[go: up one dir, main page]

CN111008673A - Method for collecting and extracting malignant data chain in power distribution network information physical system - Google Patents

Method for collecting and extracting malignant data chain in power distribution network information physical system Download PDF

Info

Publication number
CN111008673A
CN111008673A CN201911346952.8A CN201911346952A CN111008673A CN 111008673 A CN111008673 A CN 111008673A CN 201911346952 A CN201911346952 A CN 201911346952A CN 111008673 A CN111008673 A CN 111008673A
Authority
CN
China
Prior art keywords
distribution network
physical system
power distribution
data
malignant
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.)
Pending
Application number
CN201911346952.8A
Other languages
Chinese (zh)
Inventor
迟福建
王哲
李桂鑫
孙阔
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Tianjin Electric Power Co Ltd
State Grid Corp of China SGCC
Original Assignee
State Grid Tianjin Electric Power Co Ltd
State Grid Corp of China SGCC
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Tianjin Electric Power Co Ltd, State Grid Corp of China SGCC filed Critical State Grid Tianjin Electric Power Co Ltd
Priority to CN201911346952.8A priority Critical patent/CN111008673A/en
Publication of CN111008673A publication Critical patent/CN111008673A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462—Approximate or statistical queries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2474—Sequence data queries, e.g. querying versioned data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
    • G06F21/55—Detecting local intrusion or implementing counter-measures
    • G06F21/552—Detecting local intrusion or implementing counter-measures involving long-term monitoring or reporting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
    • G06F2216/03—Data mining

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Business, Economics & Management (AREA)
  • Fuzzy Systems (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computational Linguistics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Economics (AREA)
  • Computer Security & Cryptography (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Human Resources & Organizations (AREA)
  • Computer Hardware Design (AREA)
  • General Health & Medical Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the field of fault diagnosis and analysis of a power distribution network information physical system, in particular to a method for extracting a malignant data chain of the power distribution network information physical system. Establishing a malignant data link spectrum characteristic quantity model by adopting a spectrum characteristic extraction method to realize classification detection of the malignant data link of the power distribution network information physical system; simulation results show that the method for detecting the malignant data chain of the power distribution network information physical system has good adaptability and strong resolving power, and has good application value in detection and identification of the malignant data chain of the power distribution network information physical system.

Description

Method for collecting and extracting malignant data chain in power distribution network information physical system
Technical Field
The invention belongs to the field of fault diagnosis and analysis of a power distribution network information physical system, and particularly relates to a method for acquiring and extracting a malignant data chain in the power distribution network information physical system.
Background
The power distribution network is an information physical system which is composed of a physical network, information equipment and a computing unit module, has the advantages of various operation modes, high compatibility and the like, and is affected by the use environment of the power distribution network information physical system and the technical index parameters of the equipment in the power distribution network information physical system power distribution process, so that malignant data are generated in the power distribution network information physical system. The malignant data of the power distribution network information physical system mainly refer to abnormal fee deduction information of a user, malicious attack data, personal data leakage and the like. The existence of the malignant data not only hinders the operation efficiency of the power distribution network system, but also causes economic loss to power consumers. In order to solve the above problems, it is necessary to add a device for detecting malignant data to the system, to implement multi-level control of the system, and to perform accurate identification and transmission of information streams. However, the method makes the system structure more complex and the cost is higher, which causes uncertainty in the operation of the information physical system of the power distribution network. Aiming at the problems, the invention provides a rapid extraction algorithm for a malignant data chain of a power distribution network information physical system.
Disclosure of Invention
The text provides a rapid extraction algorithm for a malignant data chain of a power distribution network information physical system. The specific content of the algorithm is as follows:
the method for acquiring and extracting the malignant data chain in the power distribution network information physical system comprises the following steps:
s1, determining a data structure model of malignant data in the power distribution network information physical system;
s101, determining distribution time sequence { M) of malignancy data characteristics in power distribution network information physical system j1,2,3, N, one cluster head node S per cluster in the distribution time sequenceNAnd ifNode V in dry cluster0And solving the distance between the malignant data time series nodes by an Euclidean distance formula, wherein the calculation formula is as follows:
Figure BDA0002333644460000021
wherein x isi、xj、yi、yjRespectively representing the abscissa and the ordinate of a malignant data time sequence node i and a node j in a power distribution network information physical system, and d (i, j) representing the Euclidean distance between the two nodes;
s102, according to the malignant data time sequence node distance, combining a big data fusion method to perform similarity fusion of malignant data load capacity, and obtaining a fusion result as follows:
E(L)＝LEi
wherein E isiRepresenting the load of the intermediate node i in the malignant data; l is a transmission link set of malignant data characteristics; the load quantity of the transmission load information in the power distribution network information physical system sent to the i node is as follows:
C(nj)＝Eilδ+E(L)
in the formula, E (L) is a similarity fusion result, delta is a load ratio, and l is the number of transmission chains;
s103, according to a load fusion result, carrying out malignant data acquisition in the power distribution network information system, carrying out spectrum offset characteristic extraction of malignant data load according to the acquired data, carrying out power distribution network information physical system malignant data spectrum characteristic matching on the extracted spectrum characteristic quantity by adopting a machine learning algorithm, and combining big data output time delay to obtain a characteristic space for power distribution network information physical system malignant data information recombination, wherein the expression is as follows:
Xn＝{Xn,Xn-τ,Xn-2τ,…,Xn-(d-1)τ}
wherein, XnRepresenting the malignant data values within a time period of n, τ representing the output time delay, d representing the dimension of the feature space;
obtaining the average mutual information quantity of the malignant data of the information physical system of the power distribution network from the characteristic space of the information recombination, and obtaining a mutual information distribution set as follows:
Ri＝{R1,R2,R3,…,Rd}
in the formula, RdD-th information quantity representing mutual information distribution;
s104, mining association rules of malignant data characteristics of the information physical system of the power distribution network by adopting a parallel mining method, and performing unitary decomposition on the mutual information distribution matrix to obtain a decomposed vector set as follows:
Tr＝{X1,X2,…,Xm}
in the formula, XmAn m-th vector representing a feature space of the information reorganization;
s105, carrying out high-dimensional mapping on the malignant data of the power distribution network information physical system by adopting a singular value characteristic distributed fusion method to obtain a data structure model of the malignant data of the power distribution network information physical system in a high-dimensional mapping space:
Figure BDA0002333644460000031
s2, solving the data structure model of the malignant data in the power distribution network information physical system determined in the step S1:
s201, determining scale parameters of malignant data of the power distribution network information physical system:
Figure BDA0002333644460000032
in the formula, epsilonfsRepresenting a characteristic parameter of malignant data; d represents a time delay parameter; the time delay parameter set of the malignant data is as follows:
di＝{Xd+1,Xd+2,…Xd+m}
in the formula, Xd+mIs a time delay parameter set in the m sequence; adopting an association rule mining method to carry out structural reorganization on malignant data of the power distribution network information physical system, wherein the time delay parameter of the malignant data meets the inter-class averageAnd (4) constructing a power distribution network information physical system malignant data sequence analysis model.
S202, by adopting a correlation characteristic data mining method, carrying out inspection statistical analysis, and carrying out clustering processing on malignant data of the power distribution network information physical system to obtain a load omega balanced scheduling model as follows:
Figure BDA0002333644460000041
wherein,
Figure BDA0002333644460000042
test statistics representing rapid extraction of malignant data, test statistics of rapid extraction of malignant data of an information physical system of a power distribution network
Figure BDA0002333644460000043
Can be expressed as:
Figure BDA0002333644460000044
in the formula,
Figure BDA0002333644460000045
test values representing a linear fit, ηwThe linear fitting value of the load is represented, theta is a detection and adjustment parameter, W represents a power grid malignant data load set, H represents a malignant data chain characteristic recombination function, and the multiple collinearity characteristic linear fitting of the power distribution network information physical system malignant data needs to meet the requirement
Figure BDA0002333644460000046
Wherein, the spectrum peak value of the malignant data of the information physical system of the power distribution network
Figure BDA0002333644460000047
Can be expressed as:
Figure BDA0002333644460000048
in the formula,
Figure BDA0002333644460000049
represents the maximum peak fit value, ξ represents the multiple threshold, and Pr represents the load ω0The spectral value of (a) is determined,
Figure BDA00023336444600000410
as a test statistic
Figure BDA00023336444600000411
The mean function of (a);
s203, linear fitting is carried out on the malignant data of the power distribution network information physical system by adopting a generalized least square method, a complete malignant data chain is obtained, and the fitting result is as follows:
Figure BDA00023336444600000412
the method comprises the following steps that a characteristic space region of power distribution network information physical system data is divided into an S region and a Q region, when the S region is larger than the Q region, linear fitting is conducted on an output load omega, and otherwise, fitting operation is not conducted; setting up the solution vector of the endogenous spectrum characteristic quantity S of the malignant data of the power grid information physical system from { S }1,s2,…,snAnd if the distribution network information physical system malignant data is formed, the entropy distribution probability of the malignant data of the distribution network information physical system is Ps(si) I-1, 2, …, n, Q is defined by the solution vector { Q ] of the large data ambiguity test set1,q2,…,qnIs formed by the following steps;
s3, analyzing the sample distribution characteristics of the malignant data chain of the power distribution network physical system by adopting a spectral characteristic extraction method for the acquired malignant data chain, and detecting the malignant data chain according to the distribution characteristics;
s301, defining the detection probability P of rapid extraction of the malignant data link of the power distribution network information physical systemq(qj) J is 1,2, …, n, wherein q isjA solution vector of a big data fuzzy test set; under extreme learning training, constructing a power distribution network information physical system malignant data chain characteristic recombination model:
Figure BDA0002333644460000051
in the formula, Ps(si) Concept set s for representing distribution of characteristics of malignant data chain of information physical system of power distribution networkiProbability of appearing in affine partition region S, similarly, PqThe ontology feature concept set represents the malignant data link features of the power distribution network information physical system;
s302, initializing a data chain A from a cluster center to a cluster inner point, and obtaining the average mutual information quantity of the malignant data chain of the power distribution network information physical system as follows:
Figure BDA0002333644460000052
s303, constructing a power distribution network information physical system malignant data chain model, carrying out spectrum decomposition on a multicarrier power distribution network information physical system malignant data chain, carrying out balance control on a power distribution network information physical system malignant data chain output sensing sequence by adopting a link random distribution method, and respectively representing the obtained power distribution network information physical system malignant data chain characteristic decomposition subsequences as follows:
r1(n)＝r2(n)exp(-jω0Tp/2),n＝0,1,...,(N-3)/2
r2(n)＝A exp[j(ω0nT+θ)],n＝0,1,...,(N-3)/2
j is a complex operator, n is the grid frequency, T is the vicious processing time, TpIs a time window according to r1(n) and r2(N) carrying out (N-1)/2-point discrete transformation, and extracting the spectral characteristic quantity of the malignant data chain of the power distribution network information physical system, wherein the spectral characteristic quantity extraction model is as follows:
Figure BDA0002333644460000061
in the formula, Ti wThe extraction time of the data chain under different output loads is shown, and on the basis, the classification of the malignant data chain can be carried out according to the extracted spectral characteristic quantityDetecting a class;
s4, classifying and detecting the malignant data chain of the power distribution network information physical system, and extracting;
s401, according to the result of the spectrum characteristic system, detecting the malignant data chain of the power distribution network information physical system, and optimizing the detection of the malignant data chain of the power distribution network information physical system by adopting a neural network analysis method to obtain the load capacity of the malignant data chain in the merged cluster:
R1(k)＝R2(k)exp(-jω0Tp/2),k＝0,1,...,(N-3)/2
Figure BDA0002333644460000062
wherein, ω is0Load prediction error, T, for a vicious data link of an cyber-physical system of a power distribution networkpIs a time window, AkThe characteristic offset amplitude of the malignant data chain of the power distribution network information physical system,
Figure BDA0002333644460000063
for outputting the extended phase, N represents the number of data clustering centers;
s402, linear prediction is carried out on the malignant data link of the power distribution network information physical system, the maximum length of the data block on each merging cluster is obtained according to the global optimization result, adaptive blind separation processing is carried out on the malignant data link of the power distribution network information physical system, and the solution space of a given objective function is from RnAnd when the power distribution network information physical system malignant data chain clustering and outlier U E R is obtainednSearching a point in a data chain A of points in a cluster according to the established spectral characteristic quantity extraction model, and performing fuzzy clustering on the characteristics of the malignant data chain of the power distribution network information physical system by adopting a self-adaptive neural network learning algorithm, wherein the judgment threshold of the data clustering meets the following requirements:
0≤pk+1≤R2(k)-pk≤1；
wherein p represents the probability of the distribution network malignant data link characteristic distribution in the affine subarea area, and k represents the mutual information distribution RdThe kth information in (1)An amount;
s402, initializing N data clustering centers, performing characteristic clustering treatment on malignant data chains of the power distribution network information physical system by adopting a fuzzy clustering analysis method, and extracting the malignant data chains in the power distribution network information physical system:
Figure BDA0002333644460000071
subjectto yi-(w'Φ(xi)≤ε-ξi
ξi,≥0,i＝1,2,L,n；C＞0
wherein w represents a load value, yiOrdinate, Φ (x), representing a malignant data time series node ii) A feature space function representing the information reorganization of the malignant data, C representing the decision threshold, ξiRepresenting the peak of the spectral set, and epsilon is the set error value.
The periodicity of the malignant data is considered, the high-dimensional mapping structure of the data is obtained by calculating the time series node distance of the data, a limiting environment is provided for the accuracy rate of the malignant data detection, and the detection accuracy rate is enhanced; obtaining a malignant data chain through multiple collinearity characteristic linear fitting of the malignant data; further, calculating the average mutual information quantity of the malignant data, and constructing a spectral characteristic quantity extraction model to provide possibility for identifying the malignant data; furthermore, the load capacity of the malignant data chains in the merged cluster is calculated, fuzzy clustering of the characteristics of the malignant data chains is carried out according to the load capacity, the characteristic similar data are fused into a whole, and the time overhead of data detection is saved.
The invention has the advantages and positive effects that:
the method for rapidly extracting the malignant data chain of the power distribution network information physical system adopts a parallel mining method to mine association rules of the characteristics of the malignant data chain of the power distribution network information physical system, performs clustering processing on the malignant data chain of the power distribution network information physical system, and adopts a link random distribution method to perform balanced control on the output sensing sequence of the malignant data chain of the power distribution network information physical system, so as to rapidly extract the malignant data chain of the power distribution network information physical system; the method has the advantages of high accuracy of detecting and identifying the malignant data chain of the power distribution network information physical system, high malignant data chain extraction capacity and low time overhead.
Drawings
The technical solutions of the present invention will be described in further detail below with reference to the accompanying drawings and examples, but it should be understood that these drawings are designed for illustrative purposes only and thus do not limit the scope of the present invention. Furthermore, unless otherwise indicated, the drawings are intended to be illustrative of the structural configurations described herein and are not necessarily drawn to scale.
Fig. 1 is a schematic diagram of a terminal device used in a power distribution network cyber-physical system malignant data chain fast extraction algorithm according to an embodiment of the present invention.
FIG. 2 is a sample distribution diagram of a power distribution network physical system malignancy data chain;
FIG. 3 is extraction support of a vicious data chain of an information physical system of the power distribution network at 5-11 minutes;
FIG. 4 shows the extraction support of the malignant data chain of the cyber-physical system of the power distribution network at 65-70 minutes;
FIG. 5 is a graph comparing the accuracy of data chain detection in the examples.
Detailed Description
First, it should be noted that the specific structures, features, advantages, etc. of the present invention will be specifically described below by way of example, but all the descriptions are for illustrative purposes only and should not be construed as limiting the present invention in any way. Furthermore, any individual technical features described or implicit in the embodiments mentioned herein may still be continued in any combination or subtraction between these technical features (or their equivalents) to obtain still further embodiments of the invention that may not be mentioned directly herein.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The present invention will be specifically described with reference to fig. 1 to 5.
The method for collecting and extracting the malignant data chain in the power distribution network information physical system is characterized by comprising the following steps of: the method comprises the following steps:
s1, determining a data structure model of malignant data in the power distribution network information physical system;
s101, determining distribution time sequence { M) of malignancy data characteristics in power distribution network information physical system j1,2,3, N, one cluster head node S per cluster in the distribution time sequenceNAnd a plurality of nodes V in the cluster0And solving the distance between the malignant data time series nodes by an Euclidean distance formula, wherein the calculation formula is as follows:
Figure BDA0002333644460000091
wherein x isi、xj、yi、yjRespectively representing the abscissa and the ordinate of a malignant data time sequence node i and a node j in a power distribution network information physical system, and d (i, j) representing the Euclidean distance between the two nodes;
s102, according to the malignant data time sequence node distance, combining a big data fusion method to perform similarity fusion of malignant data load capacity, and obtaining a fusion result as follows:
E(L)＝LEi
wherein E isiRepresenting the load of the intermediate node i in the malignant data; l is a transmission link set of malignant data characteristics; the load quantity of the transmission load information in the power distribution network information physical system sent to the i node is as follows:
C(nj)＝Eilδ+E(L)
in the formula, E (L) is a similarity fusion result, delta is a load ratio, and l is the number of transmission chains;
s103, according to a load fusion result, carrying out malignant data acquisition in the power distribution network information system, carrying out spectrum offset characteristic extraction of malignant data load according to the acquired data, carrying out power distribution network information physical system malignant data spectrum characteristic matching on the extracted spectrum characteristic quantity by adopting a machine learning algorithm, and combining big data output time delay to obtain a characteristic space for power distribution network information physical system malignant data information recombination, wherein the expression is as follows:
Xn＝{Xn,Xn-τ,Xn-2τ,…,Xn-(d-1)τ}
wherein, XnRepresenting the malignant data values within a time period of n, τ representing the output time delay, d representing the dimension of the feature space;
obtaining the average mutual information quantity of the malignant data of the information physical system of the power distribution network from the characteristic space of the information recombination, and obtaining a mutual information distribution set as follows:
Ri＝{R1,R2,R3,…,Rd}
in the formula, RdD-th information quantity representing mutual information distribution;
s104, mining association rules of malignant data characteristics of the information physical system of the power distribution network by adopting a parallel mining method, and performing unitary decomposition on the mutual information distribution matrix to obtain a decomposed vector set as follows:
Tr＝{X1,X2,…,Xm}
in the formula, XmAn m-th vector representing a feature space of the information reorganization;
s105, carrying out high-dimensional mapping on the malignant data of the power distribution network information physical system by adopting a singular value characteristic distributed fusion method to obtain a data structure model of the malignant data of the power distribution network information physical system in a high-dimensional mapping space:
Figure BDA0002333644460000101
s2, solving the data structure model of the malignant data in the power distribution network information physical system determined in the step S1:
s201, determining scale parameters of malignant data of the power distribution network information physical system:
Figure BDA0002333644460000111
in the formula, epsilonfsRepresenting a characteristic parameter of malignant data; d represents a time delay parameter; the time delay parameter set of the malignant data is as follows:
di＝{Xd+1,Xd+2,…Xd+m}
in the formula, Xd+mIs a time delay parameter set in the m sequence;
s202, by adopting a correlation characteristic data mining method, carrying out inspection statistical analysis, and carrying out clustering processing on malignant data of the power distribution network information physical system to obtain a load omega balanced scheduling model as follows:
Figure BDA0002333644460000112
wherein,
Figure BDA0002333644460000113
test statistics representing rapid extraction of malignant data, test statistics of rapid extraction of malignant data of an information physical system of a power distribution network
Figure BDA0002333644460000114
Can be expressed as:
Figure BDA0002333644460000115
in the formula,
Figure BDA0002333644460000116
test values representing a linear fit, ηwThe linear fitting value of the load is represented, theta is a detection and adjustment parameter, W represents a power grid malignant data load set, H represents a malignant data chain characteristic recombination function, and the multiple collinearity characteristic linear fitting of the power distribution network information physical system malignant data needs to meet the requirement
Figure BDA0002333644460000117
Wherein, the spectrum peak value of the malignant data of the information physical system of the power distribution network
Figure BDA0002333644460000118
Can be expressed as:
Figure BDA0002333644460000119
in the formula,
Figure BDA0002333644460000121
represents the maximum peak fit value, ξ represents the multiple threshold, and Pr represents the load ω0The spectral value of (a) is determined,
Figure BDA0002333644460000122
as a test statistic
Figure BDA0002333644460000123
The mean function of (a);
s203, linear fitting is carried out on the malignant data of the power distribution network information physical system by adopting a generalized least square method, a complete malignant data chain is obtained, and the fitting result is as follows:
Figure BDA0002333644460000124
the method comprises the following steps that a characteristic space region of power distribution network information physical system data is divided into an S region and a Q region, when the S region is larger than the Q region, linear fitting is conducted on an output load omega, and otherwise, fitting operation is not conducted; setting up the solution vector of the endogenous spectrum characteristic quantity S of the malignant data of the power grid information physical system from { S }1,s2,…,snAnd if the distribution network information physical system malignant data is formed, the entropy distribution probability of the malignant data of the distribution network information physical system is Ps(si) I-1, 2, …, n, Q is defined by the solution vector { Q ] of the large data ambiguity test set1,q2,…,qnIs formed by the following steps;
s3, analyzing the sample distribution characteristics of the malignant data chain of the power distribution network physical system by adopting a spectral characteristic extraction method for the acquired malignant data chain, and detecting the malignant data chain according to the distribution characteristics;
s301, defining the detection probability P of rapid extraction of the malignant data link of the power distribution network information physical systemq(qj) J is 1,2, …, n, wherein q isjA solution vector of a big data fuzzy test set; under extreme learning training, constructing a power distribution network information physical system malignant data chain characteristic recombination model:
Figure BDA0002333644460000125
in the formula, Ps(si) Concept set s for representing distribution of characteristics of malignant data chain of information physical system of power distribution networkiProbability of appearing in affine partition region S, similarly, PqThe ontology feature concept set represents the malignant data link features of the power distribution network information physical system;
s302, initializing a data chain A from a cluster center to a cluster inner point, and obtaining the average mutual information quantity of the malignant data chain of the power distribution network information physical system as follows:
Figure BDA0002333644460000126
s303, constructing a power distribution network information physical system malignant data chain model, carrying out spectrum decomposition on a multicarrier power distribution network information physical system malignant data chain, carrying out balance control on a power distribution network information physical system malignant data chain output sensing sequence by adopting a link random distribution method, and respectively representing the obtained power distribution network information physical system malignant data chain characteristic decomposition subsequences as follows:
r1(n)＝r2(n)exp(-jω0Tp/2),n＝0,1,...,(N-3)/2
r2(n)＝A exp[j(ω0nT+θ)],n＝0,1,...,(N-3)/2
j is a complex operator, n is the grid frequency, T is the vicious processing time, TpIs a time window according to r1(n) and r2(N) carrying out (N-1)/2-point discrete transformation, and extracting the spectral characteristic quantity of the malignant data chain of the power distribution network information physical system, wherein the spectral characteristic quantity extraction model is as follows:
Figure BDA0002333644460000131
in the formula, Ti wThe extraction time of the data chain under different output loads is represented, and on the basis, classification detection of the malignant data chain can be performed according to the extracted spectral feature quantity;
s4, classifying and detecting the malignant data chain of the power distribution network information physical system, and extracting;
s401, according to the result of the spectrum characteristic system, detecting the malignant data chain of the power distribution network information physical system, and optimizing the detection of the malignant data chain of the power distribution network information physical system by adopting a neural network analysis method to obtain the load capacity of the malignant data chain in the merged cluster:
R1(k)＝R2(k)exp(-jω0Tp/2),k＝0,1,...,(N-3)/2
Figure BDA0002333644460000132
wherein, ω is0Load prediction error, T, for a vicious data link of an cyber-physical system of a power distribution networkpIs a time window, AkThe characteristic offset amplitude of the malignant data chain of the power distribution network information physical system,
Figure BDA0002333644460000141
for outputting the extended phase, N represents the number of data clustering centers;
s402, linear prediction is carried out on the malignant data link of the power distribution network information physical system, the maximum length of the data block on each merging cluster is obtained according to the global optimization result, adaptive blind separation processing is carried out on the malignant data link of the power distribution network information physical system, and the solution space of a given objective function is from RnAnd when the power distribution network information physical system malignant data chain clustering and outlier U E R is obtainednSearching a point in a data chain A of points in a cluster according to the established spectral characteristic quantity extraction model, and performing fuzzy clustering on the characteristics of the malignant data chain of the power distribution network information physical system by adopting a self-adaptive neural network learning algorithm, wherein the judgment threshold of the data clustering meets the following requirements:
0≤pk+1≤R2(k)-pk≤1；
wherein p represents the probability of the distribution network malignant data link characteristic distribution in the affine subarea area, and k represents the mutual information distribution RdThe kth information volume of (1);
s402, initializing N data clustering centers, performing characteristic clustering treatment on malignant data chains of the power distribution network information physical system by adopting a fuzzy clustering analysis method, and extracting the malignant data chains in the power distribution network information physical system:
Figure BDA0002333644460000142
subjectto yi-(w'Φ(xi)≤ε-ξi
ξi,≥0,i＝1,2,L,n；C＞0
wherein w represents a load value, yiOrdinate, Φ (x), representing a malignant data time series node ii) A feature space function representing the information reorganization of the malignant data, C representing the decision threshold, ξiRepresenting the peak of the spectral set, and epsilon is the set error value.
Fig. 1 is a schematic diagram of a terminal device provided by the method for collecting and extracting a malicious data chain in a power distribution network information physical system provided by the present invention. As shown in fig. 1, the terminal device 500 of this embodiment includes: the system comprises a processor 501, a memory 502 and a computer program 503 stored in the memory 502 and capable of running on the processor 501, such as an evaluation program of a malignant data chain acquisition and extraction method in a power distribution network cyber-physical system. When the processor 501 executes the computer program 503, the method for acquiring and extracting the malicious data chain in the cyber-physical system of the power distribution network is implemented.
Illustratively, the computer program 503 may be partitioned into one or more program modules that are stored in the memory 502 and executed by the processor 501 to implement the present invention. The one or more program modules may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used for describing the execution process of the computer program 503 in the malicious data chain acquisition and extraction method apparatus in the cyber-physical system of the power distribution network or in the terminal device 500.
The terminal device 500 may be a computing device such as a desktop computer, a notebook computer, a palm top computer, a cloud server, etc., which are merely examples of the terminal device 500, and do not constitute a limitation to the terminal device 500, and may include more or less components than those shown in the drawings, or combine some components, or different components, for example, the terminal device may further include an input/output device, a network access device, a bus, etc.
The Processor 501 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 502 may be an internal storage unit of the terminal device 500, such as a hard disk or a memory of the terminal device 500. The memory 502 may also be an external storage device of the terminal device 500, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 500. Further, the memory 502 may also include both an internal storage unit and an external storage device of the terminal device 500. The memory 502 is used for storing the computer programs and other programs and data required by the terminal device 500. The memory 502 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
For example, in this embodiment, a method for acquiring and extracting a malignant data chain in a power distribution network cyber-physical system is applied to a simulation experiment, and a performance of the method in intelligent detection of the malignant data chain in the power distribution network cyber-physical system is tested.
The distribution array of the distribution network information physical system malignant data chain is 200 x 400, the sampling bandwidth length of the distribution network information physical system malignant data chain is 12s, a power information data sample with the size of 1024MB is randomly selected from an Oracle power system information base, meanwhile, malignant data information such as abnormal fee deduction information, malicious attack data and personal data leakage with the size of 27MB is added, the period length of initial sample sequence sampling is 0.16s, the fundamental frequency of the distribution network information physical system malignant data chain is 100KHz, the text algorithm is applied to power grid customer power consumption quality detection according to the simulation environment and parameter setting, the operation behavior of the malignant data in the monitoring management system is analyzed and monitored by taking the use condition of the distribution network in a certain cell as an example, and the detection and identification of the distribution network information physical system malignant data chain are carried out. First, the distribution of the original distribution network physical system data chain of the cell is analyzed, and the distribution is shown in fig. 2.
As can be seen from fig. 2, in the cyber-physical system of the power distribution network, the malignant data link is formed by combining the malignant initial data and the malignant final data, and is aggregated together in a set. By taking the malignant data chain as a research sample, under the cloud computing environment, the malignant data chain of the power distribution network information physical system is rapidly extracted, the spectrum stripe characteristics of the malignant data chain of the power distribution network information physical system are extracted, and the results are shown in fig. 3 and 4.
As can be seen from fig. 3 and 4, the method for rapidly extracting the malignant data chain of the power distribution network cyber-physical system is adopted, the extracted data chain has high resolution capability, the accurate detection and identification capability of the malignant data chain of the power distribution network cyber-physical system is improved, and the detection accuracy of the characteristic data of the malignant data chain of the power distribution network cyber-physical system is obtained, wherein the detection accuracy calculation formula of the malignant data chain of the power distribution network cyber-physical system is as follows:
Figure BDA0002333644460000181
wherein s represents a variation rate of the deviation; feRepresenting a membership function.
According to the above formula, the mining of the malignant data chain is performed in the range of the information size of 25MB, and the mining accuracy of the malignant data chain is compared by different methods, and the comparison result is shown in fig. 5.
The result of analyzing fig. 5 shows that the accuracy of rapid extraction is continuously improved along with the increase of the number of iterations, the accuracy of detecting the malignant data chain of the information physical system of the power distribution network by using the method reaches 100%, and the average accuracy is respectively improved by 14.6% and 13.4% compared with the average accuracy of the traditional method. The time expenditure for rapidly extracting the data under different data scales is tested, the comparison result is shown in table 1, and the result of analyzing the table 1 shows that the time expenditure for detecting the malignant data chain of the physical system of the power distribution network is short, so that the real-time performance of data monitoring and identification is improved.
TABLE 1 time overhead comparison (units/s)
Figure BDA0002333644460000182
Figure BDA0002333644460000191
As can be seen from table 1, in the process of detecting and identifying the malignant data chain, the time overhead of the method is less, and the efficiency of detecting and identifying the malignant data chain is optimized to a great extent.
In conclusion, the invention provides a rapid extraction algorithm for a malignant data chain of a power distribution network information physical system. And (3) mining association rules of the characteristics of the malignant data chains of the power distribution network information physical system by adopting a parallel mining method, and clustering the malignant data chains of the power distribution network information physical system. And a link random distribution method is adopted to perform balance control on the malignant data chain output sensing sequence of the power distribution network information physical system, so that the rapid extraction of the malignant data chain of the power distribution network information physical system is realized. The method has the advantages of high accuracy of detecting and identifying the malignant data chain of the power distribution network information physical system, high malignant data chain extraction capacity and low time overhead.
The present invention has been described in detail with reference to the above examples, but the description is only for the preferred examples of the present invention and should not be construed as limiting the scope of the present invention. All equivalent changes and modifications made within the scope of the present invention shall fall within the scope of the present invention.

Claims (1)

1. The method for collecting and extracting the malignant data chain in the power distribution network information physical system is characterized by comprising the following steps of: the method comprises the following steps:
s1, determining a data structure model of malignant data in the power distribution network information physical system;
s101, determining distribution time sequence { M) of malignancy data characteristics in power distribution network information physical systemj1,2,3, N, one cluster head node S per cluster in the distribution time sequenceNAnd a plurality of nodes V in the cluster0And solving the distance between the malignant data time series nodes by an Euclidean distance formula, wherein the calculation formula is as follows:
Figure FDA0002333644450000011
wherein x isi、xj、yi、yjRespectively representing the abscissa and the ordinate of a malignant data time sequence node i and a node j in a power distribution network information physical system, and d (i, j) representing the Euclidean distance between the two nodes;
s102, according to the malignant data time sequence node distance, combining a big data fusion method to perform similarity fusion of malignant data load capacity, and obtaining a fusion result as follows:
E(L)＝LEi
wherein E isiRepresenting the load of the intermediate node i in the malignant data; l is a transmission link set of malignant data characteristics; the load quantity of the transmission load information in the power distribution network information physical system sent to the i node is as follows:
C(nj)＝Eilδ+E(L)
in the formula, E (L) is a similarity fusion result, delta is a load ratio, and l is the number of transmission chains;
s103, according to a load fusion result, carrying out malignant data acquisition in the power distribution network information system, carrying out spectrum offset characteristic extraction of malignant data load according to the acquired data, carrying out power distribution network information physical system malignant data spectrum characteristic matching on the extracted spectrum characteristic quantity by adopting a machine learning algorithm, and combining big data output time delay to obtain a characteristic space for power distribution network information physical system malignant data information recombination, wherein the expression is as follows:
Xn＝{Xn,Xn-τ,Xn-2τ,…,Xn-(d-1)τ}
wherein, XnRepresenting the malignant data values within a time period of n, τ representing the output time delay, d representing the dimension of the feature space;
obtaining the average mutual information quantity of the malignant data of the information physical system of the power distribution network from the characteristic space of the information recombination, and obtaining a mutual information distribution set as follows:
Ri＝{R1,R2,R3,…,Rd}
in the formula, RdD-th information quantity representing mutual information distribution;
s104, mining association rules of malignant data characteristics of the information physical system of the power distribution network by adopting a parallel mining method, and performing unitary decomposition on the mutual information distribution matrix to obtain a decomposed vector set as follows:
Tr＝{X1,X2,…,Xm}
in the formula, XmAn m-th vector representing a feature space of the information reorganization;
s105, carrying out high-dimensional mapping on the malignant data of the power distribution network information physical system by adopting a singular value characteristic distributed fusion method to obtain a data structure model of the malignant data of the power distribution network information physical system in a high-dimensional mapping space:
Figure FDA0002333644450000021
s2, solving the data structure model of the malignant data in the power distribution network information physical system determined in the step S1:
s201, determining scale parameters of malignant data of the power distribution network information physical system:
Figure FDA0002333644450000022
in the formula, epsilonfsRepresenting a characteristic parameter of malignant data; d represents a time delay parameter; the time delay parameter set of the malignant data is as follows:
di＝{Xd+1,Xd+2,…Xd+m}
in the formula, Xd+mIs a time delay parameter set in the m sequence;
s202, by adopting a correlation characteristic data mining method, carrying out inspection statistical analysis, and carrying out clustering processing on malignant data of the power distribution network information physical system to obtain a load omega balanced scheduling model as follows:
Figure FDA0002333644450000031
wherein,
Figure FDA0002333644450000032
test statistics representing rapid extraction of malignant data, test statistics of rapid extraction of malignant data of an information physical system of a power distribution network
Figure FDA0002333644450000033
Can be expressed as:
Figure FDA0002333644450000034
in the formula,
Figure FDA0002333644450000035
test values representing a linear fit, ηwThe linear fitting value of the load is represented, theta is a detection and adjustment parameter, W represents a power grid malignant data load set, H represents a malignant data chain characteristic recombination function, and the multiple collinearity characteristic linear fitting of the power distribution network information physical system malignant data needs to meet the requirement
Figure FDA0002333644450000036
Wherein, the spectrum peak value of the malignant data of the information physical system of the power distribution network
Figure FDA0002333644450000037
Can be expressed as:
Figure FDA0002333644450000038
in the formula,
Figure FDA0002333644450000039
represents the maximum peak fit value, ξ represents the multiple threshold, and Pr represents the load ω0The spectral value of (a) is determined,
Figure FDA00023336444500000310
as a test statistic
Figure FDA00023336444500000311
The mean function of (a);
s203, linear fitting is carried out on the malignant data of the power distribution network information physical system by adopting a generalized least square method, a complete malignant data chain is obtained, and the fitting result is as follows:
Figure FDA00023336444500000312
the method comprises the following steps that a characteristic space region of power distribution network information physical system data is divided into an S region and a Q region, when the S region is larger than the Q region, linear fitting is conducted on an output load omega, and otherwise, fitting operation is not conducted; setting up the solution vector of the endogenous spectrum characteristic quantity S of the malignant data of the power grid information physical system from { S }1,s2,…,snAnd if the distribution network information physical system malignant data is formed, the entropy distribution probability of the malignant data of the distribution network information physical system is Ps(si) I-1, 2, …, n, Q is defined by the solution vector { Q ] of the large data ambiguity test set1,q2,…,qnIs formed by the following steps;
s3, analyzing the sample distribution characteristics of the malignant data chain of the power distribution network physical system by adopting a spectral characteristic extraction method for the acquired malignant data chain, and detecting the malignant data chain according to the distribution characteristics;
s301, defining the detection probability P of rapid extraction of the malignant data link of the power distribution network information physical systemq(qj) J is 1,2, …, n, wherein q isjA solution vector of a big data fuzzy test set; under extreme learning training, constructing a power distribution network information physical system malignant data chain characteristic recombination model:
Figure FDA0002333644450000041
in the formula, Ps(si) Concept set s for representing distribution of characteristics of malignant data chain of information physical system of power distribution networkiProbability of appearing in affine partition region S, similarly, PqThe ontology feature concept set represents the malignant data link features of the power distribution network information physical system;
s302, initializing a data chain A from a cluster center to a cluster inner point, and obtaining the average mutual information quantity of the malignant data chain of the power distribution network information physical system as follows:
Figure FDA0002333644450000042
s303, constructing a power distribution network information physical system malignant data chain model, carrying out spectrum decomposition on a multicarrier power distribution network information physical system malignant data chain, carrying out balance control on a power distribution network information physical system malignant data chain output sensing sequence by adopting a link random distribution method, and respectively representing the obtained power distribution network information physical system malignant data chain characteristic decomposition subsequences as follows:
r1(n)＝r2(n)exp(-jω0Tp/2),n＝0,1,...,(N-3)/2
r2(n)＝Aexp[j(ω0nT+θ)],n＝0,1,...,(N-3)/2
j is a complex operator, n is the grid frequency, T is the vicious processing time, TpIs a time window according to r1(n) and r2(N) carrying out (N-1)/2-point discrete transformation, and extracting the spectral characteristic quantity of the malignant data chain of the power distribution network information physical system, wherein the spectral characteristic quantity extraction model is as follows:
Figure FDA0002333644450000051
in the formula, Ti wThe extraction time of the data chain under different output loads is represented, and on the basis, classification detection of the malignant data chain can be performed according to the extracted spectral feature quantity;
s4, classifying and detecting the malignant data chain of the power distribution network information physical system, and extracting;
s401, according to the result of the spectrum characteristic system, detecting the malignant data chain of the power distribution network information physical system, and optimizing the detection of the malignant data chain of the power distribution network information physical system by adopting a neural network analysis method to obtain the load capacity of the malignant data chain in the merged cluster:
R1(k)＝R2(k)exp(-jω0Tp/2),k＝0,1,...,(N-3)/2
Figure FDA0002333644450000052
wherein, ω is0Load prediction error, T, for a vicious data link of an cyber-physical system of a power distribution networkpIs a time window, AkThe characteristic offset amplitude of the malignant data chain of the power distribution network information physical system,
Figure FDA0002333644450000053
for outputting the extended phase, N represents the number of data clustering centers;
s402, linear prediction is carried out on the malignant data link of the power distribution network information physical system, the maximum length of the data block on each merging cluster is obtained according to the global optimization result, adaptive blind separation processing is carried out on the malignant data link of the power distribution network information physical system, and the solution space of a given objective function is from RnAnd when the power distribution network information physical system malignant data chain clustering and outlier U E R is obtainednThat is, a point is searched in the data chain A of the points in the cluster according to the established spectral characteristic quantity extraction model, and the self-adaptive neural network is adoptedAnd (3) fuzzy clustering of the characteristics of the malignant data chain of the power distribution network information physical system is carried out by a learning algorithm, and the judgment threshold of the data clustering meets the following conditions:
0≤pk+1≤R2(k)-pk≤1；
wherein p represents the probability of the distribution network malignant data link characteristic distribution in the affine subarea area, and k represents the mutual information distribution RdThe kth information volume of (1);
s402, initializing N data clustering centers, performing characteristic clustering treatment on malignant data chains of the power distribution network information physical system by adopting a fuzzy clustering analysis method, and extracting the malignant data chains in the power distribution network information physical system:
Figure FDA0002333644450000061
subjectto yi-(w'Φ(xi)≤ε-ξi
ξi,≥0,i＝1,2,L,n；C＞0
wherein w represents a load value, yiOrdinate, Φ (x), representing a malignant data time series node ii) A feature space function representing the information reorganization of the malignant data, C representing the decision threshold, ξiRepresenting the peak of the spectral set, and epsilon is the set error value.
CN201911346952.8A 2019-12-24 2019-12-24 Method for collecting and extracting malignant data chain in power distribution network information physical system Pending CN111008673A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911346952.8A CN111008673A (en) 2019-12-24 2019-12-24 Method for collecting and extracting malignant data chain in power distribution network information physical system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911346952.8A CN111008673A (en) 2019-12-24 2019-12-24 Method for collecting and extracting malignant data chain in power distribution network information physical system

Publications (1)

Publication Number Publication Date
CN111008673A true CN111008673A (en) 2020-04-14

Family

ID=70117748

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911346952.8A Pending CN111008673A (en) 2019-12-24 2019-12-24 Method for collecting and extracting malignant data chain in power distribution network information physical system

Country Status (1)

Country Link
CN (1) CN111008673A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112597634A (en) * 2020-12-06 2021-04-02 国网山东省电力公司电力科学研究院 Power distribution network topology data verification method and system
CN114065200A (en) * 2021-11-18 2022-02-18 安天科技集团股份有限公司 Data file detection method and device, electronic equipment and storage medium
CN115413042A (en) * 2022-08-29 2022-11-29 西华大学 Data link safety access control method based on control sequence
CN115950522A (en) * 2022-12-29 2023-04-11 长沙理工大学 Distributed optical fiber mutation detection method and device based on adaptive fitting

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090284234A1 (en) * 2007-11-16 2009-11-19 Jackman John F Power distribution system control and monitoring
CN102982394A (en) * 2012-11-20 2013-03-20 电子科技大学 Power distribution network load parameter identification method and system
US20130191052A1 (en) * 2012-01-23 2013-07-25 Steven J. Fernandez Real-time simulation of power grid disruption
CN104992382A (en) * 2015-07-21 2015-10-21 国网天津市电力公司 Data fusion method facing current situation assessment of power distribution network
CN106093703A (en) * 2016-06-07 2016-11-09 湖南大学 The identification of a kind of intelligent distribution network fault and localization method
US20190067946A1 (en) * 2017-08-28 2019-02-28 General Electric Company System and method for distribution load forecasting in a power grid
CN110334157A (en) * 2019-07-15 2019-10-15 南昌诺汇医药科技有限公司 A kind of cloud computing management system
CN110376497A (en) * 2019-08-12 2019-10-25 国网四川电力服务有限公司 Low-voltage distribution system series fault arc identification method based on full-phase deep learning

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090284234A1 (en) * 2007-11-16 2009-11-19 Jackman John F Power distribution system control and monitoring
US20130191052A1 (en) * 2012-01-23 2013-07-25 Steven J. Fernandez Real-time simulation of power grid disruption
CN102982394A (en) * 2012-11-20 2013-03-20 电子科技大学 Power distribution network load parameter identification method and system
CN104992382A (en) * 2015-07-21 2015-10-21 国网天津市电力公司 Data fusion method facing current situation assessment of power distribution network
CN106093703A (en) * 2016-06-07 2016-11-09 湖南大学 The identification of a kind of intelligent distribution network fault and localization method
US20190067946A1 (en) * 2017-08-28 2019-02-28 General Electric Company System and method for distribution load forecasting in a power grid
CN110334157A (en) * 2019-07-15 2019-10-15 南昌诺汇医药科技有限公司 A kind of cloud computing management system
CN110376497A (en) * 2019-08-12 2019-10-25 国网四川电力服务有限公司 Low-voltage distribution system series fault arc identification method based on full-phase deep learning

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
THOMAS A. FERRYMAN,BRETT G: "Statistical Analysis of Abnormal Electric Power Grid Behavior" *
ZHENGTONG WAN，JUNXIANG LI， YAN GAO: "Monitoring and diagnosis process of abnormal consumption on smart power grid" *
卫志农，陈和升，倪明，孙国强，孙永辉，厉超: "电力信息物理系统中恶性数据定义、构建与防御挑战" *
张悦;林亚平;: "关于大型数据传输信息异常快速预警仿真研究" *
王谦: "基于网络流量异常检测的电网工控系统安全监测技术" *
郝成亮;陈明;孙伟;刘洪波;刘超;: "电力信息系统网络数据的实时流量监控分析" *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112597634A (en) * 2020-12-06 2021-04-02 国网山东省电力公司电力科学研究院 Power distribution network topology data verification method and system
CN114065200A (en) * 2021-11-18 2022-02-18 安天科技集团股份有限公司 Data file detection method and device, electronic equipment and storage medium
CN114065200B (en) * 2021-11-18 2025-10-21 安天科技集团股份有限公司 Data file detection method, device, electronic device and storage medium
CN115413042A (en) * 2022-08-29 2022-11-29 西华大学 Data link safety access control method based on control sequence
CN115413042B (en) * 2022-08-29 2023-12-05 西华大学 Data link safety access control method based on control sequence
CN115950522A (en) * 2022-12-29 2023-04-11 长沙理工大学 Distributed optical fiber mutation detection method and device based on adaptive fitting

Similar Documents

Publication Publication Date Title
CN118549823B (en) Lithium battery electrical performance testing method and system
Li et al. Optimizing generalized pagerank methods for seed-expansion community detection
CN111008673A (en) Method for collecting and extracting malignant data chain in power distribution network information physical system
CN110826648A (en) Method for realizing fault detection by utilizing time sequence clustering algorithm
CN114861788A (en) Load abnormity detection method and system based on DBSCAN clustering
Jiang et al. A family of joint sparse PCA algorithms for anomaly localization in network data streams
CN113408341A (en) Load identification method and device, computer equipment and storage medium
CN113744089B (en) Transformer area household variable relation identification method and device
Zhang et al. SOH estimation and RUL prediction of lithium batteries based on multidomain feature fusion and CatBoost model
CN108197795B (en) Malicious group account identification method, device, terminal and storage medium
Tao et al. An approach to performance assessment and fault diagnosis for rotating machinery equipment
CN112200254A (en) Network intrusion detection model generation method, detection method and electronic equipment
CN113591400B (en) Power dispatching monitoring data anomaly detection method based on characteristic correlation partition regression
Dawood et al. Power quality disturbance classification based on efficient adaptive Arrhenius artificial bee colony feature selection
Roddenberry et al. Blind inference of centrality rankings from graph signals
CN111784379B (en) Estimation methods and devices for recovering electricity bills and screening methods and devices for abnormal cases
CN116707859A (en) Feature rule extraction method and device, network intrusion detection method and device
CN116821718A (en) Non-invasive industrial load identification method and system based on Mean-shift clustering and twin network
CN110097120A (en) Network flow data classification method, equipment and computer storage medium
CN113052060A (en) Bearing residual life prediction method and device based on data enhancement and electronic equipment
CN116304203B (en) A Method and System for Equipment Fault Propagation Analysis Based on Unstable Point Detection
CN115757900B (en) User demand analysis method and system applying artificial intelligent model
Prasad et al. Assessment of clustering tendency through progressive random sampling and graph-based clustering results
Qi et al. An intrusion detection feature selection method based on improved mutual information
Guo et al. Improving the Accuracy of Locally Differentially Private Community Detection by Order-consistent Data Perturbation

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200414