A regional carbon peak target design and path planning method and system

Abstract

The present application relates to power system carbon emission prediction technology, in particular to a regional carbon peak target design and path planning method and system, the method first based on logistic regression and grey theory carries out the high adaptability prediction of regional carbon emission influencing factor, then based on convolutional neural network carries out regional carbon emission prediction;Then, with the carbon peak target as the guide, the carbon peak target design based on space mapping is carried out;Finally, the fitness function based on convolutional neural network is established, the index constraint is constructed, and the genetic algorithm is solved to obtain the carbon peak implementation path. The method is different from the existing prediction method for the change trend of regional carbon emission, considering the high adaptability prediction of regional carbon emission influencing factor is the key to the change trend of regional carbon emission, at the same time, considering the superiority of convolutional neural network method for time series data feature mining, the method is simple and effective, which can guide the regional low-carbon transformation and promote the carbon peak.

Description

Technical Field

[0001] This invention belongs to the field of power system carbon emission prediction technology, and in particular relates to a regional carbon peaking target design and path planning method and system. Background Technology

[0002] As a non-renewable resource, the combustion of fossil fuels produces large amounts of carbon dioxide, leading to climate change and impacting the human environment. Achieving carbon neutrality requires resolving the conflict between development and carbon emission reduction. Clearly, carbon peaking is a critical timeframe for achieving carbon neutrality, and the realization of both carbon targets is inseparable from regional low-carbon transitions. Therefore, conducting research on regional carbon peaking targets and pathway planning is essential.

[0003] Currently, most research on regional carbon peaking target design and pathway planning focuses on macroeconomic policies, or lacks a problem- or goal-oriented approach, merely exploring regional carbon emission changes based on the development trends of various factors. This approach suffers from a lack of consideration for the social attributes of relevant data or insufficient data feature mining. Therefore, this invention proposes a method for regional carbon peaking target design and pathway planning to support the achievement of regional carbon peaking targets. Summary of the Invention

[0004] This invention provides a regional carbon peaking target design and path planning method to address the shortcomings of existing technologies that do not consider the social attributes of relevant data or do not fully mine data features. It enables the full mining of data features of regional carbon emission influencing factors, guides regional low-carbon transformation, and promotes carbon peaking.

[0005] This invention provides a method for regional carbon peaking target design and pathway planning, including regional carbon emission prediction, regional carbon emission target design, and regional carbon peaking pathway planning. Specifically, it includes the following steps:

[0006] Step 1: Conduct highly adaptive prediction of regional carbon emission influencing factors based on logistic regression and grey theory, and then conduct regional carbon emission prediction based on convolutional neural network;

[0007] Step 2: Guided by the carbon peaking target, conduct carbon peaking target design based on spatial mapping;

[0008] Step 3: Conduct carbon peaking path planning based on genetic algorithm and convolutional neural network.

[0009] According to the regional carbon peaking target design and pathway planning method provided by the present invention, step 1 includes the following steps:

[0010] Step 1.1: Obtain data on factors influencing regional carbon emissions:

[0011] V = [v 1 ,v 2 ,...,v j ,...,...,v M ]

[0012] v j =[v1 j v2 j ,...,v i j ,...,v N j ] T

[0013] Where: V represents the dataset of factors influencing regional carbon emissions; v j v represents the data for the j-th influencing factor of regional carbon emissions; i j The data for the j-th influencing factor of regional carbon emissions at the i-th time point; M is the number of influencing factors of regional carbon emissions; N is the number of sampling times for influencing factors of regional carbon emissions; the superscript symbol T is a mathematical symbol indicating the transpose of a vector or matrix.

[0014] Step 1.2: Conduct highly adaptable prediction of regional carbon emission influencing factors based on logistic regression and grey theory: Perform logistic fitting on each row of the influencing factor dataset. If the T-test is passed, predict the future value of the corresponding influencing factor based on logistic regression; otherwise, predict the future value of the corresponding influencing factor based on grey theory.

[0015] Step 1.3: Predict regional carbon emissions based on convolutional neural networks:

[0016] First, a CNN network is trained using the influencing factor dataset as input and regional carbon emissions as output, and the CNN network is generated. Then, the predicted values ​​from the influencing factor dataset obtained in step 1.2 are input into the generated CNN network to obtain the predicted values ​​for regional carbon emissions.

[0017] p = CNN(V)

[0018] p = [p1, p2, ..., p i ,...,p N ] T

[0019] Where: V represents the dataset of factors influencing regional carbon emissions; P represents the regional carbon emissions data; p i represents the data at the i-th moment of influence of regional carbon emissions; CNN(·) is the CNN network for regional carbon emissions; N is the number of sampling moments for regional carbon emissions; the superscript symbol T is a mathematical symbol, indicating taking the transpose of a vector or matrix.

[0020] According to the regional carbon peaking target design and pathway planning method provided by the present invention, step 2 includes: target design based on spatial mapping:

[0021] i∈{1,2},T i ∈[t start i ,t end i ]

[0022]

[0023]

[0024] Where: p is defined t i For region target i, the carbon emissions at time t; t 30 i The time to achieve carbon peaking under regional objective i are respectively; t start i t end i The time interval T for achieving carbon peaking under regional objective i is given. i The starting and ending points of the time; Objective 1 is to not impose measures on the region and continue the baseline scenario under the existing policies.

[0025] According to the regional carbon peaking target design and pathway planning method provided by the present invention, step 3 includes the following steps:

[0026] Step 3.1: Establish a fitness function based on a convolutional neural network and construct metric constraints:

[0027]

[0028]

[0029] u i j ≤v i j ≤1,j∈S ratio

[0030] Where obj is the fitness function value of regional carbon emissions; CNN(·) is the CNN network for regional carbon emissions; V s The population of individuals in the set of factors influencing regional carbon emissions generated by the genetic algorithm; P represents the regional carbon emission data; v i j S represents the data for the j-th influencing factor on regional carbon emissions at the i-th time point; pos S is a set of positive indicators for regional carbon emissions. inpFor a set of inverse indicators of regional carbon emissions; S ratio represents a set of indicators representing the proportion / ratio of regional carbon emissions; ||·|| is a mathematical symbol representing the 2-norm of a vector.

[0031] Step 3.2: Based on the fitness function and index constraints, use a genetic algorithm to obtain the optimal individual.

[0032]

[0033]

[0034] Where obj is the fitness function value of regional carbon emissions; CNN(·) is the CNN network for regional carbon emissions; V s V represents the population of individuals in the set of factors influencing regional carbon emissions generated by a genetic algorithm; best V represents the optimal individual in the set of factors influencing regional carbon emissions obtained by the genetic algorithm, i.e., the carbon peaking path; P represents the regional carbon emission data; v i j S represents the data for the j-th influencing factor on regional carbon emissions at the i-th time point; pos S is a set of positive indicators for regional carbon emissions. inp For a set of inverse indicators of regional carbon emissions; S ratio represents a set of indicators representing the proportion / ratio of regional carbon emissions; ||·|| is a mathematical symbol representing the 2-norm of a vector.

[0035] The present invention also provides a system for a regional carbon peaking target design and pathway planning method, including a carbon emission prediction module, a carbon emission target design module, and a carbon peaking pathway planning module.

[0036] According to the present invention, a system for regional carbon peaking target design and path planning method comprises a carbon emission prediction module for highly adaptive prediction of regional carbon emission influencing factors and regional carbon emission prediction; a carbon emission target design module for spatial mapping-based carbon peaking target design with carbon peaking as the target; and a carbon peaking path planning module for planning carbon peaking paths based on genetic algorithms and convolutional neural networks.

[0037] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the regional carbon peaking target design and path planning method as described above.

[0038] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the regional carbon peaking target design and path planning method as described above.

[0039] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the regional carbon peaking target design and path planning method as described above.

[0040] Compared with the prior art, the beneficial effects of the present invention are:

[0041] This invention differs from existing methods for predicting regional carbon emission trends. It recognizes that highly adaptive prediction of regional carbon emission influencing factors is crucial for perceiving these trends. Furthermore, it leverages the superiority of convolutional neural network methods for mining time-series data features and fully considers the inherent properties of these factors. First, it employs highly adaptive prediction of regional carbon emission influencing factors based on logistic regression and grey theory. Then, it uses convolutional neural networks to predict regional carbon emissions. Next, to achieve the inversion of carbon emission influencing factors under different carbon peaking targets, it designs carbon peaking targets based on spatial mapping, guided by these targets. Finally, it constructs a fitness function using genetic algorithms and convolutional neural networks, performs rapid and accurate inversion of carbon emission influencing factors, and realizes carbon peaking path planning. This method effectively and simply mines data features, guiding regional low-carbon transformation and promoting carbon peaking. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in this invention 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 some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0043] Figure 1 This is a flowchart of a regional carbon peaking target design and pathway planning method provided by an embodiment of the present invention;

[0044] Figure 2 This is a comparison chart of the training performance of the CNN model provided in this embodiment of the invention on the training set and the test set;

[0045] Figure 3 This is a graph showing the change in carbon emissions from 2010 to 2060 based on a CNN model, provided in an embodiment of the present invention.

[0046] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention.

[0047] Figure label:

[0048] Among them: 810 - processor, 820 - communication interface, 830 - memory, 840 - communication bus. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0050] This embodiment presents a method for regional carbon peaking target design and path planning. First, it uses logistic regression and grey theory to perform highly adaptive prediction of factors influencing regional carbon emissions. Then, it uses convolutional neural networks to predict regional carbon emissions. Next, guided by the carbon peaking target, it designs a carbon peaking target based on spatial mapping. Finally, it establishes a fitness function based on convolutional neural networks, constructs index constraints, and uses a genetic algorithm to solve for the carbon peaking implementation path. This method can fully exploit the data characteristics of regional carbon emission influencing factors. It is simple and effective, and can guide regional low-carbon transformation and promote carbon peaking.

[0051] This embodiment is achieved through the following technical solutions, such as... Figure 1 As shown, a method for regional carbon peaking target design and pathway planning includes the following steps:

[0052] S1. Based on logistic regression and grey theory, a highly adaptive prediction of factors influencing regional carbon emissions is carried out, and then a prediction of regional carbon emissions is carried out based on convolutional neural networks;

[0053] The specific steps of S1 include:

[0054] (1) Obtaining data on factors influencing regional carbon emissions:

[0055] V = [v 1 ,v 2 ,...,v j ,...,...,v M ]

[0056] v j =[v1 j v2 j ,...,v i j ,...,v N j ] T

[0057] Where: V represents the dataset of factors influencing regional carbon emissions; v j v represents the data for the j-th influencing factor of regional carbon emissions; ij The data for the j-th influencing factor of regional carbon emissions at the i-th time point; M is the number of influencing factors of regional carbon emissions; N is the number of sampling times for influencing factors of regional carbon emissions; the superscript symbol T is a mathematical symbol indicating the transpose of a vector or matrix.

[0058] (2) Highly adaptable prediction of regional carbon emission influencing factors based on logistic regression and grey theory: Logistic fitting is performed on each row of the influencing factor dataset. If the T test is passed, the future value of the corresponding influencing factor is predicted based on logistic regression; otherwise, the future value of the corresponding influencing factor is predicted based on grey theory.

[0059] (3) Predicting regional carbon emissions based on convolutional neural networks: First, train a CNN network with the influencing factor dataset as input and regional carbon emissions as output, and generate a CNN network; input the predicted values ​​of the influencing factor dataset obtained in step 1.2 into the generated CNN network to obtain the predicted values ​​of regional carbon emissions.

[0060] p = CNN(V)

[0061] p = [p1, p2, ..., p i ,...,p N ] T

[0062] Where: V represents the dataset of factors influencing regional carbon emissions; P represents the regional carbon emissions data; p i represents the data at the i-th moment of influence of regional carbon emissions; CNN(·) is the CNN network for regional carbon emissions; N is the number of sampling moments for regional carbon emissions; the superscript symbol T is a mathematical symbol, indicating taking the transpose of a vector or matrix.

[0063] S2. Guided by the carbon peaking target, conduct carbon peaking target design based on spatial mapping;

[0064] The specific steps of S2 include:

[0065] Target design based on spatial mapping:

[0066] i∈{1,2},T i ∈[t start i ,t end i ]

[0067]

[0068]

[0069] Where: p is defined ti For region target i, the carbon emissions at time t; t 30 i The time to achieve carbon peaking under regional objective i are respectively; t start i t end i The time interval T for achieving carbon peaking under regional objective i is given. i The starting and ending points of the time; Objective 1 is to not impose measures on the region and continue the baseline scenario under the existing policies.

[0070] S3. Carbon peaking path planning based on genetic algorithm and convolutional neural network.

[0071] The specific steps of S3 include:

[0072] (1) Establish a fitness function based on a convolutional neural network and construct index constraints:

[0073]

[0074]

[0075] u i j ≤v i j ≤1,j∈S ratio

[0076] Where obj is the fitness function value of regional carbon emissions; CNN(·) is the CNN network for regional carbon emissions; V s The population of individuals in the set of factors influencing regional carbon emissions generated by the genetic algorithm; P represents the regional carbon emission data; v i j S represents the data for the j-th influencing factor on regional carbon emissions at the i-th time point; pos S is a set of positive indicators for regional carbon emissions. inp For a set of inverse indicators of regional carbon emissions; S ratio , which is a set of indicators representing the proportion / ratio of regional carbon emissions; ||·||2 is a mathematical symbol representing the 2-norm of a vector.

[0077] (2) Based on the fitness function and index constraints, the optimal individual is obtained by solving the problem using a genetic algorithm:

[0078]

[0079]

[0080] Where obj is the fitness function value of regional carbon emissions; CNN(·) is the CNN network for regional carbon emissions; V sV represents the population of individuals in the set of factors influencing regional carbon emissions generated by a genetic algorithm; best V represents the optimal individual in the set of factors influencing regional carbon emissions obtained by the genetic algorithm, i.e., the carbon peaking path; P represents the regional carbon emission data; v i j S represents the data for the j-th influencing factor on regional carbon emissions at the i-th time point; pos S is a set of positive indicators for regional carbon emissions. inp For a set of inverse indicators of regional carbon emissions; S ratio , represents a set of indicators for the proportion / ratio of regional carbon emissions; ||·||2 is a mathematical symbol representing the 2-norm of a vector; argmin is a mathematical symbol representing the solution to be found when the problem takes a minimum value.

[0081] The invention will be further illustrated below with specific examples:

[0082] Taking the data from 2010 to 2020 (11 sampling time points) of a certain region as an example for case analysis, the input indicators of the regional carbon emission prediction model include: population, GDP (Gross National Product) and energy consumption, consumption of the agricultural and forestry sector, consumption of the energy supply sector, the proportion of primary fossil energy in industrial sector consumption, the proportion of primary fossil energy in residential consumption and the proportion of non-fossil energy consumption.

[0083] Based on the data analysis of influencing factors using logistic regression, it was found that population, GDP, energy consumption, and the proportion of non-fossil energy consumption follow the logistic law; however, the consumption of the agricultural and forestry sector, the consumption of the energy supply sector, the proportion of primary fossil energy in industrial sector consumption, and the proportion of primary fossil energy in residential consumption do not follow the logistic law.

[0084] Ten sampling points were randomly selected as the training set, and one sampling point was selected as the test set. Figure 2 Table 1 shows the comparison of the training performance of the CNN model on the training set and the test set, respectively. The root-mean-square error (RMSE) of the two is 259.5938 and 338.6277, respectively. The error is extremely small relative to the amount of carbon emission data, and it can be considered that the carbon emission prediction model based on CNN has been well trained.

[0085] Table 1 Comparison of CNN model prediction results on the test set

[0086]

[0087] Figure 3The graph shows the carbon emission change curves based on the CNN model from 2010 to 2060. The black "*" marks represent historical data curves, and the black "○" marks represent the CNN model prediction curves. It is clear that, with 2020 as the base year, this region can only achieve "carbon peak" around 2060, with carbon emissions of approximately 314 × 105 million tCO2. Achieving the "carbon neutrality" target will be more difficult, so corresponding measures and policies are needed to meet the requirements of the "dual carbon target".

[0088] Based on the spatial mapping-based scenario design method, Objective 1 and Objective 2 are set as shown in Table 2. The genetic algorithm parameters for this example are set as follows: 1) population size of 100, 2) number of elites of 10, 3) crossover rate of 0.75, 4) number of generations of 50, and 5) convergence threshold of 1e-6. The influencing factor data (i.e., paths) for each key time node year of Objective 2 are shown in Table 3.

[0089] Table 2 Carbon emission targets for key years under each target

[0090]

[0091] Table 3 Implementation Path for Carbon Peaking under Regional Objective 2

[0092]

[0093]

[0094] This embodiment also provides a system for regional carbon peaking target design and pathway planning methods, including a carbon emission prediction module, a carbon emission target design module, and a carbon peaking pathway planning module.

[0095] The carbon emission prediction module is used for highly adaptive prediction of factors influencing regional carbon emissions and for regional carbon emission prediction; the carbon emission target design module is used for designing carbon peaking targets based on spatial mapping with carbon peaking as the goal; and the carbon peaking path planning module is used for planning carbon peaking paths based on genetic algorithms and convolutional neural networks.

[0096] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840. The processor 810, communications interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions from the memory 830 to execute methods for regional carbon peaking target design and pathway planning.

[0097] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0098] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the methods for regional carbon peaking target design and pathway planning provided by the above methods.

[0099] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the methods for regional carbon peaking target design and pathway planning provided by the methods described above.

[0100] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0101] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions 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 invention.

Claims

1. A method for regional carbon peaking target design and pathway planning, characterized in that, Includes the following steps: A highly adaptive prediction of regional carbon emission influencing factors is based on logistic regression and grey theory, and a prediction of regional carbon emissions is based on convolutional neural networks. Carbon peaking target design based on spatial mapping, guided by the carbon peaking target; The carbon peaking target design based on spatial mapping includes: Where: Definition For regional objectives i Next time t Carbon emissions; Regional targets i The time to reach peak carbon emissions; , Regional targets i The time range for achieving carbon peak T i The starting and ending points of the time; Objective 1 is the baseline scenario of not imposing any measures on the region and continuing the existing policies. Carbon peaking path planning based on genetic algorithm and convolutional neural network; The carbon peaking path planning based on genetic algorithms and convolutional neural networks includes: Step 3.1: Establish a fitness function based on a convolutional neural network and construct metric constraints: in, This represents the regional carbon emission fitness function value. A CNN network for regional carbon emissions; V s Individuals in the population of the set of factors influencing regional carbon emissions generated by the genetic algorithm; This refers to regional carbon emission data. The first in regional carbon emissions j The first influencing factor i Data at each moment; S pos This is a set of positive indicators for regional carbon emissions. S inp A set of inverse indicators for regional carbon emissions; S ratio This represents a set of indicators for the proportion / ratio of regional carbon emissions; ||·|| is a mathematical symbol representing the 2-norm of a vector. Step 3.2: Based on the fitness function and index constraints, use a genetic algorithm to obtain the optimal individual. in, This represents the regional carbon emission fitness function value. A CNN network for regional carbon emissions; V s Individuals in the population of the set of factors influencing regional carbon emissions generated by the genetic algorithm; V best The optimal individual in the set of factors influencing regional carbon emissions obtained by the genetic algorithm represents the carbon peaking path. This refers to regional carbon emission data. The first in regional carbon emissions j The first influencing factor i Data at each moment; S pos This is a set of positive indicators for regional carbon emissions. S inp A set of inverse indicators for regional carbon emissions; S ratio represents a set of indicators representing the proportion / ratio of regional carbon emissions; ||·|| is a mathematical symbol representing the 2-norm of a vector.

2. The regional carbon peaking target design and pathway planning method according to claim 1, characterized in that, The method involves highly adaptive prediction of factors influencing regional carbon emissions, using convolutional neural networks for regional carbon emission prediction. Includes the following steps: 1.

1. Obtain data on factors influencing regional carbon emissions: in: Data set of factors influencing regional carbon emissions; The first in regional carbon emissions j Data on influencing factors; The first in regional carbon emissions j The first influencing factor i Data at each moment; M The number of factors influencing regional carbon emissions; N This represents the number of sampling times for factors influencing regional carbon emissions; the superscript symbol T is a mathematical symbol indicating the transpose of a vector or matrix. 1.

2. Perform logistic regression fitting on each row of the influencing factor dataset. If the T-test is passed, predict the future value of the corresponding influencing factor based on logistic regression; otherwise, predict the future value of the corresponding influencing factor based on grey theory. 1.

3. Using the influencing factor dataset as input and regional carbon emissions as output, train a CNN network and generate the CNN network; input the predicted values ​​of the influencing factor dataset obtained in step 1.2 into the generated CNN network to obtain the predicted values ​​of regional carbon emissions: in: Data set of factors influencing regional carbon emissions; This refers to regional carbon emission data. The first in regional carbon emissions i Data on the moment of impact; A CNN network for regional carbon emissions; N This represents the number of sampling times for regional carbon emissions; the superscript symbol T is a mathematical symbol indicating the transpose of a vector or matrix.

3. A regional carbon peaking target design and pathway planning system, used to execute the method as described in any one of claims 1-2, characterized in that, It includes a carbon emission prediction module, a carbon emission target design module, and a carbon peaking path planning module.

4. The regional carbon peaking target design and pathway planning system according to claim 3, characterized in that: The carbon emission prediction module is used for highly adaptable prediction of factors influencing regional carbon emissions and for regional carbon emission prediction. The carbon emission target design module is used to design carbon peaking targets based on spatial mapping, with carbon peaking as the objective. The carbon peaking path planning module is used to plan carbon peaking paths based on genetic algorithms and convolutional neural networks.

5. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the regional carbon peaking target design and path planning method as described in any one of claims 1 to 2.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the regional carbon peaking target design and path planning method as described in any one of claims 1 to 2.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the regional carbon peaking target design and path planning method as described in any one of claims 1 to 2.

Images