Personalized Transformation and Construction Methods and Systems for Power Grid Internet of Things Platforms

Abstract

This invention discloses a method and system for personalized transformation of a power grid Internet of Things (IoT) platform, relating to the field of platform personalized transformation. The method includes: dividing the functions of the power grid IoT platform into different parts; obtaining the weight of each function in the entire platform based on expert analysis; determining the comprehensive correlation level of functions of different numbered platforms based on their correlation with each other; setting the weight of each function transformation using a lightweight transformation-incremental upgrade approach; setting a bias coefficient for the personalized transformation cycle of the power grid IoT platform based on the personalized transformation cycle evaluation of each function of different numbered platforms; and establishing a personalized transformation sequence model for the power grid IoT platform to select the optimal sequence of function transformations. The advantage of this invention is that it can obtain the optimal sequence of function transformations based on a specific analysis of the role of each platform function, reducing the risk of system collapse due to large-scale transformations.

Description

Technical Field

[0001] This invention relates to the field of platform customization, specifically to a method and system for customizing and constructing a power grid Internet of Things platform. Background Technology

[0002] The power grid Internet of Things (IoT) platform needs to be customized according to different demand scenarios. However, large-scale transformation based on the original platform can easily lead to the collapse of the original system and reduce the processing capacity of the power grid IoT platform. In order to ensure the normal operation of the power grid IoT platform during the customization transformation, it is necessary to analyze the functions of each part of the platform, comprehensively evaluate the priority of each function, and complete the customization transformation of the power grid IoT platform in batches and step by step. It is of great significance to avoid the "large and comprehensive" customization transformation of the power grid IoT platform.

[0003] Existing technologies mainly transform power grid IoT platforms by investigating pain points in target scenarios through demand profiling. However, these technologies have low universality and can only train profiling models for specific scenarios, making it difficult to extend to other scenarios and requiring repeated modeling. Secondly, profiling is mostly based on static rules and cannot automatically adapt to changes in power grid topology, resulting in poor dynamic adaptability. Consequently, the personalized transformation of power grid IoT platforms is inefficient and lacks universality, which also increases the personalized transformation cycle and platform burden. Summary of the Invention

[0004] To address the aforementioned technical problems, this paper provides a method and system for the personalized transformation of a power grid Internet of Things (IoT) platform. This technical solution solves the problems mentioned in the background technology, such as low universality, the fact that the profile models can only be trained for specific scenarios and are difficult to extend to other scenarios, requiring repeated modeling, and the fact that the profiles are mostly based on static rules and cannot automatically adapt to changes in power grid topology, resulting in poor dynamic adaptability. Consequently, the personalized transformation of the power grid IoT platform is inefficient and lacks universality, and it also increases the personalized transformation cycle and platform burden.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A method for customizing and constructing a power grid Internet of Things (IoT) platform includes:

[0007] The functions of the power grid Internet of Things platform are divided, and the weight of each function in the entire platform is obtained based on expert analysis.

[0008] Based on the degree of correlation between the functions of different numbering platforms, determine the comprehensive level of correlation between the functions of different numbering platforms;

[0009] To adapt to the specific needs of different scenarios, a lightweight modification-incremental upgrade approach is adopted, and the weight of each function modification on the platform is set accordingly.

[0010] Based on the evaluation of the personalized transformation cycle of each function of different numbered platforms, and combined with the weight of the transformation of each function of the platform, a bias coefficient for the personalized transformation cycle of the power grid Internet of Things platform is set.

[0011] Based on a neural network model, a personalized transformation sequence model for the power grid Internet of Things platform is established to select the optimal functional transformation sequence.

[0012] Preferably, the process of dividing the functions of the power grid Internet of Things platform and obtaining the weight of each function in the entire platform based on expert analysis specifically includes:

[0013] Based on the functions of each part of the power grid Internet of Things platform, they are divided and numbered according to their functions;

[0014] Based on expert analysis, the platform functions with different numbers were scored according to the dimension of "technological irreplaceability";

[0015] A comprehensive score for the functions of different numbered platforms is obtained by weighted summation.

[0016] The weight of each function in the overall platform is determined by the proportion of its comprehensive score within the overall platform score.

[0017] Preferably, determining the comprehensive level of the correlation between the functions of different numbered platforms based on their correlation with each other specifically includes:

[0018] Obtain the associated entities and data flow types for different numbering platform functions;

[0019] Based on the construction method of data flow graph, the correlation between functions of different numbered platforms is obtained;

[0020] Based on the degree of correlation between the functions of different numbering platforms, obtain a comprehensive value of the correlation between the functions of a single numbering platform;

[0021] Based on the comprehensive value of the functional relevance of different numbered platforms, a range of level distinctions is set, and the comprehensive value of the functional relevance of different numbered platforms is divided into levels to obtain the comprehensive level of functional relevance of different numbered platforms.

[0022] The comprehensive numerical expression for the functional relevance of a single numbering platform is:

[0023]

[0024] In the formula, For the first A comprehensive value reflecting the functional relevance of each platform numbering system. For the equilibrium constant term, For the first The platform function with the number 1 The degree of relevance between each platform's functions and its functions. For the first The number of correlations between the functions of the numbered platform and the remaining functions of different numbered platforms.

[0025] Preferably, the lightweight transformation-incremental upgrade method specifically includes:

[0026] Based on the personalized transformation requirements for scenario adaptation, the personalized transformation of the power grid Internet of Things platform functions is classified according to the scenario adaptation requirements, resulting in several platform function adaptation categories.

[0027] Based on the frequency and impact of the platform function adaptation categories, determine the emphasis level of personalized transformation of the power grid Internet of Things platform functions;

[0028] Based on the priority level of the personalized modification of the power grid Internet of Things platform functions, the functions of the power grid Internet of Things platform are modified in a personalized manner, one item at a time, in a step-by-step manner.

[0029] Based on the emphasis level of the personalized transformation of the power grid Internet of Things platform functions, the weight of the transformation of each part of the platform functions is set.

[0030] Preferably, the step of setting a bias coefficient for the personalized transformation cycle of the power grid Internet of Things platform based on the evaluation of the personalized transformation cycle of each part of the platform's functions, combined with the weight of the transformation of each part of the platform's functions, specifically includes:

[0031] Based on the difficulty of customizing each function of the platform, obtain an assessment of the customization cycle for each function of different platform numbers.

[0032] Based on the target cycle of the personalized transformation of the power grid Internet of Things platform, and combined with the weight of the transformation of each part of the platform's functions, the target cycle of the personalized transformation of the power grid Internet of Things platform is refined and divided into several personalized transformation cycles of each part of the platform's functions.

[0033] Based on the evaluation and refinement of the personalized transformation cycle of each function of the power grid Internet of Things platform, a bias coefficient for the personalized transformation cycle of the power grid Internet of Things platform is set.

[0034] The expression for the personalized transformation cycle bias coefficient of the power grid Internet of Things platform is as follows:

[0035]

[0036] In the formula, The bias coefficient for the personalized transformation cycle of the power grid Internet of Things platform. The number of cycles for customizing various functions of the platform. For the first Evaluation value of the personalized modification cycle of platform functions for each number. For the customized transformation of the power grid Internet of Things platform The target cycle for personalized modification of platform functions by number.

[0037] Furthermore, this solution proposes a system for the personalized transformation and construction of a power grid Internet of Things (IoT) platform, used to implement the aforementioned method for the personalized transformation and construction of a power grid IoT platform, including:

[0038] A single-function proportioning module is used to divide the functions of the power grid Internet of Things platform and obtain the weight of each function in the entire platform based on expert analysis.

[0039] The functional correlation module is used to determine the comprehensive correlation level of functions of different numbered platforms based on the correlation between their functions.

[0040] The functional transformation bias module is used to adapt to the personalized transformation needs of the scenario. It adopts a lightweight transformation-incremental upgrade approach and sets the weight of each part of the platform's functional transformation. Based on the personalized transformation cycle evaluation of each part of the platform with different numbering, and combined with the weight of each part of the platform's functional transformation, a personalized transformation cycle bias coefficient for the power grid Internet of Things platform is set.

[0041] The comprehensive evaluation module is used to establish a personalized transformation sequence model for the power grid Internet of Things platform based on a neural network model, and to select the optimal sequence of functional transformations.

[0042] Preferably, the functional modification bias module includes:

[0043] The functional modification ratio unit is used to adapt to the personalized modification needs of the scenario, and adopts the lightweight modification-incremental upgrade approach to set the weight of each part of the platform's functional modification.

[0044] The transformation cycle bias unit is used to evaluate the personalized transformation cycle of each part of the platform based on different numbered platforms, and to set the personalized transformation cycle bias coefficient of the power grid Internet of Things platform by combining the weight of the transformation of each part of the platform's functions.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0046] By analyzing the weight of each function in the power grid Internet of Things (IoT) platform, the correlation between functions of different platform numbers, the weight of the transformation of each function, and the bias coefficient of the personalized transformation cycle of the power grid IoT platform, the priority of each function of the platform is comprehensively reflected when carrying out personalized transformation of the power grid IoT platform. After comprehensively evaluating the impact of each function of the platform on the entire system, the optimal sequence of function transformation can be obtained based on the specific analysis of the role of the platform functions, thereby reducing the risk of system collapse caused by large-scale transformation. Attached Figure Description

[0047] Figure 1 This is a flowchart of a method for personalized modification and construction of a power grid Internet of Things platform according to the present invention;

[0048] Figure 2 To divide the functions of the power grid Internet of Things platform of the present invention, a flowchart of the weight of each function in the whole platform is obtained based on the expert analysis method.

[0049] Figure 3 This is a flowchart illustrating the process of determining the comprehensive level of functional correlation between different numbered platforms based on the correlation between their functions, as described in this invention.

[0050] Figure 4 This is a flowchart illustrating the lightweight modification-incremental upgrade method of the present invention;

[0051] Figure 5 To evaluate the personalized transformation cycle of different functions of different numbered platforms in this invention, a flowchart is set up to determine the bias coefficient of the personalized transformation cycle of the power grid Internet of Things platform, taking into account the weight of the transformation of each function of the platform. Detailed Implementation

[0052] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0053] Reference Figure 1 As shown, a method for personalized transformation and construction of a power grid Internet of Things platform includes:

[0054] The functions of the power grid Internet of Things platform are divided, and the weight of each function in the entire platform is obtained based on expert analysis.

[0055] Based on the degree of correlation between the functions of different numbering platforms, determine the comprehensive level of correlation between the functions of different numbering platforms;

[0056] To adapt to the specific needs of different scenarios, a lightweight modification-incremental upgrade approach is adopted, and the weight of each function modification on the platform is set accordingly.

[0057] Based on the evaluation of the personalized transformation cycle of each function of different numbered platforms, and combined with the weight of the transformation of each function of the platform, a bias coefficient for the personalized transformation cycle of the power grid Internet of Things platform is set.

[0058] Based on a neural network model, a personalized transformation sequence model for the power grid Internet of Things platform is established to select the optimal functional transformation sequence.

[0059] This can be explained by the fact that, in order to ensure that the personalized modification of the power grid Internet of Things (IoT) platform does not disrupt the normal operation of the system, or to minimize the impact on system operation, it is necessary to analyze the functions of each part of the platform. Priority should be given to modifying functions that have a smaller impact on system operation, are frequently used, or have a smaller overall impact. This solution analyzes the weight of each function in the power grid IoT platform, the correlation between functions of different platform numbers, the weight of the modification of each function, and the bias coefficient of the personalized modification cycle of the power grid IoT platform. It studies the correlation impact from multiple levels, establishes a personalized modification sequence model for the power grid IoT platform, and selects the optimal sequence of function modifications through model optimization and comprehensive evaluation. This ensures the normal operation of the system and significantly reduces the risk of system collapse caused by large-scale modifications.

[0060] Reference Figure 2 As shown, the division of functions into different parts of the power grid Internet of Things platform, and the determination of the weight of each function in the entire platform based on expert analysis, specifically includes:

[0061] Based on the functions of each part of the power grid Internet of Things platform, they are divided and numbered according to their functions;

[0062] Based on expert analysis, the platform functions with different numbers were scored according to the dimension of "technological irreplaceability";

[0063] A comprehensive score for the functions of different numbered platforms is obtained by weighted summation.

[0064] The weight of each function in the overall platform is determined by the proportion of its comprehensive score within the overall platform score.

[0065] This can be explained by the fact that, during the personalized transformation of the power grid Internet of Things platform, some functions of the platform are "technically irreplaceable" and play a very important role, while other functions are auxiliary functions that can be replaced or have a low degree of impact. Even if they are missing, they will not affect the normal operation of the system. Therefore, this solution uses expert analysis to score the "technological irreplaceability" dimension of platform functions with different numbers, and obtains the comprehensive score of platform functions with different numbers by weighted summation. Then, based on the proportion of the comprehensive score of platform functions with different numbers in the overall comprehensive score of the platform, the weight of each function in the entire platform is obtained.

[0066] The specific expression for obtaining the comprehensive score of different platform functions through weighted summation as described in this solution is as follows:

[0067]

[0068] In the formula, For the first A comprehensive score of the platform's functions. The number of experts. For the first The platform function with the number 1 The weighting of each expert's score. For the first The platform function with the number 1 Each expert provides a rating.

[0069] Reference Figure 3 As shown, determining the comprehensive level of the correlation between the functions of different numbered platforms based on their interrelationships specifically includes:

[0070] Obtain the associated entities and data flow types for different numbering platform functions;

[0071] Based on the construction method of data flow graph, the correlation between functions of different numbered platforms is obtained;

[0072] Based on the degree of correlation between the functions of different numbering platforms, obtain a comprehensive value of the correlation between the functions of a single numbering platform;

[0073] Based on the comprehensive value of the functional relevance of different numbered platforms, a range of level distinctions is set, and the comprehensive value of the functional relevance of different numbered platforms is divided into levels to obtain the comprehensive level of functional relevance of different numbered platforms.

[0074] The comprehensive numerical expression for the functional relevance of a single numbering platform is:

[0075]

[0076] In the formula, For the first A comprehensive value reflecting the functional relevance of each platform numbering system. For the equilibrium constant term, For the first The platform function with the number 1 The degree of relevance between each platform's functions and its functions. For the first The number of correlations between the functions of the numbered platform and the remaining functions of different numbered platforms.

[0077] This can be explained by the fact that when carrying out phased and personalized transformation of the power grid Internet of Things platform, it is necessary to know the correlation between each part of the platform's functions and other functions. Prioritizing the transformation of platform functions with low correlation with other functions can effectively reduce the imbalance of the system. When conducting correlation analysis on each part of the platform's functions, since some functions are affected by the decision-making and scheduling of upstream functions and the data collection of downstream functions, it is necessary to comprehensively analyze the data flow of each part of the platform's functions. Data flow can more accurately reflect the correlation between each part of the platform's functions. Therefore, this solution can effectively obtain the correlation between platform functions with different numbers by adopting the construction method of data flow graph and ensure the accuracy of the correlation.

[0078] The specific steps for constructing the data flow graph are as follows:

[0079] Step 1: Clarify the specific functional boundaries, associated entities, and data flow types of each part of the platform;

[0080] Step 2: Define each function of the platform as a node in the graph, and draw a multi-layer data flow graph based on the density of the convergence of data flows of each function of the platform at the nodes, and take the node with the densest convergence as the top-level node.

[0081] Step 3: Based on the multi-level data flow diagram, identify the important data flow paths that run through the entire multi-level data flow diagram, and designate them as the main data flows;

[0082] Step 4: Based on the functions of each part of the platform, refine the data flow between the functions of each part of the platform, and mark the direction of inflow and outflow;

[0083] Step 5: Based on the flow direction of data flow in each function of the platform, and based on the relationship between two functions receiving traffic from the same data source, obtain the correlation of the node, that is, the degree of correlation between platform functions with different numbers.

[0084] The expression for obtaining the node's relevance based on the relationship between the two functions receiving traffic from the same data source is as follows:

[0085]

[0086] In the formula, , The first The platform functions and the number The input data sequence for each numbering platform function For the first The platform functions and the number The covariance of the input data sequence for each numbered platform function , Don't be the first The platform functions and the number The standard deviation of the input data sequence for each numbered platform function.

[0087] Reference Figure 4 As shown, the lightweight transformation-incremental upgrade method specifically includes:

[0088] Based on the personalized transformation requirements for scenario adaptation, the personalized transformation of the power grid Internet of Things platform functions is classified according to the scenario adaptation requirements, resulting in several platform function adaptation categories.

[0089] Based on the frequency and impact of the platform function adaptation categories, determine the emphasis level of personalized transformation of the power grid Internet of Things platform functions;

[0090] Based on the priority level of the personalized modification of the power grid Internet of Things platform functions, the functions of the power grid Internet of Things platform are modified in a personalized manner, one item at a time, in a step-by-step manner.

[0091] Based on the emphasis level of the personalized transformation of the power grid Internet of Things platform functions, the weight of the transformation of each part of the platform functions is set.

[0092] This can be explained by the fact that when carrying out phased personalized transformation of the power grid IoT platform, it is also necessary to consider the needs of personalized transformation for different scenarios. For scenarios with high frequency and heavy impact, personalized transformation may need to be prioritized to reduce the incompatibility of scenario functions. Therefore, this solution determines the priority level of personalized transformation of power grid IoT platform functions based on the frequency and impact of the platform function adaptation categories. Specifically, it can be analyzed using expert analysis, cross-entropy, or AHP (Analytic Hierarchy Process) to select the best option. Based on the priority level of personalized transformation of power grid IoT platform functions, the proportion of platform functions in the level is analyzed, and the weight of each part of the platform function transformation is set to achieve a better functional match for personalized transformation needs in different scenarios.

[0093] Reference Figure 5 As shown, the evaluation of the personalized transformation cycle of each function of different numbered platforms, combined with the weight of the transformation of each function of the platform, and the setting of the personalized transformation cycle bias coefficient of the power grid Internet of Things platform specifically include:

[0094] Based on the difficulty of customizing each function of the platform, obtain an assessment of the customization cycle for each function of different platform numbers.

[0095] Based on the target cycle of the personalized transformation of the power grid Internet of Things platform, and combined with the weight of the transformation of each part of the platform's functions, the target cycle of the personalized transformation of the power grid Internet of Things platform is refined and divided into several personalized transformation cycles of each part of the platform's functions.

[0096] Based on the evaluation and refinement of the personalized transformation cycle of each function of the power grid Internet of Things platform, a bias coefficient for the personalized transformation cycle of the power grid Internet of Things platform is set.

[0097] The expression for the personalized transformation cycle bias coefficient of the power grid Internet of Things platform is as follows:

[0098]

[0099] In the formula, The bias coefficient for the personalized transformation cycle of the power grid Internet of Things platform. The number of cycles for customizing various functions of the platform. For the first Evaluation value of the personalized modification cycle of platform functions for each number. For the customized transformation of the power grid Internet of Things platform The target cycle for personalized modification of platform functions by number.

[0100] This can be explained by the fact that when carrying out phased and customized transformation of the power grid IoT platform, there is a target period for the customized transformation. Without exceeding this target period, the target period needs to be refined based on the weight of each functional transformation. By calculating the evaluation of the customized transformation period for each functional part of the platform and the refined target period, a deviation coefficient is obtained, i.e., the deviation coefficient. This deviation coefficient is used to determine whether it exceeds a predetermined threshold. If it does, it indicates that the existing target period is insufficient to complete the customized transformation, and the target period needs to be reset. If not, it indicates that the existing target period is sufficient. The deviation coefficient further limits the optimal sequence of functional transformations selected by the system, thereby increasing the accuracy of the system evaluation.

[0101] The process of establishing a personalized transformation sequence model for the power grid Internet of Things platform based on a neural network model and selecting the optimal functional transformation sequence specifically includes:

[0102] The input factors are: the weight of each function in the entire platform, the comprehensive value of the correlation between functions of a single numbered platform, the weight of the transformation of each function in the platform, and the bias coefficient of the personalized transformation cycle of the power grid Internet of Things platform.

[0103] Based on big data, sample data of the personalized transformation sequence and target transformation sequence of different power grid Internet of Things platforms are extracted, and training sample sets and target sample sets are established respectively.

[0104] Based on a neural network model, a personalized transformation sequence model for the power grid Internet of Things (IoT) platform is established. By inputting the weight of each function in the entire platform, the comprehensive value of the correlation between functions of a single numbered platform, the weight of the transformation of each function in the platform, and the bias coefficient data of the personalized transformation cycle of the power grid IoT platform, the optimal sequence of function transformations is selected.

[0105] Existing neural network models can effectively fit different discrete data, automatically learn the complex mapping relationship between input and output, and effectively integrate the weight of each function in the entire platform, the comprehensive value of the functional correlation of a single numbered platform, the weight of the transformation of each function of the platform, and the bias coefficient data of the personalized transformation cycle of the power grid Internet of Things platform by learning from the training sample set and the target sample set. This allows for the automatic iteration to obtain the optimal sequence of functional transformation, thereby reducing human intervention, improving the accuracy of the model's comprehensive evaluation, and reducing the complexity of data fitting.

[0106] Furthermore, based on the same inventive concept as the aforementioned method for personalized transformation and construction of a power grid Internet of Things (IoT) platform, this solution proposes a system for personalized transformation and construction of a power grid IoT platform, comprising:

[0107] A single-function proportioning module is used to divide the functions of the power grid Internet of Things platform and obtain the weight of each function in the entire platform based on expert analysis.

[0108] The functional correlation module is used to determine the comprehensive correlation level of functions of different numbered platforms based on the correlation between their functions.

[0109] The functional transformation bias module is used to adapt to the personalized transformation needs of the scenario. It adopts a lightweight transformation-incremental upgrade approach and sets the weight of each part of the platform's functional transformation. Based on the personalized transformation cycle evaluation of each part of the platform with different numbering, and combined with the weight of each part of the platform's functional transformation, a personalized transformation cycle bias coefficient for the power grid Internet of Things platform is set.

[0110] The comprehensive evaluation module is used to establish a personalized transformation sequence model for the power grid Internet of Things platform based on a neural network model, and to select the optimal functional transformation sequence.

[0111] Functional modifications will focus on the following modules:

[0112] The functional modification ratio unit is used to adapt to the personalized modification needs of the scenario, and adopts the lightweight modification-incremental upgrade approach to set the weight of each part of the platform's functional modification.

[0113] The transformation cycle bias unit is used to evaluate the personalized transformation cycle of each part of the platform based on different numbered platforms, and to set the personalized transformation cycle bias coefficient of the power grid Internet of Things platform by combining the weight of the transformation of each part of the platform's functions.

[0114] In summary, the advantages of this invention are: it can be specifically analyzed based on the function of the platform to obtain the optimal sequence of function modifications, thereby reducing the risk of system crashes caused by large-scale modifications.

[0115] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A method for personalized transformation and construction of a power grid Internet of Things platform, characterized in that, include: The functions of the power grid Internet of Things platform are divided, and the weight of each function in the entire platform is obtained based on expert analysis. Based on the degree of correlation between the functions of different numbering platforms, determine the comprehensive level of correlation between the functions of different numbering platforms; To adapt to the specific needs of different scenarios, a lightweight modification-incremental upgrade approach is adopted, and the weight of each function modification on the platform is set accordingly. Based on the evaluation of the personalized transformation cycle of each function of different numbered platforms, and combined with the weight of the transformation of each function of the platform, a bias coefficient for the personalized transformation cycle of the power grid Internet of Things platform is set. Based on a neural network model, a personalized transformation sequence model for the power grid Internet of Things platform is established to select the optimal functional transformation sequence. The process of establishing a personalized transformation sequence model for the power grid Internet of Things platform based on a neural network model and selecting the optimal functional transformation sequence specifically includes: The input factors are: the weight of each function in the entire platform, the comprehensive value of the correlation between functions of a single numbered platform, the weight of the transformation of each function in the platform, and the bias coefficient of the personalized transformation cycle of the power grid Internet of Things platform. Based on big data, sample data of the personalized transformation sequence and target transformation sequence of different power grid Internet of Things platforms are extracted, and training sample sets and target sample sets are established respectively. Based on a neural network model, a personalized transformation sequence model for the power grid Internet of Things (IoT) platform is established. By inputting the weight of each function in the entire platform, the comprehensive value of the correlation between functions of a single numbered platform, the weight of the transformation of each function in the platform, and the bias coefficient data of the personalized transformation cycle of the power grid IoT platform, the optimal sequence of function transformations is selected.

2. The method for personalized transformation and construction of a power grid Internet of Things platform according to claim 1, characterized in that, The process of dividing the functions of the power grid Internet of Things platform and obtaining the weight of each function in the entire platform based on expert analysis specifically includes: Based on the functions of each part of the power grid Internet of Things platform, they are divided and numbered according to their functions; Based on expert analysis, the platform functions with different numbers were scored according to the dimension of "technological irreplaceability"; A comprehensive score for the functions of different numbered platforms is obtained by weighted summation. The weight of each function in the overall platform is determined by the proportion of its comprehensive score within the overall platform score.

3. The method for personalized transformation and construction of a power grid Internet of Things platform according to claim 2, characterized in that, The determination of the comprehensive level of the correlation between the functions of different numbered platforms specifically includes: Obtain the associated entities and data flow types for different numbering platform functions; Based on the construction method of data flow graph, the correlation between functions of different numbered platforms is obtained; Based on the degree of correlation between the functions of different numbering platforms, obtain a comprehensive value of the correlation between the functions of a single numbering platform; Based on the comprehensive value of the functional relevance of different numbered platforms, a range of level distinctions is set, and the comprehensive value of the functional relevance of different numbered platforms is divided into levels to obtain the comprehensive level of functional relevance of different numbered platforms. The comprehensive numerical expression for the functional relevance of a single numbering platform is: ； In the formula, For the first A comprehensive value reflecting the functional relevance of each platform numbering system. For the equilibrium constant term, For the first The platform function with the number 1 The degree of relevance between each platform's functions and its functions. For the first The number of correlations between the functions of the numbered platform and the remaining functions of different numbered platforms.

4. The method for personalized transformation and construction of a power grid Internet of Things platform according to claim 3, characterized in that, The lightweight transformation – incremental upgrade method specifically includes: Based on the personalized transformation requirements for scenario adaptation, the personalized transformation of the power grid Internet of Things platform functions is classified according to the scenario adaptation requirements, resulting in several platform function adaptation categories. Based on the frequency and impact of the platform function adaptation categories, determine the emphasis level of personalized transformation of the power grid Internet of Things platform functions; Based on the priority level of the personalized modification of the power grid Internet of Things platform functions, the functions of the power grid Internet of Things platform are modified in a personalized manner, one item at a time, in a step-by-step manner. Based on the emphasis level of the personalized transformation of the power grid Internet of Things platform functions, the weight of the transformation of each part of the platform functions is set.

5. The method for personalized transformation and construction of a power grid Internet of Things platform according to claim 4, characterized in that, The assessment of the personalized modification cycle of each function of different numbered platforms, combined with the weight of the modification of each function of the platform, and the setting of the bias coefficient for the personalized modification cycle of the power grid Internet of Things platform specifically include: Based on the difficulty of customizing each function of the platform, obtain an assessment of the customization cycle for each function of different platform numbers. Based on the target cycle of the personalized transformation of the power grid Internet of Things platform, and combined with the weight of the transformation of each part of the platform's functions, the target cycle of the personalized transformation of the power grid Internet of Things platform is refined and divided into several personalized transformation cycles of each part of the platform's functions. Based on the evaluation and refinement of the personalized transformation cycle of each function of the power grid Internet of Things platform, a bias coefficient for the personalized transformation cycle of the power grid Internet of Things platform is set. The expression for the personalized transformation cycle bias coefficient of the power grid Internet of Things platform is as follows: ； In the formula, The bias coefficient for the personalized transformation cycle of the power grid Internet of Things platform. The number of cycles for customizing various functions of the platform. For the first Evaluation value of the personalized modification cycle of platform functions for each number. For the customized transformation of the power grid Internet of Things platform The target cycle for personalized modification of platform functions by number.

6. A system for personalized transformation and construction of a power grid Internet of Things platform, characterized in that, The method for implementing the personalized transformation and construction of the power grid Internet of Things platform as described in any one of claims 1-5 includes: A single-function proportioning module is used to divide the functions of the power grid Internet of Things platform and obtain the weight of each function in the entire platform based on expert analysis. The functional correlation module is used to determine the comprehensive correlation level of functions of different numbered platforms based on the correlation between their functions. The functional transformation bias module is used to adapt to the personalized transformation needs of the scenario. It adopts a lightweight transformation-incremental upgrade approach and sets the weight of each part of the platform's functional transformation. Based on the personalized transformation cycle evaluation of each part of the platform with different numbering, and combined with the weight of each part of the platform's functional transformation, a personalized transformation cycle bias coefficient for the power grid Internet of Things platform is set. The comprehensive evaluation module is used to establish a personalized transformation sequence model for the power grid Internet of Things platform based on a neural network model, and to select the optimal sequence of functional transformations.

7. A personalized transformation and construction system for a power grid Internet of Things platform according to claim 6, characterized in that, The functional modification bias module includes: The functional modification ratio unit is used to adapt to the personalized modification needs of the scenario, and adopts the lightweight modification-incremental upgrade approach to set the weight of each part of the platform's functional modification. The transformation cycle bias unit is used to evaluate the personalized transformation cycle of each part of the platform based on different numbered platforms, and to set the personalized transformation cycle bias coefficient of the power grid Internet of Things platform by combining the weight of the transformation of each part of the platform's functions.

Images