Multi-objective function optimization method, device and equipment for solar building integrated system and medium

Abstract

The invention discloses a multi-objective function optimization method, device and equipment for a solar building integrated system and a medium, and relates to the technical field of computers.The method comprises the steps that a to-be-optimized parameter set in a multi-objective function is determined, whether the number of optimization times n reaches the maximum number of optimization times N or not is judged, and if n does not reach N, the optimization time n reaches the maximum number of optimization times N; and if the iteration times t reach the maximum iteration times T, judging whether the iteration times t reach the maximum iteration times T, if t does not reach T, generating a solution set of the t-th round based on the local solution of the (t-1)-th round and the coefficient vector of the t-th round, determining the local solution of the t-th round according to a multi-objective function, and if t reaches T, selecting an optimal target solution from the local solutions of the T rounds. And if n reaches N, outputting m optimal target solutions from the T rounds of local solutions, and finally selecting a service demand solution matched with the service demand from the m solutions. The method can solve the problems of low convergence efficiency and easy local optimum in a high-dimensional nonlinear solution space.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a multi-objective function optimization method, device, equipment and medium for a solar building integrated system. Background Art

[0002] Driven by the "dual carbon" goals, low-carbon transformation in the building sector has become a key battleground in the energy revolution. In larger public and commercial buildings, hot water systems account for up to 40% of energy consumption, and air conditioning systems account for 40%-60%.

[0003] Currently, the application of coupled solar and heat pump systems for building water heating primarily focuses on a single optimization objective. This involves optimizing the ratio of solar collector area to heat pump power to reduce operating costs, but this ignores the high carbon emissions of photovoltaic modules and collectors during the production phase. Other studies focus on operational emissions without balancing initial investment costs.

[0004] Single-objective optimization methods will find it difficult to achieve the coordinated minimization of economic costs and carbon emissions of building hot water systems throughout their entire life cycle, while existing multi-objective optimization algorithms have the defects of low convergence efficiency and easy local optimality in high-dimensional nonlinear solution space. Summary of the Invention

[0005] The present application provides a multi-objective function optimization method, device, equipment and medium for a solar building integrated system, which can effectively solve the defects of low convergence efficiency and easy local optimization in high-dimensional nonlinear solution space.

[0006] To achieve the above objectives, this application adopts the following technical solutions: In a first aspect, the present application provides a multi-objective function optimization method for solar building integration, the method comprising: Determining a parameter group to be optimized in a multi-objective function, wherein the parameter group to be optimized includes a heat collection area of ​​a solar thermal collector, an installed capacity of a photovoltaic system, a volume of a hot water storage tank, a heating capacity of an air source heat pump, and an installation inclination angle of photovoltaic and solar thermal collectors; Determine whether the optimization times n has reached the maximum optimization times N, where n is greater than 1 and is an integer; If the optimization times n does not reach the maximum optimization times N, then determine whether the iteration times t has reached the maximum iteration times T, where t is greater than 1 and is an integer; If the number of iterations t does not reach the maximum number of iterations T, then based on the local solution of the t-1th round and the coefficient vector of the tth round, a solution set of the tth round is generated, wherein the solution set includes multiple parameter groups; according to the multi-objective function, a local solution of the tth round is determined from the solution set of the tth round; if the number of iterations reaches the maximum number of iterations T, then the optimal target solution is selected from the local solutions of the tth round; If the optimization times n reaches the maximum optimization times N, then m optimal target solutions are output, where m is less than N, m is greater than 0, and m is an integer; Select the business requirement solution that matches the business requirement from the m optimal target solutions.

[0007] Optionally, the coefficient vector of the t-th round is obtained by: The convergence factor is determined according to the number of iterations t, and the expression is:

[0008] in, is the convergence factor, t is the current number of iterations, T is the maximum number of iterations, and k is the number of power functions; According to the convergence factor, the coefficient vector of the tth round is determined.

[0009] Optionally, determining the coefficient vector of the tth round according to the convergence factor includes: The coefficient vector of round t is determined by the following formula:

[0010] in, is the coefficient vector, is a random vector with values ​​in [0,1].

[0011] Optionally, generating a solution set for round t based on the local solution for round t-1 and the coefficient vector for round t includes: Based on the local solution of the t-1th round and the coefficient vector of the tth round, the solution set of the tth round is generated, and the expression is:

[0012] in, is the local solution vector, is the solution set vector, and D is the positional relationship between the local solution and the optimal solution.

[0013] Optionally, the outputting m optimal target solutions includes: The crowding distance value is determined based on the objective function value adjacent to itself and the maximum and minimum values ​​in the objective function; According to the congestion distance value, m optimal target solutions are selected from N optimal target solutions.

[0014] Optionally, the congestion distance value is determined based on the objective function values ​​of the neighboring nodes and the maximum and minimum values ​​of the objective function, including: The expression of crowding distance is:

[0015] Among them, DC (i) is the congestion distance, is the total number of objective functions, For the The objective function values, For the The objective function values, For the The maximum value among the objective functions, For the The minimum value of the objective function.

[0016] Optionally, the method of selecting m optimal target solutions from N optimal target solutions based on the congestion distance value includes: The congestion distance values ​​of the N optimal target solutions are calculated respectively, and they are arranged in descending order from large to small, so as to screen out the top m optimal target solutions.

[0017] In a second aspect, the present application provides a multi-objective function optimization device for a solar building integrated system, the device comprising: A determination module is used to determine a parameter group to be optimized in a multi-objective function, wherein the parameter group to be optimized includes the heat collection area of ​​the solar collector, the installed capacity of the photovoltaic system, the volume of the hot water storage tank, the heating capacity of the air source heat pump, and the installation inclination angle of the photovoltaic and solar collectors; An optimization module is used to determine whether the number of optimizations n has reached the maximum number of optimizations N, where n is greater than 1 and is an integer; if the number of optimizations n has not reached the maximum number of optimizations N, then determine whether the number of iterations t has reached the maximum number of iterations T, where t is greater than 1 and is an integer; if the number of iterations t has not reached the maximum number of iterations T, then generate a solution set for the tth round based on the local solution of the t-1th round and the coefficient vector of the tth round, where the solution set includes multiple parameter groups; determine the local solution for the tth round from the solution set of the tth round according to a multi-objective function; if the number of iterations has reached the maximum number of iterations T, then select the optimal target solution from the local solutions of the Tth round; if the number of optimizations n has reached the maximum number of optimizations N, then output m optimal target solutions, where m is less than N and greater than 0 and is an integer; The output module is used to select a business requirement solution that matches the business requirement from the m optimal target solutions.

[0018] In a third aspect, the present application provides a computing device, including a memory and a processor; One or more computer programs are stored in the memory, and the one or more computer programs include instructions; when the instructions are executed by the processor, the computing device executes the method as described in any one of the first aspects.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program for executing the method as described in any one of the first aspects.

[0020] It can be seen from the above technical solution that this application has at least the following beneficial effects: In this application, the method achieves systematic and efficient multi-objective optimization by clarifying the set of parameters to be optimized in the multi-objective function (five parameters: the solar collector's collection area, the installed capacity of the photovoltaic system, the volume of the hot water storage tank, the air source heat pump's heating capacity, and the installation inclination angles of the photovoltaic and solar collectors), and combining it with the dual control logic of the number of optimizations and iterations. By dynamically generating a solution set with the help of the coefficient vector and screening the local optimal solution based on the multi-objective function, it can quickly converge in the high-dimensional nonlinear solution space and avoid falling into the local optimum. By setting the maximum number of optimizations and iterations, it is ensured that the algorithm outputs m evenly distributed optimal target solutions within a reasonable computational cost, covering the multi-dimensional trade-offs between economy and low carbon. Finally, a suitable solution is screened out based on business needs (such as cost thresholds and equipment compatibility). Therefore, this method can effectively solve the defects of low convergence efficiency and easy local optimality in the high-dimensional nonlinear solution space.

[0021] It should be understood that the description of technical features, technical solutions, beneficial effects or similar language in this application does not imply that all features and advantages can be realized in any single embodiment. On the contrary, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution or beneficial effect is included in at least one embodiment. Therefore, the description of a technical feature, technical solution or beneficial effect in this specification does not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and beneficial effects described in the present embodiment can also be combined in any appropriate manner. Those skilled in the art will understand that the embodiment can be implemented without one or more specific technical features, technical solutions or beneficial effects of a specific embodiment. In other embodiments, additional technical features and beneficial effects can also be identified in specific embodiments that do not embody all embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of an application scenario provided in an embodiment of the present application; Figure 2 A flowchart of a multi-objective function optimization method for a solar building integrated system provided in an embodiment of the present application; Figure 3 A schematic diagram of a multi-objective function optimization device for a solar building integrated system provided in an embodiment of the present application; Figure 4 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The terms "first", "second" and "third" in this application specification and the accompanying drawings are used to distinguish different objects rather than to limit a specific order.

[0024] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0025] To make the description of the following embodiments clear and concise, a brief introduction to the related technologies is first given: Solar building integration is the integration of solar collectors, photovoltaic modules and other equipment with building structures to achieve the coordinated supply of heat and electricity, and combine building enclosure and energy production functions.

[0026] The full life cycle cost covers the system's investment cost from the initial construction phase and subsequent operating costs. Considering the relatively high initial investment cost, the impact of economic factors such as investment loan interest rates, actual price fluctuations and inflation rates are taken into account when establishing the model.

[0027] The carbon emissions of each stage of the life cycle carbon emission statistics system (production, transportation, operation, and demolition) include the energy consumption of material production, the power consumption of equipment operation, and the environmental impact of recycling and treatment. For example, the carbon emissions of solar collectors need to calculate the production of aluminum alloy frames, glass manufacturing and transportation processes. emission.

[0028] The multi-objective optimization algorithm is an intelligent optimization algorithm based on the cooperation mechanism of gray wolf groups. It solves multi-objective problems (such as the balance between economic costs and carbon emissions) by simulating the "encirclement-pursuit-attack" behavior.

[0029] By integrating photovoltaic modules, solar thermal collectors, and other equipment, building-integrated solar systems (BIBSs) demonstrate significant potential for building energy conservation. However, their practical application is constrained by multiple factors: core system parameters such as collector area, installed PV capacity, and heat storage tank volume do not operate independently but rather interact in complex coupling relationships. For example, while increasing installed PV capacity can reduce long-term electricity costs, initial equipment procurement and installation costs will increase significantly, creating a cyclical conflict between "cost investment" and "return on benefits." Furthermore, the optimization objectives of lifecycle costs and lifecycle carbon emissions compete with each other: expanding the scale of solar thermal collectors can reduce carbon emissions during operation, but carbon emissions generated during the manufacturing process of the aluminum alloy frames and glass materials required for the collectors may partially offset the environmental benefits of operation.

[0030] Furthermore, system performance is highly sensitive to the external environment: Fluctuations in sunlight intensity directly impact the efficiency of photovoltaic panels, while seasonal variations in building hot water demand and cooling loads (such as summer surges in cooling loads) lead to frequent adjustments to equipment operating strategies. Traditional single-objective optimization methods (such as optimizing operating costs or carbon emissions in a single phase) struggle to address these challenges. These challenges collectively limit the engineering effectiveness of building-integrated solar systems, necessitating a multi-objective collaborative optimization approach to overcome these bottlenecks.

[0031] In view of this, an embodiment of the present application provides a multi-objective function optimization method for a solar building integrated system, which can be executed by a processing device. The processing device can be a terminal or a server. Terminals include but are not limited to smartphones, tablets, laptops, personal digital assistants, or smart wearable devices. The server can be a cloud server, such as a central server in a central cloud computing cluster, or an edge server in an edge cloud computing cluster. Of course, the server can also be a server in a local data center. A local data center refers to a data center directly controlled by the user.

[0032] In this method, the whole life cycle cost and the whole life cycle carbon emission are constructed as a dual objective function. The parameters that have a significant impact on the objective function are screened out through the orthogonal test method, and the range of the optimized variable parameters is further narrowed. The screened parameters include the solar collector area S c , installed capacity of photovoltaic system W p , hot water storage tank volume V, air source heat pump heating capacity P kThe interrelationships between the inclination angles E of the photovoltaic and solar collector installations form a multidimensional parameter space, and the impact of each parameter on the objective functions of lifecycle costs and lifecycle carbon emissions is not linear but nonlinear. However, existing multi-objective algorithms suffer from low convergence efficiency and susceptibility to local optimal solutions in high-dimensional nonlinear solution spaces. To address this, the Grey Wolf Optimizer (GWO) algorithm, while capable of searching in high-dimensional spaces, suffers from insufficient convergence accuracy and prone to premature global exploration. Therefore, a nonlinear convergence factor is introduced to improve the algorithm's accuracy. By slowing down the early convergence rate, the algorithm's global exploration of the high-dimensional space is enhanced in the early stages of iteration, avoiding premature local suboptimal solutions. This is followed by accelerated convergence in the later stages, improving accuracy.

[0033] In order to make the technical solution of this application clearer and easier to understand, the application scenarios of the technical solution of this application are introduced below with reference to the accompanying drawings. Figure 1 As shown in the figure, this figure is a schematic diagram of an application scenario provided by an embodiment of the present application.

[0034] This application scenario is a solar building integrated energy supply system, primarily consisting of photovoltaic modules, solar thermal collectors, hot water storage tanks, and air-source heat pumps, deployed on building roofs and surrounding areas. The system achieves coordinated energy management through thermal pathways (hot water supply), electrical pathways (photovoltaic power generation and grid connection), and control signal pathways (weather monitoring and equipment regulation). The photovoltaic modules convert solar energy into electricity, prioritizing the building's electricity needs, with any remaining power connected to the grid. The solar thermal collectors collect heat energy, which is then used in conjunction with hot water storage tanks and air-source heat pumps to meet the hot water load, reducing traditional energy consumption.

[0035] However, while meeting the cooling and heating load requirements of the building, it is necessary to simultaneously optimize the full life cycle costs and full life cycle carbon emissions. The solar collector area S included in the system c , installed capacity of photovoltaic system W p , hot water storage tank volume V, air source heat pump heating capacity P k It is interrelated with the installation inclination angle E parameter of photovoltaic and solar collectors, and its impact on the life cycle cost and life cycle carbon emissions shows a nonlinear characteristic. For example, although increasing photovoltaic capacity can reduce carbon emissions in the operation stage by improving power generation efficiency, the initial equipment procurement and installation costs will increase significantly; expanding the collector area can reduce dependence on heat pumps and thus reduce energy consumption, but the carbon emissions of materials in the collector production stage (such as aluminum alloy frames and glass covers) will increase with the expansion of the area, forming a nonlinear game of "cost-carbon emissions".

[0036] In order to solve the multi-objective optimization problem in high-dimensional nonlinear solution space, by improving the Grey Wolf optimization algorithm and combining it with the TRNSYS simulation model to verify the parameter combination in real time, the optimal solution for life cycle costs and life cycle carbon emissions can be accurately found.

[0037] In order to make the technical solution of this application clearer and easier to understand, the multi-objective function optimization method of a solar building integrated system provided by the embodiment of this application is introduced in combination with the above application scenarios. Figure 2 As shown in the figure, this figure is a flowchart of a multi-objective function parameter optimization method provided in an embodiment of the present application.

[0038] S201. Construct a multi-objective function.

[0039] It should be noted that the multi-objective function refers to the life cycle cost function F1 and the life cycle carbon emission function F2. Optimizing the parameters in these functions lays the foundation for the following steps. After the objective function is constructed, it needs to be normalized to avoid excessive differences in the dimensions and numerical ranges of the objective functions, which may lead to excessive bias in the optimization results.

[0040] S202: Determine the parameter group to be optimized in the multi-objective function The orthogonal test is used to determine the parameter group to be optimized in the multi-objective function. The orthogonal test is an experimental method based on the expansion of the orthogonal table. The experimental method is to select evenly dispersed experimental points within the value range of the influencing factors for testing, so as to achieve a systematic evaluation of the influence of multiple factors with a small number of experiments, and the results are highly comparable. In this application, in view of the complexity of the solar building integrated system, combined with existing research and the working principle of the system, the collection area S of the solar collector is calculated. c , installed capacity of photovoltaic system W p , hot water storage tank volume V, air source heat pump heating capacity P k The five parameters of the installation inclination angle E of photovoltaic and solar thermal collectors are determined as the main influencing factors of the system, and 5 levels are selected for each factor.

[0041] Using L25(5 6 ) Orthogonal table design 25 groups of experiments, each group of experimental parameters are input into TRNSYS model simulation to obtain F1 and F2 data, the range method is used to analyze the order of influence of each parameter on the objective function and analyze the trend. For F1, the importance of factors is ranked as W p >P k >V>S c >E; for , sorted by W p >P k >E>S c> V; The variance analysis method is used to verify the significance of each parameter. The degree of freedom corresponding to the sum of squares of the deviations of each factor is 4, and the error degree of freedom is 4. The critical value F can be obtained by looking up the table. 0.01 (4,4)=15.98, for example, W p F value = 832.33> , F value of V = 43.76> , the F values ​​of all factors are much larger than the critical value, verifying their high significance to the objective function. Finally, the parameter group to be optimized in the multi-objective function is determined, and the parameter group constitutes a solution vector.

[0042] S203: Determine whether the optimization times n has reached the maximum optimization times N.

[0043] If yes, then S208 is executed; if no, then S204 is executed. The program determines whether the number of optimizations n has reached the maximum number of optimizations N, and obtains a first determination result. If the first determination result indicates that the number of optimizations n has reached the maximum number of optimizations N, then S208 is executed; if the first determination result indicates that the number of optimizations n has not reached the maximum number of optimizations N, then S204 is executed.

[0044] S204: Determine whether the number of iterations t has reached the maximum number of iterations T.

[0045] If yes, then execute S207; if no, then execute S205. The program then determines whether the number of iterations t has reached the maximum number of iterations T, obtaining a second determination result. If the second determination result indicates that the number of iterations t has reached the maximum number of iterations T, then execute S207; if the second determination result indicates that the number of iterations n has not reached the maximum number of iterations N, then execute S205.

[0046] S205: Generate a solution set for the tth round based on the local solution of the t-1th round and the coefficient vector of the tth round.

[0047] When the number of iterations is t=1, an initial solution set is generated according to the constraints, substituted into the multi-objective function, and the three best solutions (called α, β, and δ solutions) are calculated and selected.

[0048] Constraints are divided into soft constraints and hard constraints. The initial investment cost threshold, which takes into account the local economic development level and the income level of residents / merchants, is used as a soft constraint. C CB When the cost is higher than the initial investment cost threshold, the cost penalty factor is increased vF .

[0049] Hard constraints are the constraint ranges of the optimization parameters, for example, the solar collector area is 0-278 m 2The installed capacity of the photovoltaic system is 0-56400W, and the parameter range is determined by the building space limitations, equipment performance limits and local climatic conditions.

[0050] Then, an initialization solution set (100 solutions) is generated according to these constraints, and the three optimal solutions, called local solutions, are obtained by calculating the F1 and F2 values ​​constructed by S201.

[0051] When the number of iterations t>1, the coefficient vector of the tth round can be indirectly obtained according to the number of iterations of the tth round, and combined with the local solution of the t-1th round, the solution set of the tth round can be generated.

[0052] The coefficient vector is used to control the range of the search for the optimal solution. It is obtained through the convergence factor, which is related to the number of iterations and is expressed as follows (1-2): (1) (2) in, is the convergence factor, is the coefficient vector, t is the current number of iterations, T is the maximum number of iterations, k is the number of power functions, is a random vector with values ​​in [0,1].

[0053] Therefore, the coefficient vector of the tth round can be indirectly obtained according to the number of iterations of the tth round, and combined with the local solution of the t-1th round, the solution set of the tth round can be generated, and the expression is (3): (3) in, is the local solution vector, is the solution set vector, and D is the positional relationship between the local solution and the optimal solution.

[0054] S206. Determine the local solution of the tth round from the solution set of the tth round according to the multi-objective function.

[0055] The multi-objective functions are F1 and F2 constructed by S201, and the solution set is generated by S205. The values ​​of F1 and F2 in the solution set are calculated respectively, so as to select the three optimal local solutions.

[0056] S207: Select the optimal target solution from the T rounds of local solutions.

[0057] The optimal target solution is the best solution obtained from the local solutions obtained in T rounds of iterations, that is, Select the best solution from the solutions.

[0058] S208 : Select m optimal target solutions from the N optimal target solutions according to the congestion distance.

[0059] The congestion distance value is determined based on the objective function values ​​adjacent to itself and the maximum and minimum values ​​in the objective function; based on the congestion distance value, m optimal objective solutions are screened out from N optimal objective solutions.

[0060] Since the maximum number of optimizations is N, there are N optimal solutions. C (i) The distribution density of solutions is evaluated by calculating the average distance between each solution and its adjacent solutions in the target space. The larger the distance, the sparser the individuals around the solution, the better the diversity, and the solution should be retained first. For example: in the two-dimensional target space of life cycle costs and carbon emissions, if the crowding distance of a solution is large, it indicates that it is unique in the combination of life cycle costs and carbon emissions and is not overly surrounded by neighboring solutions. The crowding distance is used to eliminate solutions in dense areas and retain solutions in sparse areas to ensure the diversification of the optimization method. The calculation expression is:

[0061] in, is the total number of objective functions, For the The objective function values, For the The objective function values, For the The maximum value among the objective functions, For the The minimum value of the objective function.

[0062] Calculate the congestion distance value D of N optimal target solutions respectively C (i) and sort them in descending order from large to small to select the top m optimal target solutions.

[0063] S209: Select a business requirement solution that matches the business requirement from the m optimal target solutions.

[0064] The m optimal target solutions are all technically feasible solutions, but they may not directly meet the personalized needs at the business level. Therefore, the business demand solution is to select a suitable solution from the m solutions based on the needs. For example, the 75 optimal target solutions generated cover different trade-off combinations between life cycle costs and carbon emissions, such as "high photovoltaic capacity (low carbon emissions, high initial investment)" and "low collector area (low initial investment, slightly higher carbon emissions)". There is no absolute distinction between the 75 optimal target solutions, which only reflect the trade-off relationship of the objective function.

[0065] Based on the above description, this application has the following beneficial effects: This method achieves systematic and efficient multi-objective optimization by defining the set of parameters to be optimized within a multi-objective function (the solar collector's heat collection area, the installed capacity of the photovoltaic system, the volume of the hot water storage tank, the heating capacity of the air-source heat pump, and the installation angles of the photovoltaic and solar collectors). This method, combined with a dual control logic of optimization and iteration counts, achieves systematic and efficient multi-objective optimization. By dynamically generating a solution set using coefficient vectors and screening for local optimal solutions based on the multi-objective function, it achieves rapid convergence in high-dimensional nonlinear solution spaces, avoiding local optima. By setting a maximum number of optimizations and iterations, the algorithm ensures that m evenly distributed optimal target solutions are generated within a reasonable computational cost, covering the multi-dimensional trade-offs between economic efficiency and low carbon performance. Ultimately, a suitable solution is selected based on business requirements (such as cost thresholds and device compatibility). Therefore, this method effectively addresses the drawbacks of low convergence efficiency and the susceptibility to local optimality in high-dimensional nonlinear solution spaces.

[0066] Combined with the above Figures 1 to 2 The multi-objective function optimization method of the solar building integrated system provided in the embodiment of the present application is introduced in detail. The devices and equipment provided in the embodiment of the present application will be introduced in conjunction with the accompanying drawings.

[0067] like Figure 3 As shown in FIG, this figure is a schematic diagram of a multi-objective function optimization device for a solar building integrated system provided by an embodiment of the present application, the device comprising: Determination module 301, for determining a parameter group to be optimized in a multi-objective function, wherein the parameter group to be optimized includes the heat collection area of ​​the solar thermal collector, the installed capacity of the photovoltaic system, the volume of the hot water storage tank, the heating capacity of the air source heat pump, and the installation inclination angle of the photovoltaic and solar thermal collectors; The optimization module 302 is configured to determine whether the number of optimizations n has reached a maximum number of optimizations N, where n is greater than 1 and is an integer; if the number of optimizations n has not reached the maximum number of optimizations N, then determine whether the number of iterations t has reached a maximum number of iterations T, where t is greater than 1 and is an integer; if the number of iterations t has not reached the maximum number of iterations T, then generate a solution set for the tth round based on the local solution of the t-1th round and the coefficient vector of the tth round, where the solution set includes multiple parameter groups; determine a local solution for the tth round from the solution set of the tth round according to a multi-objective function; if the number of iterations has reached the maximum number of iterations T, then select the optimal target solution from the T-round local solutions; if the number of optimizations n has reached the maximum number of optimizations N, then output m optimal target solutions, where m is less than N and greater than 0 and is an integer; The output module 303 is configured to select a business requirement solution that matches the business requirement from the m optimal target solutions.

[0068] Optionally, the determination module 301 is specifically configured to determine the coefficient vector of the t-th round according to the convergence factor, and the coefficient vector of the t-th round is determined by the following formula:

[0069] in, is the coefficient vector, is a random vector with values ​​in [0,1].

[0070] Optionally, the optimization module 302 is specifically configured to generate a solution set for the tth round based on the local solution of the t-1th round and the coefficient vector of the tth round, and the expression is:

[0071] in, is the local solution vector, is the solution set vector, and D is the positional relationship between the local solution and the optimal solution.

[0072] Optionally, the output module 303 is specifically used to output m optimal target solutions, determine the congestion distance value based on the target function values ​​adjacent to itself and the maximum and minimum values ​​in the target function; and screen out m optimal target solutions from N optimal target solutions based on the congestion distance value.

[0073] Optionally, the determination module 301 is specifically configured to determine the congestion distance value based on the objective function value adjacent to itself and the maximum and minimum values ​​in the objective function. The expression of crowding distance is:

[0074] Among them, D C (i) is the congestion distance, is the total number of objective functions, For the The objective function values, For the The objective function values, For the The maximum value among the objective functions, For the The minimum value of the objective function.

[0075] Optionally, the output module 303 is specifically used to screen out m optimal target solutions from N optimal target solutions based on the congestion distance value, calculate the congestion distance values ​​of the N optimal target solutions respectively, and arrange them in descending order from large to small, thereby screening out the top m optimal target solutions.

[0076] The multi-objective function optimization device for the solar building integrated system according to the embodiment of the present application can correspond to the method described in the embodiment of the present application, and the above-mentioned other operations and / or functions of each module / unit of the multi-objective function optimization device for the solar building integrated system are respectively to achieve Figure 2 For the sake of brevity, the corresponding processes of the various methods in the illustrated embodiments are not described again here.

[0077] The present application also provides a computing device. Figure 4 As shown, this figure is a schematic diagram of a computing device provided by an embodiment of the present application, and the computing device 700 includes a bus 701, a processor 702, a communication interface 703 and a memory 704. The processor 702, the memory 704 and the communication interface 703 communicate with each other via the bus 701.

[0078] The bus 701 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0079] The processor 702 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0080] The communication interface 703 is used for communicating with the outside.

[0081] The memory 704 may include volatile memory, such as random access memory (RAM). The memory 704 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0082] The memory 704 stores executable codes, and the processor 702 executes the executable codes to perform the aforementioned multi-objective function optimization method for the building integrated solar energy system.

[0083] Specifically, in the implementation Figure 3 In the case of the embodiment shown, and Figure 3 When each module or unit of the multi-objective function optimization device for the solar building integrated system described in the embodiment is implemented by software, Figure 3 The software or program code required for the functions of each module / unit in the system may be partially or completely stored in the memory 704. The processor 702 executes the program code corresponding to each unit stored in the memory 704 to perform the multi-objective function optimization method of the aforementioned solar building integrated system.

[0084] Embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium can be any available medium capable of being stored by a computing device, or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, or magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the multi-objective function optimization method for building-integrated solar systems.

[0085] The present application also provides a computer program product comprising one or more computer instructions that, when loaded and executed on a computing device, fully or partially generate the process or function described in the present application.

[0086] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0087] When the computer program product is executed by a computer, the computer performs any of the aforementioned methods for optimizing the multi-objective function of a building-integrated solar system. The computer program product may be a software installation package that can be downloaded and executed on a computer when any of the aforementioned methods for optimizing the multi-objective function of a building-integrated solar system is needed.

[0088] The descriptions of the processes or structures corresponding to the above figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0089] The above description is only a specific implementation method of the present application, but the protection scope of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed in the present application should be included in the protection scope of the present application.

Claims

1. A multi-objective function optimization method for solar building integration, characterized in that: The method comprises: Determining a parameter group to be optimized in a multi-objective function, wherein the parameter group to be optimized includes a heat collection area of ​​a solar thermal collector, an installed capacity of a photovoltaic system, a volume of a hot water storage tank, a heating capacity of an air source heat pump, and an installation inclination angle of photovoltaic and solar thermal collectors; Determine whether the optimization times n has reached the maximum optimization times N, where n is greater than 1 and is an integer; If the optimization times n does not reach the maximum optimization times N, then determine whether the iteration times t has reached the maximum iteration times T, where t is greater than 1 and is an integer; If the number of iterations t does not reach the maximum number of iterations T, then based on the local solution of the t-1th round and the coefficient vector of the tth round, a solution set of the tth round is generated, wherein the solution set includes multiple parameter groups; according to the multi-objective function, a local solution of the tth round is determined from the solution set of the tth round; if the number of iterations reaches the maximum number of iterations T, then the optimal target solution is selected from the local solutions of the tth round; If the optimization times n reaches the maximum optimization times N, then m optimal target solutions are output, where m is less than N, m is greater than 0, and m is an integer; Select the business requirement solution that matches the business requirement from the m optimal target solutions.

2. The method according to claim 1, characterized in that The coefficient vector of the t-th round is obtained by the following method: The convergence factor is determined according to the number of iterations t, and the expression is: in, is the convergence factor, t is the current number of iterations, T is the maximum number of iterations, and k is the number of power functions; According to the convergence factor, the coefficient vector of the tth round is determined.

3. The method according to claim 2, characterized in that Determining the coefficient vector of the tth round according to the convergence factor includes: The coefficient vector of round t is determined by the following formula: in, is the coefficient vector, is a random vector with values ​​in [0,1].

4. The method according to claim 3, characterized in that The generating of the solution set of the tth round based on the local solution of the t-1th round and the coefficient vector of the tth round includes: Based on the local solution of the t-1th round and the coefficient vector of the tth round, the solution set of the tth round is generated, and the expression is: in, is the local solution vector, is the solution set vector, and D is the positional relationship between the local solution and the optimal solution.

5. The method according to claim 1, wherein The output of m optimal target solutions includes: The crowding distance value is determined based on the objective function value adjacent to itself and the maximum and minimum values ​​in the objective function; According to the congestion distance value, m optimal target solutions are selected from N optimal target solutions.

6. The method according to claim 5, characterized in that The congestion distance value is determined based on the objective function values ​​of the adjacent objects and the maximum and minimum values ​​in the objective function, including: The expression of crowding distance is: Among them, D C (i) is the congestion distance, is the total number of objective functions, For the The objective function values, For the The objective function values, For the The maximum value among the objective functions, For the The minimum value of the objective function.

7. The method according to claim 6, characterized in that According to the congestion distance value, m optimal target solutions are screened out from N optimal target solutions, including: The congestion distance values ​​of the N optimal target solutions are calculated respectively, and they are arranged in descending order from large to small, so as to screen out the top m optimal target solutions.

8. A multi-objective function optimization device for solar building integration, characterized in that: The device comprises: A determination module is used to determine a parameter group to be optimized in a multi-objective function, wherein the parameter group to be optimized includes the heat collection area of ​​the solar collector, the installed capacity of the photovoltaic system, the volume of the hot water storage tank, the heating capacity of the air source heat pump, and the installation inclination angle of the photovoltaic and solar collectors; An optimization module is used to determine whether the number of optimizations n has reached the maximum number of optimizations N, where n is greater than 1 and is an integer; if the number of optimizations n has not reached the maximum number of optimizations N, then determine whether the number of iterations t has reached the maximum number of iterations T, where t is greater than 1 and is an integer; if the number of iterations t has not reached the maximum number of iterations T, then generate a solution set for the tth round based on the local solution of the t-1th round and the coefficient vector of the tth round, where the solution set includes multiple parameter groups; determine the local solution for the tth round from the solution set of the tth round according to a multi-objective function; if the number of iterations has reached the maximum number of iterations T, then select the optimal target solution from the local solutions of the Tth round; if the number of optimizations n has reached the maximum number of optimizations N, then output m optimal target solutions, where m is less than N and greater than 0 and is an integer; The output module is used to select a business requirement solution that matches the business requirement from the m optimal target solutions.

9. A computing device, characterized in that including memory and processor; One or more computer programs are stored in the memory, and the one or more computer programs include instructions; when the instructions are executed by the processor, the computing device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method according to any one of claims 1 to 7.

Images