A county classification method and system suitable for energy internet planning

Abstract

The application discloses a county classification method and system suitable for energy internet planning, and the method comprises the following steps: determining external and internal development factors influencing county energy internet planning construction, constructing an evaluation index system, and performing standardized processing on index data; based on a principal component analysis method, synthesizing evaluation indexes of the external indexes and the internal indexes, and constructing a weighted undirected network with each county as a node and a similarity coefficient between counties as a weight; applying a Newman fast algorithm to divide each county into a plurality of communities, and based on a degree centrality index, analyzing typical counties in the communities, summarizing characteristics of various county communities, and realizing county classification. The application classifies counties based on external environmental factors and internal development requirements of county energy internet planning, which is helpful for implementing county energy internet planning according to local conditions, and the construction of the county classification method suitable for energy internet planning.

Description

Technical Field

[0001] This document relates to the field of energy internet planning technology, and in particular to a county-level classification method and system adapted to energy internet planning. Background Technology

[0002] With the development of small towns and the absorption of industrial transfers, county-level economic zones are absorbing a large number of industrial parks and enterprises, resulting in huge energy consumption. However, the county-level energy internet is precisely an area that has received relatively little attention from various stakeholders. The construction of the county-level energy internet is an essential path to support high-quality economic and social development in counties and to build a modern rural energy system. At the same time, the numerous and diverse counties exhibit widespread heterogeneity, making a single energy internet plan unsuitable. Therefore, it is necessary to construct a county-level classification method adapted to energy internet planning, clarify the external conditions and internal foundations of different county-level energy internet plans, provide basic parameters and planning basis for better designing county-level energy internet planning schemes tailored to local conditions, and enhance the scientific and rational nature of county-level energy internet planning. Summary of the Invention

[0003] This specification provides one or more embodiments of a county-level classification method adapted to energy internet planning, including the following steps:

[0004] Identify the external environmental factors and internal development factors affecting the planning and construction of the county-level energy internet, construct an evaluation index system, and standardize the data of each index.

[0005] Based on the principal component analysis method, evaluation indicators that can measure external and internal indicators are synthesized, and a weighted undirected network is constructed with each county under investigation as a node and the similarity coefficient between counties as a weight.

[0006] Based on the weighted undirected network, the Newman fast algorithm is applied to divide each county into several communities. Based on the degree centrality index, the typical counties within the communities are analyzed in detail, the characteristics of various county communities are summarized, the counties are classified, and the county energy internet planning scheme is determined.

[0007] This invention also provides a county-level classification system adapted to energy internet planning, including...

[0008] Influencing Factors Identification Module: Used to determine the external environmental factors and internal development factors affecting the planning and construction of the county-level energy internet;

[0009] Evaluation indicator system construction module: used to construct the evaluation indicator system based on the influencing factor identification module, and to standardize the data of each indicator;

[0010] Network construction module: Used to synthesize evaluation indicators that can measure external and internal indicators based on principal component analysis, and to construct a weighted undirected network with each county under investigation as a node and the similarity coefficient between counties as weights;

[0011] County Classification Module: Based on the weighted undirected network constructed by the network construction module, the Newman fast algorithm is applied to divide each county into several communities. Based on the degree centrality index, the module focuses on analyzing the typical counties within each community, summarizes the characteristics of each type of county community, realizes county classification, and determines the county energy internet planning scheme.

[0012] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the county-level classification method for adapting to the energy internet planning as described in any of the preceding claims.

[0013] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the county-level classification method for adapting to the energy internet planning as described in any of the preceding claims.

[0014] This invention rationally classifies counties based on external environmental factors and internal development requirements for county-level energy internet planning. This helps to promote county-level energy internet planning in a way that is tailored to local conditions. It also constructs a county-level classification method that is compatible with energy internet planning. For governments, it provides a better understanding of county-level economic industries and energy planning and construction, improving the efficiency and scientific nature of government energy planning decisions. For energy companies, it provides important environmental parameters for energy project planning and construction, improving the rationality of energy project planning and project benefits. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in 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 recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating a county-level classification method adapted for energy internet planning, provided for one or more embodiments of this specification;

[0017] Figure 2 A schematic diagram of a county-level classification system framework adapted to energy internet planning, provided for one or more embodiments of this specification;

[0018] Figure 3This is a schematic diagram of the structure of an electronic device provided for one or more embodiments of this specification. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0020] The present invention will now be described in detail with reference to specific embodiments and accompanying drawings.

[0021] Method Implementation Examples

[0022] According to embodiments of the present invention, a county-level classification method adapted to energy internet planning is provided, such as... Figure 1 As shown in the flowchart of the device monitoring display and interaction optimization method for complex scenarios according to an embodiment of the present invention, the method includes the following steps:

[0023] Step S1: Determine the external environmental factors and internal development factors affecting the planning and construction of the county-level energy internet, construct an evaluation index system, and standardize the data of each index. In this embodiment, the external environmental factors and internal development factors affecting the planning and construction of the county-level energy internet are obtained through publicly available data from relevant government departments.

[0024] Step S2: Apply principal component analysis to synthesize evaluation indicators that can measure external and internal indicators, and construct a weighted undirected network with each county under investigation as a node and the similarity coefficient between counties as a weight.

[0025] Step S3: Based on the Newman fast algorithm for community development in the weighted undirected network application complex network analysis, each county is divided into several communities. Based on the degree centrality index, the typical counties within the communities are analyzed in detail, the characteristics of various county communities are summarized, the counties are classified, and the county energy internet planning scheme is determined.

[0026] Classifying counties based on external environmental factors and internal development requirements for county-level energy internet planning helps to implement county-level energy internet planning in a way that suits local conditions. Constructing a county-level classification method adapted to energy internet planning provides governments with a better understanding of county-level economic industries and energy planning and construction, improving the efficiency and scientific nature of government energy planning decisions. For energy companies, it provides important environmental parameters for energy project planning and construction, enhancing the rationality of energy project planning and project benefits.

[0027] In this embodiment, the external environmental factors and internal development factors affecting the planning and construction of the county-level energy internet may specifically include:

[0028] External indicators are constructed from the economic and industrial level, while internal indicators are constructed from the levels of energy production, energy transmission, energy consumption, energy information, and energy value, forming an evaluation indicator system comprising six levels, as shown in Table 1 below:

[0029] 1) Economic and industrial indicators

[0030] At the economic and industrial level, the study primarily examines the economic and industrial development of the county, reflecting the economic and industrial environment factors for the planning and construction of the county's energy internet. It incorporates per capita GDP to reflect the county's economic development level; uses the proportion of the tertiary sector to reflect the sophistication of the county's industrial structure; and considers energy consumption per unit of GDP to measure the input-output efficiency of energy in the county's economy.

[0031] 2) Energy production level indicators

[0032] At the energy production level, the focus is on the development of clean energy and the capacity to guarantee energy and electricity supply in counties. The proportion of clean energy and clean electricity is included to measure the development level of clean energy and clean electricity in counties; the self-sufficiency rate is a commonly used indicator to reflect the capacity to guarantee supply, and the energy self-sufficiency rate and electricity self-sufficiency rate are used to characterize the county's energy and electricity self-sufficiency capacity.

[0033] 3) Energy transmission indicators

[0034] In terms of energy transmission, the focus is on the energy transmission capacity of the county-level energy internet. Electricity, gas, and heat are the main energy sources consumed, and their transmission networks are the main infrastructure for energy and electricity transmission within the county. For electricity, the power grid transmission capacity is used as an indicator; for gas and heat, the coverage rates of the gas network and heat network are considered respectively.

[0035] 4) Energy consumption indicators

[0036] In terms of energy consumption, the main focus is on the consumption level and regulation and security capabilities of the county-level energy internet. Higher electrification and electricity consumption levels indicate higher energy and electricity consumption levels, which are measured using the electrification rate and per capita electricity consumption indicators, respectively. Higher demand responsiveness and energy storage levels indicate stronger energy consumption regulation and security capabilities, which are measured using demand responsiveness and the proportion of energy storage in clean energy installed capacity, respectively.

[0037] 5) Energy information level indicators

[0038] At the energy information level, the main focus is on examining the information collection, transmission, and security levels of the county-level energy internet. The information collection rate directly reflects the information collection capabilities of the energy and power system. The application of digital and intelligent technologies has strengthened this capability, hence it is included in the smart terminal coverage rate indicator. The energy internet is a comprehensive and complex system; the energy information aggregation rate measures the information transmission capabilities between different systems. The network information security index reflects the level of information security in the energy and power system.

[0039] 6) Energy value indicators

[0040] From an energy value perspective, the focus is on measuring the value creation capability of county-level energy internet. This involves identifying new sources and methods of value creation in data value-added services, energy business servitization, revenue growth, and business model innovation. Data value-added services are used to characterize the data value-added capability of the county-level energy internet; the scale of comprehensive energy services characterizes energy business servitization; a common prosperity index characterizes revenue growth; and a business model innovation index characterizes business model innovation.

[0041] Table 1 Evaluation Index System for County-level Energy Internet Planning and Construction

[0042]

[0043]

[0044] Based on the established evaluation indicator system, each indicator should be standardized. The following methods are used for data standardization of quantitative indicators:

[0045] 1) For positive indicators (i.e., the higher the indicator value, the better), the lower limit value x can be determined based on the actual historical data of each indicator. min And determine its expected maximum value as the upper limit value x based on its future projections. max The standardized formula for the indicator is:

[0046]

[0047] 2) For contrarian indicators (i.e., the smaller the indicator, the better), determine its upper limit x based on the actual historical data of each indicator. max And determine the minimum value expected to be reached as the lower limit x based on its future expectations. min The standardized formula for the indicator is:

[0048]

[0049] 3) For appropriate indicators (i.e., the closer the indicator is to a certain critical value, the better), determine the upper and lower limits x based on the actual historical data of each indicator. max x min The expected moderate value x is determined based on its future projections. mid For the appropriateness index, first follow the formula:

[0050] x'=|xx mid | (3)

[0051] Convert the indicator into a contrarian indicator, and then process it as a contrarian indicator.

[0052] In this embodiment, based on the standardized indicators, a weighted undirected network is constructed with each county under investigation as a node and the similarity coefficient between counties as weights, including the following steps:

[0053] Step A1: Construct the sample covariance matrix of the variables:

[0054] This includes p-dimensional variables of secondary indicators, and an n×p sample matrix X constructed from n county samples. (i) Let be the variable for the i-th sample, represent the sample mean; the sample covariance matrix is:

[0055]

[0056] Step A2: Calculate each principal component;

[0057] Let Z1,...,Z p The sample principal components, Z l , l = 1…P can be obtained from vector α l The sample matrix X represents:

[0058] Z l =X·α l (5)

[0059] Seek Z l The objective function with the largest variance, and with α l T ·α l An optimization problem with constraint 1.

[0060]

[0061] The optimization problem is transformed into finding the eigenvalues ​​λ and eigenvariant α of S. l Select the largest eigenvalue λ max and its corresponding eigenvector α max To extract the first principal component Z = α max ·X is a comprehensive measurement index.

[0062] Step A3: Based on the extracted principal component vectors of each county, a complex network is constructed, with each county as a node and the pairwise similarity of vectors between counties as weights; where,

[0063] The distance between two nodes is calculated using the cosine of the included angle.

[0064]

[0065] The higher the similarity of kinetic energy conversion between nodes r and s, the greater the distance P. rs The smaller.

[0066] Then, the b-matching method is applied to set up a network, which connects a node to its b nearest neighbors, thereby constructing a network with distance a. ij It is an undirected, unweighted network of elements.

[0067] In this embodiment, principal component analysis (PCA) is used to transform multiple indicators into a few comprehensive indicators, reducing analytical complexity. By applying PCA and extracting single principal components, systemic variables related to the economic and energy systems that are difficult to manipulate can be constructed.

[0068] In this preferred embodiment, the Newman fast algorithm is applied for network community partitioning. This algorithm is based on the greedy algorithm idea, starting by partitioning each node into a community, and continuously merging communities to maximize the increase or minimize the decrease in the modularity of the community partitions, taking the community partitioning result corresponding to the maximum network modularity. For a complex network with N nodes, the algorithm includes the following steps:

[0069] Step B1: Initialize each node as a community, set the modularity Q = 0, and node v u The degree is k u The network has M edges. Calculate the proportion e of the edges connecting communities u and v out of all edges. uv ,for

[0070]

[0071] α u =k u / (2M) (9)

[0072] Step B2: Gradually merge clubs;

[0073] Merge community u and community v, and calculate the module degree increment after the merger:

[0074] ΔQ uv =e uv +e vu -2α u α v (10)

[0075] Choose to make ΔQ uv Each time, the largest or smallest community pair is added, a merger is performed; after each merger, the corresponding element e is... uv Update, and sum the relevant rows and columns of the merged community pair, then update the module degree Q;

[0076] Step B3: Repeat step B2 to continuously merge communities until they are merged into one community. Then, select the community division result corresponding to Q with the largest modularity as the optimal community division result.

[0077] Specifically, if the optimal community partitioning result is c communities, node v u Belongs to club C v ,δ(v u C v ) for node v u Does it belong to club C? v If the indicator variable is δ(v), then δ(v) u C v In club C v The degree in the middle is

[0078]

[0079] Each club is moderate The highest node is the representative node of the community, and can be determined based on its various dimensions Z. l By making comparisons, we can summarize the characteristics of the community.

[0080] This embodiment of the method focuses on the systematic and differentiated requirements of the external environment and internal development of county-level energy internet planning. It covers external environmental factors such as economic industries, as well as internal influencing factors such as energy supply and demand, information utilization, and value creation. It provides basic parameters and planning basis for better designing county-level energy internet planning schemes tailored to local conditions, thereby improving the scientificity and rationality of county-level energy internet planning.

[0081] System Implementation Examples

[0082] According to embodiments of the present invention, a county-level classification system adapted to energy internet planning is provided, such as... Figure 2 As shown in the figure, a county-level classification system framework for adapting to the energy internet planning according to an embodiment of the present invention is presented. The system includes:

[0083] The influencing factor identification module is used to determine the external environmental factors and internal development factors affecting the planning and construction of the county-level energy internet; among them,

[0084] The evaluation indicator system includes economic and industrial level indicators of external environmental factors; and energy production level indicators, energy transmission level indicators, energy consumption level indicators, energy information level indicators, and energy value level indicators of internal development factors.

[0085] Evaluation indicator system construction module: This module is used to construct the evaluation indicator system based on the influencing factor identification module, and to standardize the data for each indicator. The standardization steps include:

[0086] 1) For positive indicators (i.e., the higher the indicator value, the better), the lower limit value x can be determined based on the actual historical data of each indicator. min And determine its expected maximum value as the upper limit value x based on its future projections. max The standardized formula for the indicator is:

[0087]

[0088] 2) For contrarian indicators (i.e., the smaller the indicator, the better), determine its upper limit x based on the actual historical data of each indicator. max And determine the minimum value expected to be reached as the lower limit x based on its future expectations. min The standardized formula for the indicator is:

[0089]

[0090] 3) For appropriate indicators (i.e., the closer the indicator is to a certain critical value, the better), determine the upper and lower limits x based on the actual historical data of each indicator. max x min The expected moderate value x is determined based on its future projections. mid For the appropriateness index, first follow the formula:

[0091] x'=|xx mid | (14)

[0092] Convert the indicator into a contrarian indicator, and then process it as a contrarian indicator.

[0093] Network construction module: Used to synthesize evaluation indicators that can measure external and internal indicators based on principal component analysis, and to construct a weighted undirected network with each county under investigation as a node and the similarity coefficient between counties as weights; specifically including the following steps:

[0094] Step C1: Construct the sample covariance matrix of the variables:

[0095] This includes p-dimensional variables of secondary indicators, and an n×p sample matrix X constructed from n county samples. (i) Let be the variable for the i-th sample, represent the sample mean; the sample covariance matrix is:

[0096]

[0097] Step C2: Calculate each principal component;

[0098] Let Z1,...,Z p The sample principal components, Z l , l = 1…P can be obtained from vector α i The sample matrix X represents:

[0099] Z l =X·α l (16)

[0100] Seek Z i The objective function with the largest variance, and with α l T ·α l An optimization problem with constraint 1.

[0101]

[0102] The optimization problem is transformed into finding the eigenvalues ​​λ and eigenvariant α of S. l Select the largest eigenvalue λ max and its corresponding eigenvector α max To extract the first principal component Z = α max ·X is a comprehensive measurement index.

[0103] Step C3: Based on the extracted principal component vectors of each county, a complex network is constructed, with each county as a node and the pairwise similarity of vectors between counties as weights; where,

[0104] The distance between two nodes is calculated using the cosine of the included angle.

[0105]

[0106] The higher the similarity of kinetic energy conversion between nodes r and s, the greater the distance P. rs The smaller;

[0107] Then, the b-matching method is applied to set up a network, which connects a node to its b nearest neighbors, thereby constructing a network with distance a. ij It is an undirected, unweighted network of elements.

[0108] County Classification Module: Based on the weighted undirected network constructed by the network construction module, the Newman fast algorithm is applied to divide each county into several communities. Based on the degree centrality index, typical counties within each community are analyzed in detail, and the characteristics of each type of county community are summarized to achieve county classification and determine the county-level energy internet planning scheme. Specific steps include:

[0109] Step D1: Initialize each node as a community, set the modularity Q = 0, and node v u The degree is k u The network has M edges. Calculate the proportion e of the edges connecting communities u and v out of all edges. uv ,for

[0110]

[0111] α u =k u / (2M) (20)

[0112] Step D2: Gradually merge clubs;

[0113] Merge community u and community v, and calculate the module degree increment after the merger:

[0114] ΔQ uv =e uv +e vu -2α u α v (twenty one)

[0115] Choose to make ΔQ uv Each time, the largest or smallest community pair is added, a merger is performed; after each merger, the corresponding element e is... uv Update, and sum the relevant rows and columns of the merged community pair, then update the module degree Q;

[0116] Step D3: Repeat step D2 to continuously merge communities until they are merged into one community. Then, select the community division result corresponding to Q with the largest modularity as the final community division result.

[0117] Specifically, if the optimal community partitioning result is c communities, node v u Belongs to club C v ,δ(v u C v ) for node v u Does it belong to club C? v If the indicator variable is δ(v), then δ(v) u C v In club C v The degree in the middle is

[0118]

[0119] Each club is moderate The highest node is the representative node of the community, and can be determined based on its various dimensions Z. i By making comparisons, we can summarize the characteristics of the community.

[0120] Its working principle is the same as that of the above-described method embodiments, and its specific details can be found in the description of the above embodiments, which will not be repeated here.

[0121] like Figure 3 As shown, the present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements the county-level classification method adapted to the energy internet planning in the above embodiments, or when the computer program is executed by a processor, it implements the county-level classification method adapted to the energy internet planning in the above embodiments.

[0122] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0123] 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 or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A county-level classification method adapted to energy internet planning, characterized in that, Includes the following steps: Identify the external environmental factors and internal development factors affecting the planning and construction of the county-level energy internet, construct an evaluation index system, and standardize the data of each index. Based on principal component analysis, evaluation indicators measuring external and internal indicators are synthesized, and a weighted undirected network is constructed with each county under investigation as a node and the similarity coefficient between counties as weights. The construction of this weighted undirected network includes the following steps: Step A1: Construct the sample covariance matrix of the variables: This includes p-dimensional variables of secondary indicators, and an n×p sample matrix X constructed from n county samples. (i) Let be the variable for the i-th sample, represent the sample mean; the sample covariance matrix is: Step A2: Calculate each principal component; Let Z1,...,Z p The sample principal components, Z i , l = 1…P can be obtained from vector α i The sample matrix X represents: Z l =X·α l Seek Z i The objective function with the largest variance, and with For the constrained optimization problem: The optimization problem is transformed into finding the eigenvalues ​​λ and eigenvariant α of S. l Select the largest eigenvalue λ max and its corresponding eigenvector α max To extract the first principal component Z = α max ·X is a comprehensive measurement index; Step A3: Based on the extracted principal component vectors of each county, a complex network is constructed, with each county as a node and the pairwise similarity of vectors between counties as weights; where, The distance between two nodes is calculated using the cosine of the included angle. Among them, the higher the similarity of kinetic energy conversion between nodes r and s, the greater the distance P. rs The smaller; Then, the b-matching method is applied to set up a network, which connects a node to its b nearest neighbors, thereby constructing a network with distance a. ij An undirected, unweighted network of elements; Based on the weighted undirected network, the Newman fast algorithm is applied to divide each county into several communities. Based on the degree centrality index, the typical counties within the communities are analyzed in detail, the characteristics of various county communities are summarized, the counties are classified, and the county energy internet planning scheme is determined.

2. The county-level classification method for adapting to energy internet planning as described in claim 1, characterized in that, The method described above, based on a weighted undirected network and applying the Newman fast algorithm, divides each county into several communities. It then focuses on analyzing typical counties within each community based on degree centrality, summarizing the characteristics of various county-level communities to achieve county classification. The steps include: Using the Newman fast algorithm, each node is initialized as a community. Communities are merged one by one, and the modularity increment of the merged community is calculated in turn until they are merged into a single community. The community partitioning result corresponding to the community with the largest modularity increment is selected as the final community partitioning result.

3. The county-level classification method for adapting to energy internet planning as described in claim 1, characterized in that, The evaluation index system includes Economic and industrial indicators of external environmental factors; Internal development factors include energy production indicators, energy transmission indicators, energy consumption indicators, energy information indicators, and energy value indicators.

4. The county-level classification method for adapting to energy internet planning as described in claim 1, characterized in that, The method described above, based on a weighted undirected network and applying the Newman fast algorithm, divides each county into several communities. It then focuses on analyzing typical counties within each community based on degree centrality, summarizing the characteristics of various county-level communities to achieve county classification. The steps include: Step B1: Initialize each node as a community, set the modularity Q = 0, and node v u The degree is k u The network has M edges. Calculate the proportion e of the edges connecting communities u and v out of all edges. uv ,for α u =k u / (2M) Step B2: Gradually merge clubs; Merge community u and community v, and calculate the module degree increment after the merger: ΔQ uv =e uv +e vu -2a u a v Choose to make ΔQ uv Each time, the largest or smallest community pair is added, a merger is performed; after each merger, the corresponding element e is... uv Update, and sum the relevant rows and columns of the merged community pair, then update the module degree Q; Step B3: Repeat step B2 to continuously merge communities until they are merged into one community. Then, select the community division result corresponding to Q with the largest modularity as the optimal community division result.

5. A county-level classification system adapted to the energy internet planning, characterized in that, include Influencing Factors Identification Module: Used to determine the external environmental factors and internal development factors affecting the planning and construction of the county-level energy internet; Evaluation indicator system construction module: used to construct the evaluation indicator system based on the influencing factor identification module, and to standardize the data of each indicator; Network construction module: used to synthesize evaluation indicators that can measure external and internal indicators based on principal component analysis, and to construct a weighted undirected network with each county under investigation as a node and the similarity coefficient between counties as weights; the construction of the weighted undirected network with each county under investigation as a node and the similarity coefficient between counties as weights includes the following steps: Step A1: Construct the sample covariance matrix of the variables: This includes p-dimensional variables of secondary indicators, and an n×p sample matrix X constructed from n county samples. (i) Let be the variable for the i-th sample, represent the sample mean; the sample covariance matrix is: Step A2: Calculate each principal component; Let Z1,...,Z p The sample principal components, Z i , l = 1…P can be obtained from vector α i The sample matrix X represents: Z l =X·α l Seek Z i The objective function with the largest variance, and with For the constrained optimization problem: The optimization problem is transformed into finding the eigenvalues ​​λ and eigenvariant α of S. l Select the largest eigenvalue λ max and its corresponding eigenvector α max To extract the first principal component Z = α max ·X is a comprehensive measurement index; Step A3: Based on the extracted principal component vectors of each county, a complex network is constructed, with each county as a node and the pairwise similarity of vectors between counties as weights; where, The distance between two nodes is calculated using the cosine of the included angle. Among them, the higher the similarity of kinetic energy conversion between nodes r and s, the greater the distance P. rs The smaller; Then, the b-matching method is applied to set up a network, which connects a node to its b nearest neighbors, thereby constructing a network with distance a. ij An undirected, unweighted network of elements; County Classification Module: Based on the weighted undirected network constructed by the network construction module, the Newman fast algorithm is applied to divide each county into several communities. Based on the degree centrality index, the typical counties within the communities are analyzed in detail, the characteristics of each type of county community are summarized, the county classification is realized, and the county energy internet planning scheme is determined.

6. The county-level classification system adapted to the energy internet planning as described in claim 5, characterized in that, The specific implementation steps of the county-level classification determination module include: Using the Newman fast algorithm, each node is initialized as a community. Communities are merged one by one, and the modularity increment of the merged community is calculated in turn until they are merged into a single community. The community partitioning result corresponding to the community with the largest modularity increment is selected as the final community partitioning result.

7. The county-level classification system adapted to the energy internet planning as described in claim 5, characterized in that, The evaluation index system includes Economic and industrial indicators of external environmental factors; Internal development factors include energy production indicators, energy transmission indicators, energy consumption indicators, energy information indicators, and energy value indicators.

8. A computer 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 computer program, it implements the county-level classification method for adapting to the energy internet planning as described in any one of claims 1 to 4.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the county-level classification method for adapting to the energy internet planning as described in any one of claims 1 to 4.

Images