Load center coupling correction method and system based on cross-border regional characteristic industry

Abstract

The application discloses a load center coupling correction method and system based on a cross-border area characteristic industry, comprising: collecting data of the cross-border area characteristic industry and preprocessing; establishing a dynamic coupling model, calculating the coupling influence factor of the industry on the load center according to the dynamic coupling model; calculating the coupling correction relationship of the characteristic industry on the load center and verifying. The application constructs a typical energy supply and consumption scene in the southwest cross-border area, analyzes the seasonality and migration of the characteristic industry, reveals the influence of the distribution density and diversity of the industry on the space-time characteristics, and solves the problem that the traditional load center determination and calculation method fails to consider the regional industry characteristics. Meanwhile, the calculation result of the industry influence factor is quantitatively given, the industry correction formula is provided for the determination and calculation of the regional load center, the corrected load center can better reflect the season-industry coupling characteristics of the cross-border area, and the problems of the easy migration and difficult positioning of the multi-energy load center in the border area are solved.

Description

Technical Field

[0001] This invention relates to the field of integrated energy planning technology, specifically to a load center coupling correction method and system based on characteristic industries in border and cross-border regions. Background Technology

[0002] Industries in border and cross-border regions possess strong regional characteristics and exert a crucial influence on regional load. Compared to load centers in other regions, multi-energy load centers in border areas exhibit stronger "seasonal-industry" characteristics, leading to problems such as easy migration and difficulty in locating load centers. Therefore, research on load center coupling correction for characteristic industries in border and cross-border regions is of great importance.

[0003] Accurate load forecasting can provide effective guidance for energy-saving optimization of heating and air conditioning (HVAC) systems. In practical engineering, the heating and cooling loads of HVAC systems are affected by many internal and external environmental factors. Changes in these uncertain factors can cause variations in the heating and cooling loads, thereby affecting the overall system operation. Without accurate HVAC load forecasting and timely optimization control, system energy consumption will increase. If accurate HVAC load data can be obtained in advance, and the operating parameters of the HVAC system can be adjusted and set based on the pre-obtained load data during actual operation, it can not only greatly improve the stability of the HVAC system but also achieve "on-demand cooling / heating," reducing HVAC operating energy consumption.

[0004] To obtain more accurate load forecasts, excellent forecasting methods play a crucial role. Many scholars both domestically and internationally have been striving to innovate and improve load forecasting methods, achieving remarkable results. Different forecasting methods each have their own advantages, but they are also constrained by the conditions of use and thus have certain limitations. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by this invention is that traditional methods for determining and calculating load centers often fail to take into account the influence of regional industrial characteristics. Regional industrial research often focuses on industrial development trends and key concentrated areas, but fails to reveal the impact of industrial distribution density and industrial diversity on spatiotemporal characteristics.

[0007] To address the aforementioned technical problems, this invention provides the following technical solution: a load center coupling correction method based on characteristic industries in border and cross-border areas, comprising: collecting data on characteristic industries in border and cross-border areas and performing preprocessing; establishing a dynamic coupling model, calculating the coupling influence factor of industries on load centers based on the dynamic coupling model; calculating and verifying the coupling correction relationship of characteristic industries on load centers.

[0008] As a preferred embodiment of the load center coupling correction method based on the characteristic industries of border and cross-border regions described in this invention, the data of the characteristic industries includes tourism data, regional characteristic industry data, socio-economic data, and environmental data.

[0009] As a preferred embodiment of the load center coupling correction method based on characteristic industries in border and cross-border regions described in this invention, the preprocessing includes: processing missing values ​​using the mean method, deleting outliers, and normalizing the data.

[0010]

[0011] Where, x i This represents the preprocessed data; x represents the original data; min(x) i ) represents the minimum value of the original data; max(x) i ) represents the maximum value of the original data.

[0012] As a preferred embodiment of the load center coupling correction method based on characteristic industries in border and cross-border areas described in this invention, the dynamic coupling model includes calculating the comprehensive development level through a gradient boosting tree.

[0013]

[0014] Among them, y i,t Indicates the overall development level of region i at time t; M represents the number of trees; γ m h represents the weight of the m-th tree; m x represents the number of the m-th tree; i,t Represents the industry data for region i; d ij Let x represent the distance between industries i and j; when the distance between industries i and j decreases, if industry j has a positive impact on industry i, then x i,t Increase, y i,t Increase; if industry j has a negative impact on industry i, then x i,t Decrease, y i,t Decrease; when the distance between industry i and industry j increases, if industry j has a positive impact on industry i, then x i,t Decrease, y i,t Reduce; if industry j has a negative impact on industry i, then x i,t Increase, y i,t Increase; when x i,t >x i,t-1 hour, This indicates that region i has a positive growth rate, y i,t Increase; when x i,t <x i,t-1hour, This indicates that region i has a negative growth rate, y i,t Decrease; when x i,t =x i,t-1 hour, This indicates that region i has a growth rate that remains unchanged, y i,t By x i,t Decide.

[0015] As a preferred embodiment of the load center coupling correction method based on the characteristic industries of border and cross-border areas described in this invention, the dynamic coupling model further includes measuring the absolute and relative differences of load centers in border and cross-border areas using the standard deviation and coefficient of variation method, and distinguishing the level of industrial development by using the primacy degree.

[0016]

[0017]

[0018] S = y1 / y2

[0019] Where SD represents the standard deviation; n represents the total number of regions; y1 represents the average comprehensive development level of n regions; CV represents the coefficient of variation; S represents the primacy; y1 represents the highest comprehensive development level; and y2 represents the second highest comprehensive development level.

[0020] As a preferred embodiment of the load center coupling correction method based on characteristic industries in border and cross-border areas described in this invention, the coupling influence factor includes: using a simulation platform to simulate and calculate the load center in the border and cross-border area, and using the ratio of the load center migration distance before the influence of characteristic industries to the load center migration distance after the influence of characteristic industries is added as the coupling influence factor of characteristic industries on the load center.

[0021] As a preferred embodiment of the load center coupling correction method based on characteristic industries in border and cross-border areas described in this invention, the coupling correction relationship between the characteristic industries and the load center is expressed as follows:

[0022]

[0023] Q = a·S

[0024] Among them, P i This indicates the coupling correction relationship; Q represents the intensity of the influence of the specialty industry on the load center; Let represent the load center migration distance of regional energy form z at time t; C represents the influence coefficient; a represents the influence coefficient.

[0025] Secondly, this invention also provides a load center coupling correction system based on characteristic industries in border and cross-border areas, comprising: a data acquisition module, which collects data on characteristic industries in border and cross-border areas, processes missing values ​​using the mean method, deletes outliers, normalizes the data, and uploads the processed data to a model building module; a model building module, which constructs a dynamic coupling model based on the collected data, calculates the comprehensive development level through a gradient boosting tree, obtains the coupling influence factor using a simulation platform, and transmits it to a correction relationship module; and a correction relationship module, which calculates and verifies the coupling correction relationship between characteristic industries and load centers based on the data provided by the model building module.

[0026] Thirdly, the present invention also provides a computing device, including: a memory and a processor;

[0027] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the load center coupling correction method based on the characteristic industries of border and cross-border regions.

[0028] Fourthly, the present invention also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the load center coupling correction method based on the characteristic industries of border and cross-border regions.

[0029] The beneficial effects of this invention are as follows: This invention constructs a typical cross-border energy supply and consumption scenario in southwestern China, analyzes the seasonality and migration of characteristic industries, and reveals the impact of industrial distribution density and diversity on spatiotemporal characteristics. This solves the problem that traditional methods for determining and calculating load centers fail to consider regional industrial characteristics. Furthermore, based on the distribution and migration characteristics of characteristic industries, it quantitatively provides calculation results for industrial impact factors, offering an industrial correction formula for determining and calculating regional load centers. This makes the corrected load centers more reflective of the "seasonal-industry" coupling characteristics of cross-border regions, solving the problems of easy migration and difficulty in locating multi-energy load centers in border areas. Attached Figure Description

[0030] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0031] Figure 1 The overall flowchart of a load center coupling correction method based on characteristic industries in border and cross-border areas provided in an embodiment of the present invention;

[0032] Figure 2 A graph showing the standard deviation and coefficient of variation of the tourism industry in the load center coupling correction method based on the characteristic industries of border and cross-border regions provided in the second embodiment of the present invention.

[0033] Figure 3 The standard deviation and coefficient of variation of the sugar industry in the load center coupling correction method based on the characteristic industries of border and cross-border regions provided in the second embodiment of the present invention are shown in the figure. Detailed Implementation

[0034] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0035] Example 1

[0036] Reference Figure 1 As an embodiment of the present invention, a load center coupling correction method based on characteristic industries in border and cross-border areas is provided, including:

[0037] S1: Collect and preprocess data on characteristic industries in border and cross-border areas.

[0038] Furthermore, we conducted research and compiled data on the development and distribution characteristics of major industries in border and cross-border areas, including tourism data, regional characteristic industry data, socio-economic data, and environmental data.

[0039] Tourism data includes tourist arrivals, tourism revenue, and tourism resources. The development level and scale of the tourism industry directly affect the vitality of the regional economy and energy demand, thus influencing the location and scale of load centers. Regional characteristic industry data involves the region's leading industries or industries with local characteristics, such as agricultural product processing and handicraft production. The scale, growth rate, output value, and number of employees in these characteristic industries are all factors that need to be considered, as they affect the region's energy distribution and changes in load centers.

[0040] Due to their unique geographical location and border environment, border and cross-border areas tend to place greater emphasis on the development of tourism and specialty industries. Compared to inland areas, load centers in border and cross-border areas are more affected by specialty industries, which is a factor that must be considered when establishing load centers.

[0041] Furthermore, for the collected raw data, missing values ​​are handled using the mean method, outliers are removed, and the data is normalized.

[0042]

[0043] Where, x i This represents the preprocessed data; x represents the original data; min(x) i ) represents the minimum value of the original data; max(x) i ) represents the maximum value of the original data.

[0044] Normalization can unify various data from distinctive industries in border and cross-border regions to the same scale. For example, tourism data and socioeconomic data may differ greatly in magnitude, but normalization can make them comparable in the model.

[0045] S2: Establish a dynamic coupling model and calculate the coupling impact factor of the industry on the load center based on the dynamic coupling model.

[0046] Furthermore, since the data collected by this invention contains a large amount of continuous, categorical, ordered or unordered data, different types of data have potentially complex relationships, and the development of border and cross-border regions is uneven, there will also be a situation of category imbalance in the data.

[0047] In the coupling model, the interactions between industries can be highly nonlinear. To uniformly reflect the development level of each region, and considering data, a gradient boosting tree is chosen to establish a dynamic coupling model, including calculating the overall development level.

[0048]

[0049] Among them, y i,t Indicates the overall development level of region i at time t; M represents the number of trees; γ m h represents the weight of the m-th tree; m x represents the number of the m-th tree; i,t Represents the industry data for region i; d ij This represents the distance between i and j.

[0050] Considering that regional industrial development is influenced by related industries in neighboring regions, when two regions are close together (i.e., their data points are relatively close in the feature space), it indicates a strong correlation or complementarity between their industries. In this case, the development of one industry may positively influence the development of the other, thus positively impacting the region's overall development level. However, if two regions have identical industries, competition may slow down industrial development. Therefore, spatial correlation features are introduced into the gradient tree to calculate the impact on the region's overall development level.

[0051] When the distance between industry i and industry j decreases, if industry j has a positive impact on industry i, then x i,tIncrease, y i,t Increase; if industry j has a negative impact on industry i, then x i,t Decrease, y i,t Decrease; when the distance between industry i and industry j increases, if industry j has a positive impact on industry i, then x i,t Decrease, y i,t Reduce; if industry j has a negative impact on industry i, then x i,t Increase, y i,t Increase.

[0052] The overall development level is also affected by the growth rate characteristics. For example, if two regions have the same development level in a given year, but one region is growing while the other is declining, the overall development level of the two regions cannot be considered the same because their development prospects are different.

[0053] When x i,t >x i,t-1 hour, This indicates that region i has a positive growth rate, y i,t Increase; when x i,t <x i,t-1 hour, This indicates that region i has a negative growth rate, y i,t Decrease; when x i,t =x i,t-1 hour, This indicates that region i has a growth rate that remains unchanged, y i,t By x i,t Decide.

[0054] Furthermore, primacy can quantitatively reflect the concentration of a certain factor in the largest city. This invention introduces primacy measurement to assess the structural distribution of industries, environmental systems, and coupling coordination in border and cross-border areas, and measures the absolute and relative differences of load centers in border and cross-border areas using the standard deviation and coefficient of variation method.

[0055]

[0056]

[0057] S = y1 / y2

[0058] Where SD represents the standard deviation; n represents the total number of regions; y1 represents the average comprehensive development level of n regions; CV represents the coefficient of variation; S represents the primacy; y1 represents the highest comprehensive development level; and y2 represents the second highest comprehensive development level.

[0059] It should be noted that in the coupled model, the interaction between industries is highly nonlinear. GBT optimizes the loss function by progressively building decision trees. The construction of each new tree is to correct the prediction error of the previous tree. By iteratively learning, it captures the nonlinear relationship between industries, thereby accurately simulating the comprehensive development level of each region.

[0060] S3: Calculate and verify the coupling correction relationship between the characteristic industries and the load center.

[0061] Furthermore, in border and cross-border areas, economic and industrial conditions are constantly changing. This dynamism requires the assessment method to reflect these temporal changes. A simulation platform is used to calculate the load center in these areas. The ratio of the load center migration distance before and after the introduction of the influence of the specialized industry is used as the coupling influence factor of the specialized industry on the load center. This satisfies the dynamism requirement while quantifying the specific degree of influence of the specialized industry on the load center. The coupling correction relationship of the specialized industry on the load center is expressed as follows:

[0062]

[0063] Q = a·S

[0064] Among them, P i This indicates the coupling correction relationship; Q represents the intensity of the influence of the specialty industry on the load center; Let represent the load center migration distance of regional energy form z at time t; C represents the influence coefficient; a represents the influence coefficient.

[0065] Furthermore, historical data is used to verify the accuracy of the model. The model's predictions are compared with actual historical data. The mean squared error (MSE) is used to measure the average size of the difference between the predicted and actual values. The root mean square error (RMSE) is calculated to provide a sense of the scale of the error. The coefficient of determination (R2) is calculated to measure the extent to which the model explains the actual changes.

[0066] This embodiment also provides a load center coupling correction system based on characteristic industries in border and cross-border areas, including: a data acquisition module, which collects data on characteristic industries in border and cross-border areas, processes missing values ​​using the mean method, deletes outliers, normalizes the data, and uploads the processed data to a model building module; a model building module, which constructs a dynamic coupling model based on the collected data, calculates the comprehensive development level using a gradient boosting tree, obtains coupling influence factors using a simulation platform, and transmits them to a correction relationship module; and a correction relationship module, which calculates and verifies the coupling correction relationship between characteristic industries and load centers based on the data provided by the model building module.

[0067] This embodiment also provides a computing device, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the load center coupling correction method based on the characteristic industries of border and cross-border regions proposed in the above embodiment.

[0068] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the load center coupling correction method based on the characteristic industries of border and cross-border areas as proposed in the above embodiments.

[0069] The storage medium proposed in this embodiment and the load center coupling correction method based on the characteristic industries of border and cross-border regions proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0070] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, 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 a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0071] Example 2

[0072] Reference Figure 2 and Figure 3 As an embodiment of the present invention, a load center coupling correction method based on the characteristic industries of border and cross-border regions is provided.

[0073] Through field investigation and data review, tourism environment data for a certain cross-border area in recent years was obtained. The comprehensive development level and related indicators were calculated using this method, and the data are summarized in the table below. The standard deviation and coefficient of variation are shown in the table below. Figure 2 As shown.

[0074] Table 1. Comprehensive Development Level of Tourism Industry System in a Certain Cross-Border Area

[0075]

[0076] The results show that the average annual growth rate of the comprehensive development level of the tourism industry in border areas reached 8.082%. The growth rate during the study period did not exhibit obvious stage-specific characteristics, indicating that the development of tourism-related supporting elements such as economy, ecology, society, and services in border areas was relatively stable, and the related element system was gradually improving, driving the continuous optimization of the tourism industry and its sustained improvement in development level, providing important support for the high-quality development of the tourism industry in border areas. The tourism industry in each region exhibits a relatively obvious uneven development characteristic. Its standard deviation (SD) increased by 46.285% overall, indicating that the absolute differences are gradually widening; while its coefficient of variation (CV) decreased by -37.784% overall, indicating that the relative differences are gradually narrowing. Among them, regions E and G have relatively high comprehensive development levels of the tourism industry. The primacy index (S) of the comprehensive development level of the tourism industry in each region decreased from 1.159 to 1.086, and remained below 2 during the study period, indicating that the scale and structure of the tourism industry development are gradually becoming more reasonable, and related elements are appropriately concentrated within the border areas.

[0077] Meanwhile, a survey was conducted on the local sugarcane industry, and the data, after analysis and collation, is shown in the table below. The standard deviation and coefficient of variation are as follows: Figure 3 As shown.

[0078] Table 2. Comprehensive Development Level of Sugarcane Industry in a Certain Cross-Border Area

[0079]

[0080] The results showed that: (1) The average level of comprehensive development of the sugarcane industry in various border areas continued to improve, from 0.125 in 2010 to 0.425 in 2020, with an average annual increase of 11.774%. The growth rate generally accelerated from slow to fast, with 2015 as the dividing line. This indicates that with the steady development of the social economy and the continuous expansion of land planting scale in border areas, the sugarcane industry in border areas has achieved in-depth development in recent years, and the comprehensive development level has been rapidly improved.

[0081] (2) The overall development level of the sugarcane industry in various regions showed an uneven development trend. The standard deviation increased from 0.072 in 2010 to 0.221 in 2020, an overall increase of 205.64%, indicating that the absolute difference was widening rapidly. The coefficient of variation decreased from 0.579 in 2010 to 0.520 in 2020, an overall decrease of -10.16%, indicating that the relative difference was gradually narrowing. Among them, regions D, F, and G had a relatively high overall development level of the sugarcane industry, with an average value above 0.37 during the study period. Region H had the lowest overall development level of the sugarcane industry, with an average value of only 0.054 during the study period. It was in the early stage of sugarcane industry development and followed the law of diminishing marginal returns. Its sugarcane industry level was low and its scale was small, but its average annual growth rate was as high as 18.543%, far ahead of other regions in the border area, showing strong development momentum.

[0082] (3) The primacy index of the comprehensive development level of the sugar industry in each region has gradually increased from 1.008 in 2010 to 1.202 in 2020. During the study period, it was less than 2, indicating that the scale and structure of the sugar industry in border areas are gradually becoming more concentrated, and the trend of agglomeration of tourism sugar elements is becoming increasingly significant.

[0083] Based on the above analysis and impact assessment results for each industry, the load center in the border and cross-border area was simulated using a simulation platform. The migration changes before and after the addition of industry influence were compared. The ratio of the migration distances before and after the addition of industry influence was used as the coupling influence factor of industry on the load center. The results are summarized as follows:

[0084] Table 3. Analysis of the Intensity of the Impact of the Comprehensive Development Level of the Tourism Industry on Load Center Migration

[0085] 2010 0.339 0.251 0.189 0.309 0.194 0.261 0.393 0.073 0.251 2011 0.319 0.273 0.231 0.364 0.242 0.300 0.454 0.121 0.288 2012 0.412 0.256 0.319 0.410 0.285 0.322 0.442 0.150 0.324 2013 0.456 0.283 0.337 0.452 0.315 0.355 0.485 0.191 0.359 2014 0.502 0.386 0.373 0.512 0.369 0.387 0.595 0.213 0.417 2015 0.560 0.481 0.397 0.553 0.404 0.437 0.646 0.233 0.464 2016 0.601 0.456 0.429 0.585 0.428 0.428 0.694 0.231 0.481 2017 0.631 0.475 0.510 0.659 0.473 0.468 0.692 0.250 0.520 2018 0.642 0.473 0.537 0.680 0.498 0.521 0.696 0.257 0.538 2019 0.594 0.464 0.506 0.737 0.546 0.536 0.725 0.295 0.550 2020 0.633 0.523 0.555 0.801 0.592 0.581 0.737 0.315 0.592 mean 0.517 0.393 0.398 0.551 0.395 0.418 0.596 0.212

[0086] Table 4. Analysis of the Intensity of the Impact of the Comprehensive Development Level of the Sugarcane Industry on Load Center Migration

[0087]

[0088]

[0089] The actual situation is consistent with the industry-load center coupling correction relationship obtained by this invention, proving the feasibility and effectiveness of this invention. This invention constructs a typical cross-border energy supply and consumption scenario, analyzes the seasonality and migration of characteristic industries, reveals the impact of industrial distribution density and industrial diversity on spatiotemporal characteristics, and solves the problem that traditional load center determination and calculation methods fail to take into account regional industrial characteristics.

[0090] Meanwhile, based on the distribution and migration characteristics of characteristic industries, quantitative calculation results of industry impact factors are given, providing an industry correction formula for the determination and calculation of regional load centers. This makes the corrected load centers more reflective of the "seasonal-industry" coupling characteristics of border and cross-border areas, and solves the problems of easy migration and difficulty in locating multi-energy load centers in border areas.

[0091] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A load center coupling correction method based on characteristic industries in border and cross-border areas, characterized in that, include: Collect and preprocess data on distinctive industries in border and cross-border areas; Establish a dynamic coupling model and calculate the coupling impact factor of the industry on the load center based on the dynamic coupling model; Calculate and verify the coupling correction relationship between the specialized industries and the load center; The data on the featured industries include tourism data, regional featured industry data, socio-economic data, and environmental data; The dynamic coupling model includes calculating the overall development level through a gradient boosting tree. in, Indicates region In time The overall level of development; Indicates the number of trees; Indicates the first Weight of the number of trees; Indicates the first Number of trees; Indicates region Industry data; express and The distance between them; when industries and When the distance between industries is shortened, if The industry If it has a positive impact on the industry, then Increase, Increase; if The industry If it has a negative impact on the industry, then reduce, reduce; when industries and When the distance between industries increases, if The industry If it has a positive impact on the industry, then reduce, Reduce; if The industry If it has a negative impact on the industry, then Increase, Increase; when > hour, >0 indicates a region There is a positive growth rate. Increase; when < hour, <0 indicates region There is a negative growth rate. reduce; when = hour, =0 indicates a region One of them had no change in growth rate. Depend on Decide; The coupling influence factor includes: using a simulation platform to simulate and calculate the load center in the border and cross-border area, and using the ratio of the load center migration distance before the addition of the influence of the characteristic industry to the load center migration distance after the addition of the influence of the characteristic industry as the coupling influence factor of the characteristic industry on the load center; The coupling correction relationship between the specialized industry and the load center is expressed as follows: in, Indicates a coupling correction relationship; This indicates the intensity of the impact of specialized industries on load centers; express Time-region energy form The distance of load center migration; Indicates the influence coefficient; This represents the influence coefficient.

2. The load center coupling correction method based on characteristic industries in border and cross-border areas as described in claim 1, characterized in that: The preprocessing includes handling missing values ​​using the mean method, deleting outliers, and normalizing the data. in, This represents the preprocessed data; represents the original data; min represents the minimum value of the original data; max represents the maximum value of the original data.

3. The load center coupling correction method based on characteristic industries in border and cross-border areas as described in claim 2, characterized in that: The dynamic coupling model also includes measuring the absolute and relative differences of load centers in border and cross-border areas using the standard deviation and coefficient of variation method, and distinguishing the level of industrial development using the primacy degree. in, Indicates standard deviation; Indicates the total number of regions; express The average level of comprehensive development in each region; Indicates the coefficient of variation; Indicates primacy; This indicates the highest level of comprehensive development; This indicates the second highest level of comprehensive development.

4. A load center coupling correction system based on characteristic industries in border and cross-border areas, employing the method described in any one of claims 1 to 3, characterized in that, include, The data acquisition module collects data on characteristic industries in border and cross-border areas, uses the mean method to handle missing values, deletes outliers, normalizes the data, and uploads the processed data to the model building module. The model building module constructs a dynamic coupling model based on the collected data, calculates the comprehensive development level through gradient boosting tree, obtains the coupling influence factor using the simulation platform, and transmits it to the correction relationship module. The relationship correction module calculates and verifies the coupling correction relationship between the characteristic industries and the load center based on the data provided by the model building module.

5. A computing device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the method according to any one of claims 1 to 3.

6. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1 to 3.

Images