CN115905360A - Abnormal data measurement identification method and device based on random construction matrix - Google Patents
Abnormal data measurement identification method and device based on random construction matrix Download PDFInfo
- Publication number
- CN115905360A CN115905360A CN202211517924.XA CN202211517924A CN115905360A CN 115905360 A CN115905360 A CN 115905360A CN 202211517924 A CN202211517924 A CN 202211517924A CN 115905360 A CN115905360 A CN 115905360A
- Authority
- CN
- China
- Prior art keywords
- matrix
- data
- random
- index
- energy spectrum
- 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
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Complex Calculations (AREA)
Abstract
The invention belongs to the technical field of power systems, and discloses an abnormal data measurement identification method and device based on a random construction matrix, wherein the method comprises the following steps: acquiring electrical index data and non-electrical index data of a target power grid within a preset time length; constructing a random matrix based on the electrical index data and the non-electrical index data; determining a target area in the random matrix, and performing matrix transformation on the target matrix in the target area; respectively performing first energy spectrum analysis and second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index; determining the distribution state of the feature root according to the first screening index and the second screening index; and determining a data exception result based on the distribution state of the characteristic root. The method can quickly and accurately identify and screen the abnormal data in the power grid.
Description
Technical Field
The invention relates to the technical field of power systems, in particular to an abnormal data measurement identification method and device based on a random construction matrix.
Background
The Smart Electrical Grid (SEG) is a comprehensive intelligent system developed by parallel coordination of a transmission network and each level of power Grid, and is characterized in that each voltage level between transmission, transformation and distribution is informationized and automated. With the continuous construction of SEG, the scale of the power system is continuously enlarged, and the power system becomes a typical big data system. The data obtained by the power grid measuring system and the edge perception data types such as urban weather are multiple, so that the problems of large data dimension, wide data source, abnormal data and difficulty in identification and screening are difficult to avoid, the relevance between weather factors and load power consumption behaviors is mined by quickly and accurately utilizing mass data in the power grid, and the method has important significance for assisting follow-up power scheduling decision, improving the response capability of extreme weather of the power grid and ensuring the power supply reliability of important power users.
Electricity is a fundamental energy source for people to perform production activities. With the continuous development of economy, the power supply reliability requirement of a user on electric power energy is continuously improved; meanwhile, the scale of the power distribution network is continuously increased, and a large amount of multi-dimensional data are input into the measurement system, and the data not only comprise the data of electrical indexes, but also comprise the data of non-electrical indexes such as meteorological indexes. The data are inevitably abnormal and difficult to identify and screen.
Therefore, how to quickly and accurately identify and screen the abnormal data in the power grid, and provide technical support for mining the correlation between the non-electrical factors and the load power utilization behaviors and assisting the subsequent power scheduling and other behavior decisions, which is a problem to be solved urgently by technical staff in the field.
Disclosure of Invention
The embodiment of the invention provides an abnormal data measurement identification method and device based on a random construction matrix, so that the abnormal identification and screening of mass data in a power grid can be rapidly and accurately carried out, and technical support is provided for mining the correlation between non-electrical factors and load electricity utilization behaviors and assisting in decision making of behaviors such as subsequent power dispatching and the like. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
According to a first aspect of the embodiments of the present invention, a method for identifying abnormal data measurement based on a random construction matrix is provided.
In some embodiments, the method comprises:
acquiring electrical index data and non-electrical index data of a target power grid within a preset time length;
constructing a random matrix based on the electrical index data and the non-electrical index data;
determining a target area in the random matrix, and performing matrix transformation on the target matrix in the target area to obtain a transformed matrix;
respectively performing first energy spectrum analysis and second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index;
determining the distribution state of the feature root according to the first screening index and the second screening index;
and determining a data exception result based on the distribution state of the characteristic root.
In some embodiments, the electrical index data comprises N a And the basic state variables at least comprise active load data, node voltage data and branch circuit current data.
In some embodiments, the non-electrical data comprises N b And the influencing factor variables at least comprise sunshine data, temperature data and humidity data of the target site.
In some embodiments, the random matrix constructed based on the electrical metric data and the non-electrical metric data is:
where X denotes a matrix element, nj denotes the number of nodes, and ti denotes the time point.
In some embodiments, determining the target region in the random matrix specifically includes:
and constructing a movable window in the random matrix, and taking a region in the movable window as the target region.
In some embodiments, performing matrix transformation on the target matrix in the target region to obtain a transformed matrix specifically includes:
at the target sampling moment, acquiring an original matrix from a database;
converting the original matrix into a standard non-Hermitian matrix;
calculating a plurality of singular value equivalent matrices of the standard non-Hermitian matrix;
and multiplying each singular value equivalent matrix cumulatively to form a matrix to be analyzed.
In some embodiments, each of the singular value equivalent matrices is multiplied cumulatively to form a matrix to be analyzed, and then:
converting the matrix to be analyzed into a standard matrix, and calculating a covariance matrix of the standard matrix;
and taking the covariance matrix as the transformed matrix.
In some embodiments, the standard matrix has a mean of 1 and a variance of 0.
In some embodiments, the performing a first energy spectrum analysis and a second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index respectively includes:
the first energy spectrum analysis is a single cycle rate analysis, and the first screening index is an average spectrum radius.
In some embodiments, the single cycle rate analysis specifically comprises:
is provided with
A random matrix that is not a Hermitian feature, based on which a value is evaluated>
Each element in the (b) is a random variable conforming to an independent and same distribution, and the elements satisfy the following relational expression:
μ(x i )＝0,σ 2 (x i )＝1
in the formula, mu (x) i ) Denotes the mean value, σ 2 (x i ) Representing a variance value;
when in use
N and T tend to be infinite and the empirical spectral distribution of eigenvalues of the singular value equivalence matrix converges to a circular ring while keeping c = N/T constant, where c represents the ratio of the number of rows and columns of the matrix. />
In some embodiments, in the single ring rate analysis, the probability density function is:
in the formula (I), the compound is shown in the specification,
is a matrix eigenvalue, L is the cumulative number of singular value equivalence matrices, and the inner radius of the circular ring is (1-c) L/2 The outer radius of the ring is 1.
In some embodiments, the performing a first energy spectrum analysis and a second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index includes:
the second energy spectrum analysis is M-P law analysis, and the second screening index is an M-P curve.
In some embodiments, the M-P law analysis specifically includes:
is provided with
A random matrix that is not a Hermitian feature, based on which a value is evaluated>
Each element in the (b) is a random variable conforming to an independent and same distribution, and the elements satisfy the following relational expression:
μ(x i )＝0,σ 2 (x i )＝constant<∞
the covariance matrix is defined as:
wherein S is a covariance matrix, N is a matrix line number, X is an original matrix after data acquisition, and T is a mathematical symbol representing matrix transposition;
after matrix transformation, the energy spectrum distribution of the covariance matrix is as follows:
in the formula, λ S Is the eigenvalue of the matrix, c is the ratio of the row and column dimensions of the matrix, should be between 0 and 1,
wherein, a is the minimum value of the characteristic value radius distribution in the ring rate, b is the maximum value of the characteristic value radius distribution in the ring rate, and d is the average value of the characteristic value distribution in the ring rate.
In some embodiments, determining a data abnormal result based on the distribution state of the feature root specifically includes:
if the distribution of the characteristic values is scattered and the value of the average spectrum radius is gradually reduced to the circle center, the data abnormal result is that the data is abnormal;
and if the characteristic values are uniformly distributed and the value of the average spectrum radius is stable, the data abnormal result is that the data is not abnormal.
According to a second aspect of the embodiments of the present invention, an abnormal data measurement identification apparatus based on a random construction matrix is provided.
In some embodiments, the apparatus comprises:
the data acquisition unit is used for acquiring electrical index data and non-electrical index data of a target power grid within preset time;
a matrix construction unit for constructing a random matrix based on the electrical index data and the non-electrical index data;
the matrix transformation unit is used for determining a target area in the random matrix and carrying out matrix transformation on the target matrix in the target area to obtain a transformed matrix;
the energy spectrum analysis unit is used for respectively carrying out first energy spectrum analysis and second energy spectrum analysis on the transformed matrix so as to obtain a first screening index and a second screening index;
the distribution determining unit is used for determining the distribution state of the feature root according to the first screening index and the second screening index;
and the result output unit is used for determining a data abnormal result based on the distribution state of the characteristic root.
According to a third aspect of embodiments of the present invention, there is provided a computer apparatus.
In some embodiments, the computer device comprises a memory storing a computer program and a processor implementing the steps of the above method when executing the computer program.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
according to the abnormal data measurement and identification method based on the random construction matrix, the random matrix is constructed based on the electric index data and the non-electric index data by acquiring the electric index data and the non-electric index data of a target power grid within a preset time length; determining a target area in the random matrix, and performing matrix transformation on the target matrix in the target area to obtain a transformed matrix; respectively performing first energy spectrum analysis and second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index; and determining the distribution state of the characteristic root according to the first screening index and the second screening index, and determining a data abnormal result based on the distribution state of the characteristic root. According to the method provided by the invention, the large amount of high-dimensional data is subjected to abnormity detection and identification and is positioned, so that the rapid and efficient utilization of the data is further met, the abnormity identification and screening of the large amount of data in the power grid can be rapidly and accurately performed, and the technical support is provided for mining the correlation between non-electrical factors and load power utilization behaviors, assisting in behavior decisions such as subsequent power scheduling and the like.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow diagram illustrating a method for anomaly data measurement identification based on a random-constructed matrix in accordance with an exemplary embodiment;
FIG. 2 is a flow chart of the construction of the random matrix provided by the present invention;
FIG. 3 is a schematic diagram of modeling a random matrix provided by the present invention;
FIG. 4 is a schematic diagram of a matrix transformation process provided by the present invention;
FIG. 5 is a block diagram illustrating an anomalous data metrology identification device based on a randomly constructed matrix in accordance with an exemplary embodiment;
FIG. 6 is a schematic block diagram of a computer device shown in accordance with an exemplary embodiment.
Reference numerals:
501-a data acquisition unit, 502-a matrix construction unit, 503-a matrix transformation unit, 504-a quantity spectrum analysis unit, 505-a distribution determination unit, and 506-a result output unit.
Detailed Description
The following description and the drawings sufficiently illustrate specific embodiments herein to enable those skilled in the art to practice them. Portions and features of some embodiments may be included in or substituted for those of others. The scope of the embodiments herein includes the full ambit of the claims, as well as all available equivalents of the claims. The terms "first," "second," and the like, herein are used solely to distinguish one element from another without requiring or implying any actual such relationship or order between such elements. In practice, a first element can also be referred to as a second element, and vice versa. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a structure, apparatus, or device that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such structure, apparatus, or device. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a structure, device, or apparatus that comprises the element. The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like herein, as used herein, are defined as orientations or positional relationships based on the orientation or positional relationship shown in the drawings, and are used for convenience in describing and simplifying the description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present invention. In the description herein, unless otherwise specified and limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may include, for example, mechanical or electrical connections, communications between two elements, direct connections, and indirect connections via intermediary media, where the specific meaning of the terms is understood by those skilled in the art as appropriate.
Herein, the term "plurality" means two or more, unless otherwise specified.
Herein, the character "/" indicates that the preceding and succeeding objects are in an "or" relationship. For example, A/B represents: a or B.
Herein, the term "and/or" is an associative relation describing an object, and means that there may be three relations. For example, a and/or B, represents: a or B, or A and B.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flowchart illustrating an abnormal data measurement identification method based on a random building matrix according to an exemplary embodiment.
In one embodiment, the method for identifying abnormal data measurement based on a random construction matrix includes the following steps:
s110: and acquiring the electrical index data and the non-electrical index data of the target power grid within a preset time length. In particular, the electrical index data comprises N a A basic state variable, the non-electrical data including N b And (4) influencing factor variables. For example, the basic state variables at least comprise active load data, node voltage data and branch current data, and the influencing factor variables at least comprise meteorological data such as sunshine data, temperature data and humidity data of a target site.
S120: constructing a random matrix based on the electrical index data and the non-electrical index data, wherein the random matrix is as follows:
where X represents a matrix element, nj represents the number of nodes, and ti represents a time point. When the random matrix is constructed, the data measured by the power system measurement system are exported, and then the meteorological data are exported and spliced.
S130: and determining a target area in the random matrix, and performing matrix transformation on the target matrix in the target area to obtain a transformed matrix. In determining the target region, a movable window may be constructed in the random matrix, with a region in the movable window as the target region.
In this embodiment, the technical route of the present invention adopts a random construction matrix theory, as shown in fig. 2. And constructing a random matrix for the acquired information, and performing matrix transformation, wherein the modeling of the random constructed matrix is shown in fig. 3, and the matrix transformation process is shown in fig. 4. In order to effectively reflect the influence of the influence factors on the state of the power grid and accurately screen the power grid data and the influence factor data, when constructing the random matrix, attention needs to be paid to the fact that the ratio c1 of the dimension of the influence factor variable to the dimension of the power grid variable is maintained between 0.5 and 1. If the collected influence factor variable data is less, the collected data needs to be copied until the limit requirement of the dimension ratio is met. When the dimension of the random matrix tends to infinity and the row-column ratio c is fixed, the empirical spectral distribution of eigenvalues converges to theoretical features according to the random matrix theory. In practical applications, however, a fairly accurate asymptotic convergence result can be observed as long as the dimension of the matrix is relatively moderate, for example, tens to hundreds, which is a theoretical basis on which the random matrix theory can be applied to the power system analysis.
S140: respectively performing first energy spectrum analysis and second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index;
s150: determining the distribution state of the characteristic root according to the first screening index and the second screening index;
s160: determining a data anomaly result based on the distribution state of the feature root; for example, if the distribution of the characteristic values is scattered and the value of the average spectrum radius is gradually reduced to the center of the circle, the data abnormal result is that the data is abnormal; and if the characteristic values are uniformly distributed and the value of the average spectrum radius is stable, the data abnormal result is that the data is not abnormal.
In principle, the invention adopts the constructed random matrix as a data processing tool, and has the following advantages:
firstly, a random construction matrix theory in a big data technology is a mathematical tool suitable for statistical analysis of a complex system, and the application angle of the random construction matrix theory is mainly focused on energy spectrum analysis. In recent years, the random construction matrix theory is widely applied to power systems, and particularly, bright results are obtained in the fields of big data reconstruction, situation awareness, abnormal data analysis, fault detection and the like. For example, by comparing the distribution of the characteristic values of the data matrix of the power system in the normal state and the abnormal state, and combining the average spectrum radius value, whether the power system has the abnormal state is judged; the disturbance or fault location can be realized through the characteristic value distribution of the regional chip type data matrix and the average spectrum radius mean value. The random matrix construction theory has the outstanding advantages of capability of carrying out large-scale data fusion and capability of bearing a large amount of multi-dimensional data. Specifically, the random construction matrix can bear regional electrical indexes such as node voltage, current, phase angle and active load data; and weather non-electrical indexes such as illumination, humidity, temperature and the like can be borne.
Secondly, the direct utilization rate of the random construction matrix to the data is high, the data processing is very quick, the processing of removing units is not needed, the random construction matrix is suitable for the background with severe meteorological conditions, and the requirement of quick processing under the critical condition is met. Meteorological factors have the characteristics of complexity and rapid change, and increasingly become important factors influencing the load characteristics of the power system. And the accurate judgment of the load behavior is the basis of the stable operation of the power grid. At present, the random construction matrix theory is widely applied to fault location, line selection and the like, but is not applied to basic data identification. Therefore, the invention discloses an abnormal data measurement and identification system based on a random construction matrix, which is used for carrying out abnormal detection and identification on a large amount of high-dimensional data and positioning the data, so that the rapid and efficient utilization of the data is met, and the safe operation of a power system is ensured.
In fig. 4, performing matrix transformation on the target matrix in the target region to obtain a transformed matrix, which specifically includes the following steps:
at the target sampling moment, acquiring an original matrix from a database;
converting the original matrix into a standard non-Hermitian matrix;
calculating a plurality of singular value equivalent matrices of the standard non-Hermitian matrix;
multiplying each singular value equivalent matrix cumulatively to form a matrix to be analyzed;
and converting the matrix to be analyzed into a standard matrix, and calculating a covariance matrix of the standard matrix, wherein the mean value of the standard matrix is 1, and the variance is 0.
And taking the covariance matrix as the transformed matrix.
In some embodiments, the performing a first energy spectrum analysis and a second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index includes:
the first energy spectrum analysis is single-cycle rate analysis, and the first screening index is average spectrum radius.
Wherein the analysis of the single Ring rate (Ring Law) specifically comprises the following steps:
is provided with
A random matrix that is not a Hermitian feature, based on which a value is evaluated>
Each element in the (1) is a random variable which is independent and distributed identically, and the elements of the random variable satisfy the following relational expression:
μ(x i )＝0,σ 2 (x i )＝1
in the formula, mu (x) i ) Denotes the mean value, σ 2 (x i ) Representing a variance value;
when in use
OfThe degrees N and T tend to be infinite and the empirical spectral distribution of eigenvalues of the singular value equivalence matrix converges to a circular ring while keeping c = N/T constant, where c represents the ratio of the number of rows and columns of the matrix.
The probability density function is:
in the formula (I), the compound is shown in the specification,
is a matrix eigenvalue, L is the cumulative number of singular value equivalence matrices, and the inner radius of the circular ring is (1-c) L/2 The outer radius of the ring is 1.
In some embodiments, the performing a first energy spectrum analysis and a second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index respectively includes:
the second energy spectrum analysis is M-P law analysis, and the second screening index is an M-P curve.
Wherein, the M-P law (Marchenko-Passturlaw) analysis specifically comprises:
is provided with
A random matrix that is not a Hermitian feature, based on which a value is evaluated>
Each element in the (b) is a random variable conforming to an independent and same distribution, and the elements satisfy the following relational expression:
μ(x i )＝0,σ 2 (x i )＝constant<∞
the covariance matrix is defined as:
wherein S is a covariance matrix, N is a matrix line number, X is an original matrix after data acquisition, and T is a mathematical symbol representing matrix transposition;
after matrix transformation, the energy spectrum distribution of the covariance matrix is:
in the formula, λ S Is the eigenvalue of the matrix, c is the ratio of the row and column dimensions of the matrix, should be between 0 and 1,
wherein, a is the minimum value of the characteristic value radius distribution in the ring rate, b is the maximum value of the characteristic value radius distribution in the ring rate, and d is the average value of the characteristic value distribution in the ring rate.
In a specific use scenario, still referring to fig. 2 and fig. 3, a movable small window is constructed in the formed model matrix, data in the small window is used as a research object, and data transformation is performed according to the M-P law and the formula of the single-loop law to obtain an average spectrum radius and an M-P curve. The average spectral radius and the M-P curve obtained in the above steps are two indexes for identifying and screening abnormal data in this embodiment, and the distribution of the characteristic root can be seen through the two indexes. If the distribution of the characteristic values is scattered and the value of the average spectrum radius is gradually reduced to the circle center, the data in the small window is abnormal; if the characteristic values are uniformly distributed and the value of the average spectrum radius is relatively stable, the data of the small window has no abnormity.
When finding out the data abnormality of a certain small window, the invention also comprises the following steps:
firstly, returning the row and column positions of the data of the small window;
reducing the row number and the column number of the window, traversing the whole matrix by the small window according to the moving direction in the figure 2, and repeatedly carrying out iteration data processing on the reduced window;
and continuously reducing the row and column number of the abnormal matrix until the abnormal matrix is accurately positioned.
In the above embodiment, the method for measuring and identifying abnormal data based on a randomly constructed matrix provided by the invention comprises the steps of obtaining electrical index data and non-electrical index data of a target power grid within a preset time length, and constructing the random matrix based on the electrical index data and the non-electrical index data; determining a target area in the random matrix, and performing matrix transformation on the target matrix in the target area to obtain a transformed matrix; respectively performing first energy spectrum analysis and second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index; and determining the distribution state of the characteristic root according to the first screening index and the second screening index, and determining a data abnormal result based on the distribution state of the characteristic root. The method provided by the invention can be used for carrying out abnormity detection and identification and positioning on a large amount of high-dimensional data, so that the rapid and efficient utilization of the data is further met, the abnormity identification and screening of the large amount of data in the power grid can be rapidly and accurately carried out, and the technical support is provided for mining the correlation between non-electrical factors and load power utilization behaviors, assisting the decision of behaviors such as subsequent power dispatching and the like.
According to a second aspect of the embodiments of the present invention, an abnormal data measurement identification apparatus based on a random building matrix is provided.
In some embodiments, as shown in fig. 5, the apparatus comprises:
the data acquisition unit 501 is configured to acquire electrical index data and non-electrical index data of a target power grid within a preset time length;
a matrix construction unit 502 for constructing a random matrix based on the electrical index data and the non-electrical index data;
a matrix transformation unit 503, configured to determine a target area in the random matrix, and perform matrix transformation on the target matrix in the target area to obtain a transformed matrix;
a spectrum analysis unit 504, configured to perform a first energy spectrum analysis and a second energy spectrum analysis on the transformed matrix, respectively, to obtain a first screening index and a second screening index;
a distribution determining unit 505, configured to determine a distribution state of the feature root according to the first screening index and the second screening index;
a result output unit 506, configured to determine a data exception result based on the distribution state of the feature root.
In some embodiments, the electrical index data comprises N a And the basic state variables at least comprise active load data, node voltage data and branch circuit current data.
In some embodiments, the non-electrical data comprises N b And an influencing factor variable, wherein the influencing factor variable at least comprises sunshine data, temperature data and humidity data of the target site.
In some embodiments, the random matrix constructed based on the electrical metric data and the non-electrical metric data is:
where X denotes a matrix element, nj denotes the number of nodes, and ti denotes the time point.
In some embodiments, determining the target region in the random matrix specifically includes:
and constructing a movable window in the random matrix, and taking a region in the movable window as the target region.
In some embodiments, performing matrix transformation on the target matrix in the target region to obtain a transformed matrix specifically includes:
at the target sampling moment, acquiring an original matrix from a database;
converting the original matrix into a standard non-Hermitian matrix;
calculating a plurality of singular value equivalent matrices of the standard non-Hermitian matrix;
and multiplying each singular value equivalent matrix cumulatively to form a matrix to be analyzed.
In some embodiments, each of the singular value equivalent matrices is multiplied cumulatively to form a matrix to be analyzed, and then:
converting the matrix to be analyzed into a standard matrix, and calculating a covariance matrix of the standard matrix;
and taking the covariance matrix as the transformed matrix.
In some embodiments, the standard matrix has a mean of 1 and a variance of 0.
In some embodiments, the performing a first energy spectrum analysis and a second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index includes:
the first energy spectrum analysis is single-cycle rate analysis, and the first screening index is average spectrum radius.
In some embodiments, the single cycle rate analysis specifically comprises:
is provided with
Random matrix that is a non-Hermitian feature, based on a predetermined criterion>
Each element in the (b) is a random variable conforming to an independent and same distribution, and the elements satisfy the following relational expression:
μ(x i )＝0,σ 2 (x i )＝1
in the formula, mu (x) i ) Denotes the mean value, σ 2 (x i ) Representing a variance value;
when in use
And with c = N/T constant, the empirical spectral distribution of eigenvalues of the singular value equivalence matrix converges to a circular ring, where c represents the ratio of the number of rows and columns of the matrix.
In some embodiments, in the single ring rate analysis, the probability density function is:
in the formula (I), the compound is shown in the specification,
is a matrix eigenvalue, L is the cumulative number of singular value equivalence matrices, and the inner radius of the circular ring is (1-c) L/2 The outer radius of the ring is 1.
In some embodiments, the performing a first energy spectrum analysis and a second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index includes:
the second energy spectrum analysis is M-P law analysis, and the second screening index is an M-P curve.
In some embodiments, the M-P law analysis specifically includes:
is provided with
A random matrix that is not a Hermitian feature, based on which a value is evaluated>
Each element in the (b) is a random variable conforming to an independent and same distribution, and the elements satisfy the following relational expression:
μ(x i )＝0,σ 2 (x i )＝constant<∞
the covariance matrix is defined as:
wherein S is a covariance matrix, N is a matrix line number, X is an original matrix after data acquisition, and T is a mathematical symbol representing matrix transposition;
after matrix transformation, the energy spectrum distribution of the covariance matrix is:
in the formula (I), the compound is shown in the specification,λ S is the eigenvalue of the matrix, c is the ratio of the row and column dimensions of the matrix, should be between 0 and 1,
wherein a is the minimum value of the characteristic value radius distribution in the circular ring rate, b is the maximum value of the characteristic value radius distribution in the circular ring rate, and d is the mean value of the characteristic value distribution in the circular ring rate.
In some embodiments, determining the data abnormal result based on the distribution state of the feature root specifically includes:
if the distribution of the characteristic values is scattered and the value of the average spectrum radius is gradually reduced to the circle center, the data abnormal result is that the data is abnormal;
and if the characteristic values are uniformly distributed and the value of the average spectrum radius is stable, the data abnormal result is that the data is not abnormal.
In the above embodiment, the anomaly data measurement and identification device based on the randomly constructed matrix provided by the invention is used for constructing the random matrix based on the electrical index data and the non-electrical index data by acquiring the electrical index data and the non-electrical index data of the target power grid within a preset time length; determining a target area in the random matrix, and performing matrix transformation on the target matrix in the target area to obtain a transformed matrix; respectively performing first energy spectrum analysis and second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index; and determining the distribution state of the characteristic root according to the first screening index and the second screening index, and determining a data abnormal result based on the distribution state of the characteristic root. The device provided by the invention can be used for carrying out abnormity detection and identification and positioning on a large amount of high-dimensional data, so that the rapid and efficient utilization of the data is further met, the abnormity identification and screening of the large amount of data in the power grid can be rapidly and accurately carried out, and the technical support is provided for mining the correlation between non-electrical factors and load power utilization behaviors, assisting the decision of behaviors such as subsequent power dispatching and the like.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing static information and dynamic information data. The network interface of the computer device is used for communicating with an external terminal through a network connection. Which computer program is executed by a processor to carry out the steps in the above-described method embodiments.
Those skilled in the art will appreciate that the configuration shown in fig. 6 is a block diagram of only a portion of the configuration associated with aspects of the present invention and is not intended to limit the computing devices to which aspects of the present invention may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases or other media used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), for example.
The present invention is not limited to the structures that have been described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (16)
1. An abnormal data measurement identification method based on a random construction matrix is characterized by comprising the following steps:
acquiring electrical index data and non-electrical index data of a target power grid within a preset time length;
constructing a random matrix based on the electrical index data and the non-electrical index data;
determining a target area in the random matrix, and performing matrix transformation on the target matrix in the target area to obtain a transformed matrix;
respectively performing first energy spectrum analysis and second energy spectrum analysis on the transformed matrix to obtain a first screening index and a second screening index;
determining the distribution state of the feature root according to the first screening index and the second screening index;
and determining a data exception result based on the distribution state of the characteristic root.
2. The method of claim 1, wherein the electrical index data comprises N a And the basic state variables at least comprise active load data, node voltage data and branch circuit current data.
3. The method of claim 1, wherein the non-electrical data comprises N b And an influencing factor variable, wherein the influencing factor variable at least comprises sunshine data, temperature data and humidity data of the target site.
4. The method of claim 1, wherein the random matrix constructed based on the electrical index data and the non-electrical index data is:
where X represents a matrix element, nj represents the number of nodes, and ti represents a time point.
5. The method of claim 1, wherein determining the target area in the random matrix comprises:
and constructing a movable window in the random matrix, and taking a region in the movable window as the target region.
6. The method for identifying abnormal data measurement based on a randomly constructed matrix as claimed in claim 1, wherein performing matrix transformation on the target matrix in the target region to obtain a transformed matrix specifically comprises:
at the target sampling moment, acquiring an original matrix from a database;
converting the original matrix into a standard non-Hermitian matrix;
calculating a plurality of singular value equivalent matrices of the standard non-Hermitian matrix;
and multiplying the equivalent matrixes of the singular values to form a matrix to be analyzed.
7. The method of claim 6, wherein the singular value equivalent matrices are multiplied together to form a matrix to be analyzed, and further comprising:
converting the matrix to be analyzed into a standard matrix, and calculating a covariance matrix of the standard matrix;
and taking the covariance matrix as the transformed matrix.
8. The method of claim 7, wherein the mean of the standard matrix is 1 and the variance is 0.
9. The method for measuring and identifying abnormal data based on the random construction matrix according to any one of claims 1 to 8, wherein the first energy spectrum analysis and the second energy spectrum analysis are respectively performed on the transformed matrix to obtain a first screening index and a second screening index, and specifically comprises:
the first energy spectrum analysis is single-cycle rate analysis, and the first screening index is average spectrum radius.
10. The method as claimed in claim 9, wherein the single loop rate analysis specifically comprises:
is provided with
Random matrix that is a non-Hermitian feature, based on a predetermined criterion>
Each element in the (b) is a random variable conforming to an independent and same distribution, and the elements satisfy the following relational expression:
μ(x i )＝0,σ 2 (x i )＝1
in the formula, mu (x) i ) Denotes the mean value, σ 2 (x i ) Representing a variance value;
when in use
N and T tend to be infinite and the empirical spectral distribution of eigenvalues of the singular value equivalence matrix converges to a circular ring while keeping c = N/T constant, where c represents the matrixThe ratio of the number of rows to the number of columns.
11. The method as claimed in claim 10, wherein the probability density function in the single-loop rate analysis is:
in the formula (I), the compound is shown in the specification,
is the matrix eigenvalue, L is the cumulative number of singular value equivalent matrices, the inner radius of the ring is (1-c) L/2 The outer radius of the ring is 1.
12. The method for measuring and identifying abnormal data based on the random construction matrix according to any one of claims 1 to 8, wherein the first energy spectrum analysis and the second energy spectrum analysis are respectively performed on the transformed matrix to obtain a first screening index and a second screening index, and specifically comprises:
the second energy spectrum analysis is M-P law analysis, and the second screening index is an M-P curve.
13. The method of claim 12, wherein the M-P law analysis specifically comprises:
is provided with
Random matrix that is a non-Hermitian feature, based on a predetermined criterion>
Each element in the (1) is a random variable which is independent and distributed identically, and the elements of the random variable satisfy the following relational expression:
μ(x i )＝0,σ 2 (x i )＝constant<∞
the covariance matrix is defined as:
wherein S is a covariance matrix, N is the number of matrix lines, X is an original matrix after data acquisition, and T is a mathematical symbol representing matrix transposition;
after matrix transformation, the energy spectrum distribution of the covariance matrix is:
in the formula, λ S Is the eigenvalue of the matrix, c is the ratio of the row and column dimensions of the matrix, should be between 0 and 1,
wherein, a is the minimum value of the characteristic value radius distribution in the ring rate, b is the maximum value of the characteristic value radius distribution in the ring rate, and d is the average value of the characteristic value distribution in the ring rate.
14. The method for identifying abnormal data measurement based on random construction matrix according to any one of claims 1-8, wherein determining the abnormal data result based on the distribution state of the feature root specifically comprises:
if the distribution of the characteristic values is scattered and the value of the average spectrum radius is gradually reduced to the circle center, the data abnormal result is that the data is abnormal;
and if the characteristic values are uniformly distributed and the value of the average spectrum radius is stable, the data abnormal result is that the data is not abnormal.
15. An abnormal data measurement and identification device based on a random construction matrix, the device comprising:
the data acquisition unit is used for acquiring the electric index data and the non-electric index data of the target power grid within a preset time length;
a matrix construction unit for constructing a random matrix based on the electrical index data and the non-electrical index data;
the matrix transformation unit is used for determining a target area in the random matrix and carrying out matrix transformation on the target matrix in the target area to obtain a transformed matrix;
the energy spectrum analysis unit is used for respectively carrying out first energy spectrum analysis and second energy spectrum analysis on the transformed matrix so as to obtain a first screening index and a second screening index;
the distribution determining unit is used for determining the distribution state of the feature root according to the first screening index and the second screening index;
and the result output unit is used for determining a data abnormal result based on the distribution state of the characteristic root.
16. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 14.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211517924.XA CN115905360A (en) | 2022-11-29 | 2022-11-29 | Abnormal data measurement identification method and device based on random construction matrix |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211517924.XA CN115905360A (en) | 2022-11-29 | 2022-11-29 | Abnormal data measurement identification method and device based on random construction matrix |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115905360A true CN115905360A (en) | 2023-04-04 |
Family
ID=86480308
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211517924.XA Pending CN115905360A (en) | 2022-11-29 | 2022-11-29 | Abnormal data measurement identification method and device based on random construction matrix |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115905360A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829689A (en) * | 2024-03-05 | 2024-04-05 | 顺通信息技术科技(大连)有限公司 | Cloud computing-based business data screening method and system |
-
2022
- 2022-11-29 CN CN202211517924.XA patent/CN115905360A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829689A (en) * | 2024-03-05 | 2024-04-05 | 顺通信息技术科技(大连)有限公司 | Cloud computing-based business data screening method and system |
| CN117829689B (en) * | 2024-03-05 | 2024-05-14 | 顺通信息技术科技(大连)有限公司 | Cloud computing-based business data screening method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112862630B (en) | Photovoltaic power prediction method, terminal and medium based on weather type index interval | |
| CN107909212B (en) | Climbing event prediction method based on mesoscale wind power development process serialization | |
| Li et al. | Deep learning-based transient stability assessment framework for large-scale modern power system | |
| CN115905360A (en) | Abnormal data measurement identification method and device based on random construction matrix | |
| CN112651576A (en) | Long-term wind power prediction method and device | |
| CN116702992A (en) | Power generation power prediction method and device, electronic equipment and storage medium | |
| CN113837434A (en) | Solar photovoltaic power generation prediction method and device, electronic equipment and storage medium | |
| CN113570106A (en) | Power load prediction method and device based on expressway neural network | |
| CN117113086A (en) | Energy storage unit load prediction method, system, electronic equipment and medium | |
| CN117033923A (en) | Method and system for predicting crime quantity based on interpretable machine learning | |
| Zi-hao et al. | A thermal energy usage prediction method for electric thermal storage heaters based on deep learning | |
| CN113449466B (en) | Solar radiation prediction method and system for optimizing RELM based on PCA and chaos GWO | |
| Hua | Power quality prediction of active distribution network based on CNN-LSTM deep learning model | |
| Li et al. | Dimension-reduction and reconstruction of multi-dimension spatial wind power data based on optimal RBF kernel principal component analysis | |
| Dang-Ha et al. | Graph of virtual actors (gova): A big data analytics architecture for IoT | |
| CN114662970A (en) | Construction method based on RES power grid vulnerability assessment model containing multiple heterogeneous objects | |
| KR20230066927A (en) | Method and apparatus for predicting power generation | |
| CN111612289A (en) | Electric power system risk assessment method based on new energy multi-scene risk feature guidance | |
| Vergura | Big data and efficiency of PV plants | |
| CN116796926B (en) | Low-voltage side new energy resource aggregation capacity assessment method and device, medium and equipment | |
| CN110766218A (en) | Power load prediction method and prediction system | |
| Su et al. | A Short-term PV Power Forecasting Method based on NWP Correction Considering Meteorological Coupling Correlation | |
| CN113989073B (en) | Photovoltaic high-duty distribution network voltage space-time multidimensional evaluation method based on big data mining | |
| Verma et al. | Development of Artificial Intelligence Techniques for Solar PV Power Forecasting for Dehradun Region of India. | |
| CN114528907B (en) | Industrial abnormal data detection method and device |
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 |