Node credibility evaluation method, system, device and medium for power data governance

Abstract

The application discloses a node credibility evaluation method and system for power data governance, equipment and medium, belongs to the technical field of power data node evaluation, and comprises the following steps: constructing a multi-dimensional index system for evaluating the credibility of power data nodes, collecting index data, calculating the optimal combination weight of evaluation indexes based on the multi-dimensional index data by using a dynamic combination weighting method, normalizing and positively processing the multi-dimensional index data, weighting and aggregating the processed multi-dimensional index data by using the optimal combination weight, calculating the direct credibility, constructing a node correlation graph, calculating the indirect credibility of each node based on the node correlation graph and the direct credibility by using a trust propagation model, fusing the comprehensive credibility, setting a credibility threshold, and matching a processing scheme. The application realizes comprehensive quantitative evaluation and closed-loop management of the credibility of power data nodes, and effectively improves the data quality control and equipment operation foresight.

Description

Technical Field

[0001] This invention relates to the field of power data node evaluation technology, specifically to node credibility evaluation methods, systems, equipment, and media for power data governance. Background Technology

[0002] With the rapid development of smart grid and Internet of Things (IoT) technologies, the number of data nodes in power systems has surged, and data sources have become increasingly diversified. Data governance has become a key link in ensuring the safe and stable operation of the power grid. In the field of power data governance, node credibility assessment, as an important means of data quality control and risk warning, has received widespread attention from academia and industry in recent years. Existing technologies mostly adopt single-dimensional static assessment methods, such as simple weighted scoring based on indicators like data integrity and timeliness, or isolated assessment based on equipment status, which are difficult to comprehensively reflect the true credibility level of power data nodes. At the same time, traditional methods often ignore the correlation between nodes and fail to effectively utilize the characteristics of the power grid topology and communication network for credibility propagation and dynamic updates, resulting in deviations between assessment results and actual operating conditions. In addition, existing technologies often rely on fixed empirical values ​​or single weighting methods in weight allocation, lacking adaptability to dynamic changes in power grid operation modes and making it difficult to achieve accurate assessments under complex operating conditions.

[0003] Current node credibility assessment technologies in power data governance suffer from the following significant shortcomings: First, the multi-dimensional indicator system is incomplete. Most methods focus only on data quality, neglecting key influencing factors such as node status and environmental context, leading to a one-sided assessment perspective. Second, the weight allocation mechanism lacks scientific rigor and dynamism. Traditional methods either rely on subjective experience for weighting, resulting in insufficient objectivity, or depend entirely on objective data while ignoring expert knowledge, making it difficult to balance the advantages of subjective experience and data-driven approaches. Third, existing technologies generally lack the ability to model node relationships, failing to achieve dynamic inference of indirect credibility through trust propagation mechanisms, making it difficult for assessment results to reflect the mutual influence and risk transmission between nodes. Finally, in terms of application of assessment results, existing methods mostly remain at the level of static threshold judgment, lacking a dynamic early warning mechanism based on continuous monitoring, making it difficult to support proactive operation and maintenance decisions such as equipment overhaul. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by this invention are: focusing only on the data quality dimension while ignoring key influencing factors such as node status and environmental context, resulting in a one-sided evaluation perspective; difficulty in balancing the advantages of subjective experience and data-driven approaches; inability to achieve dynamic inference of indirect credibility through trust propagation mechanisms, making it difficult for evaluation results to reflect the mutual influence and risk transmission between nodes; and lack of a dynamic early warning mechanism based on continuous monitoring, making it difficult to support proactive operation and maintenance decisions such as equipment maintenance.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a node credibility assessment method for power data governance, comprising the following steps:

[0007] A multi-dimensional indicator system for evaluating the reliability of power data nodes was constructed, and indicator data was collected. Based on the multi-dimensional indicator data, a dynamic combination weighting method was adopted to calculate the optimal combination weight of the evaluation indicators.

[0008] The multi-dimensional indicator data is normalized and positiveized. The processed multi-dimensional indicator data is then weighted and aggregated using the optimal combination weights to calculate the direct credibility of each power data node.

[0009] A node association graph is constructed based on the relationships between power grid nodes. Based on the node association graph and direct trustworthiness, the indirect trustworthiness of each node is calculated through a trust propagation model. The graphs are then fused to obtain a comprehensive trustworthiness. A trustworthiness threshold is set, and a matching processing scheme is implemented.

[0010] As a preferred embodiment of the node credibility assessment method for power data governance described in this invention, the multi-dimensional indicator system includes data quality dimension, node status dimension, and environmental context dimension.

[0011] The data quality dimension includes data integrity, timeliness, and accuracy; the node status dimension includes equipment health and communication status; and the environmental context dimension includes the current power grid operation mode and regional load level.

[0012] As a preferred embodiment of the node credibility assessment method for power data governance described in this invention, the dynamic combination weighting method includes: calling a matching judgment matrix from a pre-set expert knowledge base according to the current power grid operation mode; calculating a dynamic subjective weight vector using the analytic hierarchy process; calculating an objective weight vector using an improved CRITIC method based on multi-dimensional index data; and obtaining the optimal combination weight vector by solving an optimization problem using game theory.

[0013] The formula for calculating the dynamic subjective weight vector is expressed as follows:

[0014] W s =[w s1,w s2 ,...,w sj ,...,w sm ]

[0015] Among them, w sj Let W be the subjective weight of the j-th indicator, m be the total number of indicators, and W be the weight of the j-th indicator. s For subjective weight vectors;

[0016] The formula for calculating the objective weight vector is expressed as follows:

[0017]

[0018] W o =[w o1 ,w o2 ,...,w oj ,...,w om ]

[0019] Among them, C j Let σ be the total information content of the j-th indicator. j Let r be the standard deviation of the j-th indicator. jk Let r be the Pearson correlation coefficient between the j-th and k-th indicators. jY Let w be the correlation coefficient between the j-th index and the ideal sequence Y. oj Let C be the objective weight of the j-th indicator. k This represents the total information content of the k-th indicator;

[0020] The formula for obtaining the optimal combined weight vector is expressed as:

[0021] min||W'-W s || 2 +||W'-W o || 2

[0022] W' = [w'1, w'2, ..., w j ',...,w' m ]

[0023] Where W' is the optimal combination weight vector, W o W is the objective weight vector. s For the subjective weight vector, ||·|| 2 Let be the Euclidean norm of the vector.

[0024] As a preferred embodiment of the node credibility assessment method for power data governance described in this invention, the calculation of the direct credibility of each power data node includes: normalizing and positiveizing multi-dimensional indicator data; normalizing benefit-type indicators using the range method; and calculating positiveizing and normalizing cost-type indicators; and weighting and aggregating the processed multi-dimensional indicator data using the optimal combination weights to calculate the direct credibility of each power data node.

[0025] The normalization formula is expressed as:

[0026]

[0027] Among them, z ij Let x be the standardized value of the j-th index of the i-th node. ij For the original data value of the j-th indicator of the i-th node, min(x) j ) represents the minimum value of the j-th indicator in the evaluated node, and max(x) j ) represents the maximum value of the j-th indicator in the node being evaluated;

[0028] The forwarding formula is expressed as:

[0029] x′ ij =max(x j )-x ij

[0030] Where, x' ij Let x be the original value of the j-th index of the i-th node after positive transformation. ij This represents the original data value of the j-th indicator for the i-th node;

[0031] The formula for calculating direct credibility is expressed as:

[0032]

[0033] Among them, TD i Let w be the direct confidence level of the i-th node. j ' represents the optimal combination weight for the j-th indicator, z ij Let be the standardized value of the j-th index of the i-th node.

[0034] As a preferred embodiment of the node trust assessment method for power data governance described in this invention, the construction of the node association graph includes constructing a node association graph based on the power grid physical topology and communication network topology, wherein the edge weights in the graph represent the degree of attenuation of trust propagation from node a to node i, and the rules for determining the values ​​of the edge weights are specified.

[0035] As a preferred embodiment of the node credibility assessment method for power data governance described in this invention, the calculation of the indirect credibility of each node includes: using the direct credibility as the initial value, iteratively propagating through the node association graph; in each iteration, the update of the indirect credibility combines the direct credibility of the node and the indirect credibility of the neighboring nodes, and introduces a damping factor and edge weight for adjustment; the iteration process continues until the change in the indirect credibility of all nodes is less than the preset minimum convergence threshold, and then stops, thus obtaining the indirect credibility of each node.

[0036] The formula for iterative propagation is expressed as:

[0037]

[0038] in, Let TD be the indirect confidence level of node i after the (t+1)th iteration. i Let be the direct confidence level of the i-th node, α be the damping factor, and N(i) be the set of neighboring nodes of node i. Let β be the indirect credibility of the l-th neighbor node of node i after the (t+1)-th iteration. ln Let β be the edge weight from node l to node n, N(l) be the set of neighboring nodes of node l, and β be the edge weight from node l to node n. li Let be the edge weight from node i to node l. Let ε be the indirect confidence level of node i after the t-th iteration, and let ε be the preset minimum convergence threshold.

[0039] As a preferred embodiment of the node credibility assessment method for power data governance described in this invention, the method for obtaining comprehensive credibility includes: weighting the direct credibility and the converged indirect credibility using preset harmonic parameters to obtain the comprehensive credibility of each node.

[0040] The formula for calculating overall credibility is expressed as:

[0041] T i =γ·TD i +(1-γ)·TI i

[0042] Among them, T i Let γ be the overall confidence level of node i, and TD be the harmonic parameter. i For the direct trust level of node i, TI i Let i be the indirect credibility of node i;

[0043] The matching processing scheme includes: pre-setting a first threshold and a second threshold, wherein the first threshold is greater than the second threshold; when the overall credibility is lower than the first threshold, the quality inspection process is automatically triggered; when the overall credibility is lower than the second threshold for N consecutive evaluation cycles, an equipment maintenance warning is generated, wherein N is a preset positive integer.

[0044] This invention provides a node credibility assessment system for power data governance.

[0045] To address the aforementioned technical problems, this invention provides the following technical solution: a node credibility assessment system for power data governance, comprising: a multi-source data perception and preprocessing module, a dynamic combined weight calculation module, a networked credibility synthesis module, and a strategy matching module.

[0046] The multi-source data sensing and preprocessing module is used to collect multi-dimensional raw indicator data related to node credibility from heterogeneous data sources of the power grid, and to perform standardization and positive preprocessing on the raw data.

[0047] The dynamic combined weight calculation module is used to integrate subjective weights through the dynamic AHP method, and to obtain objective weights by analyzing the comparative strength, conflict and correlation with the ideal sequence of the indicator data through the improved CRITIC method. The module then uses a game theory model to combine and optimize the subjective and objective weights to solve for the optimal combined weights.

[0048] The networked credibility synthesis module is used to calculate the direct credibility of nodes using weights, construct a node association graph based on the power grid topology, simulate the diffusion process of credibility among nodes through a trust propagation model, calculate the indirect credibility, and weight and fuse the direct and indirect credibility to output the comprehensive credibility score of each node.

[0049] The strategy matching module is used to classify the overall credibility according to a preset threshold and match strategies.

[0050] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, characterized in that the processor executes the computer program to implement the steps of the node credibility assessment method for power data governance.

[0051] The present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the node credibility assessment method for power data governance.

[0052] The beneficial effects of this invention are as follows: By constructing a multi-dimensional indicator system and employing a dynamic combination weighting method to calculate the optimal combination weights, comprehensive coverage and scientific quantification of the credibility assessment of power data nodes are achieved, providing basic data support and weighting basis for subsequent assessments; by normalizing and positively processing the multi-dimensional indicator data and weighting aggregation, direct credibility is calculated, eliminating the influence of differences in indicator dimensions and directions, and improving calculation accuracy and comparability; based on the relationship between power grid nodes, a node association graph is constructed and a trust propagation model is introduced. Iterative calculation is performed by combining direct credibility and indirect credibility of neighboring nodes, realizing the dynamic propagation and updating of credibility in the topology, reflecting the mutual influence and risk transmission mechanism between nodes; by setting edge weight value rules, differentiated modeling is achieved. The degree of trust propagation attenuation under the same communication method reflects the actual impact of the communication medium on the efficiency of trust transmission. Introducing a damping factor and a preset minimum convergence threshold to control the iteration process ensures stable convergence and efficient termination of indirect trust calculation, avoiding iterative oscillations and resource waste. By weighting and fusing direct and indirect trust through harmonic parameters, a comprehensive trust score is obtained, taking into account both the node's own state and the system's interconnected impact, thus improving the comprehensiveness of the evaluation results and their decision-making reference value. Finally, by setting a first and second threshold and matching them with a quality verification process and equipment maintenance early warning mechanism, hierarchical processing and proactive intervention for low-trust nodes are achieved, supporting closed-loop management and risk prevention in power data governance, and significantly improving data quality control and the forward-looking nature of equipment operation and maintenance. Attached Figure Description

[0053] 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 accompanying 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.

[0054] Figure 1 The above is a flowchart of a node credibility assessment method for power data governance provided in one embodiment of the present invention.

[0055] Figure 2 This is a system scheme module diagram of a node credibility assessment system for power data governance provided in one embodiment of the present invention. Detailed Implementation

[0056] 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.

[0057] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a node credibility assessment method for power data governance, including:

[0058] S1: Construct a multi-dimensional indicator system for evaluating the credibility of power data nodes, collect indicator data, and calculate the optimal combination weight of evaluation indicators based on the multi-dimensional indicator data and a dynamic combination weighting method.

[0059] Furthermore, the multi-dimensional indicator system includes data quality dimension, node status dimension, and environmental context dimension;

[0060] The data quality dimension includes data integrity, timeliness, and accuracy; the node status dimension includes equipment health and communication status; and the environmental context dimension includes the current power grid operation mode and regional load level.

[0061] Furthermore, the dynamic combination weighting method includes: calling a matching judgment matrix from a pre-set expert knowledge base according to the current power grid operation mode; calculating a dynamic subjective weight vector using the analytic hierarchy process; calculating an objective weight vector using an improved CRITIC method based on multi-dimensional index data; and obtaining the optimal combination weight vector by solving an optimization problem using game theory.

[0062] The formula for calculating the dynamic subjective weight vector is expressed as follows:

[0063] W s =[w s1 ,w s2 ,...,w sj ,...,w sm ]

[0064] Among them, w sj Let W be the subjective weight of the j-th indicator, m be the total number of indicators, and W be the weight of the j-th indicator. s For subjective weight vectors;

[0065] The formula for calculating the objective weight vector is expressed as follows:

[0066]

[0067] W o =[wo1 ,w o2 ,...,w oj ,...,w om ]

[0068] Among them, C j Let σ be the total information content of the j-th indicator. j Let r be the standard deviation of the j-th indicator. jk Let r be the Pearson correlation coefficient between the j-th and k-th indicators. jY Let w be the correlation coefficient between the j-th index and the ideal sequence Y. oj Let C be the objective weight of the j-th indicator. k This represents the total information content of the k-th indicator;

[0069] The formula for obtaining the optimal combined weight vector is expressed as:

[0070] min||W'-W s || 2 +||W'-W o || 2

[0071] W' = [w'1, w'2, ..., w j ',...,w' m ]

[0072] Where W' is the optimal combination weight vector, W o W is the objective weight vector. s For the subjective weight vector, ||·|| 2 Let be the Euclidean norm of the vector.

[0073] It should be noted that the optimal combination weight of the evaluation indicators is calculated by using a dynamic combination weighting method, which achieves comprehensive coverage and scientific quantification of multiple dimensions such as data quality, node status and environmental context, providing basic data support and weight basis for subsequent credibility assessment.

[0074] S2: Normalize and positiveize the multi-dimensional indicator data, and use the optimal combination weights to perform weighted aggregation on the processed multi-dimensional indicator data to calculate the direct credibility of each power data node.

[0075] The calculation of the direct credibility of each power data node includes normalizing and positiveizing multi-dimensional indicator data, normalizing benefit-type indicators using the range method, and calculating positiveizing and normalizing cost-type indicators. The processed multi-dimensional indicator data is then weighted and aggregated using the optimal combination weights to calculate the direct credibility of each power data node.

[0076] Furthermore, the normalization formula is expressed as:

[0077]

[0078] Among them, z ij Let x be the standardized value of the j-th index of the i-th node. ij For the original data value of the j-th indicator of the i-th node, min(x) j ) represents the minimum value of the j-th indicator in the evaluated node, and max(x) j ) represents the maximum value of the j-th indicator in the node being evaluated;

[0079] The forwarding formula is expressed as:

[0080] x′ ij =max(x j )-x ij

[0081] Where, x' ij Let x be the original value of the j-th index of the i-th node after positive transformation. ij This represents the original data value of the j-th indicator for the i-th node;

[0082] The formula for calculating direct credibility is expressed as:

[0083]

[0084] Among them, TD i Let w be the direct confidence level of the i-th node. j ' represents the optimal combination weight for the j-th indicator, z ij Let be the standardized value of the j-th index of the i-th node.

[0085] It should be noted that by normalizing and positiveizing multi-dimensional indicator data, and using the optimal combination weights to weight and aggregate the processed indicator data, the direct credibility of each power data node is calculated. This achieves standardized processing and comprehensive quantification of different types of indicators, eliminates the impact of differences in indicator dimensions and directions on the evaluation results, and improves the accuracy and comparability of direct credibility calculation.

[0086] S3: Construct a node association graph based on the relationship between power grid nodes, and calculate the indirect trustworthiness of each node based on the node association graph and direct trustworthiness through a trust propagation model, and then merge them to obtain a comprehensive trustworthiness. Set a trustworthiness threshold and match the processing scheme.

[0087] Furthermore, the construction of the node association graph includes constructing a node association graph based on the power grid physical topology and the communication network topology. The edge weights in the graph represent the degree of attenuation of trust propagating from node a to node i, and the rules for determining the values ​​of the edge weights are specified.

[0088] The edge weights are determined as follows: for direct fiber optic connections, the edge weight is 0.9; for power line carrier communication, the edge weight is 0.7; and for wireless public network communication, the edge weight is 0.5.

[0089] The calculation of the indirect credibility of each node includes taking the direct credibility as the initial value, iterating through the node association graph, and in each iteration, the update of the indirect credibility combines the direct credibility of the node and the indirect credibility of the neighboring nodes, and introduces a damping factor and edge weight for adjustment. The iteration process continues until the change of the indirect credibility of all nodes is less than the preset minimum convergence threshold, and then stops to obtain the indirect credibility of each node.

[0090] The formula for iterative propagation is expressed as:

[0091]

[0092] in, Let TD be the indirect confidence level of node i after the (t+1)th iteration. i Let be the direct confidence level of the i-th node, α be the damping factor, and N(i) be the set of neighboring nodes of node i. Let β be the indirect credibility of the l-th neighbor node of node i after the (t+1)-th iteration. ln Let β be the edge weight from node l to node n, N(l) be the set of neighboring nodes of node l, and β be the edge weight from node l to node n. li Let be the edge weight from node i to node l. Let ε be the indirect confidence level of node i after the t-th iteration, and let ε be the preset minimum convergence threshold.

[0093] It should be noted that by constructing a node association graph based on the relationship between power grid nodes, and introducing a trust propagation model to combine direct trustworthiness and indirect trustworthiness of neighboring nodes for iterative calculation, the dynamic propagation and updating of node trustworthiness in the power grid topology is realized, reflecting the mutual influence and risk transmission mechanism between nodes, improving the dynamism and system correlation of trustworthiness assessment results, and by setting edge weight value rules, differentiated modeling of the degree of trust propagation attenuation under different communication methods is realized, reflecting the actual impact of communication medium on trust transmission efficiency.

[0094] Furthermore, obtaining the comprehensive credibility includes weighting the direct credibility and the converged indirect credibility using preset harmonic parameters to obtain the comprehensive credibility of each node.

[0095] The formula for calculating overall credibility is expressed as:

[0096] T i =γ·TD i+(1-γ)·TI i

[0097] Among them, T i Let γ be the overall confidence level of node i, and TD be the harmonic parameter. i For the direct trust level of node i, TI i Let i be the indirect credibility of node i;

[0098] The matching processing scheme includes: pre-setting a first threshold and a second threshold, wherein the first threshold is greater than the second threshold; when the overall credibility is lower than the first threshold, the quality inspection process is automatically triggered; when the overall credibility is lower than the second threshold for N consecutive evaluation cycles, an equipment maintenance warning is generated, wherein N is a preset positive integer.

[0099] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not 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.

[0100] Example 2, refer to Figure 2 This is the second embodiment of the present invention. This embodiment provides a node credibility assessment system for power data governance, including: a multi-source data perception and preprocessing module, a dynamic combined weight calculation module, a networked credibility synthesis module, and a strategy matching module.

[0101] The multi-source data sensing and preprocessing module is used to collect multi-dimensional raw indicator data related to node credibility from heterogeneous data sources of the power grid, and to perform standardization and positive preprocessing on the raw data.

[0102] The dynamic combined weight calculation module is used to integrate subjective weights through the dynamic AHP method, and to obtain objective weights by analyzing the comparative strength, conflict and correlation with the ideal sequence of the indicator data through the improved CRITIC method. The module then uses a game theory model to combine and optimize the subjective and objective weights to solve for the optimal combined weights.

[0103] The networked credibility synthesis module is used to calculate the direct credibility of nodes using weights, construct a node association graph based on the power grid topology, simulate the diffusion process of credibility among nodes through a trust propagation model, calculate the indirect credibility, and weight and fuse the direct and indirect credibility to output the comprehensive credibility score of each node.

[0104] The strategy matching module is used to classify the overall credibility according to a preset threshold and match strategies.

[0105] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not 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.

[0106] Example 3 is the third embodiment of the present invention, which differs from the previous two embodiments in that:

[0107] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0108] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0109] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0110] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

Claims

1. A node credibility assessment method for power data governance, characterized by: include, A multi-dimensional indicator system for evaluating the reliability of power data nodes was constructed, and indicator data was collected. Based on the multi-dimensional indicator data, a dynamic combination weighting method was adopted to calculate the optimal combination weight of the evaluation indicators. The multi-dimensional indicator data is normalized and positiveized. The processed multi-dimensional indicator data is then weighted and aggregated using the optimal combination weights to calculate the direct credibility of each power data node. A node association graph is constructed based on the relationship between power grid nodes. Based on the node association graph and direct trustworthiness, the indirect trustworthiness of each node is calculated through a trust propagation model. The graphs are then fused to obtain a comprehensive trustworthiness. A trustworthiness threshold is set, and a matching processing scheme is implemented. The multi-dimensional indicator system includes data quality, node status, and environmental context dimensions. The data quality dimension includes data integrity, timeliness, and accuracy; the node status dimension includes equipment health and communication status; and the environmental context dimension includes the current power grid operation mode and regional load level. The construction of the node association graph includes constructing the node association graph based on the power grid physical topology and communication network topology. The edge weights in the graph represent the degree of attenuation of trust propagation from node a to node i, and the rules for determining the values ​​of the edge weights are specified. The edge weights are determined as follows: for direct fiber optic connections, the edge weight is 0.9; for power line carrier communication, the edge weight is 0.7; and for wireless public network communication, the edge weight is 0.

5. The calculation of the indirect credibility of each node includes taking the direct credibility as the initial value, iterating through the node association graph, and in each iteration, the update of the indirect credibility combines the direct credibility of the node and the indirect credibility of the neighboring nodes, and introduces a damping factor and edge weight for adjustment. The iteration process continues until the change of the indirect credibility of all nodes is less than the preset minimum convergence threshold, and then stops to obtain the indirect credibility of each node. The formula for iterative propagation is expressed as: in, Let be the indirect confidence level of node i after the (t+1)th iteration. Let be the direct credibility of the i-th node. The damping factor, Let i be the set of neighboring nodes of node i. Let be the indirect credibility of the l-th neighbor node of node i after the t-th iteration. Let the weight of the edge from node l to node n be . Let be the set of neighboring nodes of node l. Let be the edge weight from node i to node l. Let be the indirect confidence level of node i after the t-th iteration. This is the preset minimum convergence threshold.

2. The node credibility assessment method for power data governance as described in claim 1, characterized in that: The dynamic combination weighting method includes: calling a matching judgment matrix from a pre-set expert knowledge base according to the current power grid operation mode; calculating a dynamic subjective weight vector using the analytic hierarchy process; calculating an objective weight vector using an improved CRITIC method based on multi-dimensional index data; and obtaining the optimal combination weight vector by solving an optimization problem using game theory. The formula for calculating the dynamic subjective weight vector is expressed as follows: in, Let m be the subjective weight of the j-th indicator, and m be the total number of indicators. For subjective weight vectors; The formula for calculating the objective weight vector is expressed as follows: in, The total information content of the j-th indicator. Let j be the standard deviation of the j-th indicator. Let be the Pearson correlation coefficient between the j-th and k-th indicators. Let be the correlation coefficient between the j-th index and the ideal sequence Y. Let j be the objective weight of the j-th indicator. This represents the total information content of the k-th indicator; The formula for obtaining the optimal combined weight vector is expressed as: in, The optimal combination weight vector, For objective weight vectors, For subjective weight vectors, Let be the Euclidean norm of the vector.

3. The node credibility assessment method for power data governance as described in claim 2, characterized in that: The calculation of the direct credibility of each power data node includes normalizing and positiveizing multi-dimensional indicator data, normalizing benefit-type indicators using the range method, and calculating positiveizing and normalizing cost-type indicators. The processed multi-dimensional indicator data is then weighted and aggregated using the optimal combination weights to calculate the direct credibility of each power data node. The normalization formula is expressed as: in, Let j be the standardized value of the j-th index of the i-th node. Let j be the original data value of the j-th indicator of the i-th node. Let be the minimum value of the j-th indicator in the node being evaluated. The maximum value of the j-th indicator in the node being evaluated; The forwarding formula is expressed as: in, This represents the original value of the j-th index of the i-th node after positive transformation. This represents the original data value of the j-th indicator for the i-th node; The formula for calculating direct credibility is expressed as: in, Let be the direct credibility of the i-th node. The optimal combination weight for the j-th indicator is... Let be the standardized value of the j-th index of the i-th node.

4. The node credibility assessment method for power data governance as described in claim 3, characterized in that: The process of obtaining the overall credibility includes weighting the direct credibility and the converged indirect credibility using preset harmonic parameters to obtain the overall credibility of each node. The formula for calculating overall credibility is expressed as: in, Let i be the overall credibility of node i. For harmonic parameters, Let be the direct credibility of node i. Let i be the indirect credibility of node i; The matching processing scheme includes: pre-setting a first threshold and a second threshold, wherein the first threshold is greater than the second threshold; when the overall credibility is lower than the first threshold, the quality inspection process is automatically triggered; when the overall credibility is lower than the second threshold for N consecutive evaluation cycles, an equipment maintenance warning is generated, wherein N is a preset positive integer.

5. A node credibility assessment system for power data governance, employing the node credibility assessment method for power data governance as described in any one of claims 1 to 4, characterized in that, include: The module includes a multi-source data perception and preprocessing module, a dynamic combined weight calculation module, a networked credibility synthesis module, and a policy matching module. The multi-source data sensing and preprocessing module is used to collect multi-dimensional raw indicator data related to node reliability from heterogeneous data sources of the power grid, and to perform standardization and positive preprocessing on the raw data. The dynamic combined weight calculation module is used to integrate subjective weights through the dynamic AHP method, and to obtain objective weights by analyzing the comparative strength, conflict and correlation with the ideal sequence of the indicator data through the improved CRITIC method. The module then uses a game theory model to combine and optimize the subjective and objective weights to solve for the optimal combined weights. The networked credibility synthesis module is used to calculate the direct credibility of nodes using weights, construct a node association graph based on the power grid topology, simulate the diffusion process of credibility among nodes through a trust propagation model, calculate the indirect credibility, and weight and fuse the direct and indirect credibility to output the comprehensive credibility score of each node. The strategy matching module is used to classify the overall credibility according to a preset threshold and match strategies.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the node credibility assessment method for power data governance as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the node credibility assessment method for power data governance as described in any one of claims 1 to 4.

Images