CN112612781A - Data correction method, device, equipment and medium - Google Patents

Data correction method, device, equipment and medium Download PDF

Info

Publication number
CN112612781A
CN112612781A CN201911268112.4A CN201911268112A CN112612781A CN 112612781 A CN112612781 A CN 112612781A CN 201911268112 A CN201911268112 A CN 201911268112A CN 112612781 A CN112612781 A CN 112612781A
Authority
CN
China
Prior art keywords
meteorological
data
historical
corrected
elements
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911268112.4A
Other languages
Chinese (zh)
Inventor
丁明月
孔伯骏
匡宇
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.)
Jiangsu Jinfeng Software Technology Co ltd
Beijing Goldwind Smart Energy Service Co Ltd
Original Assignee
Jiangsu Jinfeng Software Technology Co ltd
Beijing Goldwind Smart Energy Service Co Ltd
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 Jiangsu Jinfeng Software Technology Co ltd, Beijing Goldwind Smart Energy Service Co Ltd filed Critical Jiangsu Jinfeng Software Technology Co ltd
Priority to CN201911268112.4A priority Critical patent/CN112612781A/en
Publication of CN112612781A publication Critical patent/CN112612781A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • 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
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/219—Managing data history or versioning
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Abstract

The embodiment of the invention discloses a data correction method, a data correction device, data correction equipment and a data correction medium. The method comprises the following steps: acquiring historical forecast data and real-time forecast data of a plurality of meteorological elements of a target site and historical observation data of elements to be corrected of the target site; determining a correlation coefficient between each meteorological element and the element to be corrected according to the historical forecast data and the historical observation data; screening meteorological elements with correlation coefficients meeting a preset threshold range according to the correlation coefficients; performing dimensionality reduction processing on the screened historical forecast data and real-time forecast data of the meteorological elements to obtain a minimum meteorological element characteristic set containing at least one meteorological element characteristic; and determining real-time forecast data of the elements to be corrected according to the minimum meteorological element feature set and historical observation data of the elements to be corrected. The data correction method, the data correction device, the data correction equipment and the data correction medium can correct real-time forecast data and improve the accuracy of the real-time forecast data.

Description

Data correction method, device, equipment and medium
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a data correction method, apparatus, device, and medium.
Background
Data such as wind speed and wind direction of numerical weather forecast are used as input quantities, and forecasted meteorological elements are converted into output power forecast of a wind power plant and photovoltaic through a forecasting algorithm. Therefore, accurate prediction of numerical weather forecast data can provide important decision support for power scheduling, and is one of important decision factors of new energy power generation prediction accuracy.
The numerical weather forecast refers to a method for predicting the atmospheric motion state and the weather phenomenon in a certain period of time according to the actual atmospheric conditions by using a large-scale computer to perform numerical calculation under certain initial value and boundary value conditions, solving the fluid mechanics and thermodynamics equation set in the weather evolution process.
The current numerical weather forecasting methods mainly include a Model Output Statistical (MOS) forecasting method, a Perfect Prediction (PP) method, a kalman filter forecasting method, an ensemble forecasting method, and an analog forecasting (analog ensemble) method.
However, the data predicted by the above method may not be accurate, and thus, the predicted data needs to be corrected to improve the accuracy of the predicted data.
Disclosure of Invention
Embodiments of the present invention provide a data correction method, apparatus, device, and medium, which can correct real-time forecast data and improve accuracy of the real-time forecast data.
In one aspect, an embodiment of the present invention provides a data correction method based on a minimum meteorological element feature set, including:
acquiring historical forecast data and real-time forecast data of a plurality of meteorological elements of a target site and historical observation data of elements to be corrected of the target site;
determining a correlation coefficient between each meteorological element and the element to be corrected according to historical forecast data of a plurality of meteorological elements and historical observation data of the element to be corrected;
screening meteorological elements with correlation coefficients meeting a preset threshold range according to the correlation coefficients;
performing dimensionality reduction processing on the screened historical forecast data and real-time forecast data of the meteorological elements to obtain a minimum meteorological element characteristic set containing at least one meteorological element characteristic;
and determining real-time forecast data of the elements to be corrected according to the minimum meteorological element feature set and historical observation data of the elements to be corrected.
In one embodiment of the present invention, determining a correlation coefficient between each meteorological element and the element to be corrected according to historical forecast data of a plurality of meteorological elements and historical observation data of the element to be corrected comprises:
determining the correlation coefficient of each meteorological element and the element to be corrected according to the following formula:
Figure BDA0002313441020000021
wherein E is a correlation coefficient; fiFor the ith historical forecast data of a certain meteorological element,
Figure BDA0002313441020000022
the historical forecast data average value of a certain meteorological element is obtained; o isiFor the ith historical observation of the element to be corrected,
Figure BDA0002313441020000023
the average value of the historical observation data of the elements to be corrected is obtained; x is the quantity of historical forecast data of a certain meteorological element; and Y is the number of the historical observation data of the elements to be corrected.
In an embodiment of the present invention, performing dimension reduction processing on the historical forecast data and the real-time forecast data of the screened meteorological elements to obtain a minimum meteorological element feature set including at least one meteorological element feature, includes:
and performing dimensionality reduction on the screened historical forecast data and real-time forecast data of the meteorological elements by using a principal component analysis method to obtain a minimum meteorological element characteristic set containing at least one meteorological element characteristic.
In one embodiment of the present invention, determining real-time forecast data of a factor to be corrected according to a minimum feature set of meteorological factors and historical observation data of the factor to be corrected includes:
determining a second meteorological element characteristic similar to the first meteorological element characteristic in the minimum meteorological element characteristic set by using a similar forecasting algorithm, wherein the first meteorological element characteristic corresponds to real-time forecasting data, and the second meteorological element characteristic corresponds to historical forecasting data;
acquiring historical observation data of the element to be corrected corresponding to the second meteorological element characteristic in time;
and averaging the acquired historical observation data to be used as real-time forecast data of the element to be corrected.
In one embodiment of the invention, the elements to be modified comprise meteorological elements and/or other elements than meteorological elements.
In another aspect, an embodiment of the present invention provides a data correction apparatus based on a minimum meteorological element feature set, including:
the acquisition module is used for acquiring historical forecast data and real-time forecast data of a plurality of meteorological elements of a target site and historical observation data of elements to be corrected of the target site;
the determining module is used for determining a correlation coefficient between each meteorological element and the element to be corrected according to historical forecast data of a plurality of meteorological elements and historical observation data of the element to be corrected;
the screening module is used for screening meteorological elements of which the correlation coefficients accord with a preset threshold range according to the correlation coefficients;
the dimension reduction module is used for carrying out dimension reduction processing on the historical forecast data and the real-time forecast data of the screened meteorological elements to obtain a minimum meteorological element feature set containing at least one meteorological element feature;
and the correction module is used for determining real-time forecast data of the element to be corrected according to the minimum meteorological element feature set and the historical observation data of the element to be corrected.
In an embodiment of the present invention, the determining module is specifically configured to:
determining the correlation coefficient of each meteorological element and the element to be corrected according to the following formula:
Figure BDA0002313441020000031
wherein E is a correlation coefficient; fiFor the ith historical forecast data of a certain meteorological element,
Figure BDA0002313441020000032
the historical forecast data average value of a certain meteorological element is obtained; o isiFor the ith historical observation of the element to be corrected,
Figure BDA0002313441020000033
the average value of the historical observation data of the elements to be corrected is obtained; x is the quantity of historical forecast data of a certain meteorological element; and Y is the number of the historical observation data of the elements to be corrected.
In an embodiment of the present invention, the dimension reduction module is specifically configured to:
performing dimensionality reduction on the historical forecast data and the real-time forecast data of the screened meteorological elements by using a principal component analysis method to obtain a minimum meteorological element feature set containing at least one meteorological element feature
In an embodiment of the present invention, the modification module is specifically configured to:
determining a second meteorological element similar to the first meteorological element characteristic in the minimum meteorological element characteristic set by using a similar forecasting algorithm, wherein the first meteorological element characteristic corresponds to real-time forecasting data, and the second meteorological element characteristic corresponds to historical forecasting data;
acquiring historical observation data of the element to be corrected corresponding to the second meteorological element characteristic in time;
and averaging the acquired historical observation data to be used as real-time forecast data of the element to be corrected.
In one embodiment of the invention, the elements to be modified comprise meteorological elements and/or other elements than meteorological elements.
In another aspect, an embodiment of the present invention provides a data correction device based on a minimum meteorological element feature set, including: a processor, a memory, and a computer program stored on the memory and executable on the processor;
when the processor executes the computer program, the data correction method based on the minimum meteorological element feature set provided by the embodiment of the invention is realized.
In another aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the data correction method based on a minimum meteorological element feature set provided by an embodiment of the present invention.
The data correction method, device, equipment and medium based on the minimum meteorological element feature set can correct the real-time forecast data of the elements to be corrected, and improve the accuracy of the real-time forecast data of the elements to be corrected.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a data modification method based on a minimum meteorological element feature set according to an embodiment of the invention;
FIG. 2 is a schematic diagram illustrating the real-time forecast data corresponding to the features of meteorological elements according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating features of meteorological elements corresponding to historical forecast data according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a data modification apparatus based on a minimum meteorological element feature set according to an embodiment of the present invention;
FIG. 5 sets forth a block diagram of an exemplary hardware architecture of computing devices capable of implementing the minimum meteorological element feature set based data correction method and apparatus according to embodiments of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In order to make the purpose, technical solution and technical effects of the present application more clear, embodiments of the present invention will be described in further detail below with reference to the accompanying drawings. First, several terms referred to in the present application will be introduced and explained.
And (3) forecasting data in real time: when weather forecast is carried out, the forecast weather data is calculated by the computer according to the existing data in the latest period of time.
Historical forecast data: the predicted weather forecast data is calculated by the computer before the time point when the weather forecast is required at present, and the data is stored in the computer device and is calculated historical data.
Historical observation data: the actual data collected by the meteorological equipment can be meteorological data or non-meteorological data, such as power data, grain yield, cold drink sales quantity and the like.
Meteorological elements: the basic data parameters related to weather indicate the physical state of the atmosphere and various elements of physical phenomena, such as air temperature, humidity, air pressure, wind speed, ultraviolet intensity, illumination intensity, air density and the like.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific examples. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart illustrating a data correction method based on a minimum meteorological element feature set according to an embodiment of the present invention. The data correction method based on the minimum meteorological element feature set can comprise the following steps:
s101: historical forecast data and real-time forecast data of a plurality of meteorological elements of the target site and historical observation data of elements to be corrected of the target site are obtained.
The elements to be corrected of the embodiment of the invention can be meteorological elements, and can also be other elements besides meteorological elements, such as power, grain yield, cold drink sales quantity and the like.
S102: and determining a correlation coefficient between each meteorological element and the element to be corrected according to the historical forecast data of the meteorological elements and the historical observation data of the element to be corrected.
S103: and screening out meteorological elements with the correlation coefficients meeting a preset threshold range according to the correlation coefficients.
S104: and performing dimensionality reduction processing on the screened historical forecast data and real-time forecast data of the meteorological elements to obtain a minimum meteorological element characteristic set containing at least one meteorological element characteristic.
S105: and determining real-time forecast data of the elements to be corrected according to the minimum meteorological element feature set and historical observation data of the elements to be corrected.
The data correction method based on the minimum meteorological element feature set can correct the real-time forecast data of the element to be corrected, and improves the accuracy of the real-time forecast data of the element to be corrected.
For example, it is assumed that the unit time of data acquisition (also referred to as data time resolution) is 15 minutes, i.e., one data is acquired every 15 minutes.
If the N-number of weather elements are acquired and the data time resolution is 15 minutes, then (60/15) × 24 × N is 96N pieces of history forecast data for each weather element. The 96N historical forecast data of the ith meteorological element can be represented as H1,i、H2,i、H3,i、……、H96N,i。
The historical forecast data for N days of M meteorological elements can be represented by a matrix T1 as:
Figure BDA0002313441020000071
wherein, the data in the ith column in the matrix T1 represents the historical forecast data of the ith meteorological element in the N days.
And acquiring real-time forecast data of the M meteorological elements for the next n days, wherein each meteorological element has (60/15) × 24 × n ═ 96n historical forecast data. The 96n real-time forecast data of the ith meteorological element can be represented as F1,i、F2,i、F3,i、……、F96n,i。
The historical forecast data for n days of M meteorological elements can be represented by a matrix T2 as:
Figure BDA0002313441020000072
wherein, the data in the ith column in the matrix T2 represents the real-time forecast data of the ith meteorological element for n days.
If the historical observation data of the element to be corrected for N days is acquired according to the same data time resolution, the element to be corrected has (60/15) × 24 × N ═ 96N historical forecast data. The 96N historical observations of the element to be corrected are denoted O1、O2、O3、……、O96N。
And determining a correlation coefficient of each meteorological element and the element to be corrected in the M meteorological elements according to the historical forecast data of the M meteorological elements in the N days and the historical observation data of the element to be corrected in the N days.
In one embodiment of the present invention, the correlation coefficient between each meteorological element of the M meteorological elements and the element to be corrected can be determined by using the following formula (1).
Figure BDA0002313441020000073
Wherein, in the formula (1), E is a correlation coefficient; fiFor the ith historical forecast data of a certain meteorological element,
Figure BDA0002313441020000074
the historical forecast data average value of the meteorological element is obtained; o isiFor the ith historical observation of the element to be corrected,
Figure BDA0002313441020000075
the average value of the historical observation data of the elements to be corrected is obtained; x is the quantity of the historical forecast data of the meteorological element; calendar with Y as correction elementThe number of historical observations.
The correlation coefficient between the 1 st meteorological element and the element to be corrected in the M meteorological elements, the correlation coefficient between the 2 nd meteorological element and the element to be corrected in the M meteorological elements, … … and the correlation coefficient between the M meteorological element and the element to be corrected in the M meteorological elements can be determined through the formula (1).
And screening out meteorological elements of which the correlation coefficients accord with a preset threshold range after determining the correlation coefficients of each meteorological element in the M meteorological elements and the elements to be corrected.
In one embodiment of the present invention, meteorological elements with correlation coefficients smaller than a preset threshold value may be discarded, and only meteorological elements with correlation coefficients higher than the preset threshold value may be retained.
By screening the meteorological elements by using the correlation coefficient, meteorological elements having small correlation with the element to be corrected can be filtered out from the M meteorological elements, and when correcting the real-time forecast data of the element to be corrected, only meteorological elements having large correlation with the element to be corrected can be used. Through the operation, the efficiency of correcting the real-time forecast data of the element to be corrected can be improved.
After the meteorological elements with the correlation coefficients meeting the preset threshold range are screened out, dimension reduction processing can be performed on historical forecast data and real-time forecast data of the screened meteorological elements, and a minimum meteorological element feature set containing at least one meteorological element feature is obtained.
In an embodiment of the present invention, a Principal Component Analysis (PCA) method may be used to perform dimension reduction processing on the historical forecast data and the real-time forecast data of the screened meteorological elements, so as to obtain a minimum meteorological element feature set including at least one meteorological element feature.
In an embodiment of the present invention, the meteorological element characteristics are principal components corresponding to historical forecast data and real-time forecast data of the meteorological element.
Specifically, m meteorological elements are obtained after screening, and historical forecast data and real-time forecast data of the m meteorological elements for N + N days can be represented by a matrix T3:
Figure BDA0002313441020000081
wherein, Z is 96N + 96N. The data in the ith column in the matrix T3 represents the N-day historical forecast data and the N-day real-time forecast data of the ith meteorological element among the screened m meteorological elements.
After matrix T3 is obtained, the average of the respective columns is subtracted from each column to de-center the matrix.
Then, eigenvalues and eigenvectors of the covariance matrix corresponding to the decentralized matrix T3 are calculated. And selecting the largest K eigenvalues from the plurality of eigenvalues, wherein eigenvectors corresponding to the K eigenvalues form an eigenvector matrix, and the matrix is the minimum meteorological element feature set and comprises at least one meteorological element feature. It should be noted that the larger the eigenvalue is, the larger the difference between the meteorological element and other meteorological elements is, K pieces of information with large difference are reserved, that is, original information of data can be greatly reserved while data dimensionality is reduced, and information overlapping with information of other dimensionalities is ignored.
At this time, dimension reduction is performed on the historical forecast data and the real-time forecast data of the m meteorological elements for N + N days into a feature vector matrix corresponding to the K eigenvalues, namely, the dimension reduction is performed on the m-dimensional matrix into a K-dimensional matrix.
The minimum meteorological feature set shared matrix T4 containing at least one meteorological feature is represented as:
Figure BDA0002313441020000091
wherein, Z is 96N + 96N.
And then, determining real-time forecast data of the element to be corrected according to the minimum meteorological element feature set and the historical observation data of the element to be corrected.
In one embodiment of the present invention, a similarity prediction algorithm may be used to determine a second meteorological element characteristic similar to a first meteorological element characteristic in the minimum set of meteorological element characteristics, where the first meteorological element characteristic is a meteorological element characteristic corresponding to real-time forecast data and the second meteorological element characteristic is a meteorological element characteristic corresponding to historical forecast data. Then, historical observation data of the element to be corrected corresponding to the second meteorological element characteristic in time is obtained. And finally, averaging the acquired historical observation data to be used as real-time forecast data of the elements to be corrected.
Specifically, the minimum meteorological element feature set is used as k meteorological element sets and input into a similarity forecasting system, similar weather systems are searched in historical simulation according to real-time simulation, and similarity criteria are as follows:
Figure BDA0002313441020000092
wherein, in the formula (2), FtReal-time forecast data at the moment t, wherein t is a time point in the real-time forecast; a. thet′The historical forecast data at the time t 'corresponding to the time t, wherein t' is a time window set for resisting the error of the advance or delay of the model simulation result in time (namely, a similar thing of a certain time in real-time forecast is searched in a plurality of times around the time of the historical forecast, in order to prevent the advance or delay of the weather forecast in time, a time window is set for t ', and if the time window is set to be 1, t' is epsilon [ t-1, t +1 ]]If the time window is N, then the N days obtain (2N +1) N metric values); II Ft,At′II is FtAnd At′The similarity of (2); n is a radical ofvIs the number of meteorological elements; w is aiThe weight ratio is corresponding to the ith meteorological element; sigmafiThe standard deviation corresponding to the historical forecast data of the ith meteorological element;
Figure BDA0002313441020000101
(i.e. the
Figure BDA0002313441020000102
) To ensure historical and real-time forecastingA time window set with the same trend,
Figure BDA0002313441020000103
is the lower limit value of the time window,
Figure BDA0002313441020000107
is the upper limit value of the time window; fi,t+jRepresenting real-time forecast data of the ith meteorological element at time t + j, Ai,t′+jHistorical forecast data of the ith meteorological element at the time t' + j is represented;
Figure BDA0002313441020000104
to represent
Figure BDA0002313441020000105
The number of j in the range is,
Figure BDA0002313441020000106
in the embodiment of the invention, since the minimum meteorological element feature set is input into the similarity forecasting system, and data in the set is the meteorological element features without units, F is used for calculating the similarity coefficient by using the formula (2)tFeatures of meteorological elements, A, corresponding to real-time forecast data at time tt′Is a meteorological element characteristic corresponding to historical forecast data at time t' corresponding to time t, Fi,t+jRepresenting the meteorological element characteristics corresponding to the real-time forecast data of the ith meteorological element at the time of t + j, Ai,t′+jAnd the weather element characteristics corresponding to the historical forecast data of the ith weather element at the time t' + j are shown.
For example, when selecting a weather system for real-time forecasting of similar weather around the tth time point for a weather element i, the weather element feature (i.e. the first weather element feature) corresponding to the real-time forecasting data of the weather element of at least 2h around the tth time point may be set as the weather element feature
Figure BDA0002313441020000108
As shown in fig. 2Fig. 2 shows the meteorological features corresponding to the real-time forecast data with a length of 1 day.
The time point t (marked as t') of each day in the historical forecast is approximated and
Figure BDA0002313441020000109
the weather element characteristics corresponding to the historical forecast data of the weather elements having the same time series are set as
Figure BDA00023134410200001010
Figure BDA00023134410200001011
As shown in fig. 3, fig. 3 shows the meteorological element characteristics (i.e., the second meteorological element characteristics) corresponding to the historical forecast data with a length of N days.
In order to find historical weather similar to the time t in real-time forecast, the weather is acquired
Figure BDA00023134410200001012
Figure BDA00023134410200001013
And
Figure BDA00023134410200001014
then, the calculation is performed by substituting the formula (2) to obtain N metric values. In addition, to prevent the weather forecast from advancing or lagging in time, t 'may be set with a time window, and if set to 1, t' ∈ [ t-1, t +1 ]]Then the historical forecast gets 3 metric values per day and 3N metric values for N days. If the time window is N, N days will get (2N +1) N metric values.
For example, when looking for a similar (second meteorological element characteristic corresponding to historical forecast data) when t is 10, as will
Figure BDA00023134410200001016
Is set to be 3, then
Figure BDA00023134410200001015
Are respectively set to be 7 and 13; when t is equal to 1, the reaction solution is,
Figure BDA00023134410200001017
is set to be 3, then
Figure BDA00023134410200001018
Respectively 1 and 4. When looking for an analog of t 10, t' is set to 1, and then for at＝9、at＝10、at＝11The calculations were performed separately, and 3 metric values were obtained each day.
Then, the metric values at each moment are sorted from small to large, the smallest S metric values are taken, and the historical moment corresponding to the corresponding second meteorological element characteristics is determined. And then finding out historical observation data of the elements to be corrected at the moment corresponding to the meteorological element characteristics, and averaging the historical observation data to obtain a corrected simulation result, wherein the result is real-time forecast data of the elements to be corrected.
Corresponding to the above method embodiment, the embodiment of the present invention further provides a data correction apparatus. As shown in fig. 4, fig. 4 is a schematic structural diagram of a data correction apparatus according to an embodiment of the present invention.
The data correction apparatus may include:
the acquiring module 201 is configured to acquire historical forecast data and real-time forecast data of a plurality of meteorological elements of a target site, and historical observation data of a factor to be corrected of the target site;
the determining module 202 is used for determining a correlation coefficient between each meteorological element and the element to be corrected according to historical forecast data of a plurality of meteorological elements and historical observation data of the element to be corrected;
the screening module 203 is used for screening out meteorological elements of which the correlation coefficients accord with a preset threshold range according to the correlation coefficients;
the dimension reduction module 204 is configured to perform dimension reduction processing on the screened historical forecast data and real-time forecast data of the meteorological elements to obtain a minimum meteorological element feature set including at least one meteorological element feature;
and the correcting module 205 is configured to determine real-time forecast data of the element to be corrected according to the minimum meteorological element feature set and historical observation data of the element to be corrected.
In an embodiment of the present invention, the determining module 202 may be specifically configured to:
determining the correlation coefficient of each meteorological element and the element to be corrected according to the following formula:
Figure BDA0002313441020000111
wherein E is a correlation coefficient; fiFor the ith historical forecast data of a certain meteorological element,
Figure BDA0002313441020000112
the historical forecast data average value of a certain meteorological element is obtained; o isiFor the ith historical observation of the element to be corrected,
Figure BDA0002313441020000113
the average value of the historical observation data of the elements to be corrected is obtained; x is the quantity of historical forecast data of a certain meteorological element; and Y is the number of the historical observation data of the elements to be corrected.
In an embodiment of the present invention, the dimension reduction module 204 may be specifically configured to:
and performing dimensionality reduction on the screened historical forecast data and real-time forecast data of the meteorological elements by using a principal component analysis method to obtain a minimum meteorological element characteristic set containing at least one meteorological element characteristic.
In an embodiment of the present invention, the modification module 205 may be specifically configured to:
determining a second meteorological element similar to the first meteorological element characteristic in the minimum meteorological element characteristic set by using a similar forecasting algorithm, wherein the first meteorological element characteristic corresponds to real-time forecasting data, and the second meteorological element characteristic corresponds to historical forecasting data;
acquiring historical observation data of the element to be corrected corresponding to the second meteorological element characteristic in time;
and averaging the acquired historical observation data to be used as real-time forecast data of the element to be corrected.
In one embodiment of the invention, the elements to be modified comprise meteorological elements and/or other elements than meteorological elements.
FIG. 5 sets forth a block diagram of an exemplary hardware architecture of a computing device capable of implementing data correction based on a minimum set of meteorological element features according to embodiments of the present invention. As shown in fig. 5, computing device 300 includes an input device 301, an input interface 302, a central processor 303, a memory 304, an output interface 305, and an output device 306. The input interface 302, the central processing unit 303, the memory 304, and the output interface 305 are connected to each other through a bus 310, and the input device 301 and the output device 306 are connected to the bus 310 through the input interface 302 and the output interface 305, respectively, and further connected to other components of the computing device 300.
Specifically, the input device 301 receives input information from the outside and transmits the input information to the central processor 303 through the input interface 302; central processor 303 processes the input information based on computer-executable instructions stored in memory 304 to generate output information, stores the output information temporarily or permanently in memory 304, and then transmits the output information to output device 306 through output interface 305; output device 306 outputs the output information external to computing device 300 for use by the user.
That is, the computing device shown in fig. 5 may also be implemented as a minimum meteorological element feature set-based data correction device, which may include: the data correction method based on the minimum meteorological element feature set comprises the steps of processing, storing and operating a computer program which is stored on the storage and can be executed on a processor, wherein the processor realizes the data correction method based on the minimum meteorological element feature set when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium; when being executed by a processor, the computer program realizes the data correction method based on the minimum meteorological element feature set provided by the embodiment of the invention.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.

Claims (12)

1. A data correction method based on a minimum meteorological element feature set is characterized by comprising the following steps:
acquiring historical forecast data and real-time forecast data of a plurality of meteorological elements of a target site and historical observation data of elements to be corrected of the target site;
determining a correlation coefficient between each meteorological element and the element to be corrected according to historical forecast data of the meteorological elements and historical observation data of the element to be corrected;
screening meteorological elements of which the correlation coefficients accord with a preset threshold range according to the correlation coefficients;
performing dimensionality reduction processing on the screened historical forecast data and real-time forecast data of the meteorological elements to obtain a minimum meteorological element characteristic set containing at least one meteorological element characteristic;
and determining real-time forecast data of the element to be corrected according to the minimum meteorological element feature set and the historical observation data of the element to be corrected.
2. The method of claim 1, wherein determining a correlation coefficient between each meteorological element and the element to be corrected according to historical forecast data of the plurality of meteorological elements and historical observation data of the element to be corrected comprises:
determining a correlation coefficient of each meteorological element and the element to be corrected according to the following formula:
Figure FDA0002313441010000011
wherein E is a correlation coefficient; fiFor the ith historical forecast data of a certain meteorological element,
Figure FDA0002313441010000012
the historical forecast data average value of the certain meteorological element is obtained; o isiFor the ith historical observation of the element to be corrected,
Figure FDA0002313441010000013
the historical observation data average value of the element to be corrected is obtained; x is the quantity of historical forecast data of the certain meteorological element; and Y is the number of the historical observation data of the elements to be corrected.
3. The method of claim 1, wherein the performing dimension reduction on the historical forecast data and the real-time forecast data of the screened meteorological elements to obtain a minimum meteorological element feature set comprising at least one meteorological element feature comprises:
and performing dimensionality reduction on the screened historical forecast data and real-time forecast data of the meteorological elements by using a principal component analysis method to obtain a minimum meteorological element characteristic set containing at least one meteorological element characteristic.
4. The method according to claim 1, wherein the determining real-time forecast data of the element to be corrected according to the minimum feature set of meteorological elements and historical observation data of the element to be corrected comprises:
determining a second meteorological element characteristic similar to the first meteorological element characteristic in the minimum meteorological element characteristic set by using a similar forecasting algorithm, wherein the first meteorological element characteristic corresponds to real-time forecasting data, and the second meteorological element characteristic corresponds to historical forecasting data;
acquiring historical observation data of the element to be corrected corresponding to the second meteorological element characteristic in time;
and averaging the acquired historical observation data to be used as real-time forecast data of the element to be corrected.
5. The method according to claim 1, wherein the element to be corrected comprises a meteorological element and/or an element other than the meteorological element.
6. A data modification apparatus based on a minimum feature set of meteorological elements, the apparatus comprising:
the acquisition module is used for acquiring historical forecast data and real-time forecast data of a plurality of meteorological elements of a target site and historical observation data of elements to be corrected of the target site;
the determining module is used for determining a correlation coefficient between each meteorological element and the element to be corrected according to historical forecast data of the meteorological elements and historical observation data of the element to be corrected;
the screening module is used for screening out meteorological elements of which the correlation coefficients accord with a preset threshold range according to the correlation coefficients;
the dimension reduction module is used for carrying out dimension reduction processing on the historical forecast data and the real-time forecast data of the screened meteorological elements to obtain a minimum meteorological element feature set containing at least one meteorological element feature;
and the correction module is used for determining real-time forecast data of the element to be corrected according to the minimum meteorological element feature set and the historical observation data of the element to be corrected.
7. The apparatus of claim 6, wherein the determining module is specifically configured to:
determining a correlation coefficient of each meteorological element and the element to be corrected according to the following formula:
Figure FDA0002313441010000031
wherein E is a correlation coefficient; fiFor the ith historical forecast data of a certain meteorological element,
Figure FDA0002313441010000032
the historical forecast data average value of the certain meteorological element is obtained; o isiFor the ith historical observation of the element to be corrected,
Figure FDA0002313441010000033
the historical observation data average value of the element to be corrected is obtained; x is the quantity of historical forecast data of the certain meteorological element; and Y is the number of the historical observation data of the elements to be corrected.
8. The apparatus of claim 1, wherein the dimension reduction module is specifically configured to:
and performing dimensionality reduction on the screened historical forecast data and real-time forecast data of the meteorological elements by using a principal component analysis method to obtain a minimum meteorological element characteristic set containing at least one meteorological element characteristic.
9. The apparatus of claim 6, wherein the modification module is specifically configured to:
determining a second meteorological element similar to the first meteorological element characteristic in the minimum meteorological element characteristic set by using a similar forecasting algorithm, wherein the first meteorological element characteristic corresponds to real-time forecasting data, and the second meteorological element characteristic corresponds to historical forecasting data;
acquiring historical observation data of the element to be corrected corresponding to the second meteorological element characteristic in time;
and averaging the acquired historical observation data to be used as real-time forecast data of the element to be corrected.
10. The apparatus of claim 6, wherein the element to be modified comprises a meteorological element and/or an element other than the meteorological element.
11. A data modification apparatus based on a minimum set of meteorological element features, the apparatus comprising: a processor, a memory, and a computer program stored on the memory and executable on the processor;
the processor, when executing the computer program, implements the method for data modification based on a minimum set of meteorological element features according to any one of claims 1 to 5.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the method for data modification based on a minimum set of meteorological element features according to any one of claims 1 to 5.
CN201911268112.4A 2019-12-11 2019-12-11 Data correction method, device, equipment and medium Pending CN112612781A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911268112.4A CN112612781A (en) 2019-12-11 2019-12-11 Data correction method, device, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911268112.4A CN112612781A (en) 2019-12-11 2019-12-11 Data correction method, device, equipment and medium

Publications (1)

Publication Number Publication Date
CN112612781A true CN112612781A (en) 2021-04-06

Family

ID=75224308

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911268112.4A Pending CN112612781A (en) 2019-12-11 2019-12-11 Data correction method, device, equipment and medium

Country Status (1)

Country Link
CN (1) CN112612781A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113075752A (en) * 2021-04-16 2021-07-06 中国气象局气象探测中心 Method and device for judging correctness of three-dimensional space position of meteorological observation station
CN114814091A (en) * 2022-04-08 2022-07-29 天津光电华典科技有限公司 Atmospheric gaseous pollutant detection method and device and electronic equipment
CN115508917A (en) * 2022-11-22 2022-12-23 中国民用航空局空中交通管理局航空气象中心 Method, device, equipment and storage medium for forecasting airport meteorological elements

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113075752A (en) * 2021-04-16 2021-07-06 中国气象局气象探测中心 Method and device for judging correctness of three-dimensional space position of meteorological observation station
CN114814091A (en) * 2022-04-08 2022-07-29 天津光电华典科技有限公司 Atmospheric gaseous pollutant detection method and device and electronic equipment
CN115508917A (en) * 2022-11-22 2022-12-23 中国民用航空局空中交通管理局航空气象中心 Method, device, equipment and storage medium for forecasting airport meteorological elements
CN115508917B (en) * 2022-11-22 2023-04-28 中国民用航空局空中交通管理局航空气象中心 Airport weather element forecasting method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
Yang et al. State-of-the-art one-stop handbook on wind forecasting technologies: An overview of classifications, methodologies, and analysis
Sharma et al. Forecasting daily global solar irradiance generation using machine learning
CN112612781A (en) Data correction method, device, equipment and medium
EP3161527B1 (en) Solar power forecasting using mixture of probabilistic principal component analyzers
CN110689190A (en) Power grid load prediction method and device and related equipment
Zjavka Numerical weather prediction revisions using the locally trained differential polynomial network
Adnan et al. Estimating evapotranspiration using machine learning techniques
CN113281790A (en) Beidou satellite clock error forecasting method and device
WO2024077969A1 (en) Lstm-svr subway station temperature prediction method based on characteristic of multiple periods
Elhariri et al. H-ahead multivariate microclimate forecasting system based on deep learning
CN113822418A (en) Wind power plant power prediction method, system, device and storage medium
CN115456306A (en) Bus load prediction method, system, equipment and storage medium
Lyu et al. Dynamic feature selection for solar irradiance forecasting based on deep reinforcement learning
CN112580844A (en) Meteorological data processing method, device, equipment and computer readable storage medium
CN114117852B (en) Regional heat load rolling prediction method based on finite difference working domain division
Zaman et al. Wind speed forecasting using ARMA and neural network models
CN114385962A (en) Day-ahead photovoltaic power generation power prediction method and system based on similar days
CN115544890A (en) Short-term power load prediction method and system
CN111323847A (en) Method and apparatus for determining weight ratios for analog integration algorithms
CN105701027B (en) The prediction technique and prediction meanss of data storage capacity
KR20230066927A (en) Method and apparatus for predicting power generation
Li et al. An innovated integrated model using singular spectrum analysis and support vector regression optimized by intelligent algorithm for rainfall forecasting
Peng et al. An extreme learning machine and gene expression programming-based hybrid model for daily precipitation prediction
CN112580845A (en) Meteorological data processing method, device, equipment and computer readable storage medium
CN114154684A (en) Short-term photovoltaic power prediction method based on data mining and multi-core support vector machine

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