multi-source heterogeneous decision information data of the target existing building is obtained, extracted, transformed and integrated to perform multi-objective simulation optimization, iterative evaluation and multi-criteria evaluation on the design of the additional photovoltaic system for the target existing building, so as to obtain the final design plan of the additional photovoltaic system.

2. The intelligent decision support method for designing an additional photovoltaic system for an existing building according to claim 1, characterized in that: The framework for design decision elements for adding photovoltaic systems to existing buildings includes: Obtain and analyze historical design cases, literature research, and standard specifications for photovoltaic systems attached to existing buildings to obtain a set of decision variables; Obtain and sort out literature research and policy guidance on adding photovoltaic systems to existing buildings to obtain decision-making objectives, where the decision-making objectives include economic benefit indicators, energy income indicators, and carbon reduction potential indicators; Obtain building structure information, surrounding environment information, climate change data, decision maker preferences and the standard specifications as decision constraints; The design decision element framework of the photovoltaic system attached to the existing building is constructed according to the decision variable set, the decision target and the decision constraint condition.

3. The intelligent decision support method for designing an additional photovoltaic system for an existing building according to claim 1, characterized in that: The intelligent decision support model for designing additional photovoltaic systems for existing buildings includes a decision information data input sub-model, a photovoltaic system performance simulation sub-model, a multi-objective optimization sub-model and a multi-criteria scheme evaluation and ranking sub-model.

4. The intelligent decision support method for designing an additional photovoltaic system for an existing building according to claim 3, characterized in that: The method, based on the existing building additional photovoltaic system design decision element framework and the existing building additional photovoltaic system design intelligent decision support model, obtains and extracts, transforms and integrates multi-source heterogeneous decision information data of the target existing building, so as to perform multi-objective simulation optimization, iterative evaluation and multi-criteria evaluation on the additional photovoltaic system design of the target existing building, so as to obtain the final additional photovoltaic system design scheme, including: Based on the existing building additional photovoltaic system design decision factor framework, multi-source heterogeneous decision information data of the target existing building is obtained, and the multi-source heterogeneous decision information data is input into the decision information data input sub-model for extraction, conversion and arrangement to obtain decision factors; Inputting the decision factors into the multi-objective optimization sub-model to randomly generate a plurality of initial design solutions; Transmitting the multiple initial design schemes to the photovoltaic system performance simulation sub-model to generate decision-making target simulation results of economic benefits, energy benefits, and carbon reduction potential of the multiple initial design schemes; Feeding the decision target simulation results back to the multi-objective optimization sub-model, so as to perform multi-objective optimization using a multi-objective optimization intelligent algorithm, obtain a sub-generation design solution, iterate the photovoltaic system performance simulation and multi-objective optimization process, until a preset number of iterations is reached, and obtain a Pareto optimal design solution set; The Pareto optimal design solution set is input into the multi-criteria solution evaluation and ranking sub-model to obtain a final additional photovoltaic system design solution for the target existing building.

5. The intelligent decision support method for designing an additional photovoltaic system for an existing building according to claim 4, characterized in that: The inputting of the multi-source heterogeneous decision information data into the decision information data input sub-model for extraction, conversion and arrangement to obtain decision elements includes: Based on the existing building additional photovoltaic system design decision element framework, the multi-source heterogeneous decision information data is identified to classify the multi-source heterogeneous decision information data into the decision variable set, the decision target and the decision constraint conditions to obtain the decision elements, wherein the unstructured source data in the decision variable set, the decision target and the decision constraint conditions need to be extracted and structured to obtain actionable structured data.

6. The intelligent decision support method for designing an additional photovoltaic system for an existing building according to claim 4, characterized in that: The transmitting the multiple initial design schemes to the photovoltaic system performance simulation sub-model to generate decision-making target simulation results of economic benefits, energy benefits, and carbon reduction potential of the multiple initial design schemes includes: Using the multiple initial design schemes to perform irradiance simulation to evaluate the irradiance and shadow conditions of the surface of the target existing building; The life cycle power generation is simulated according to the surface irradiance and surface shadow conditions of the target existing building, and the life cycle power generation is used as the energy benefit indicator; According to the multiple initial design schemes and the life cycle power generation simulation, an initial investment cost and an internal rate of return are obtained, and the initial investment cost and the internal rate of return are used as the economic benefit indicators; Simulating a carbon payback period based on the multiple initial design solutions and the life cycle power generation, and using the carbon payback period as the carbon reduction potential indicator; The life cycle power generation, the internal rate of return and the carbon payback period are used as the decision target simulation results.

7. The intelligent decision support method for designing an additional photovoltaic system for an existing building according to claim 4, characterized in that: Feeding back the decision target simulation result to the multi-objective optimization sub-model to perform multi-objective optimization using a multi-objective optimization intelligent algorithm to obtain a sub-generation design solution includes: Feeding back the decision target simulation result to the multi-objective optimization sub-model to perform non-dominated sorting on the multiple initial design solutions to obtain a non-dominated sorting result; Screening out solutions with a higher order and a higher degree of congestion in the same order from the non-dominated ordering results, and obtaining a plurality of screened initial design solutions; The multiple initial design solutions after screening are subjected to crossover and mutation operations to obtain the offspring design solution.

8. The intelligent decision support method for designing an additional photovoltaic system for an existing building according to claim 4, characterized in that: The step of inputting the Pareto optimal design solution set into the multi-criteria solution evaluation and ranking sub-model to obtain a final additional photovoltaic system design solution for the target existing building includes: Normalizing the decision-making target simulation results of the economic benefit, energy benefit, and carbon reduction potential of each alternative design solution in the Pareto optimal design solution set to obtain each alternative design solution after the normalized decision-making target; Determining a positive ideal solution and a negative ideal solution according to the normalized alternative design solutions; Calculating the Euclidean distances between the normalized alternative design solutions and the positive ideal solution and the negative ideal solution; Combined with the weight distribution of each decision-making target by the decision maker, the relative closeness between each normalized alternative design scheme and the positive ideal solution is calculated as an evaluation score; Arranging the normalized alternative design solutions in descending order according to the evaluation scores to obtain a descending result; The first design solution is selected from the descending results as the final additional photovoltaic system design solution for the target existing building.

9. An intelligent decision support device for designing an additional photovoltaic system for an existing building, characterized in that: include: The first building block is used to construct a framework of decision-making elements for designing additional photovoltaic systems for existing buildings; The second building block is used to construct an intelligent decision support model for the design of additional photovoltaic systems for existing buildings; The simulation optimization module is used to obtain, extract, transform and integrate multi-source heterogeneous decision information data of the target existing building based on the existing building additional photovoltaic system design decision element framework and the existing building additional photovoltaic system design intelligent decision support model, so as to perform multi-objective simulation optimization, iterative evaluation and multi-criteria evaluation on the additional photovoltaic system design of the target existing building, so as to obtain the final additional photovoltaic system design plan.

10. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent decision support method for designing an additional photovoltaic system for an existing building as described in any one of claims 1 to 8.

11. A computer program product, characterized in that When the computer program / instruction is executed by a processor, the intelligent decision support method for designing an additional photovoltaic system for an existing building as described in any one of claims 1 to 8 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the intelligent decision support method for designing an additional photovoltaic system for an existing building as described in any one of claims 1 to 8.

Images