Multi-objective design optimization method suitable for photovoltaic integrated envelope structure

Abstract

The application relates to the technical field of multi-target design, in particular to a multi-target design optimization method suitable for photovoltaic integrated envelope structures, which comprises the following steps: under each scheme, analyzing the correlation between environmental parameters and photovoltaic panel power generation and the contribution degree of environmental parameters to photovoltaic panel power generation, so as to construct environmental performance influence values of each scheme; based on the environmental performance influence values, the photovoltaic panel power generation and indoor temperature, a target sequence is constructed, and the solution set state optimization degree of each scheme is calculated by combining an entropy weight method and a technique for order preference by similarity to ideal solution (TOPSIS) method, so as to dynamically adjust the inertia weight of a multi-target particle swarm optimization algorithm, and iteratively optimizing the design variables of the photovoltaic integrated envelope structure. The application solves the problems that the traditional optimization algorithm is prone to falling into local optimization and low convergence precision in a complex environment, and improves the precision and reliability of multi-target optimization of the photovoltaic integrated envelope structure.

Description

Technical Field

[0001] This application relates to the field of multi-objective design technology, specifically to a multi-objective design optimization method applicable to photovoltaic integrated building envelopes. Background Technology

[0002] With the increasing global demand for energy-saving buildings, photovoltaic integrated building envelopes have become a key structure for the low-carbon transformation of building complexes. Traditional photovoltaic integrated building envelopes mainly focus on power generation efficiency, but neglect the relationship between thermal performance, lighting, and economics. In recent years, parametric modeling has enabled multi-objective design methods, thereby balancing the optimization of photovoltaic integrated building envelopes among power generation, energy saving, cost, and aesthetics, providing key technical support for sustainable urban energy structures.

[0003] In the multi-objective optimization of photovoltaic integrated building envelopes, traditional algorithms are prone to getting trapped in local optima due to the complex nonlinear coupling relationship between environmental parameters and power generation performance, making it difficult to approach the global Pareto front. Existing technologies often rely on preference information to reduce the solution set, but this is severely limited by prior knowledge, lacks robustness, and cannot fundamentally solve the problems of low convergence efficiency and local optima, thus reducing the accuracy and reliability of multi-objective optimization of photovoltaic integrated building envelopes. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a multi-objective design optimization method applicable to photovoltaic integrated building envelopes, thereby resolving the existing issues.

[0005] The multi-objective design optimization method applicable to photovoltaic integrated building envelopes in this application adopts the following technical solution: One embodiment of this application provides a multi-objective design optimization method applicable to photovoltaic integrated building envelopes, the method comprising the following steps: In photovoltaic integrated building envelope, the tilt angle, azimuth angle and material properties of photovoltaic panels are combined into a ternary set. Each ternary set represents a scheme. The photovoltaic power generation, indoor temperature and various environmental parameters of the photovoltaic integrated building envelope under each scheme are obtained in real time. Among them, the environmental parameters include: solar radiation intensity, outdoor ambient temperature and photovoltaic panel surface temperature. Under each scheme, the correlation between any environmental parameter and the photovoltaic power generation within a preset time period before the current moment is analyzed, and the contribution of any environmental parameter to the photovoltaic power generation is analyzed, so as to construct the environmental performance impact value of each scheme at the current moment. Based on the environmental performance impact value, photovoltaic power generation and indoor temperature, a target sequence is constructed, and the optimality of the solution set state of each scheme at the current time is calculated by combining the entropy weight method and the approximation ideal solution sorting method. The inertial weights of the multi-objective particle swarm optimization algorithm are dynamically adjusted based on the optimality of the solution set state to iteratively optimize the design variables of the photovoltaic integrated building envelope.

[0006] Preferably, the environmental performance impact value of each scheme at the current moment is positively correlated with the correlation between any environmental parameter and the photovoltaic power generation within a preset time period before the current moment, and the contribution of any environmental parameter to the photovoltaic power generation.

[0007] Preferably, the result obtained by using a grey relational analysis algorithm on any environmental parameter under each scheme and the photovoltaic power generation within a preset time period before the current time is used as the correlation degree between any environmental parameter under each scheme and the photovoltaic power generation at the current time.

[0008] Preferably, the method for determining the contribution of any environmental parameter to the photovoltaic panel's power generation is as follows: Under each scheme, all environmental parameters within a preset time period before the current moment are used as independent variables in the multivariate fitting algorithm, and the photovoltaic power generation is used as the dependent variable to obtain a multivariate fitting function. The absolute value of the partial regression coefficients of various environmental parameters in the multivariate fitting function is used as the contribution of any environmental parameter to the photovoltaic power generation.

[0009] Preferably, the construction of the target sequence based on environmental performance impact value, photovoltaic power generation, and indoor temperature includes: Calculate the average photovoltaic power generation and average indoor temperature under each scheme within the preset time period before the current time, and record them as power generation performance and building envelope energy-saving effect, respectively; record the sequence composed of environmental performance impact value, power generation performance and building envelope energy-saving effect under each scheme as the target sequence under each scheme at the current time.

[0010] Preferably, the calculation process for the optimality of the solution set state for each scheme at the current moment is as follows: For each scheme, the entropy weight method is used to determine the weight of each element in the target sequence; The relative proximity of each element in the target sequence under each scheme is calculated using the approximation of ideal solution sorting method. The result of weighted averaging of all elements and their corresponding weights is recorded as the solution set state optima of each scheme at the current time.

[0011] Preferably, the process for determining the weight of each element in the target sequence is as follows: The matrix composed of the target sequences of all schemes at the current moment is denoted as the decision matrix, where the rows of the decision matrix represent different schemes, and the columns represent the environmental performance impact value, power generation performance, and building envelope energy-saving effect, respectively. Using the decision matrix as input to the entropy weight method, the weights of environmental performance impact, power generation performance, and building envelope energy-saving effect are output respectively.

[0012] Preferably, the process of dynamically adjusting the inertia weights of the multi-objective particle swarm optimization algorithm is as follows: Inertia weight at time t+1 The expression: In the formula, This represents the normalized value of the mean state optima of all possible solutions at time t. Indicates the preset parameter tuning factor; represents the upper limit and lower limit of the preset inertia weight, respectively; exp[ ] represents the exponential function with the natural constant as the base.

[0013] Preferably, the iterative optimization of the design variables for the photovoltaic integrated building envelope includes: All solutions are combined into a particle swarm optimization algorithm; Obtain the average annual cost for each option, and construct an objective function based on photovoltaic power generation, indoor temperature, and average annual cost; The particle velocity and position are updated using the adjusted inertial weights, and the optimal solution for the photovoltaic integrated enclosure structure is obtained through iterative search.

[0014] Preferably, the objective function The expression is: In the formula, , , Let $x$ represent the photovoltaic power generation, the deviation between the indoor temperature and the preset comfortable temperature, and the average annual cost under the x-th scheme, respectively; $min{}$ represents the minimum value function.

[0015] This application has at least the following beneficial effects: This application integrates grey relational analysis and multiple linear regression to quantify the trend following and numerical sensitivity of environmental parameters on power generation, effectively eliminating nonlinear interference under multi-factor coupling. This achieves precise measurement of the impact of environmental factors on the power generation performance of integrated photovoltaic (PV) envelope structures, providing accurate quantitative indicators for subsequent multi-objective collaborative optimization. Furthermore, this application objectively quantifies the distribution differences of dynamic time-series data using the entropy weight method and comprehensively evaluates the approximation degree of each scheme in the multi-dimensional objective space using the approximation ideal solution ranking method. It constructs an evaluation index that can perceive the population convergence state and optimization potential in real time, effectively solving the problem that traditional static evaluation cannot adapt to dynamic environmental changes, and providing accurate feedback for subsequent adaptive adjustment of algorithm parameters. Finally, this application introduces the solution set state optima as a feedback factor to construct a nonlinear adaptive adjustment mechanism for inertia weights, achieving a dynamic balance between the algorithm's global exploration and local development capabilities. This effectively overcomes the problem that traditional algorithms are prone to getting trapped in local optima or have low convergence efficiency due to fixed parameters. Ultimately, it outputs an optimal design scheme that combines high power generation efficiency, thermal comfort, and economic rationality, improving the accuracy and reliability of multi-objective optimization of integrated PV envelope structures. Attached Figure Description

[0016] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating the steps of a multi-objective design optimization method for photovoltaic integrated building envelopes provided in one embodiment of this application; Figure 2 This is a schematic diagram of the solution set state optimization process provided in one embodiment of this application. Detailed Implementation

[0018] To further illustrate the technical means and effects adopted by this application to achieve the intended inventive objective, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the multi-objective design optimization method for photovoltaic integrated enclosure structures proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0020] The following description, in conjunction with the accompanying drawings, details the specific scheme of the multi-objective design optimization method for photovoltaic integrated building envelopes provided in this application.

[0021] This application provides a multi-objective design optimization method for photovoltaic integrated building envelopes, specifically, the following method is provided. Please refer to [link to relevant documentation]. Figure 1 The method includes the following steps: Step S1: In the photovoltaic integrated building envelope, the tilt angle, azimuth angle and material properties of the photovoltaic panels are combined into a ternary set. Each ternary set represents a scheme. The photovoltaic power generation, indoor temperature and various environmental parameters of the photovoltaic integrated building envelope under each scheme are obtained in real time. Among them, the environmental parameters include: solar radiation intensity, outdoor ambient temperature and photovoltaic panel surface temperature.

[0022] In the photovoltaic integrated building envelope, the tilt angle, azimuth angle, and material properties of the photovoltaic panels are combined into a ternary set, with each ternary set representing a scheme. A parametric model of the photovoltaic integrated building envelope is constructed. Using building performance simulation software (such as EnergyPlus), typical meteorological year data is input to simulate and obtain the photovoltaic power generation, indoor temperature, and various environmental parameters of the photovoltaic integrated building envelope at various simulation steps for each scheme. The data acquisition frequency is set to f. In this embodiment, the data acquisition frequency is 0.1Hz. In actual applications, as other implementation methods, implementers can also set it according to specific circumstances. This embodiment does not impose any special restrictions.

[0023] All the above data are aligned and integrated with a unified timestamp, and each type of data is normalized to eliminate the influence of dimensions. In this embodiment, the maximum and minimum value normalization method is used to normalize each type of data. In practical applications, as other implementation methods, implementers may also use other normalization methods to normalize the data. This embodiment does not impose any special restrictions.

[0024] The process of normalizing data using the maximum-minimum normalization method is a well-known technique and will not be elaborated further.

[0025] Step S2: Under each scheme, analyze the correlation between any environmental parameter and the photovoltaic power generation within a preset time period before the current moment, and analyze the contribution of any environmental parameter to the photovoltaic power generation, so as to construct the environmental performance impact value of each scheme at the current moment.

[0026] Because integrated photovoltaic (PV) envelope structures operate in a complex dynamic environment, environmental parameters such as solar radiation intensity, ambient temperature, and PV panel surface temperature do not act in isolation but exhibit strong coupling and time-delay effects. For example, increased solar radiation directly boosts power generation but also raises panel temperature, thus inhibiting power generation efficiency. This nonlinear superposition makes it difficult to separate the actual contributions of each factor from single-dimensional measurements, resulting in an inability to accurately quantify the true impact of various environmental factors on the system.

[0027] To address the aforementioned quantitative challenges, an evaluation mechanism capable of comprehensively reflecting both the "intensity" and "direction of contribution" of environmental parameters must be constructed. Specifically, single-dimensional analysis has limitations: analyzing only trends fails to quantify the specific impact magnitude, while analyzing only magnitude easily overlooks dynamic follow-up. Therefore, this embodiment analyzes the correlation between any environmental parameter and photovoltaic panel power generation within a preset time period prior to the current moment, and analyzes the contribution of any environmental parameter to the photovoltaic panel power generation, to construct the environmental performance impact value of each scheme at the current moment. This overcomes the accuracy bottleneck of traditional methods under multi-factor coupled conditions, providing accurate data support for subsequent multi-objective collaborative optimization. The specific process is as follows: In this embodiment, the environmental performance impact value of each scheme at the current moment is positively correlated with the correlation between any environmental parameter and the photovoltaic power generation within a preset time period before the current moment, and the contribution of any environmental parameter to the photovoltaic power generation.

[0028] The methods for determining the correlation between any environmental parameter and the photovoltaic panel's power generation, as well as the contribution of any environmental parameter to the photovoltaic panel's power generation, are as follows: In this embodiment, the result obtained by using the grey relational analysis algorithm on any environmental parameter under each scheme and the photovoltaic power generation within a preset time period before the current time is used as the correlation degree between any environmental parameter under each scheme and the photovoltaic power generation at the current time.

[0029] The process of calculating the correlation degree using the grey relational analysis algorithm is a well-known technique and will not be elaborated further.

[0030] Under each scheme, all environmental parameters within a preset time period before the current moment are used as independent variables in the multivariate fitting algorithm, and the photovoltaic power generation is used as the dependent variable to obtain a multivariate fitting function. The absolute value of the partial regression coefficients of various environmental parameters in the multivariate fitting function is used as the contribution of any environmental parameter to the photovoltaic power generation.

[0031] The process of fitting data using a multivariate fitting algorithm is a well-known technique. Therefore, the specific process of fitting environmental parameters and photovoltaic power generation using a multivariate fitting algorithm will not be described in detail.

[0032] It should be noted that the preset duration is set manually. In this embodiment, the preset duration is 1 hour. In actual applications, as other implementation methods, implementers can also set it according to specific circumstances. This embodiment does not impose any special restrictions.

[0033] It should be understood that a positive correlation means that the dependent variable increases as the independent variable increases, and the dependent variable decreases as the independent variable decreases. The specific relationship can be additive or multiplicative, etc., and is determined by the actual application. This application does not impose any special restrictions.

[0034] Preferably, as one implementation method, in this embodiment, under each scheme, the product of the correlation degree and the corresponding contribution degree between any environmental parameter and the photovoltaic power generation within a preset time period before the current time is calculated, and the sum of the products of all environmental parameters is used as the environmental performance impact value of each scheme at the current time.

[0035] Based on the environmental performance impact value, it can be understood that the environmental performance impact value is used to characterize the comprehensive strength and significance of the effect of various environmental parameters on photovoltaic power generation under the current environmental coupling conditions. It reflects the sensitivity of the actual operating performance of the photovoltaic system under complex multivariate interaction. The calculation of the environmental performance impact value is jointly affected by the correlation degree and the contribution degree. When the correlation degree and the contribution degree are larger, it indicates that the corresponding environmental parameter and the change trend of power generation are more consistent and the impact caused by a unit change is larger. At this time, the environmental performance impact value is larger, reflecting that the dominant role of the corresponding environmental factor on the power generation performance of the photovoltaic integrated enclosure structure is more significant. In the optimization process, the control of the corresponding parameter should be given priority. Conversely, when the correlation degree and the contribution degree are smaller, it indicates that the dynamic tracking of the corresponding environmental parameter on the power generation of the photovoltaic panel is poor and the impact is weak. At this time, the environmental performance impact value is smaller, reflecting that the constraint of the corresponding environmental factor on the power generation of the photovoltaic panel is weak under the current operating conditions. It belongs to the secondary influencing factor and can effectively reduce the calculation interference in the optimization process.

[0036] Thus, this embodiment, by integrating grey relational analysis and multiple linear regression, quantifies the trend following and numerical sensitivity of environmental parameters on power generation, effectively eliminating nonlinear interference under multi-factor coupling, and achieving accurate measurement of the degree of influence of environmental factors on the power generation performance of photovoltaic integrated building envelope, providing accurate quantitative indicators for subsequent multi-objective collaborative optimization.

[0037] Step S3: Based on the environmental performance impact value, photovoltaic power generation and indoor temperature, construct the target sequence, and combine the entropy weight method and the approximation ideal solution sorting method to calculate the optimality of the solution set state of each scheme at the current time.

[0038] In the multi-objective design of photovoltaic integrated building envelopes, there are nonlinear conflicts and dynamic coupling relationships among multiple objectives such as power generation efficiency, energy saving effect, and economic cost. In actual operation, these objectives are not static but exhibit significant dynamic fluctuations with time-varying environmental parameters such as solar radiation and ambient temperature. For example, the power generation objective fluctuates drastically during midday, while the energy saving objective fluctuates significantly at night. If fixed weights are used, not only will they fail to respond to this time-varying characteristic, but the optimization results will also be severely biased in the dynamic environment, causing one objective to be overoptimized at the expense of overall performance.

[0039] Therefore, based on the above analysis, this embodiment constructs a target sequence based on the environmental performance impact value, photovoltaic power generation, and indoor temperature, and calculates the optimality of the solution set state for each scheme at the current moment by combining the entropy weight method and the approximation ideal solution sorting method. The specific process is as follows: In this embodiment, firstly, a target sequence is constructed based on the environmental performance impact value, photovoltaic panel power generation, and indoor temperature. Specifically: In this embodiment, the average power generation of the photovoltaic panels and the average indoor temperature under each scheme within a preset time period before the current time are calculated and recorded as power generation performance and building envelope energy-saving effect, respectively. The sequence composed of the environmental performance impact value, power generation performance and building envelope energy-saving effect under each scheme is recorded as the target sequence under each scheme at the current time.

[0040] Furthermore, this embodiment calculates the optimality of the solution set state for each scheme at the current time based on the target sequence and by combining the entropy weight method and the approximation ideal solution sorting method. Specifically: In this embodiment, the entropy weight method is used to determine the weight of each element in the target sequence for each scheme. Specifically, the matrix composed of the target sequences of all schemes at the current time is denoted as the decision matrix, where the rows of the decision matrix represent different schemes, and the columns represent the environmental performance impact value, power generation performance, and building envelope energy-saving effect, respectively. The decision matrix is ​​used as the input of the entropy weight method, and the weights of the environmental performance impact value, power generation performance, and building envelope energy-saving effect are output respectively. The process of determining the weights using the entropy weight method is a well-known technique and will not be described in detail here.

[0041] The Approximation Ideal Solution Ranking Method (TOPSIS) is used to calculate the relative closeness of each element in the target sequence under each scheme. Specifically, the target sequence under each scheme is used as the input of the Approximation Ideal Solution Ranking Method. The evaluation index is set to be an extremely large index, that is, the larger the value, the better. The ideal solution and the negative ideal solution are respectively taken as the optimal value and the worst value of each attribute. Finally, the relative closeness of each element in the target sequence is output. Furthermore, the result of averaging all elements with their corresponding weights is denoted as the optimality of the solution set state for each scheme at the current moment.

[0042] The process of calculating the relative closeness using the approximation of ideal solution sorting method is a well-known technique and will not be elaborated further.

[0043] Preferably, the schematic diagram of the solution set state optima extraction process provided in this embodiment is as follows: Figure 2 As shown.

[0044] Based on the solution set state tendency, it can be understood that the solution set state tendency is used to characterize the overall quality of various schemes in the current population in approaching the ideal Pareto front in a multi-objective decision space. It reflects the overall convergence performance and distribution quality of the scheme set under the multi-dimensional objectives of power generation, energy conservation, and comprehensive efficiency. The calculation of the solution set state tendency is jointly affected by the target sequence weight and relative proximity. When the weight and relative proximity are larger, it indicates that the corresponding scheme performs well on the high-weight objective and is closer to the ideal solution. At this time, the solution set state tendency is larger, reflecting that the current population has approached the global optimum region, and the algorithm search has entered the refinement development stage. The inertia weight should be reduced to avoid missing the optimal solution. Conversely, when the weight and proximity are smaller, it indicates that the corresponding scheme is scattered or in a disadvantageous region. At this time, the solution set state tendency is smaller, reflecting that the population is still in the early stage of global exploration or has fallen into local stagnation. The inertia weight needs to be increased to enhance the particle's ability to jump out and expand the search range.

[0045] Thus, this embodiment objectively quantifies the distribution differences of dynamic time-series data using the entropy weight method, and comprehensively evaluates the approximation degree of each scheme in the multidimensional target space using the approximation ideal solution ranking method. It constructs an evaluation index that can perceive the population convergence status and optimization potential in real time, effectively solving the problem that traditional static evaluation cannot adapt to dynamic environmental changes, and providing accurate feedback basis for the adaptive adjustment of subsequent algorithm parameters.

[0046] Step S4: Based on the optimality of the solution set state, dynamically adjust the inertia weight of the multi-objective particle swarm optimization algorithm to iteratively optimize the design variables of the photovoltaic integrated enclosure structure.

[0047] To address the high-dimensional nonlinear objective conflict problem in the multi-objective optimization of photovoltaic integrated building envelopes, traditional single-objective algorithms struggle to achieve a balance among mutually constraining indices. Therefore, this embodiment introduces a multi-objective particle swarm optimization algorithm. Based on the optima of the solution set state, the inertial weights of the multi-objective particle swarm optimization algorithm are dynamically adjusted. Utilizing its global search mechanism based on population co-evolution, the design variables of the photovoltaic integrated building envelope are iteratively optimized, thereby providing diversified decision support for balancing power generation, thermal performance, and economic performance. The specific process is as follows: In this embodiment, 100 schemes are randomly selected as the initial particle swarm, and the initial velocity of the particles is set to 0. The implementer can also set the number of particles and the initial velocity of the particles according to the specific situation. This embodiment does not impose any special restrictions.

[0048] Secondly, construct the objective function of the multi-objective particle swarm optimization algorithm. : In the formula, , , Let $x$ represent the photovoltaic power generation, the deviation between the indoor temperature and the preset comfortable temperature, and the average annual cost under the x-th scheme, respectively; $min{}$ represents the minimum value function.

[0049] The method for obtaining the average annual cost is as follows: obtain the purchase cost of photovoltaic modules, brackets and auxiliary materials, installation and construction costs, and initial operation and maintenance investment of the photovoltaic integrated enclosure structure under each scheme, and sum them up. Use this sum as the input of the capital recovery formula, and record the output as the average annual equivalent cost. Divide the average annual equivalent cost by the total area of ​​the photovoltaic integrated enclosure structure to obtain the average annual cost under each scheme.

[0050] It should be noted that the preset comfort temperature is set manually. In this embodiment, the preset comfort temperature is 26°C. In actual application, the implementer can also set it according to the specific situation. This embodiment does not impose any special restrictions.

[0051] Furthermore, the individual optimal and global optimal solution sets are updated by comparing the current particle with its historical best position and the Pareto front of the entire population.

[0052] Furthermore, the particle velocity is adjusted using the standard velocity update formula, and the particle position is updated accordingly.

[0053] Finally, repeat the above iterations until the termination condition is met.

[0054] However, when dealing with high-dimensional problems, multi-objective particle swarm optimization algorithms typically use fixed inertia weights, which are insufficient to meet the needs of different search stages. During iteration, improper inertia weight settings can cause particles to converge prematurely to the Pareto front. Traditional fixed inertia weights cannot adaptively adjust based on the overall performance of the current solution set. Therefore, this embodiment dynamically adjusts the inertia weights of the multi-objective particle swarm optimization algorithm based on the optimality of the solution set state. Specifically: Inertia weight at time t+1 The expression: In the formula, This represents the normalized value of the mean state optima of all possible solutions at time t. Indicates the preset parameter tuning factor; represents the upper limit and lower limit of the preset inertia weight, respectively; exp[ ] represents the exponential function with the natural constant as the base.

[0055] It should be noted that the values ​​of the preset inertia weight upper limit, preset inertia weight lower limit, and preset parameter tuning factor are all manually set. The preset inertia weight upper limit ranges from 0.7 to 0.9, and in this embodiment, the preset inertia weight upper limit is set to 0.9. The preset inertia weight lower limit ranges from 0.2 to 0.4, and in this embodiment, the preset inertia weight lower limit is set to 0.4. The preset parameter tuning factor is set to 1. In actual applications, implementers can also set these values ​​according to specific circumstances. This embodiment does not impose any special restrictions.

[0056] It should be noted that in this embodiment, the optimality of the solution set is normalized using the maximum-minimum normalization method, which maps it to the range of [0,1]. In practical applications, as other implementation methods, implementers may also use other normalization methods according to specific circumstances. This embodiment does not impose any special restrictions.

[0057] Based on the optimization expression of the inertia weight, it can be understood that this formula establishes a nonlinear adaptive adjustment mechanism based on the population evolution state, aiming to balance the algorithm's global exploration and local exploitation capabilities. The formula introduces the solution set state tendency degree. As a feedback factor, when When the value is small, it indicates that the overall population performance is poor and it is in the early stages of the search. The exponential term approaches 1, indicating inertia weight. The value is close to the upper limit. This allows for larger step sizes to enable wide-area exploration; as iterations proceed, when The gradual increase indicates that the population is converging towards the ideal solution set, the value of the exponential term is decreasing, and the inertial weight... According to the exponential decay law By moving closer together, the particle velocity is automatically reduced to achieve stable development of local fine regions, thereby ensuring that the algorithm can dynamically adjust the search strategy according to the real-time quality of the solution set and avoid getting trapped in local optima.

[0058] Thus, this embodiment introduces the solution set state optima as a feedback factor to construct a nonlinear adaptive adjustment mechanism for inertial weights, achieving a dynamic balance between the algorithm's global exploration and local development capabilities. This effectively overcomes the problem that traditional algorithms are prone to getting trapped in local optima or have low convergence efficiency due to fixed parameters. Ultimately, it outputs an optimal design scheme that combines high power generation efficiency, thermal comfort, and economic rationality, improving the accuracy and reliability of multi-objective optimization of photovoltaic integrated building envelope structures.

[0059] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0060] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0061] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; modifications to the technical solutions described in the foregoing embodiments, or equivalent substitutions of some of the technical features, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A multi-objective design optimization method applicable to photovoltaic integrated building envelopes, characterized in that, The method includes the following steps: In photovoltaic integrated building envelope, the tilt angle, azimuth angle and material properties of photovoltaic panels are combined into a ternary set. Each ternary set represents a scheme. The photovoltaic power generation, indoor temperature and various environmental parameters of the photovoltaic integrated building envelope under each scheme are obtained in real time. Among them, the environmental parameters include: solar radiation intensity, outdoor ambient temperature and photovoltaic panel surface temperature. Under each scheme, the correlation between any environmental parameter and the photovoltaic power generation within a preset time period before the current moment is analyzed, and the contribution of any environmental parameter to the photovoltaic power generation is analyzed, so as to construct the environmental performance impact value of each scheme at the current moment. Based on the environmental performance impact value, photovoltaic power generation and indoor temperature, a target sequence is constructed, and the optimality of the solution set state of each scheme at the current time is calculated by combining the entropy weight method and the approximation ideal solution sorting method. The inertial weights of the multi-objective particle swarm optimization algorithm are dynamically adjusted based on the optimality of the solution set state to iteratively optimize the design variables of the photovoltaic integrated building envelope.

2. The multi-objective design optimization method for photovoltaic integrated building envelopes as described in claim 1, characterized in that, At the current moment, the environmental performance impact value of each scheme is positively correlated with the correlation between any environmental parameter and the photovoltaic power generation within a preset time period prior to the current moment, and the contribution of any environmental parameter to the photovoltaic power generation.

3. The multi-objective design optimization method for photovoltaic integrated building envelopes as described in claim 2, characterized in that, The result obtained by using the grey relational analysis algorithm to analyze the environmental parameters and photovoltaic power generation of each scheme within a preset time period before the current moment will be used as the correlation degree between the environmental parameters and photovoltaic power generation of each scheme at the current moment.

4. The multi-objective design optimization method applicable to photovoltaic integrated building envelopes as described in claim 2, characterized in that, The method for determining the contribution of any environmental parameter to the photovoltaic power generation is as follows: Under each scheme, all environmental parameters within a preset time period before the current moment are used as independent variables in the multivariate fitting algorithm, and the photovoltaic power generation is used as the dependent variable to obtain a multivariate fitting function. The absolute value of the partial regression coefficients of various environmental parameters in the multivariate fitting function is used as the contribution of any environmental parameter to the photovoltaic power generation.

5. The multi-objective design optimization method for photovoltaic integrated building envelopes as described in claim 1, characterized in that, The target sequence, constructed based on environmental performance impact values, photovoltaic panel power generation, and indoor temperature, includes: Calculate the average photovoltaic power generation and average indoor temperature under each scheme within the preset time period before the current time, and record them as power generation performance and building envelope energy-saving effect, respectively; record the sequence composed of environmental performance impact value, power generation performance and building envelope energy-saving effect under each scheme as the target sequence under each scheme at the current time.

6. The multi-objective design optimization method for photovoltaic integrated building envelopes as described in claim 5, characterized in that, The calculation process for the optimality of the solution set state for each scheme at the current moment is as follows: For each scheme, the entropy weight method is used to determine the weight of each element in the target sequence; The relative proximity of each element in the target sequence under each scheme is calculated using the approximation of ideal solution sorting method. The result of weighted averaging of all elements and their corresponding weights is recorded as the solution set state optima of each scheme at the current time.

7. The multi-objective design optimization method for photovoltaic integrated building envelopes as described in claim 6, characterized in that, The process for determining the weight of each element in the target sequence is as follows: The matrix composed of the target sequences of all schemes at the current moment is denoted as the decision matrix, where the rows of the decision matrix represent different schemes, and the columns represent the environmental performance impact value, power generation performance, and building envelope energy-saving effect, respectively. Using the decision matrix as input to the entropy weight method, the weights of environmental performance impact, power generation performance, and building envelope energy-saving effect are output respectively.

8. The multi-objective design optimization method for photovoltaic integrated building envelopes as described in claim 1, characterized in that, The process of dynamically adjusting the inertia weights in the multi-objective particle swarm optimization algorithm is as follows: Inertia weight at time t+1 The expression: In the formula, This represents the normalized value of the mean state optima of all possible solutions at time t. Indicates the preset parameter tuning factor; represents the upper limit and lower limit of the preset inertia weight, respectively; exp[ ] represents the exponential function with the natural constant as the base.

9. The multi-objective design optimization method for photovoltaic integrated building envelopes as described in claim 1, characterized in that, The iterative optimization of design variables for photovoltaic integrated building envelope includes: All solutions are combined into a particle swarm optimization algorithm; Obtain the average annual cost for each option, and construct an objective function based on photovoltaic power generation, indoor temperature, and average annual cost; The particle velocity and position are updated using the adjusted inertial weights, and the optimal solution for the photovoltaic integrated enclosure structure is obtained through iterative search.

10. The multi-objective design optimization method for photovoltaic integrated building envelopes as described in claim 9, characterized in that, objective function The expression is: In the formula, , , Let x represent the photovoltaic power generation, the deviation between the indoor temperature and the preset comfortable temperature, and the average annual cost under the x-th scheme, respectively. min{} represents the minimum value function.

Images