CN113408788A - High-dimensional construction and completion method, system, device and medium for microclimate monitoring device - Google Patents

High-dimensional construction and completion method, system, device and medium for microclimate monitoring device Download PDF

Info

Publication number
CN113408788A
CN113408788A CN202110575454.1A CN202110575454A CN113408788A CN 113408788 A CN113408788 A CN 113408788A CN 202110575454 A CN202110575454 A CN 202110575454A CN 113408788 A CN113408788 A CN 113408788A
Authority
CN
China
Prior art keywords
microclimate
tensor
information
dimensional
monitoring device
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110575454.1A
Other languages
Chinese (zh)
Other versions
CN113408788B (en
Inventor
欧阳森
陈义森
张真
杨墨缘
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.)
South China University of Technology SCUT
Original Assignee
South China University of Technology SCUT
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 South China University of Technology SCUT filed Critical South China University of Technology SCUT
Priority to CN202110575454.1A priority Critical patent/CN113408788B/en
Publication of CN113408788A publication Critical patent/CN113408788A/en
Application granted granted Critical
Publication of CN113408788B publication Critical patent/CN113408788B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01W—METEOROLOGY
    • G01W1/00—Meteorology
    • G01W1/10—Devices for predicting weather conditions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases
    • G06F16/285—Clustering or classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • General Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Environmental & Geological Engineering (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Remote Sensing (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Primary Health Care (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Evolutionary Biology (AREA)
  • Atmospheric Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Ecology (AREA)
  • Environmental Sciences (AREA)
  • Geophysics And Detection Of Objects (AREA)
  • Alarm Systems (AREA)

Abstract

The invention discloses a high-dimensional construction and completion method, a high-dimensional construction and completion system, a high-dimensional construction and completion device and a high-dimensional construction and completion medium for a microclimate monitoring device, wherein the method comprises the following steps of: acquiring geographic longitude and latitude information of the distribution point of the microclimate monitoring device, and analyzing the regional and chronological characteristics of microclimate; clustering analysis based on longitude and latitude two-dimensional information is carried out on the microclimate monitoring devices according to the geographic longitude and latitude information, and the microclimate monitoring devices with similar spatial geographic distances are divided into the same class; the method comprises the steps of obtaining monitoring information of the microclimate monitoring devices which are divided into the same class, constructing a three-dimensional missing tensor according to the monitoring information, and filling missing values of the microclimate monitoring devices according to the three-dimensional missing tensor and a low-rank tensor completion algorithm. According to the method, missing values of the microclimate monitoring information with wrong and missing information are filled according to the time-space correlation of the microclimate monitoring information, decision support can be provided for planning operation, meteorological modeling and post-disaster analysis of the overhead transmission line of the power system, and the method can be widely applied to the technical field of meteorological disaster early warning.

Description

High-dimensional construction and completion method, system, device and medium for microclimate monitoring device
Technical Field
The invention relates to the technical field of meteorological disaster early warning, in particular to a high-dimensional construction and completion method, a high-dimensional construction and completion system, a high-dimensional construction and completion device and a high-dimensional construction and completion medium for a microclimate monitoring device.
Background
The microclimate area is a local area which shows worse and more complex than surrounding meteorological conditions due to special geographic characteristics, and the microclimate monitoring devices are distributed in the microclimate area in a form of being hung on an overhead transmission line power iron tower. The microclimate monitoring device is powered by the solar panel, and a remote data channel is constructed by using networks such as 3G/GPRS and the like to monitor and transmit field data in real time. Because the microclimate monitoring device is in severe weather and strong electromagnetic interference areas for a long time, monitoring interruption and data loss caused by insufficient electric quantity or unstable transmission channels are inevitable. The complete microclimate data can provide decision support for planning and running of the overhead transmission line of the power system, and also can provide data support for meteorological modeling and post-disaster reason analysis, so that the missing data of the microclimate monitoring device is filled up, and the microclimate monitoring device has important engineering value.
The data collected by the microclimate monitoring device is typical time sequence data. At present, many research achievements are made on sequential data filling at home and abroad, common missing value filling methods include mean value filling, polynomial interpolation, regression models, nearest distance filling and the like, however, the filling methods are based on measurement numerical distance, filling is only performed from 1-dimensional sequential data or 2-dimensional indexes and sequential coupling relations, high-dimensional space-time correlation of data to be filled is not considered, and the situation of high data missing rate is difficult to effectively deal with.
In addition, the data acquired by the microclimate monitoring device has regional and time-domain characteristics, and due to the geographical difference of the distribution points of the monitoring device, the microclimate data can present different trends, periodicities and randomness; the microclimate data such as air temperature and sunlight intensity have potential time sequence correlation coupling, and accordingly, the microclimate data have high-dimensional space-time correlation.
In summary, the method for filling missing values of the microclimate monitoring device is focused on 1-dimensional or 2-dimensional missing values, and the missing value modeling from the perspective of high-dimensional intrinsic structures and high-order dependency of microclimate monitoring data is not researched yet. With the interactive access of multi-source information such as a wide area measurement technology, external meteorological monitoring information and the like, the microclimate monitoring device information with missing data is filled, and the method has important significance for further utilizing artificial intelligence and a big data mining technology to improve the stability of the power system.
Disclosure of Invention
To solve at least one of the technical problems in the prior art to a certain extent, the present invention provides a high-dimensional construction and completion method, system, device and medium for a microclimate monitoring device.
The technical scheme adopted by the invention is as follows:
a high-dimensional construction and completion method for a microclimate monitoring device comprises the following steps:
acquiring geographic longitude and latitude information of the distribution point of the microclimate monitoring device, and analyzing the regional and chronological characteristics of microclimate;
clustering analysis based on longitude and latitude two-dimensional information is carried out on the microclimate monitoring devices according to the geographic longitude and latitude information, and the microclimate monitoring devices with similar spatial geographic distances are divided into the same class;
acquiring monitoring information of microclimate monitoring devices classified into the same class, constructing a three-dimensional missing tensor according to the monitoring information, and realizing missing value filling of the microclimate monitoring devices according to the three-dimensional missing tensor and a low-rank tensor completion algorithm;
the dimensions of the three-dimensional missing tensor comprise the distribution number, the statistical days and the time section of the microclimate monitoring device.
Further, the microclimate monitoring device is applied to the overhead transmission line and is hung on the transmission line;
the regional and chronological characteristics of the microclimate are analyzed, and the method comprises the following steps:
the microclimate monitoring device monitors environmental information around a mounting point of the microclimate monitoring device in real time, and analyzes the regional and chronological characteristics of microclimate according to the environmental information;
the regional and time-sequence characteristics refer to the weather change difference of the weather values recorded by the micrometeorological monitoring stationing due to different geographic positions;
wherein the environmental information includes at least one of temperature, humidity, wind speed, wind direction, rainfall, light radiation and atmospheric pressure.
Further, the clustering analysis based on longitude and latitude two-dimensional information is carried out on the microclimate monitoring device according to the geographical longitude and latitude information, and the clustering analysis comprises the following steps:
setting longitude and latitude of n microclimate monitoring device distribution points to form a set X ═ X1，x2，...xi...，xnIn which xiThe two-dimensional column vector is formed by geographic longitude and latitude values;
dividing the n microclimate monitoring devices into t types by adopting a fuzzy C-means clustering algorithm;
the expression of the objective function J adopted in the fuzzy C-means clustering algorithm is as follows:
Figure BDA0003084128630000021
wherein u isijThe ith micrometeorological monitoring device is divided into the jth class of membership; m is an algorithm fuzzy coefficient; c is a clustering center of each type of longitude and latitude; u is a membership matrix.
Further, the missing value filling of the microclimate monitoring device is realized according to a three-dimensional missing tensor and low-rank tensor completion algorithm, and the method comprises the following steps:
a1, setting three-dimensional missing tensor
Figure BDA0003084128630000022
Wherein n is1The distribution quantity n of the micrometeorological monitoring devices representing the similar geographical space division2Representing the statistical number of days of acquisition，n3Representing the number of time segments of a day of the microclimate monitoring device;
a2, setting one and tensor
Figure BDA0003084128630000023
Tensor of the same size
Figure BDA0003084128630000024
Its element value is defined as two values (0,1), and satisfies a first condition:
Figure BDA0003084128630000031
a3, obtaining a target function of the low-rank tensor completion algorithm and constraint conditions thereof:
Figure BDA0003084128630000032
Figure BDA0003084128630000033
wherein:
Figure BDA0003084128630000034
is the original tension
Figure BDA0003084128630000035
An estimated value of (d);
Figure BDA0003084128630000036
are all of size n1×n2×n3The three-dimensional tensor of (a); matrix array
Figure BDA0003084128630000037
Is that
Figure BDA0003084128630000038
Tensor expansion in modality 1 of size n1×(n2×n3) (ii) a In the same way, the matrix
Figure BDA0003084128630000039
Is that
Figure BDA00030841286300000310
Tensor expansion under modality 2, matrix
Figure BDA00030841286300000311
Is that
Figure BDA00030841286300000312
Tensor expansion under modality 3; alpha is alpha1，α2，α3A weighting factor of an objective function, which satisfies a1+α2+α3Constraint of 1;
a4 obtaining the weighting factor of the low rank tensor completion algorithm
Figure BDA00030841286300000313
Scaling the coefficient rho and the maximum iteration number K;
a5 initializing the estimation tensor
Figure BDA00030841286300000314
The estimate tensor
Figure BDA00030841286300000315
The following constraints are satisfied:
Figure BDA00030841286300000316
a6, obtaining intermediate variables of low-rank tensor completion algorithm
Figure BDA00030841286300000317
Listening the intermediate variable to be a three-dimensional all-zero tensor;
a7, sequentially updating tensors according to a preset formula
Figure BDA00030841286300000318
Estimating tensor
Figure BDA00030841286300000319
Subject to intermediate variables
Figure BDA00030841286300000320
A8, if the iteration number of the algorithm is less than K, returning to execute the step A7; if the iteration number of the algorithm is equal to K, stopping the operation, and outputting the estimated tensor after missing value completion
Figure BDA00030841286300000321
Further, the expression of the preset formula is as follows:
Figure BDA00030841286300000322
Figure BDA00030841286300000323
Figure BDA00030841286300000324
wherein: foldq() As an operator, representing the reduction of the matrix into a tensor;
Figure BDA00030841286300000325
for operators, singular value decomposition of the matrix is indicated.
Further, the high-dimensional construction and completion method of the microclimate monitoring device further comprises the following steps:
calculating and dividing microclimate information envelope lines of the same type of microclimate monitoring devices in the same time zone, and realizing conservative early warning of regional microclimate monitoring history and synchronization according to the microclimate information envelope lines.
Further, the conservative early warning for realizing the regional microclimate monitoring history synchronization according to the microclimate information envelope curve comprises the following steps:
filling missing values of the monitoring information to obtain complete values, and arranging the complete values according to the counting days sequence of the micrometeorological monitoring device;
when the microclimate region in the same history period needs to be evaluated, the minimum value of meteorological parameters of the microclimate monitoring devices which are divided into the same class at the same moment is calculated, and an envelope curve is obtained according to the minimum value of the meteorological parameters and is used as a conservative early warning value of the microclimate region.
The other technical scheme adopted by the invention is as follows:
a micrometeorological monitoring devices high dimension constructs and completes the system, including:
the information acquisition module is used for acquiring geographic longitude and latitude information of the distribution point of the microclimate monitoring device and analyzing the regional and chronological characteristics of microclimate;
the information clustering module is used for carrying out clustering analysis based on longitude and latitude two-dimensional information on the microclimate monitoring devices according to the geographic longitude and latitude information and dividing the microclimate monitoring devices with similar spatial geographic distances into the same class;
the data filling module is used for acquiring monitoring information of the microclimate monitoring devices which are divided into the same class, constructing a three-dimensional missing tensor according to the monitoring information, and filling missing values of the microclimate monitoring devices according to the three-dimensional missing tensor and a low-rank tensor completion algorithm;
the dimensions of the three-dimensional missing tensor comprise the distribution number, the statistical days and the time section of the microclimate monitoring device.
The other technical scheme adopted by the invention is as follows:
a micrometeorological monitoring devices high dimension is constructed and is mended device, includes:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method described above.
The other technical scheme adopted by the invention is as follows:
a storage medium having stored therein a processor-executable program for performing the method as described above when executed by a processor.
The invention has the beneficial effects that: according to the method, missing values of the microclimate monitoring information with wrong and missing information are filled according to the time-space correlation of the microclimate monitoring information, and decision support can be provided for planning operation, meteorological modeling and post-disaster analysis of the overhead transmission line of the power system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description is made on the drawings of the embodiments of the present invention or the related technical solutions in the prior art, and it should be understood that the drawings in the following description are only for convenience and clarity of describing some embodiments in the technical solutions of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a high-dimensional construction and completion method of a microclimate monitoring device for an overhead transmission line in an embodiment of the invention;
FIG. 2 is a spatial division view of a microclimate monitoring device according to an embodiment of the present invention;
FIG. 3 is a comparison of thermodynamic diagrams under the 30% miss rate scenario in an embodiment of the invention;
FIG. 4 is a comparison of thermodynamic diagrams under the 60% miss rate scenario in an embodiment of the invention;
FIG. 5 is a comparison of thermodynamic diagrams under a 90% miss ratio scenario in an embodiment of the invention;
FIG. 6 is a schematic diagram of a convergence result under a 30% miss rate scenario in an embodiment of the present invention;
FIG. 7 is a schematic diagram of a convergence result under the scenario of 60% miss rate in the embodiment of the present invention;
fig. 8 is a schematic diagram of a convergence result under a situation of a 90% miss rate in the embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided only for convenience of illustration, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
As shown in fig. 1, the present embodiment provides a high-dimensional construction and completion method for a microclimate monitoring device of an overhead transmission line, including the following steps:
and S1, analyzing the regional and time sequence characteristics of microclimate, and reading the geographical longitude and latitude information of the distribution points of the microclimate monitoring devices distributed and installed along the power transmission line.
The microclimate monitoring device hung on the power transmission line can monitor information such as ambient temperature, humidity, wind speed, wind direction, rainfall, light radiation and atmospheric pressure around a mounting point in real time, and transmits the information to the centralized controller for monitoring at the acquisition frequency of 10 min/time. The regional and time-sequence characteristics of the microclimate monitoring data mean that the meteorological values recorded by the microclimate monitoring stations show certain meteorological variation differences due to different geographic positions. Microclimate monitoring devices with similar geographic positions can present approximate trend and time sequence correlation, microclimate monitoring information of the microclimate monitoring devices can present approximate increasing, converging or descending characteristics in the same time period in the future, and potential time sequence correlation coupling exists in data rules of different meteorological information such as air temperature and sunlight intensity; the microclimate monitoring device with the remote geographic position has the advantages that monitoring information can show periodicity and randomness in different seasons, distribution rules of the same monitoring value in the same time period are different greatly, and the microclimate monitoring device is easily influenced by local microtopography to show certain randomness.
And S2, performing clustering analysis based on longitude and latitude two-dimensional information on the microclimate monitoring devices by adopting a fuzzy C-means clustering algorithm, and dividing the microclimate monitoring devices with similar space geographic distances into the same class.
Step S2 includes steps S201-S206:
s201, setting a longitude and latitude composition set X ═ X of n microclimate monitoring device distribution points1，x2，...xi...，xnIn which xiDividing n microclimate monitoring devices into t classes for 2-dimensional column vectors formed by geographic longitude and latitude values based on a fuzzy C-means clustering algorithm, and setting the clustering center of each class of longitude and latitude as C ═ C1，c2，...cj...，ctAnd the fuzzy C-means clustering algorithm realizes clustering division by minimizing the following objective function J:
Figure BDA0003084128630000061
wherein: u. ofijThe ith micrometeorological monitoring device is divided into the jth class of membership; and m is an algorithm fuzzy coefficient. The steps of partitioning by using the fuzzy C-means clustering algorithm are as follows:
s202, initializing algorithm parameters including a stop threshold epsilon, a fuzzy coefficient m, iteration termination times T and a randomized clustering center C0And membership matrix U0。
S203, checking an algorithm membership normalization condition:
Figure BDA0003084128630000062
s204, sequentially updating the clustering center C and the membership degree U according to the following 2 formulas:
Figure BDA0003084128630000063
Figure BDA0003084128630000071
wherein: dij＝||xi-cj||，dik＝||xi-ckAnd | | represents the Euclidean distance calculation.
S205, taking the objective function satisfying J (U, C) < epsilon or reaching the maximum iteration number T as an algorithm termination criterion, outputting a division result of the microclimate monitoring device, and returning to the step S204 if 2 criteria are not satisfied.
And S206, performing iterative computation on C and U by using a fuzzy C-means clustering algorithm to minimize a target function, and further completing space division of the microclimate monitoring device.
And S3, reading the monitoring information of the microclimate monitoring devices which are divided into the same class, constructing a 3-dimensional missing tensor according to the distribution number, the statistical days and the time section of the microclimate monitoring devices, and realizing missing value filling of the microclimate monitoring devices based on a low-rank tensor completion algorithm.
Step S3 includes steps S301 to S309:
s301, the information collected by the microclimate monitoring device is meteorological monitoring data with the statistical date of 10min, the meteorological monitoring data comprises two dimensions of statistical days and time sections, and the space division result of the microclimate monitoring device can be obtained according to the step S2, so that missing values of the monitoring devices divided into the same class can be filled, and the third dimension of the distribution quantity of the monitoring devices is obtained. Therefore, the three-dimensional missing tensor of the microclimate monitoring data can be constructed.
S302, setting a three-dimensional missing tensor
Figure BDA0003084128630000072
Wherein n is1The distribution quantity n of the micrometeorological monitoring devices representing the similar geographical space division2Representing the number of statistical days of acquisition, n3Representing the number of time sections of a day of the microclimate monitoring device, the elements in the tensor represent the meteorological data collected by the microclimate monitoring device, and the index corresponding to the observed non-empty element is recorded as (i, j, k) epsilon omega.
S303, setting one and
Figure BDA0003084128630000073
tensor of the same size
Figure BDA0003084128630000074
The element value is limited to two values (0,1), and the following condition is satisfied:
Figure BDA0003084128630000075
s304, an objective function of the column write tensor completion algorithm and constraint conditions thereof:
Figure BDA0003084128630000076
Figure BDA0003084128630000077
wherein:
Figure BDA0003084128630000078
is the original tension
Figure BDA0003084128630000079
An estimated value of (d);
Figure BDA00030841286300000710
are all of size n1×n2×n3A 3-dimensional tensor of; matrix array
Figure BDA00030841286300000711
Is that
Figure BDA00030841286300000712
Tensor expansion in modality 1 of size n1×(n2×n3) (ii) a In the same way, the matrix
Figure BDA00030841286300000713
Is that
Figure BDA00030841286300000714
Tensor expansion under modality 2, matrix
Figure BDA00030841286300000715
Is that
Figure BDA00030841286300000716
Tensor expansion under modality 3; alpha is alpha1，α2，α3A weighting factor of an objective function, which satisfies a1+α2+α3Constraint of 1.
S305, presetting weighting factors of algorithm
Figure BDA0003084128630000081
Scaling factor p and maximum iteration number K.
S306, initializing the estimation tensor
Figure BDA00030841286300000813
It satisfies the following constraints:
Figure BDA0003084128630000083
s307, setting algorithm intermediate variables
Figure BDA0003084128630000084
Which is a three-dimensional all-zero tensor.
S308, sequentially updating the tensor according to the following 3 formulas
Figure BDA0003084128630000085
Estimating tensor
Figure BDA0003084128630000086
And intermediate variables
Figure BDA0003084128630000087
Figure BDA0003084128630000088
Figure BDA0003084128630000089
Figure BDA00030841286300000810
Wherein: foldq() As an operator, representing the reduction of the matrix into a tensor;
Figure BDA00030841286300000811
for operators, singular value decomposition of the matrix is indicated.
S309, taking the iteration number of the algorithm as a termination criterion. If the iteration frequency of the algorithm is less than K, returning to the step S308, if the iteration frequency of the algorithm is less than K, and the likeStopping the operation at K, and outputting the estimated tensor after the missing value is completed
Figure BDA00030841286300000812
S4, calculating microclimate information envelope curves of the same type of microclimate monitoring devices in the same time section, and further realizing conservative early warning of regional microclimate monitoring history and synchronization;
step S4 specifically includes steps S401 to S402:
s401, according to the complete numerical value after the microclimate monitoring information is filled in the step S3, the numerical value can be arranged according to the counting days sequence of the microclimate monitoring device.
S402, when the microclimate region in the same history period is to be evaluated, the minimum value of the meteorological parameters of the microclimate monitoring device divided into the same region at the same moment can be calculated, and an envelope curve is formed according to the minimum value and is used as a conservative early warning value of the region.
The above method is explained in detail below with reference to specific embodiments and the accompanying drawings.
Here, the information is arranged in chronological order (date order, 1 month 1 day, 1 month 2 days, 1 month 3 days …), which is a natural timing of the recording of the information by the monitoring apparatus. The purpose of the chronological order is: the meteorological monitoring data with similar time and date have similarity, and the algorithm utilizes the monitoring values of adjacent dates to fill up missing values. The microclimate data of the historical synchronization can be analyzed by directly calling the same date (for example, if microclimate data of 1 month and 1 day of 2020 is filled up, data of 1 month and 1 day of 2021 can be evaluated according to the historical synchronization of 2020).
156 microclimate monitoring devices in a certain area are used as research objects for analysis. Firstly, reading geographical longitude and latitude information of 156 microclimate monitoring devices distributed and installed along a power transmission line, and carrying out z-scores normalization on the geographical longitude and latitude information to form a longitude and latitude forming set X ═ X1，x2，...xi...，xnAnd then constructing an objective function based on a fuzzy C-means clustering algorithm:
Figure BDA0003084128630000091
and setting a fuzzy coefficient m of the algorithm to be 1, a stop threshold epsilon to be 0.001 and iteration termination times T to be 100, and after multiple attempts, obtaining the optimal result when the clusters are divided into 5 classes, wherein a scatter diagram of the division result is shown in a figure 2, and the space division classes and the number of the microclimate device are shown in a table 1.
TABLE 1 micrometeorological device space partitioning results
Figure BDA0003084128630000092
The information collected by the microclimate monitoring device is meteorological monitoring data with statistical dates of 10min, the meteorological monitoring data comprises 2 dimensions of statistical days and time sections, and space division results of the microclimate monitoring device can be obtained according to the table 1, so that missing values of monitoring devices divided into the same type can be filled, and the 3 rd dimension of the distribution number of the monitoring devices is obtained. From this, a 3-dimensional missing tensor for the microclimate monitoring data can be constructed.
Taking the class A division result of the microclimate device as an example, in order to verify the effectiveness of the method, the temperature data set without the missing 30 microclimate monitoring information in the class A of the region is manually selected for example analysis. Let 3-dimensional missing tensor
Figure BDA0003084128630000093
Wherein n is1Representing the number of the distributed microclimate monitoring devices of the same type with similar geographic space division, wherein the A type has 30, namely n1＝30；n2Representing the obtained statistical days, taking the data set of the missing gas temperature in July of a certain year as an object to be filled, and obtaining n2＝31；n3Representing the number of time sections of a day of the microclimate monitoring device, wherein the element represents the temperature data collected by the microclimate monitoring device, the information collected by the microclimate monitoring device is the weather monitoring data with the statistical date of 10min, and the monitoring time section of 24h is n3＝144。
Setting random missing elements through a program, wherein the specific method comprises the following steps: set one and
Figure BDA0003084128630000094
tensor of the same size
Figure BDA0003084128630000095
The element value is limited to two values (0,1), and the following condition is satisfied:
Figure BDA0003084128630000096
here, 30%, 60%, 90% of the cases in the case data set were randomly missing for verification.
Then, the target function and the constraint condition of the column write tensor completion algorithm are set, and the weighting factor of the algorithm is preset
Figure BDA0003084128630000101
The scaling factor ρ is 0.01 and the maximum iteration number K is 1000.
In the case, the error is evaluated by using two indexes of Root Mean Square Error (RMSE) and average relative error (MRE), and the filling evaluation result of the microclimate monitoring device is shown in a table 2.
TABLE 2 iteration number and filling error under different miss rate scenarios
Figure BDA0003084128630000102
As can be seen from table 2, the RMSE of the proposed method does not exceed 1.5 and the MRE thereof is less than 0.05 in the case of dealing with 30% and 60% deletion rates. When the deletion rate reaches 90%, the RMSE of the method is 2.9709, the MRE is 0.0979, and the result still has certain reference value. The filling result is visually displayed, and the comparison under the condition of 30%, 60% and 90% of deletion rate can be seen in attached figures 3-5; the convergence results in the 30%, 60%, 90% deficiency rate scenarios can be seen in fig. 6-8.
And obtaining a complete numerical value after the microclimate monitoring information is filled, and arranging the complete numerical value according to the statistical days sequence of the microclimate monitoring device. When the microclimate region in the same history period is to be evaluated, the minimum value of meteorological parameters of the microclimate monitoring device divided into the same region at the same moment can be calculated, and an envelope curve is formed according to the minimum value and is used as a conservative early warning value of the region. It should be noted that, the obtained filling effect varies according to different microclimate monitoring information, and at this time, it is indicated that the microclimate monitoring information has weak temporal and spatial correlation.
In summary, compared with the prior art, the method of the embodiment of the present invention has the following beneficial effects:
(1) the method analyzes that meteorological data acquired by the microclimate monitoring device of the power system transmission line has high-dimensional space-time correlation, and provides that modeling analysis can be performed on the meteorological data by utilizing a tensor algorithm, the tensor algorithm can mine the coupling among high-dimensional arrays, more potential information is provided for filling of missing values, and then the filling accuracy is improved.
(2) According to the embodiment, the geographical longitude and latitude of the distribution point of the microclimate monitoring device can be utilized for clustering division, so that the spatial dimension of microclimate information in a power transmission corridor area is represented, and classification information is provided for the construction of a subsequent 3-dimensional missing tensor.
(3) The embodiment provides that a 3-dimensional missing tensor can be constructed based on the distribution number, the statistical number of days and the time section of the microclimate monitoring device, and missing value filling is performed by using a low-rank tensor completion algorithm. The missing value filling can be performed according to the logic for the power parameters (such as current values) in other fields of the power system, and the key is to construct a tensor with dimensions of 3 or more than 3.
(4) According to the method, historical contemporaneous conservative early warning of regional microclimate information can be performed by using the space division result of the microclimate monitoring device, and complete microclimate information can be filled to provide decision support for planning operation, meteorological modeling and post-disaster analysis of the overhead transmission line of the power system.
This embodiment still provides a little meteorological monitoring device high dimension and constructs and completion system, includes:
the information acquisition module is used for acquiring geographic longitude and latitude information of the distribution point of the microclimate monitoring device and analyzing the regional and chronological characteristics of microclimate;
the information clustering module is used for carrying out clustering analysis based on longitude and latitude two-dimensional information on the microclimate monitoring devices according to the geographic longitude and latitude information and dividing the microclimate monitoring devices with similar spatial geographic distances into the same class;
the data filling module is used for acquiring monitoring information of the microclimate monitoring devices which are divided into the same class, constructing a three-dimensional missing tensor according to the monitoring information, and filling missing values of the microclimate monitoring devices according to the three-dimensional missing tensor and a low-rank tensor completion algorithm;
the dimensions of the three-dimensional missing tensor comprise the distribution number, the statistical days and the time section of the microclimate monitoring device.
The microclimate monitoring device high-dimensional construction and completion system can execute the microclimate monitoring device high-dimensional construction and completion method provided by the method embodiment of the invention, can execute any combination implementation steps of the method embodiment, and has corresponding functions and beneficial effects of the method.
This embodiment still provides a little meteorological monitoring device high dimension and constructs and completion device, includes:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method shown in fig. 1.
The microclimate monitoring device high-dimensional construction and completion device provided by the embodiment of the invention can execute the microclimate monitoring device high-dimensional construction and completion method provided by the embodiment of the method of the invention, can execute any combination implementation steps of the embodiment of the method, and has corresponding functions and beneficial effects of the method.
The embodiment of the application also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and executed by the processor to cause the computer device to perform the method illustrated in fig. 1.
The embodiment also provides a storage medium, which stores instructions or programs capable of executing the high-dimensional construction and completion method of the microclimate monitoring device provided by the embodiment of the method, and when the instructions or the programs are operated, the steps can be implemented by any combination of the embodiment of the method, so that the method has corresponding functions and beneficial effects.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the foregoing description of the specification, reference to the description of "one embodiment/example," "another embodiment/example," or "certain embodiments/examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (10)

1. A micrometeorological monitoring device high-dimensional construction and completion method is characterized by comprising the following steps:
acquiring geographic longitude and latitude information of the distribution point of the microclimate monitoring device, and analyzing the regional and chronological characteristics of microclimate;
clustering analysis based on longitude and latitude two-dimensional information is carried out on the microclimate monitoring devices according to the geographic longitude and latitude information, and the microclimate monitoring devices with similar spatial geographic distances are divided into the same class;
acquiring monitoring information of microclimate monitoring devices classified into the same class, constructing a three-dimensional missing tensor according to the monitoring information, and realizing missing value filling of the microclimate monitoring devices according to the three-dimensional missing tensor and a low-rank tensor completion algorithm;
the dimensions of the three-dimensional missing tensor comprise the distribution number, the statistical days and the time section of the microclimate monitoring device.
2. The micrometeorological monitoring device high-dimensional construction and completion method according to claim 1, characterized in that, the micrometeorological monitoring device is applied to an overhead transmission line, and the micrometeorological monitoring device is hung on the transmission line;
the regional and chronological characteristics of the microclimate are analyzed, and the method comprises the following steps:
the microclimate monitoring device monitors environmental information around a mounting point of the microclimate monitoring device in real time, and analyzes the regional and chronological characteristics of microclimate according to the environmental information;
the regional and time-sequence characteristics refer to the weather change difference of the weather values recorded by the micrometeorological monitoring stationing due to different geographic positions;
wherein the environmental information includes at least one of temperature, humidity, wind speed, wind direction, rainfall, light radiation and atmospheric pressure.
3. The high-dimensional construction and completion method for the microclimate monitoring device according to claim 1, wherein the clustering analysis based on longitude and latitude two-dimensional information is performed on the microclimate monitoring device according to the geographical longitude and latitude information, and comprises the following steps:
setting longitude and latitude of n microclimate monitoring device distribution points to form a set X ═ X1,x2,...xi...,xnIn which xiThe two-dimensional column vector is formed by geographic longitude and latitude values;
dividing the n microclimate monitoring devices into t types by adopting a fuzzy C-means clustering algorithm;
the expression of the objective function J adopted in the fuzzy C-means clustering algorithm is as follows:
Figure FDA0003084128620000011
wherein u isijThe ith micrometeorological monitoring device is divided into the jth class of membership; m is an algorithm fuzzy coefficient; c is a clustering center of each type of longitude and latitude; u is a membership matrix.
4. The method for constructing and completing the microclimate monitoring device in the high dimension according to claim 1, wherein the missing value filling of the microclimate monitoring device is achieved according to a three-dimensional missing tensor and low-rank tensor completion algorithm, and the method comprises the following steps:
a1, setting three-dimensional missing tensor
Figure FDA0003084128620000012
Wherein n is1The distribution quantity n of the micrometeorological monitoring devices representing the similar geographical space division2Representing the number of statistical days of acquisition, n3Representing the number of time segments of a day of the microclimate monitoring device;
a2, setting one and tensor
Figure FDA0003084128620000013
Tensor of the same size
Figure FDA0003084128620000014
Its element value is defined as two values (0,1), and satisfies a first condition:
Figure FDA0003084128620000021
a3, obtaining a target function of the low-rank tensor completion algorithm and constraint conditions thereof:
Figure FDA0003084128620000022
Figure FDA0003084128620000023
wherein:
Figure FDA0003084128620000024
is the original tension
Figure FDA0003084128620000025
An estimated value of (d);
Figure FDA0003084128620000026
are all of size n1×n2×n3The three-dimensional tensor of (a); matrix array
Figure FDA0003084128620000027
Is that
Figure FDA0003084128620000028
Tensor expansion in modality 1 of size n1×(n2×n3) (ii) a In the same way, the matrix
Figure FDA0003084128620000029
Is that
Figure FDA00030841286200000210
Tensor expansion under modality 2, matrix
Figure FDA00030841286200000211
Is that
Figure FDA00030841286200000212
Tensor expansion under modality 3; alpha is alpha1,α2,α3A weighting factor of an objective function, which satisfies a1+α2+α3Constraint of 1;
a4 obtaining the weighting factor of the low rank tensor completion algorithm
Figure FDA00030841286200000213
Scaling the coefficient rho and the maximum iteration number K;
a5 initializing the estimation tensor
Figure FDA00030841286200000214
The estimate tensor
Figure FDA00030841286200000215
The following constraints are satisfied:
Figure FDA00030841286200000216
a6 method for obtaining low rank tensor completion algorithmIntermediate variables
Figure FDA00030841286200000217
The intermediate variable is a three-dimensional all-zero tensor;
a7, sequentially updating tensors according to a preset formula
Figure FDA00030841286200000218
Estimating tensor
Figure FDA00030841286200000219
And intermediate variables
Figure FDA00030841286200000220
A8, if the iteration number of the algorithm is less than K, returning to execute the step A7; if the iteration number of the algorithm is equal to K, stopping the operation, and outputting the estimated tensor after missing value completion
Figure FDA00030841286200000221
5. The micrometeorological monitoring device high-dimensional construction and completion method according to claim 1, characterized in that the expression of the preset formula is:
Figure FDA00030841286200000222
Figure FDA00030841286200000223
Figure FDA00030841286200000224
wherein: foldq() As an operator, representing the reduction of the matrix into a tensor;
Figure FDA00030841286200000225
for operators, singular value decomposition of the matrix is indicated.
6. The micrometeorological monitoring device high-dimensional construction and completion method according to claim 1, characterized in that the micrometeorological monitoring device high-dimensional construction and completion method further comprises the following steps:
calculating and dividing microclimate information envelope lines of the same type of microclimate monitoring devices in the same time zone, and realizing conservative early warning of regional microclimate monitoring history and synchronization according to the microclimate information envelope lines.
7. The high-dimensional construction and completion method for the microclimate monitoring device according to claim 6, wherein the conservative early warning of the regional microclimate monitoring history period according to microclimate information envelope curves comprises the following steps:
filling missing values of the monitoring information to obtain complete values, and arranging the complete values according to the counting days sequence of the micrometeorological monitoring device;
when the microclimate region in the same history period needs to be evaluated, the minimum value of meteorological parameters of the microclimate monitoring devices which are divided into the same class at the same moment is calculated, and an envelope curve is obtained according to the minimum value of the meteorological parameters and is used as a conservative early warning value of the microclimate region.
8. The utility model provides a micrometeorological monitoring devices high dimension constructs and completes system which characterized in that includes:
the information acquisition module is used for acquiring geographic longitude and latitude information of the distribution point of the microclimate monitoring device and analyzing the regional and chronological characteristics of microclimate;
the information clustering module is used for carrying out clustering analysis based on longitude and latitude two-dimensional information on the microclimate monitoring devices according to the geographic longitude and latitude information and dividing the microclimate monitoring devices with similar spatial geographic distances into the same class;
the data filling module is used for acquiring monitoring information of the microclimate monitoring devices which are divided into the same class, constructing a three-dimensional missing tensor according to the monitoring information, and filling missing values of the microclimate monitoring devices according to the three-dimensional missing tensor and a low-rank tensor completion algorithm;
the dimensions of the three-dimensional missing tensor comprise the distribution number, the statistical days and the time section of the microclimate monitoring device.
9. The utility model provides a micrometeorological monitoring devices high dimension constructs and completes device which characterized in that includes:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method of any one of claims 1-7.
10. A storage medium having stored therein a program executable by a processor, wherein the program executable by the processor is adapted to perform the method of any one of claims 1-7 when executed by the processor.
CN202110575454.1A 2021-05-26 2021-05-26 High-dimensional construction and completion method, system, device and medium for microclimate monitoring device Active CN113408788B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110575454.1A CN113408788B (en) 2021-05-26 2021-05-26 High-dimensional construction and completion method, system, device and medium for microclimate monitoring device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110575454.1A CN113408788B (en) 2021-05-26 2021-05-26 High-dimensional construction and completion method, system, device and medium for microclimate monitoring device

Publications (2)

Publication Number Publication Date
CN113408788A true CN113408788A (en) 2021-09-17
CN113408788B CN113408788B (en) 2022-05-24

Family

ID=77675158

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110575454.1A Active CN113408788B (en) 2021-05-26 2021-05-26 High-dimensional construction and completion method, system, device and medium for microclimate monitoring device

Country Status (1)

Country Link
CN (1) CN113408788B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115327675A (en) * 2022-10-13 2022-11-11 安徽省大气探测技术保障中心 Method, system, equipment and storage medium for monitoring running state of meteorological equipment
CN115840881A (en) * 2023-02-15 2023-03-24 湖南红普创新科技发展有限公司 Air data processing method and device and related equipment
CN116450636A (en) * 2023-06-20 2023-07-18 石家庄学院 Internet of things data completion method, equipment and medium based on low-rank tensor decomposition

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109063975A (en) * 2018-07-11 2018-12-21 国网黑龙江省电力有限公司电力科学研究院 A kind of electric power microclimate disaster monitoring and prior-warning device
CN109241491A (en) * 2018-07-28 2019-01-18 天津大学 The structural missing fill method of tensor based on joint low-rank and rarefaction representation
CN111224467A (en) * 2019-12-25 2020-06-02 云南电网有限责任公司信息中心 Power transmission line monitoring system and method based on space-time information unified service
CN112286914A (en) * 2020-10-12 2021-01-29 国网天津市电力公司电力科学研究院 Icing galloping early warning system and method based on microclimate online data of power transmission line

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109063975A (en) * 2018-07-11 2018-12-21 国网黑龙江省电力有限公司电力科学研究院 A kind of electric power microclimate disaster monitoring and prior-warning device
CN109241491A (en) * 2018-07-28 2019-01-18 天津大学 The structural missing fill method of tensor based on joint low-rank and rarefaction representation
CN111224467A (en) * 2019-12-25 2020-06-02 云南电网有限责任公司信息中心 Power transmission line monitoring system and method based on space-time information unified service
CN112286914A (en) * 2020-10-12 2021-01-29 国网天津市电力公司电力科学研究院 Icing galloping early warning system and method based on microclimate online data of power transmission line

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
樊子德 等: "顾及时空异质性的缺失数据时空插值方法", 《测绘学报》 *
欧阳森 等: "考虑外部环境信息的电网故障识别与原因分析方法", 《高电压技术》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115327675A (en) * 2022-10-13 2022-11-11 安徽省大气探测技术保障中心 Method, system, equipment and storage medium for monitoring running state of meteorological equipment
CN115327675B (en) * 2022-10-13 2023-01-06 安徽省大气探测技术保障中心 Method, system, equipment and storage medium for monitoring running state of meteorological equipment
CN115840881A (en) * 2023-02-15 2023-03-24 湖南红普创新科技发展有限公司 Air data processing method and device and related equipment
CN116450636A (en) * 2023-06-20 2023-07-18 石家庄学院 Internet of things data completion method, equipment and medium based on low-rank tensor decomposition
CN116450636B (en) * 2023-06-20 2023-08-18 石家庄学院 Internet of things data completion method, equipment and medium based on low-rank tensor decomposition

Also Published As

Publication number Publication date
CN113408788B (en) 2022-05-24

Similar Documents

Publication Publication Date Title
CN113408788B (en) High-dimensional construction and completion method, system, device and medium for microclimate monitoring device
Li et al. Attention-based interpretable neural network for building cooling load prediction
Ali et al. Review of urban building energy modeling (UBEM) approaches, methods and tools using qualitative and quantitative analysis
CN113962364B (en) Multi-factor power load prediction method based on deep learning
Taşpınar et al. Forecasting of daily natural gas consumption on regional basis in Turkey using various computational methods
US20230128989A1 (en) Systems and methods of data preprocessing and augmentation for neural network climate forecasting models
Carpinone et al. Markov chain modeling for very-short-term wind power forecasting
US20150317589A1 (en) Forecasting system using machine learning and ensemble methods
Li et al. A spatial-temporal layer-wise relevance propagation method for improving interpretability and prediction accuracy of LSTM building energy prediction
Ahmad et al. Novel deep supervised ML models with feature selection approach for large-scale utilities and buildings short and medium-term load requirement forecasts
EP4226473A1 (en) Estimating energy consumption for a building using dilated convolutional neural networks
CN116796168A (en) CNN-BiLSTM high-altitude multi-factor power transmission line audible noise prediction method based on multi-head attention mechanism
Zhang et al. Forecasting of electricity prices using deep learning networks
Alarie et al. Snow water equivalent estimation using blackbox optimization
Cibin et al. Machine learning-based algorithms to estimate thermal dynamics of residential buildings with energy flexibility
Guo et al. Traffic Flow Forecasting for Road Tunnel Using PSO‐GPR Algorithm with Combined Kernel Function
Sanzana et al. Charging water load prediction for a thermal-energy-storage air-conditioner of a commercial building with a multilayer perceptron
Nezzar et al. Mid-long term Algerian electric load forecasting using regression approach
Omirgaliyev et al. Application of machine learning methods for the analysis of heat energy consumption by zones with a change in outdoor temperature: Case study for Nur-Sultan city
Xiong et al. An ultra-short-term wind speed correction method based on the fluctuation characteristics of wind speed
Stopps et al. Smart choice or flawed approach? An exploration of connected thermostat data fidelity and use in data-driven modelling in high-rise residential buildings
Shahid et al. Autoencoders for Anomaly Detection in Electricity and District Heating Consumption: A Case Study in School Buildings in Sweden
Chen et al. An advanced airport terminal cooling load forecasting model integrating SSA and CNN-Transformer
Morales et al. Renewable energy sources—Modeling and forecasting
Wang et al. Short-term probability density function forecasting of industrial loads based on ConvLSTM-MDN

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant