CN118260789A - Electric energy meter data storage method and system based on data analysis - Google Patents
Electric energy meter data storage method and system based on data analysis Download PDFInfo
- Publication number
- CN118260789A CN118260789A CN202410690686.5A CN202410690686A CN118260789A CN 118260789 A CN118260789 A CN 118260789A CN 202410690686 A CN202410690686 A CN 202410690686A CN 118260789 A CN118260789 A CN 118260789A
- Authority
- CN
- China
- Prior art keywords
- electric energy
- data
- energy meter
- risk
- meter data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000007405 data analysis Methods 0.000 title claims abstract description 30
- 238000013500 data storage Methods 0.000 title claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 55
- 238000005516 engineering process Methods 0.000 claims abstract description 19
- 238000011156 evaluation Methods 0.000 claims description 53
- 238000004422 calculation algorithm Methods 0.000 claims description 32
- 238000004458 analytical method Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 14
- 230000010354 integration Effects 0.000 claims description 11
- 238000007621 cluster analysis Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000003064 k means clustering Methods 0.000 claims description 5
- 239000006185 dispersion Substances 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 230000001364 causal effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Bioethics (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an electric energy meter data storage method and system based on data analysis, and relates to the technical field of electric energy meter data analysis, wherein the method comprises the following steps: acquiring electric energy meter data by utilizing the internet of things technology, and carrying out integrated processing on the electric energy meter data to obtain an electric energy meter data set; calculating the risk degree of the electric energy meter data set based on an information entropy method, and dividing the electric energy meter data set into different risk grades; establishing edge computing nodes based on geographic position information of the electric energy meter, and carrying out different types of encryption processing on the electric energy meter data sets according to risk division results of the electric energy meter data sets; and transmitting the encrypted electric energy meter data to a cloud server, and compressing and storing the encrypted electric energy meter data. According to the risk division result of the electric energy meter data set, different types of encryption processing are carried out on the data set, the privacy and the safety of the data are protected, the data are prevented from being revealed and tampered, and the requirement of data safety is met.
Description
Technical Field
The invention relates to the technical field of ammeter data analysis, in particular to an ammeter data storage method and system based on data analysis.
Background
With rapid advances in technology, power resources have become an extremely important energy source in social development. Under the background, the continuous improvement of the running reliability of the power grid by utilizing the high and new technology is a core target pursued by the power industry. Particularly, as one of key technologies in the intelligent process of the power grid, the intelligent electric meter greatly promotes the effectiveness of power resource management, and has been widely applied to various fields of society. The intelligent electric energy meter can accurately measure the electricity consumption condition of the user and increase the transparency of the information of the power enterprise, so that the user is endowed with more informed rights. However, in practical applications, electrical energy meter data such as instantaneous voltage, instantaneous current, instantaneous power, and power factor often fail to fully play its potential value. With the progress of meter reading systems, the meter reading frequency of the electric energy meter data is obviously increased, so that the mass data needs to be stored.
Under the current technical background, with the increase of data leakage events, data security and privacy protection have become important issues of public and enterprise concern. Particularly for data related to personal and enterprise sensitive information such as electric energy meter data, security and privacy protection are important. However, the prior art has obvious defects in the aspect of data management of the electric energy meter, and especially lacks effective measures in the aspects of evaluation and management mechanisms of potential risks of the data; this is not limited to technical drawbacks such as the singleness of the encryption method and the inadequacy of the protection measures, but also to policy and methodology drawbacks such as the difficulty of implementing hierarchical management and protection according to the specific risk level of the electric energy meter data. This causes a serious problem in that it is difficult to take effective protection measures to avoid data leakage even when exposed to obvious security threats, thereby forming a remarkable blind area of data security management.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for storing data of an electric energy meter based on data analysis, so as to solve the above-mentioned problem of lack of effective measures in terms of evaluation and management mechanism of potential risk of data.
In order to solve the problems, the invention adopts the following specific technical scheme:
according to an aspect of the present invention, there is provided a data storage method of an electric energy meter based on data analysis, the data storage method of the electric energy meter based on data analysis comprising the steps of:
S1, acquiring electric energy meter data by utilizing an Internet of things technology, and carrying out integrated processing on the electric energy meter data to obtain an electric energy meter data set;
S2, calculating the risk degree of the electric energy meter data set based on an information entropy method, and dividing the electric energy meter data set into different risk grades;
S3, establishing edge computing nodes based on geographical position information of the electric energy meter, and carrying out different types of encryption processing on the electric energy meter data sets according to risk division results of the electric energy meter data sets;
and S4, transmitting the encrypted electric energy meter data to a cloud server, and compressing and storing the encrypted electric energy meter data.
Preferably, the method for obtaining the electric energy meter data by utilizing the internet of things technology and carrying out integrated processing on the electric energy meter data to obtain the electric energy meter data set comprises the following steps:
S11, preprocessing electric energy meter data through a PCA algorithm according to the electric energy meter data acquired by the Internet of things equipment;
s12, carrying out cluster analysis on the preprocessed electric energy meter data by using a clustering algorithm to obtain a plurality of base clustering results;
s13, carrying out quality analysis on the obtained plurality of base clustering results based on a standard mutual information method, and selecting the base clustering results meeting the quality as candidate base clusters;
s14, calculating a final clustering result by a hierarchical clustering method according to the selected candidate base clusters, and taking the final clustering result as an electric energy meter data set.
Preferably, the clustering algorithm is used for carrying out clustering analysis on the preprocessed electric energy meter data, and the step of obtaining a plurality of base clustering results comprises the following steps:
s121, calculating the deviation degree between each two data points by utilizing Euclidean distance according to the preprocessed electric energy meter data;
s122, constructing a deviation matrix according to a deviation calculation result, and calculating the mean deviation of each data point;
S123, selecting a clustering center through a heuristic algorithm according to the mean deviation degree of each data point;
S124, distributing each data point to the nearest clustering center by using a K-means clustering algorithm according to the principle of nearest distance.
Preferably, selecting the cluster center by a heuristic algorithm according to the mean deviation of each data point comprises the following steps:
S1231, selecting the data point with the largest mean deviation as an initial clustering center point,
S1232, calculating the total deviation degree of all data point sets, and selecting the data point with the largest mean deviation degree except the selected clustering center point as a secondary clustering center point;
S1233, after removing the data points selected as the initial clustering centers, selecting the data point with the largest mean deviation degree again, calculating the deviation degree of the data point and the selected clustering center point, taking the data point as a new clustering center if the deviation degree is larger than the total deviation degree of all data point sets, otherwise, selecting the second largest mean deviation degree until the new clustering center is selected;
s1234, repeatedly executing the step S1233 until a predetermined number of cluster centers are selected.
Preferably, the calculation formula for calculating the total deviation of all data point sets is:
；
where G represents the overall degree of deviation for all sets of data points;
n represents the total number of data points in the set of data points;
m represents the dimension number of the data points in the data point set;
x ik represents the value of the kth dimension of data point x i;
x jk represents the value of the kth dimension of data point x j.
Preferably, the quality analysis is carried out on a plurality of obtained basic clustering results based on a standard mutual information method, and the basic clustering results meeting the quality are selected and used as candidate basic clustering, and the method comprises the following steps:
S131, for each basic clustering result, calculating a standard mutual information value between each basic cluster, and calculating an average value of the standard mutual information values of each basic cluster and all other basic clusters according to the standard mutual information value to obtain a consistency value of the basic clusters;
S132, dividing the consistency value of each basic cluster by the maximum value in the consistency values of all the basic clusters to obtain a standardized basic cluster consistency value;
s133, for the standardized consistency value of each base cluster, selecting the base clusters with preset proportion as candidate base clusters meeting the quality requirement after the base clusters are arranged from large to small.
Preferably, calculating the risk degree of the electric energy meter data set based on the information entropy method and dividing the electric energy meter data set into different risk grades comprises the following steps:
S21, collecting historical failure data of the electric energy meter, analyzing factors of failure generated by the historical failure data of the electric energy meter by adopting an event tree system, and determining risk evaluation factors of a data set of the electric energy meter;
s22, evaluating the invalidity score of each risk evaluation factor by using an electric energy meter failure mode and an influence analysis method;
s23, calculating weights of all risk evaluation factors based on an information entropy method, and carrying out weighted summation on failure scores and weights of all risk evaluation factors to obtain risk degrees of an electric energy meter data set;
s24, dividing the electric energy meter data set into different risk levels according to the risk degree of the electric energy meter data set obtained through calculation and a preset risk level standard.
Preferably, calculating the weight of each risk evaluation factor based on the information entropy method includes the following steps:
s231, establishing a risk evaluation factor matrix based on the determined risk evaluation factors;
s232, performing information entropy calculation on each risk evaluation factor in the risk evaluation factor matrix, and evaluating the dispersion degree of each risk evaluation factor;
S233, calculating the information entropy weight of each risk evaluation factor according to the information entropy calculation result;
s234, carrying out normalization processing on the information entropy weight to obtain a final risk evaluation factor weight.
Preferably, the method for establishing the edge computing node based on the geographical position information of the electric energy meter and carrying out different types of encryption processing on the electric energy meter data set according to the risk division result of the electric energy meter data set comprises the following steps:
S31, determining geographic position information of the electric energy meter by utilizing a satellite map technology, analyzing the geographic position information of the electric energy meter, determining the optimal position of the edge computing node and deploying the edge computing node;
s32, determining encryption modes and encryption intensities corresponding to different risk levels according to risk division results of the electric energy meter data set;
S33, encrypting the electric energy meter data set according to the determined encryption mode and encryption strength.
According to another aspect of the present invention, there is provided a data analysis-based electric energy meter data storage system including: the data integration processing module, the risk grade dividing module, the data encryption processing module and the data transmission storage module are sequentially connected with each other;
The data integration processing module is used for acquiring the electric energy meter data by utilizing the internet of things technology and carrying out integration processing on the electric energy meter data to obtain an electric energy meter data set;
The risk level classification module is used for calculating the risk level of the electric energy meter data set based on the information entropy method and classifying the electric energy meter data set into different risk levels;
the data encryption processing module is used for establishing edge computing nodes based on geographic position information of the electric energy meter and carrying out encryption processing of different types on the electric energy meter data set according to risk division results of the electric energy meter data set;
And the data transmission storage module is used for transmitting the encrypted electric energy meter data to the cloud server and compressing and storing the encrypted electric energy meter data.
Compared with the prior art, the invention provides the electric energy meter data storage method and system based on data analysis, which have the following beneficial effects:
(1) According to the invention, the data of the electric energy meter is obtained by utilizing the internet of things technology and is subjected to integrated processing, the scattered data can be integrated into a unified data set, management and analysis are convenient, the risk degree of the data set of the electric energy meter is calculated based on the information entropy method, the data set is divided into different risk grades, the risk degree of the data is recognized and understood, the edge computing node is established based on the geographic position information of the electric energy meter, the data processing and analysis can be carried out nearby at a data generation source, the data transmission delay is reduced, the data processing efficiency and instantaneity are improved, different types of encryption processing are carried out on the data set according to the risk division result of the data set of the electric energy meter, the privacy and the safety of the data are protected, the data leakage and the data tampering are prevented, and the requirement of the data safety is met.
(2) According to the invention, the PCA algorithm is used for preprocessing the data of the electric energy meter, so that the data dimension can be reduced, noise and redundant information can be removed, the problem that the K-means algorithm converges to a local optimal solution can be effectively avoided by selecting the clustering center through the heuristic algorithm, the quality of the clustering result is improved, the quality analysis is carried out on the clustering result based on the standard mutual information method, the consistency and accuracy of different clustering results can be evaluated, thereby selecting a base cluster with higher quality as a candidate base cluster, calculating a final clustering result through the hierarchical clustering method, further merging the candidate base clusters to obtain a more robust and accurate clustering result, and providing a reliable basis for subsequent data processing and analysis.
(3) According to the invention, the historical failure data of the electric energy meter are collected and analyzed by adopting the event tree system, so that various factors causing the failure of the electric energy meter can be comprehensively known, and the risk evaluation factors are determined, the failure property of each risk evaluation factor is evaluated by utilizing the failure mode and the influence analysis method of the electric energy meter, the influence degree of each factor on the failure of the electric energy meter can be quantified, the weight of each risk evaluation factor is calculated based on the information entropy method, the importance and contribution degree of each factor can be objectively evaluated, and the effective weighting treatment on different factors is facilitated, so that potential risk problems can be found in time, and the safety and reliability of the electric energy meter data are ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a flow chart of a method for storing data of an electric energy meter based on data analysis according to an embodiment of the invention;
fig. 2 is a functional block diagram of a data storage system for a power meter based on data analysis in accordance with an embodiment of the present invention.
In the figure:
1. A data integration processing module; 2. a risk level dividing module; 3. a data encryption processing module; 4. and the data transmission storage module.
Detailed Description
In order to make the technical solution of the present application better understood by those skilled in the art, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments of the present application. All other embodiments, based on the embodiments of the application, which would be apparent to one of ordinary skill in the art without undue burden are intended to be within the scope of the application.
According to the embodiment of the invention, an electric energy meter data storage method and system based on data analysis are provided.
The invention will be further described with reference to the accompanying drawings and detailed description, as shown in fig. 1, according to an embodiment of the invention, there is provided a data storage method of an electric energy meter based on data analysis, the data storage method of the electric energy meter based on data analysis including the steps of:
S1, acquiring electric energy meter data by utilizing an Internet of things technology, and carrying out integrated processing on the electric energy meter data to obtain an electric energy meter data set;
As a preferred embodiment, the method for acquiring the electric energy meter data by utilizing the internet of things technology and carrying out integrated processing on the electric energy meter data to obtain an electric energy meter data set comprises the following steps:
S11, preprocessing electric energy meter data through a PCA algorithm according to the electric energy meter data acquired by the Internet of things equipment;
specifically, preprocessing the data of the electric energy meter through the PCA algorithm comprises the following steps:
The average value of each dimension of the data of the electric energy meter is subtracted, and then the standard deviation is divided, so that the data is subjected to standardized processing;
the normalized data are used for calculating a covariance matrix, and the covariance matrix reflects the correlation among the dimensions of the data of the electric energy meter;
By solving eigenvalues and eigenvectors of the covariance matrix, the principal direction (i.e., principal component) of the data can be determined;
Selecting main components according to the magnitude of the characteristic values; in general, the larger the feature value is, the larger the amount of information contained in the corresponding main component is.
Converting the original electric energy meter data into a new feature space composed of selected principal components by multiplying the original electric energy meter data with the feature vector;
The converted data is analyzed to determine which principal components best represent the original energy meter data, while removing those components that contain noise or unimportant information.
S12, carrying out cluster analysis on the preprocessed electric energy meter data by using a clustering algorithm to obtain a plurality of base clustering results;
as a preferred embodiment, the clustering method for clustering the preprocessed electric energy meter data to obtain a plurality of base clustering results comprises the following steps:
s121, calculating the deviation degree between each two data points by utilizing Euclidean distance according to the preprocessed electric energy meter data;
It should be noted that, the calculation of the degree of deviation between each data point in the preprocessed electric energy meter data by using the euclidean distance is a method in the cluster analysis, especially in the K-means clustering algorithm, the euclidean distance can reflect the absolute distance between two data points in the multidimensional space, and is the most intuitive distance measurement mode.
S122, constructing a deviation matrix according to a deviation calculation result, and calculating the mean deviation of each data point;
S123, selecting a clustering center through a heuristic algorithm according to the mean deviation degree of each data point;
It should be noted that, the core ideas of the heuristic algorithm include:
Balance of: in the process of selecting the clustering centers, the balance among the centers is ensured as much as possible, namely, the clustering centers are prevented from being too concentrated in a certain area, and meanwhile, the points too far at the edges are prevented from being selected, so that the clustering accuracy is not affected.
Representative: and each clustering center can represent the data distribution characteristics of the area where the clustering center is located, so that the clustering result has higher accuracy and interpretation.
Through the heuristic algorithm, a proper cluster center can be effectively selected from the data set, and a good foundation is laid for subsequent cluster analysis.
As a preferred embodiment, selecting a cluster center by a heuristic algorithm based on the mean deviation of each data point comprises the steps of:
S1231, selecting the data point with the largest mean deviation as an initial clustering center point,
S1232, calculating the total deviation degree of all data point sets, and selecting the data point with the largest mean deviation degree except the selected clustering center point as a secondary clustering center point;
specifically, the calculation formula for calculating the total deviation of all data point sets is as follows:
；
where G represents the overall degree of deviation for all sets of data points;
n represents the total number of data points in the set of data points;
m represents the dimension number of the data points in the data point set;
x ik represents the value of the kth dimension of data point x i;
x jk represents the value of the kth dimension of data point x j.
S1233, after removing the data points selected as the initial clustering centers, selecting the data point with the largest mean deviation degree again, calculating the deviation degree of the data point and the selected clustering center point, taking the data point as a new clustering center if the deviation degree is larger than the total deviation degree of all data point sets, otherwise, selecting the second largest mean deviation degree until the new clustering center is selected;
s1234, repeatedly executing the step S1233 until a predetermined number of cluster centers are selected.
S124, distributing each data point to the nearest clustering center by using a K-means clustering algorithm according to the principle of nearest distance.
Specifically, according to the distance nearest principle, the method for assigning each data point to the nearest cluster center by using the K-means clustering algorithm comprises the following steps:
According to the initial clustering center selected by the heuristic method before, calculating the distance from each point in the data set to all the selected clustering centers;
each data point is assigned to its nearest cluster center, and once all data points are assigned to the nearest cluster center, the next step is to recalculate the center of each cluster. The new cluster center is typically the mean of all points in the cluster;
and repeatedly executing the reassignment of the data points and the updating process of the clustering centers until the clustering result is stable, namely, the change of the clustering centers of two successive iterations is smaller than a certain preset threshold value, or the preset iteration times are reached.
S13, carrying out quality analysis on the obtained plurality of base clustering results based on a standard mutual information method, and selecting the base clustering results meeting the quality as candidate base clusters;
As a preferred embodiment, the quality analysis is performed on the obtained plurality of base clustering results based on a standard mutual information method, and the selection of the base clustering results meeting the quality and serving as candidate base clusters comprises the following steps:
S131, for each basic clustering result, calculating a standard mutual information value between each basic cluster, and calculating an average value of the standard mutual information values of each basic cluster and all other basic clusters according to the standard mutual information value to obtain a consistency value of the basic clusters;
The mutual information value is an index for measuring the shared information amount of two random variables, and reflects the information amount provided by knowing one variable about the other variable. In cluster analysis, mutual information values are often used to evaluate the quality of a clustered result, especially to measure the similarity between two clustered results.
S132, dividing the consistency value of each basic cluster by the maximum value in the consistency values of all the basic clusters to obtain a standardized basic cluster consistency value;
S133, for the standardized consistency value of each basic cluster, selecting the basic clusters with preset proportion as candidate basic clusters meeting the quality requirement after the basic clusters are arranged from large to small, for example, the first 95% of basic clusters can be selected as candidate basic clusters meeting the quality requirement.
S14, calculating a final clustering result by a hierarchical clustering method according to the selected candidate base clusters, and taking the final clustering result as an electric energy meter data set.
Specifically, according to the selected candidate base clusters, calculating a final clustering result by a hierarchical clustering method, and taking the final clustering result as an electric energy meter data set comprises the following steps:
Calculating the distance between candidate base clusters, and forming a distance matrix from the distance calculation result;
performing hierarchical clustering by using the distance matrix, wherein the hierarchical clustering method gradually merges the data points into larger and larger clusters until a certain stopping criterion is met;
According to the hierarchical clustering result, a proper clustering number can be selected, namely, the cutting position in a tree diagram (the tree diagram shows the relation among different clustering layers) is determined, and the step is to find a proper cutting point by observing the tree diagram, so that the obtained clustering result has a certain degree of separation and the data cannot be excessively segmented;
And taking the clusters obtained according to the selected cutting points as final clustering results, and applying the clustering labels to each data point in the original data set, so as to form the final clustering results of the electric energy meter data set.
S2, calculating the risk degree of the electric energy meter data set based on an information entropy method, and dividing the electric energy meter data set into different risk grades;
As a preferred embodiment, calculating the risk degree of the electric energy meter data set based on the information entropy method and dividing the electric energy meter data set into different risk levels comprises the following steps:
S21, collecting historical failure data of the electric energy meter, analyzing factors of failure generated by the historical failure data of the electric energy meter by adopting an event tree system, and determining risk evaluation factors of a data set of the electric energy meter;
Specifically, collecting historical failure data of the electric energy meter, analyzing factors of failure generated by the historical failure data of the electric energy meter by adopting an event tree system, and determining risk evaluation factors of a data set of the electric energy meter, wherein the risk evaluation factors comprise the following steps:
Collecting historical failure data of the electric energy meter from channels such as maintenance records, fault reports, maintenance logs and the like of the electric energy meter;
Constructing an event tree by utilizing collected historical failure data, wherein the event tree is a graphical analysis tool used for representing possible paths and related causal relationships of system failure, determining the root cause of the failure of the electric energy meter and representing the root cause as a top event or a root node of the event tree;
In the event tree, various factors causing the failure are identified according to different paths and possible reasons of the failure of the electric energy meter, and the factors are represented as intermediate events or leaf nodes in the event tree;
analyzing the constructed event tree, and determining the causal relationship and the influence degree among all the factors;
And determining key factors influencing the failure of the electric energy meter according to the analysis result of the event tree, wherein the factors are risk evaluation factors.
S22, evaluating the invalidity score of each risk evaluation factor by using an electric energy meter failure mode and an influence analysis method;
It should be noted that, for each evaluation factor, a possible failure mode is identified, where the failure mode refers to a possible failure mode of the electric energy meter under a specific condition, for example, a short circuit, a data transmission error, inaccurate reading, etc., and the possible results of each failure mode are analyzed, including an influence on the performance of the electric energy meter, a potential threat to the safety of users and the power grid, a maintenance cost, and an influence on reputation, etc.
Evaluating influence factors of each failure mode, determining the possibility and influence degree of the influence factors on the failure, distributing corresponding failure scores for each failure mode according to the possibility and influence degree of the failure, and evaluating the failure modes through methods such as expert evaluation, historical data analysis, experimental test and the like; and assigning the invalidity scores to corresponding evaluation factors to reflect the contribution degree of the factors to the failure of the electric energy meter.
S23, calculating weights of all risk evaluation factors based on an information entropy method, and carrying out weighted summation on failure scores and weights of all risk evaluation factors to obtain risk degrees of an electric energy meter data set;
As a preferred embodiment, calculating the weight of each risk assessment factor based on the information entropy method includes the steps of:
s231, establishing a risk evaluation factor matrix based on the determined risk evaluation factors;
s232, performing information entropy calculation on each risk evaluation factor in the risk evaluation factor matrix, and evaluating the dispersion degree of each risk evaluation factor;
For each risk evaluation factor, calculating the specific gravity or probability distribution of the risk evaluation factor in the whole according to the normalized evaluation value, and calculating the information entropy by multiplying the product of the probability distribution of each factor and the logarithmic value, wherein the information entropy measures the uncertainty or the dispersion degree of the risk evaluation factor in the sample. The higher the information entropy is, the more the values of the representation factors are dispersed, and the more the data in the sample are diversified; the lower the information entropy, the more concentrated the value of the representation factor, and the more consistent the data in the sample.
S233, calculating the information entropy weight of each risk evaluation factor according to the information entropy calculation result;
What needs to be stated is that the information entropy value of each factor is divided by the sum of the information entropy values of all the factors to obtain the information entropy weight of each factor; if the entropy of a factor is high, its entropy weight will typically be high, because of its higher uncertainty or degree of variation in the sample, and the impact on the overall risk assessment.
S234, carrying out normalization processing on the information entropy weight to obtain a final risk evaluation factor weight.
S24, dividing the electric energy meter data set into different risk levels according to the risk degree of the electric energy meter data set obtained through calculation and a preset risk level standard.
Specifically, a set of risk level criteria is preset based on industry specifications or expertise, and it is common practice to divide risk levels into three levels, including low risk, medium risk, and high risk levels. And then, according to the calculated risk degree of the electric energy meter data set, each data point or each sample in the data set is distributed into a corresponding risk level.
Specifically, the classification may be performed according to a predetermined threshold or score range, for example, if the risk level is below a certain threshold, assigning the data point to a low risk level; assigning a risk level to the risk level if the risk level is within a certain range; if the risk level is higher than another threshold value, the risk level is allocated to a high risk level, and the dividing method can be adjusted and optimized according to actual conditions so as to meet specific requirements and management requirements.
S3, establishing edge computing nodes based on geographical position information of the electric energy meter, and carrying out different types of encryption processing on the electric energy meter data sets according to risk division results of the electric energy meter data sets;
as a preferred embodiment, establishing an edge computing node based on geographical position information of the electric energy meter, and performing different types of encryption processing on the electric energy meter data set according to risk division results of the electric energy meter data set, wherein the method comprises the following steps:
S31, determining geographic position information of the electric energy meter by utilizing a satellite map technology, analyzing the geographic position information of the electric energy meter, determining the optimal position of the edge computing node and deploying the edge computing node;
It should be noted that, the geographic position information of the electric energy meter is visualized by using satellite map technology (such as google map, hundred degree map, etc.); through the satellite map, the distribution condition of the electric energy meter, the conditions of the surrounding environment such as the terrain, the road and the like can be intuitively known.
Analyzing the geographical position information of the electric energy meter, and considering the following factors: density distribution of the electric energy meter, population density of the area, electricity consumption requirement, network connectivity and communication infrastructure;
Combining geographical position information and analysis results of the electric energy meter, determining an optimal position of an edge computing node, wherein the optimal position is possibly positioned near a dense area of the electric energy meter, so that data transmission delay and network congestion are reduced, and data processing efficiency is improved;
according to the determined optimal position, the edge computing nodes are deployed, so that the edge computing nodes can fully cover the target area, and can effectively communicate and exchange data with the electric energy meter.
S32, determining encryption modes and encryption intensities corresponding to different risk levels according to risk division results of the electric energy meter data set;
different layers of encryption processing are adopted according to the risk level of the data of the electric energy meter, for example, the data with low risk level is subjected to primary encryption processing, the data with high risk level is subjected to secondary encryption processing, and the like, and the method is called multi-layer encryption or cascade encryption. The specific implementation mode is as follows:
Encryption of low risk level data: for low risk level electric energy meter data, a simpler encryption algorithm, such as AES or DES in a symmetric encryption algorithm, can be selected, and the data is encrypted by using a key.
Data encryption of medium risk level: for power meter data at risk level, more complex encryption algorithms, such as RSA, may be selected. After the data is encrypted once, the encrypted data is encrypted again for the second time.
High risk level data encryption: for high risk levels of power meter data, a higher level of security may be required, a combination of multiple encryption algorithms may be considered, or a longer key length may be used. The encryption process may be performed again on the data that has been encrypted one or more times to increase the security of the data.
S33, encrypting the electric energy meter data set according to the determined encryption mode and encryption strength.
And S4, transmitting the encrypted electric energy meter data to a cloud server, and compressing and storing the encrypted electric energy meter data.
Specifically, the method for transmitting the encrypted electric energy meter data to the cloud server and compressing and storing the encrypted electric energy meter data comprises the following steps:
The encrypted electric energy meter data are transmitted to a cloud server by using a safe communication protocol (such as HTTPS), so that confidentiality and integrity of the data in the transmission process are ensured;
Before data transmission, compressing the encrypted electric energy meter data to reduce the time of data transmission and the consumption of network bandwidth;
Storing the compressed encrypted data in a secure storage area on a cloud server, such as a database or an object storage service;
The stored encrypted data is backed up regularly to prevent the data from being lost or damaged, ensure that the backup data is consistent with the original data and can be quickly recovered when needed;
monitoring the storage and transmission process of the encrypted data on the cloud server, and timely finding and coping with abnormal conditions.
As shown in fig. 2, according to an embodiment of the present invention, there is provided a data analysis-based electric energy meter data storage system including: the data integration processing module 1, the risk level dividing module 2, the data encryption processing module 3 and the data transmission storage module 4 are sequentially connected with each other;
The data integration processing module 1 is used for acquiring electric energy meter data by utilizing the internet of things technology and carrying out integration processing on the electric energy meter data to obtain an electric energy meter data set;
The risk level dividing module 2 is used for calculating the risk level of the electric energy meter data set based on an information entropy method and dividing the electric energy meter data set into different risk levels;
The data encryption processing module 3 is used for establishing edge computing nodes based on geographical position information of the electric energy meter and carrying out encryption processing of different types on the electric energy meter data set according to risk division results of the electric energy meter data set;
and the data transmission storage module 4 is used for transmitting the encrypted electric energy meter data to the cloud server and compressing and storing the encrypted electric energy meter data.
In summary, by means of the technical scheme, the distributed data can be integrated into a unified data set by acquiring the electric energy meter data and performing integrated processing through the Internet of things technology, management and analysis are convenient, the risk degree of the electric energy meter data set is calculated based on an information entropy method, the data set is divided into different risk levels, the risk degree of the data is recognized and understood, an edge computing node is established based on geographic position information of the electric energy meter, data processing and analysis can be performed nearby at a data generation source, data transmission delay is reduced, data processing efficiency and instantaneity are improved, different types of encryption processing are performed on the data set according to risk division results of the electric energy meter data set, privacy and safety of the data are protected, data leakage and tampering are prevented, and requirements of data safety are met; according to the invention, the PCA algorithm is used for preprocessing the data of the electric energy meter, so that the data dimension can be reduced, noise and redundant information can be removed, the clustering center is selected through the heuristic algorithm, the problem that the K-means algorithm converges to a local optimal solution can be effectively avoided, the quality of a clustering result is improved, the quality analysis is carried out on the clustering result based on the standard mutual information method, the consistency and the accuracy of different clustering results can be evaluated, thereby selecting a base cluster with higher quality as a candidate base cluster, calculating a final clustering result through the hierarchical clustering method, further merging the candidate base clusters to obtain a more robust and accurate clustering result, and providing a reliable basis for subsequent data processing and analysis; according to the invention, the historical failure data of the electric energy meter are collected and analyzed by adopting the event tree system, so that various factors causing the failure of the electric energy meter can be comprehensively known, and the risk evaluation factors are determined, the failure property of each risk evaluation factor is evaluated by utilizing the failure mode and the influence analysis method of the electric energy meter, the influence degree of each factor on the failure of the electric energy meter can be quantified, the weight of each risk evaluation factor is calculated based on the information entropy method, the importance and contribution degree of each factor can be objectively evaluated, and the effective weighting treatment on different factors is facilitated, so that potential risk problems can be found in time, and the safety and reliability of the electric energy meter data are ensured.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. The electric energy meter data storage method based on the data analysis is characterized by comprising the following steps of:
S1, acquiring electric energy meter data by utilizing an Internet of things technology, and carrying out integrated processing on the electric energy meter data to obtain an electric energy meter data set;
S2, calculating the risk degree of the electric energy meter data set based on an information entropy method, and dividing the electric energy meter data set into different risk grades;
S3, establishing edge computing nodes based on geographical position information of the electric energy meter, and carrying out different types of encryption processing on the electric energy meter data sets according to risk division results of the electric energy meter data sets;
and S4, transmitting the encrypted electric energy meter data to a cloud server, and compressing and storing the encrypted electric energy meter data.
2. The method for storing data of an electric energy meter based on data analysis according to claim 1, wherein the steps of obtaining the data of the electric energy meter by using the internet of things technology, and performing integrated processing on the data of the electric energy meter to obtain the data set of the electric energy meter comprise the following steps:
S11, preprocessing electric energy meter data through a PCA algorithm according to the electric energy meter data acquired by the Internet of things equipment;
s12, carrying out cluster analysis on the preprocessed electric energy meter data by using a clustering algorithm to obtain a plurality of base clustering results;
s13, carrying out quality analysis on the obtained plurality of base clustering results based on a standard mutual information method, and selecting the base clustering results meeting the quality as candidate base clusters;
s14, calculating a final clustering result by a hierarchical clustering method according to the selected candidate base clusters, and taking the final clustering result as an electric energy meter data set.
3. The method for storing data of an electric energy meter based on data analysis according to claim 2, wherein the step of performing cluster analysis on the preprocessed data of the electric energy meter by using a clustering algorithm to obtain a plurality of base cluster results comprises the steps of:
s121, calculating the deviation degree between each two data points by utilizing Euclidean distance according to the preprocessed electric energy meter data;
s122, constructing a deviation matrix according to a deviation calculation result, and calculating the mean deviation of each data point;
S123, selecting a clustering center through a heuristic algorithm according to the mean deviation degree of each data point;
S124, distributing each data point to the nearest clustering center by using a K-means clustering algorithm according to the principle of nearest distance.
4. A method for storing data in an electric energy meter based on data analysis according to claim 3, wherein the selecting a cluster center by a heuristic algorithm according to the mean deviation of each data point comprises the following steps:
S1231, selecting the data point with the largest mean deviation as an initial clustering center point,
S1232, calculating the total deviation degree of all data point sets, and selecting the data point with the largest mean deviation degree except the selected clustering center point as a secondary clustering center point;
S1233, after removing the data points selected as the initial clustering centers, selecting the data point with the largest mean deviation degree again, calculating the deviation degree of the data point and the selected clustering center point, taking the data point as a new clustering center if the deviation degree is larger than the total deviation degree of all data point sets, otherwise, selecting the second largest mean deviation degree until the new clustering center is selected;
s1234, repeatedly executing the step S1233 until a predetermined number of cluster centers are selected.
5. The method for storing data in an electric energy meter based on data analysis according to claim 4, wherein the calculation formula for calculating the total deviation of all data point sets is:
；
where G represents the overall degree of deviation for all sets of data points;
n represents the total number of data points in the set of data points;
m represents the dimension number of the data points in the data point set;
x ik represents the value of the kth dimension of data point x i;
x jk represents the value of the kth dimension of data point x j.
6. The method for storing electric energy meter data based on data analysis according to claim 2, wherein the quality analysis is performed on the obtained plurality of base clustering results based on the standard mutual information method, and the step of selecting the base clustering result satisfying the quality and serving as the candidate base clustering comprises the following steps:
S131, for each basic clustering result, calculating a standard mutual information value between each basic cluster, and calculating an average value of the standard mutual information values of each basic cluster and all other basic clusters according to the standard mutual information value to obtain a consistency value of the basic clusters;
S132, dividing the consistency value of each basic cluster by the maximum value in the consistency values of all the basic clusters to obtain a standardized basic cluster consistency value;
s133, for the standardized consistency value of each base cluster, selecting the base clusters with preset proportion as candidate base clusters meeting the quality requirement after the base clusters are arranged from large to small.
7. The method for storing electric energy meter data based on data analysis according to claim 1, wherein the calculating risk of the electric energy meter data set based on the information entropy method and dividing the electric energy meter data set into different risk levels comprises the following steps:
S21, collecting historical failure data of the electric energy meter, analyzing factors of failure generated by the historical failure data of the electric energy meter by adopting an event tree system, and determining risk evaluation factors of a data set of the electric energy meter;
s22, evaluating the invalidity score of each risk evaluation factor by using an electric energy meter failure mode and an influence analysis method;
s23, calculating weights of all risk evaluation factors based on an information entropy method, and carrying out weighted summation on failure scores and weights of all risk evaluation factors to obtain risk degrees of an electric energy meter data set;
s24, dividing the electric energy meter data set into different risk levels according to the risk degree of the electric energy meter data set obtained through calculation and a preset risk level standard.
8. The method for storing electric energy meter data based on data analysis according to claim 7, wherein the calculating the weight of each risk evaluation factor based on the information entropy method comprises the steps of:
s231, establishing a risk evaluation factor matrix based on the determined risk evaluation factors;
s232, performing information entropy calculation on each risk evaluation factor in the risk evaluation factor matrix, and evaluating the dispersion degree of each risk evaluation factor;
S233, calculating the information entropy weight of each risk evaluation factor according to the information entropy calculation result;
s234, carrying out normalization processing on the information entropy weight to obtain a final risk evaluation factor weight.
9. The method for storing data of an electric energy meter based on data analysis according to claim 1, wherein the step of establishing edge computing nodes based on geographical location information of the electric energy meter and performing different types of encryption processing on the data set of the electric energy meter according to risk division results of the data set of the electric energy meter comprises the following steps:
S31, determining geographic position information of the electric energy meter by utilizing a satellite map technology, analyzing the geographic position information of the electric energy meter, determining the optimal position of the edge computing node and deploying the edge computing node;
s32, determining encryption modes and encryption intensities corresponding to different risk levels according to risk division results of the electric energy meter data set;
S33, encrypting the electric energy meter data set according to the determined encryption mode and encryption strength.
10. A data analysis-based electric energy meter data storage system for implementing the data analysis-based electric energy meter data storage method of any one of claims 1 to 9, characterized in that the data analysis-based electric energy meter data storage system comprises: the system comprises a data integration processing module, a risk grade dividing module, a data encryption processing module and a data transmission storage module, wherein the data integration processing module, the risk grade dividing module, the data encryption processing module and the data transmission storage module are sequentially connected;
the data integration processing module is used for acquiring the data of the electric energy meter by utilizing the internet of things technology and carrying out integration processing on the data of the electric energy meter to obtain an electric energy meter data set;
The risk level classification module is used for calculating the risk level of the electric energy meter data set based on an information entropy method and classifying the electric energy meter data set into different risk levels;
The data encryption processing module is used for establishing edge computing nodes based on geographical position information of the electric energy meter and carrying out encryption processing of different types on the electric energy meter data set according to risk division results of the electric energy meter data set;
The data transmission storage module is used for transmitting the encrypted electric energy meter data to the cloud server and compressing and storing the encrypted electric energy meter data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410690686.5A CN118260789B (en) | 2024-05-30 | 2024-05-30 | Electric energy meter data storage method and system based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410690686.5A CN118260789B (en) | 2024-05-30 | 2024-05-30 | Electric energy meter data storage method and system based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118260789A true CN118260789A (en) | 2024-06-28 |
| CN118260789B CN118260789B (en) | 2024-08-02 |
Family
ID=91613566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410690686.5A Active CN118260789B (en) | 2024-05-30 | 2024-05-30 | Electric energy meter data storage method and system based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118260789B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108305014A (en) * | 2018-02-23 | 2018-07-20 | 国家电网公司 | A kind of failure model and effect analysis method based on reliability room and Rough Ideals point method |
| CN111198979A (en) * | 2019-12-31 | 2020-05-26 | 中国电力科学研究院有限公司 | Method and system for cleaning big data for power transmission and transformation reliability evaluation |
| CN111291452A (en) * | 2020-03-06 | 2020-06-16 | 威海海洋职业学院 | Method and system for determining risk of failure mode of ship electric propulsion system |
| CN115222427A (en) * | 2022-07-29 | 2022-10-21 | 平安科技（深圳）有限公司 | Artificial intelligence-based fraud risk identification method and related equipment |
| CN116595553A (en) * | 2023-05-18 | 2023-08-15 | 马贤 | Encryption method of intelligent electric meter of Internet of things with differential privacy protection |
| CN116739389A (en) * | 2023-08-14 | 2023-09-12 | 广东创能科技股份有限公司 | Smart city management method and system based on cloud computing |
| CN116974490A (en) * | 2023-08-28 | 2023-10-31 | 北京宝联之星科技股份有限公司 | Big data storage method and system based on multi-terminal cloud computing cluster |
| CN117633571A (en) * | 2023-12-05 | 2024-03-01 | 广东电网有限责任公司 | Abnormal user early warning method and device based on multiple clusters |
-
2024
- 2024-05-30 CN CN202410690686.5A patent/CN118260789B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108305014A (en) * | 2018-02-23 | 2018-07-20 | 国家电网公司 | A kind of failure model and effect analysis method based on reliability room and Rough Ideals point method |
| CN111198979A (en) * | 2019-12-31 | 2020-05-26 | 中国电力科学研究院有限公司 | Method and system for cleaning big data for power transmission and transformation reliability evaluation |
| CN111291452A (en) * | 2020-03-06 | 2020-06-16 | 威海海洋职业学院 | Method and system for determining risk of failure mode of ship electric propulsion system |
| CN115222427A (en) * | 2022-07-29 | 2022-10-21 | 平安科技（深圳）有限公司 | Artificial intelligence-based fraud risk identification method and related equipment |
| CN116595553A (en) * | 2023-05-18 | 2023-08-15 | 马贤 | Encryption method of intelligent electric meter of Internet of things with differential privacy protection |
| CN116739389A (en) * | 2023-08-14 | 2023-09-12 | 广东创能科技股份有限公司 | Smart city management method and system based on cloud computing |
| CN116974490A (en) * | 2023-08-28 | 2023-10-31 | 北京宝联之星科技股份有限公司 | Big data storage method and system based on multi-terminal cloud computing cluster |
| CN117633571A (en) * | 2023-12-05 | 2024-03-01 | 广东电网有限责任公司 | Abnormal user early warning method and device based on multiple clusters |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118260789B (en) | 2024-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9367683B2 (en) | Cyber security | |
| US10437696B2 (en) | Proactive information technology infrastructure management | |
| CN110620759A (en) | Network security event hazard index evaluation method and system based on multidimensional correlation | |
| CN109117641A (en) | A kind of network security risk evaluation method based on I-HMM | |
| Messinis et al. | Unsupervised classification for non-technical loss detection | |
| CN111782484A (en) | Anomaly detection method and device | |
| Zhang et al. | Automatic Traffic Anomaly Detection on the Road Network with Spatial‐Temporal Graph Neural Network Representation Learning | |
| CN114978877A (en) | Exception handling method and device, electronic equipment and computer readable medium | |
| Doostan et al. | Predicting lightning-related outages in power distribution systems: A statistical approach | |
| CN117674119A (en) | Power grid operation risk assessment method, device, computer equipment and storage medium | |
| Gao et al. | A data mining method using deep learning for anomaly detection in cloud computing environment | |
| CN118260789B (en) | Electric energy meter data storage method and system based on data analysis | |
| US20230164162A1 (en) | Valuable alert screening method efficiently detecting malicious threat | |
| CN117009186A (en) | Chip mounter software and hardware interaction information real-time monitoring analysis method and system | |
| CN113064812A (en) | Project development process quality defect prediction method, device and medium | |
| CN118447459B (en) | Landslide accumulation monitoring method and system based on deep learning | |
| Kostadinov et al. | Reducing the number of incidents in converged IT infrastructure using correlation approach | |
| CN118363812B (en) | Computer information security intelligent monitoring method and system based on artificial intelligence | |
| Lehna et al. | Fault Detection for agents on power grid topology optimization: A Comprehensive analysis | |
| Chentoufi et al. | Intrusion Detection Systems based on Machine Learning | |
| CN118520378B (en) | Power data classification and classification method and system based on ensemble learning | |
| CN118504676B (en) | Substation online monitoring method and system combined with sensing analysis | |
| CN117131464B (en) | Availability evaluation method and system for power grid data | |
| Vasilyev et al. | Cybersecurity risk analysis of industrial automation systems on the basis of cognitive modeling technology | |
| Kim et al. | Feature Construction Scheme for Efficient Intrusion Detection System. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |