Zero-carbon park carbon evaluation model construction method based on multi-energy collaborative optimization

Abstract

The invention relates to the technical field of comprehensive energy system carbon evaluation, and particularly discloses a zero-carbon park carbon evaluation model construction method based on multi-energy collaborative optimization, and the method comprises the steps: obtaining the overall layout of a zero-carbon park, dividing a carbon emission region according to the overall layout of the zero-carbon park, and building a carbon emission topological graph according to the carbon emission region; determining an evaluation function of each carbon emission area according to the carbon emission topological graph, and establishing a carbon evaluation model according to the evaluation function of each carbon emission area; and screening out a to-be-optimized carbon emission region according to the carbon evaluation model, and optimizing the to-be-optimized carbon emission region based on an optimization algorithm to obtain a system optimization strategy combination of the to-be-optimized carbon emission region. According to the method, the carbon evaluation model of the multi-energy collaborative comprehensive energy system is established by establishing the carbon emission topological graph of the zero-carbon park, so that the carbon emission of the zero-carbon park can be accurately evaluated, and the energy utilization efficiency of the comprehensive energy system is improved.

Description

Technical Field

[0001] The present application relates to the technical field of carbon evaluation of integrated energy systems, and more specifically, to a method for constructing a carbon evaluation model of a zero-carbon park based on multi-energy collaborative optimization. Background Art

[0002] In the process of promoting the green and low-carbon transformation of parks in China, the names of various types of park concepts have been constantly changing, and their connotations have been continuously enriched, gradually moving from ecological parks and green parks to zero-carbon parks; during this process, the digital construction level and importance of parks have been continuously improved, and through the efficient management of various resource elements in the park, including energy, the energy consumption level of the park has been continuously reduced and the energy structure has been continuously optimized. Therefore, digital means and intelligent technologies are key factors throughout the whole process of the construction and operation of zero-carbon parks.

[0003] In the existing zero-carbon parks of the electric-thermal-hydrogen integrated energy system, due to the characteristics of a large amount of user information, diverse data types, and high information density in the carbon emission evaluation of the park, it is difficult to comprehensively consider the carbon emission evaluation data in the park when conducting carbon evaluation on a zero-carbon park with multi-energy collaborative optimization, resulting in an inability to accurately conduct a comprehensive carbon evaluation of the park. Summary of the Invention

[0004] The present invention provides a method for constructing a carbon evaluation model of a zero-carbon park based on multi-energy collaborative optimization to solve the problem of inaccurate carbon evaluation of a zero-carbon park with multi-energy collaborative optimization in the prior art, including:

[0005] Obtain the overall layout of the zero-carbon park, divide the carbon emission areas according to the overall layout of the zero-carbon park, and establish a carbon emission topology diagram based on the carbon emission areas;

[0006] Determine the evaluation function of each carbon emission area according to the carbon emission topology diagram, and establish a carbon evaluation model based on the evaluation function of each carbon emission area;

[0007] Screen out the carbon emission areas to be optimized according to the carbon evaluation model, and optimize the carbon emission areas to be optimized based on an optimization algorithm to obtain a system optimization strategy combination for the carbon emission areas to be optimized.

[0008] Further, the dividing the carbon emission areas according to the overall layout of the zero-carbon park includes:

[0009] Collect carbon emission nodes according to the overall layout of the zero-carbon park, determine the energy conversion efficiency and fuel type coefficient according to the carbon emission characteristic coefficient of the carbon emission nodes, and cluster the carbon emission nodes based on the energy conversion efficiency and fuel type coefficient by using the k-means clustering algorithm;

[0010] Determine the clustering clusters to which each carbon emission node belongs according to the clustering results, and divide the carbon emission nodes into corresponding carbon emission regions according to the clustering clusters.

[0011] Further, the k-means clustering algorithm clusters the carbon emission nodes according to the energy conversion efficiency and the fuel type coefficient, including:

[0012] Establish a characteristic data set according to the energy conversion efficiency and the fuel type coefficient, and randomly select k initial clustering centers of the characteristic data set;

[0013] Calculate the Euclidean distance from the characteristic data in the characteristic data set to the initial clustering centers, and divide each pixel point into the corresponding clustering cluster according to the Euclidean distance from the characteristic data in the characteristic data set to the initial clustering centers;

[0014] Calculate the average value of the characteristic data in each clustering cluster, and re-determine the clustering centers according to the average value of the characteristic data in each clustering cluster;

[0015] Repeat the above steps iteratively until the clustering centers no longer change or the number of iterations reaches the preset iteration threshold, and obtain the clustering results of each carbon emission node.

[0016] Further, the establishment of the carbon emission topology map according to the carbon emission region includes:

[0017] Collect the energy supply of each node in the carbon emission region, and calculate the correlation coefficient between the historical energy supply and the carbon emissions of the park according to the historical energy supply of each node in the carbon emission region and the carbon emissions of the park;

[0018] Obtain the preset standard correlation coefficient, calculate the correlation coefficient difference between each node in the same carbon emission region, and connect the two nodes with a correlation coefficient difference less than the preset standard correlation coefficient to form a carbon emission topology map.

[0019] Further, the determination of the evaluation function of each carbon emission region according to the carbon emission topology map includes:

[0020] Determine the carbon emission indicators of each carbon emission region according to the carbon emission topology map. The carbon emission indicators specifically include the clustering center value of the carbon emission region, the number of carbon emission nodes, the degree centrality of each carbon emission node, and the carbon emissions of the carbon emission region. Determine the carbon evaluation function according to the carbon emission indicators.

[0021] Further, the determination of the carbon evaluation function according to the carbon emission indicators includes:

[0022] Determine the evaluation function of each carbon emission region according to the carbon emission topology map. The evaluation function is specifically,

[0023]

[0024] Among them, R is the evaluation function, α, β, and γ are the first preset weight, the second preset weight, and the third preset weight respectively, p1 is the ratio of the clustering center value of the carbon emission area to the number of carbon emission nodes, C i is the degree centrality of the i-th carbon emission node in the carbon emission area, G i is the correlation coefficient between the historical energy supply of the i-th carbon emission node and the carbon emission of the park, n is the number of carbon emission nodes in the carbon emission area, and p3 is the carbon emission of the carbon emission area.

[0025] Furthermore, establishing a carbon evaluation model according to the evaluation functions of each carbon emission area includes:

[0026] Obtain the historical evaluation functions and corresponding evaluation results of each carbon emission area in the park, and preprocess the historical evaluation functions and corresponding evaluation results;

[0027] Establish a training sample set according to the preprocessed historical evaluation functions and corresponding evaluation results, and establish a carbon evaluation model according to the training sample set;

[0028] Train the carbon evaluation model according to the training sample set to obtain a trained carbon evaluation model.

[0029] Furthermore, screening out the carbon emission areas to be optimized according to the carbon evaluation model includes:

[0030] Input the evaluation functions of each carbon emission area in the current park into the trained carbon evaluation model to obtain the corresponding evaluation results of the current carbon emission areas, and screen out the carbon emission areas to be optimized according to the evaluation results.

[0031] Furthermore, optimizing the areas with abnormal carbon emissions based on an optimization algorithm includes:

[0032] Initialize the particle swarm parameters, set the evaluation function corresponding to the area with abnormal carbon emissions as the fitness function, calculate the fitness values of the particles, and determine the local optimal value and the global optimal value;

[0033] Draw a curve of the change in the fitness values of the particles according to the change trend of the fitness values with the number of iterations, and calculate the average slope of the fitness values within a preset iteration number interval according to the curve of the change in the fitness values of the particles;

[0034] Update the inertia weight of the particles according to the average slope of the fitness values within a preset iteration number interval, and update the particles according to the updated value of the inertia weight;

[0035] Judge whether the current number of iterations meets the algorithm termination condition. If it meets, output the system optimization strategy combination of the optimal fitness function according to the global optimal value. If it does not meet, continue the iteration.

[0036] Further, updating the inertial weight of the particle according to the average slope of the fitness value within the preset iteration number range includes:

[0037] Updating the inertial weight of the particle according to the inertial weight update formula, and the specific inertial weight update formula is

[0038] w = (w max - w min ) exp(k - k α ) - w min

[0039] where w is the inertial weight, w min is the minimum value of the inertial weight, w max is the maximum value of the inertial weight, k is the average slope of the fitness value within the preset iteration number range, and k α is the preset standard average slope.

[0040] The beneficial effects of the present invention are as follows

[0041] By applying the above technical solutions, the present invention establishes a carbon evaluation model of a multi - energy collaborative integrated energy system by establishing a carbon emission topology map of a zero - carbon park, integrates an electric - heat - hydrogen multi - energy coupling system, proposes an optimization algorithm for a zero - carbon park, realizes the intelligent linkage of park carbon evaluation and energy scheduling, accurately evaluates the carbon emissions of the zero - carbon park, and improves the energy utilization efficiency of the integrated energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 Shows the overall flowchart of a method for constructing a carbon evaluation model of a zero - carbon park based on multi - energy collaborative optimization proposed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0045] The embodiment of the present application provides a method for constructing a carbon evaluation model of a zero-carbon park based on multi-energy collaborative optimization, as Figure 1 shown, including:

[0046] S101, obtain the overall layout of the zero-carbon park, divide the carbon emission areas according to the overall layout of the zero-carbon park, and establish a carbon emission topology map according to the carbon emission areas;

[0047] In some embodiments of the present application, the dividing the carbon emission areas according to the overall layout of the zero-carbon park includes: collecting carbon emission nodes according to the overall layout of the zero-carbon park, determining the energy conversion efficiency and fuel type coefficient according to the carbon emission characteristic coefficient of the carbon emission nodes, and clustering the carbon emission nodes based on the energy conversion efficiency and fuel type coefficient by using the k-means clustering algorithm; determining the clustering clusters to which each carbon emission node belongs according to the clustering result, and dividing the carbon emission nodes into the corresponding carbon emission areas according to the clustering clusters.

[0048] In this embodiment, systems such as energy storage or power generation with carbon emissions in the zero-carbon park are set as carbon emission nodes, and the carbon emission areas are divided by collecting the energy conversion efficiency and fuel type coefficient of the carbon emission nodes. The fuel type coefficient is set corresponding to the required fuel type of the energy storage / power generation system. The more carbon emissions generated by the fuel, the smaller the corresponding fuel type coefficient.

[0049] In some embodiments of the present application, the clustering the carbon emission nodes based on the energy conversion efficiency and fuel type coefficient by using the k-means clustering algorithm includes: establishing a characteristic data set according to the energy conversion efficiency and fuel type coefficient, and randomly selecting k initial clustering centers of the characteristic data set; calculating the Euclidean distance from the characteristic data in the characteristic data set to the initial clustering centers, and dividing each pixel point into the corresponding clustering cluster according to the Euclidean distance from the characteristic data in the characteristic data set to the initial clustering centers; calculating the average value of the characteristic data in each clustering cluster, and re-determining the clustering centers according to the average value of the characteristic data in each clustering cluster; repeating the above steps iteratively until the clustering centers no longer change or the number of iterations reaches a preset iteration threshold, and obtaining the clustering result of each carbon emission node.

[0050] In some embodiments of the present application, the establishing a carbon emission topology map according to the carbon emission areas includes: collecting the energy supply of each node in the carbon emission area, calculating the correlation coefficient between the historical energy supply and the carbon emissions of the park according to the historical energy supply of each node in the carbon emission area and the carbon emissions of the park; obtaining a preset standard correlation coefficient, calculating the correlation coefficient difference between each node in the same carbon emission area, and connecting two nodes with a correlation coefficient difference less than the preset standard correlation coefficient to form a carbon emission topology map.

[0051] In this embodiment, by calculating the correlation coefficient between the energy supply amount of each carbon emission node for the integrated energy system and the overall carbon emission amount of the park, the carbon emission nodes with similar correlation coefficients are connected. The correlation coefficient can represent the sensitivity of the energy supply amount of the carbon emission node to the carbon emission amount. Connecting each carbon emission node through the correlation coefficient can reflect the overall sensitivity level of the carbon emission area.

[0052] S102. Determine the evaluation function of each carbon emission area according to the carbon emission topology diagram, and establish a carbon evaluation model according to the evaluation function of each carbon emission area;

[0053] In some embodiments of the present application, the determining the evaluation function of each carbon emission area according to the carbon emission topology diagram includes: determining the carbon emission index of each carbon emission area according to the carbon emission topology diagram. The carbon emission index specifically includes the clustering center value of the carbon emission area, the number of carbon emission nodes, the degree centrality of each carbon emission node, and the carbon emission amount of the carbon emission area, and determining the carbon evaluation function according to the carbon emission index.

[0054] In some embodiments of the present application, the determining the carbon evaluation function according to the carbon emission index includes: determining the evaluation function of each carbon emission area according to the carbon emission topology diagram. The evaluation function is specifically

[0055]

[0056] where R is the evaluation function, α, β, and γ are the first preset weight, the second preset weight, and the third preset weight respectively, p1 is the ratio of the clustering center value of the carbon emission area to the number of carbon emission nodes, C i is the degree centrality of the i-th carbon emission node in the carbon emission area, G i is the correlation coefficient between the historical energy supply amount of the i-th carbon emission node and the carbon emission amount of the park, n is the number of carbon emission nodes in the carbon emission area, and p3 is the carbon emission amount of the carbon emission area.

[0057] In this embodiment, after establishing the carbon emission topology diagram, an evaluation function is established through the carbon emission indexes of each carbon emission node in the carbon emission topology diagram to evaluate the carbon emission nodes. The carbon emission indexes specifically include the clustering center value of the carbon emission area, the number of carbon emission nodes, the degree centrality of each carbon emission node, and the carbon emission amount of the carbon emission area. The degree centrality is specifically the number of connections of the node in the topology diagram, and the importance of the node can be reflected through the degree centrality.

[0058] In some embodiments of the present application, establishing a carbon evaluation model according to the evaluation functions of each carbon emission region includes: obtaining the historical evaluation functions and corresponding evaluation results of each carbon emission region in the park, and preprocessing the historical evaluation functions and corresponding evaluation results; establishing a training sample set according to the preprocessed historical evaluation functions and corresponding evaluation results, and establishing a carbon evaluation model according to the training sample set; training the carbon evaluation model according to the training sample set to obtain a trained carbon evaluation model.

[0059] In some embodiments of the present application, screening out the carbon emission regions to be optimized according to the carbon evaluation model includes: inputting the evaluation functions of each carbon emission region in the current park into the trained carbon evaluation model to obtain the corresponding evaluation results of the current carbon emission regions, and screening out the carbon emission regions to be optimized according to the evaluation results.

[0060] In this embodiment, the carbon emission regions are divided into abnormal regions, problem regions, and normal regions through the carbon evaluation model, and the abnormal regions are screened out as the regions to be optimized through the evaluation results.

[0061] S103, screening out the carbon emission regions to be optimized according to the carbon evaluation model, and optimizing the carbon emission regions to be optimized based on an optimization algorithm to obtain a system optimization strategy combination for the carbon emission regions to be optimized.

[0062] In some embodiments of the present application, optimizing the regions with abnormal carbon emissions based on an optimization algorithm includes: initializing the particle swarm parameters, setting the evaluation function corresponding to the regions with abnormal carbon emissions as the fitness function, calculating the fitness values of the particles, and determining the local optimal value and the global optimal value; drawing a change curve of the fitness values of the particles according to the change trend of the fitness values with the number of iterations, and calculating the average slope of the fitness values within a preset iteration number interval according to the change curve of the fitness values of the particles; updating the inertia weight of the particles according to the average slope of the fitness values within the preset iteration number interval, and updating the particles according to the updated value of the inertia weight; determining whether the current number of iterations meets the algorithm termination condition, if so, outputting the system optimization strategy combination of the optimal fitness function according to the global optimal value, if not, continuing the iteration.

[0063] In some embodiments of the present application, updating the inertia weight of the particles according to the average slope of the fitness values within a preset iteration number interval includes: updating the inertia weight of the particles according to the inertia weight update formula, and the inertia weight update formula is specifically

[0064] w=(w max -w min )exp(k-k α )-w min

[0065] Among them, w is the inertia weight, w min is the minimum value of the inertia weight, w max is the maximum value of the inertia weight, k is the average slope of the fitness value within the preset iteration number range, k α is the preset standard average slope.

[0066] In this embodiment, the average slope of the fitness value within the preset iteration number range is specifically the average of the slopes at both endpoints of the preset iteration number range. The magnitude of the average slope can reflect the speed of increase or decrease of the fitness value. w min takes 0.2, w max takes 0.7, k α is set according to experience. The faster the fitness value changes, the larger the value of the inertia weight, which can improve the global search ability of the algorithm. The slower the fitness value changes, it indicates that the system optimization strategy combination is already close to the optimal. Therefore, the value of the inertia weight is smaller, which improves the local search ability of the algorithm, speeds up the convergence speed, and improves the calculation efficiency.

[0067] By applying the above technical solutions, the present invention obtains the overall layout of the zero-carbon park, divides the carbon emission areas according to the overall layout of the zero-carbon park, and establishes a carbon emission topology map based on the carbon emission areas; determines the evaluation function of each carbon emission area according to the carbon emission topology map, and establishes a carbon evaluation model according to the evaluation function of each carbon emission area; screens out the carbon emission areas to be optimized according to the carbon evaluation model, and optimizes the carbon emission areas to be optimized based on an optimization algorithm to obtain a system optimization strategy combination for the carbon emission areas to be optimized. The present invention establishes a carbon evaluation model for the integrated energy system with multi-energy collaboration by establishing a carbon emission topology map of the zero-carbon park, and can achieve accurate evaluation of the carbon emissions of the zero-carbon park, and improve the energy utilization efficiency of the integrated energy system.

[0068] Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present invention.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for constructing a zero-carbon park carbon assessment model based on multi-energy collaborative optimization, characterized in that: The method comprises: Obtain the overall layout of the zero-carbon park, divide the carbon emission areas according to the overall layout of the zero-carbon park, and establish a carbon emission topology map according to the carbon emission areas; Determine the evaluation function of each carbon emission area according to the carbon emission topology map, and establish a carbon evaluation model according to the evaluation function of each carbon emission area; The carbon emission areas to be optimized are screened out according to the carbon evaluation model, and the carbon emission areas to be optimized are optimized based on the optimization algorithm to obtain a system optimization strategy combination for the carbon emission areas to be optimized.

2. The method for constructing a zero-carbon park carbon evaluation model based on multi-energy collaborative optimization according to claim 1 is characterized in that: The carbon emission areas are divided according to the overall layout of the zero-carbon park, including: Carbon emission nodes are collected according to the overall layout of the zero-carbon park, and the energy conversion efficiency and fuel type coefficient are determined according to the carbon emission characteristic coefficient of the carbon emission nodes. The carbon emission nodes are clustered according to the energy conversion efficiency and fuel type coefficient based on the k-means clustering algorithm; According to the clustering results, the cluster to which each carbon emission node belongs is determined, and the carbon emission nodes are divided into corresponding carbon emission areas according to the clustering cluster.

3. The method for constructing a zero-carbon park carbon evaluation model based on multi-energy collaborative optimization according to claim 2 is characterized in that: The k-means clustering algorithm is used to cluster carbon emission nodes according to energy conversion efficiency and fuel type coefficient, including: A characteristic data set is established according to the energy conversion efficiency and fuel type coefficient, and k initial cluster centers of the characteristic data set are randomly selected; Calculate the Euclidean distance from the characteristic data in the characteristic data set to the initial cluster center, and divide each pixel point into a corresponding cluster cluster according to the Euclidean distance from the characteristic data in the characteristic data set to the initial cluster center; Calculate the average value of the characteristic data within each cluster, and re-determine the cluster center based on the average value of the characteristic data within each cluster; The above steps are iterated repeatedly until the cluster center no longer changes or the number of iterations reaches a preset iteration threshold, and the clustering results of each carbon emission node are obtained.

4. The method for constructing a zero-carbon park carbon assessment model based on multi-energy collaborative optimization according to claim 3 is characterized in that: The step of establishing a carbon emission topology map according to the carbon emission area includes: Collect the energy supply of each node in the carbon emission area, and calculate the correlation coefficient between the historical energy supply and the carbon emissions of the park based on the historical energy supply of each node in the carbon emission area and the carbon emissions of the park; The preset standard correlation coefficient is obtained, the correlation coefficient difference of each node in the same carbon emission area is calculated, and two nodes whose correlation coefficient difference is less than the preset standard correlation coefficient are connected to form a carbon emission topology map.

5. The method for constructing a zero-carbon park carbon assessment model based on multi-energy collaborative optimization according to claim 4 is characterized in that: The step of determining the evaluation function of each carbon emission area according to the carbon emission topology map includes: The carbon emission index of each carbon emission area is determined according to the carbon emission topology map. The carbon emission index specifically includes the cluster center value of the carbon emission area, the number of carbon emission nodes, the degree centrality of each carbon emission node and the carbon emission of the carbon emission area. The carbon evaluation function is determined according to the carbon emission index.

6. The method for constructing a zero-carbon park carbon assessment model based on multi-energy collaborative optimization according to claim 5 is characterized in that: Determining the carbon evaluation function according to the carbon emission index includes: The evaluation function of each carbon emission area is determined according to the carbon emission topology map. The evaluation function is specifically: Wherein, R is the evaluation function, α, β, γ are the first preset weight, the second preset weight and the third preset weight respectively, p1 is the ratio of the cluster center value of the carbon emission area to the number of carbon emission nodes, C i is the degree centrality of the i-th carbon emission node in the carbon emission region, C i is the correlation coefficient between the historical energy supply of the ith carbon emission node and the carbon emissions of the park, n is the number of carbon emission nodes in the carbon emission area, and p3 is the carbon emissions of the carbon emission area.

7. The method for constructing a zero-carbon park carbon assessment model based on multi-energy collaborative optimization according to claim 6 is characterized in that: The carbon evaluation model is established according to the evaluation function of each carbon emission area, including: Obtain the historical evaluation functions and corresponding evaluation results of each carbon emission area in the park, and pre-process the historical evaluation functions and corresponding evaluation results; Establish a training sample set according to the preprocessed historical evaluation function and the corresponding evaluation results, and establish a carbon evaluation model according to the training sample set; The carbon assessment model is trained according to the training sample set to obtain a trained carbon assessment model.

8. The method for constructing a zero-carbon park carbon assessment model based on multi-energy collaborative optimization according to claim 7 is characterized in that: The method of selecting the carbon emission areas to be optimized according to the carbon assessment model includes: The evaluation functions of each carbon emission area in the current park are input into the trained carbon evaluation model to obtain the evaluation results corresponding to the current carbon emission area, and the carbon emission areas to be optimized are screened out according to the evaluation results.

9. The method for constructing a zero-carbon park carbon assessment model based on multi-energy collaborative optimization according to claim 8 is characterized in that: The optimization of the area with abnormal carbon emissions based on the optimization algorithm includes: Initialize the particle swarm parameters, set the evaluation function corresponding to the area with abnormal carbon emissions as the fitness function, calculate the fitness value of the particles, and determine the local optimal value and the global optimal value; According to the changing trend of the fitness value with the number of iterations, a fitness value change curve of the particle is drawn, and according to the fitness value change curve of the particle, the slope mean of the fitness value within the preset number of iterations is calculated; The inertia weight of the particle is updated according to the slope mean of the fitness value within the preset iteration number interval, and the particle is updated according to the updated value of the inertia weight; Determine whether the current number of iterations meets the algorithm termination condition. If so, output the system optimization strategy combination of the optimal fitness function according to the global optimal value. If not, continue to iterate.

10. The method for constructing a zero-carbon park carbon assessment model based on multi-energy collaborative optimization according to claim 9, characterized in that: The updating of the particle inertia weight according to the slope mean of the fitness value within a preset iteration number interval includes: The inertia weight of the particle is updated according to the inertia weight update formula, and the inertia weight update formula is specifically: w=(w max -w min )exp(k-K α )-w min Among them, w is the inertia weight, w min is the minimum inertia weight, w max is the maximum value of the inertia weight, k is the slope mean of the fitness value within the preset iteration number interval, k α is the preset standard slope mean.

Images