CN112163695A - Copula function-based wind power photovoltaic power generation prediction method, system and medium - Google Patents
Copula function-based wind power photovoltaic power generation prediction method, system and medium Download PDFInfo
- Publication number
- CN112163695A CN112163695A CN202010939289.9A CN202010939289A CN112163695A CN 112163695 A CN112163695 A CN 112163695A CN 202010939289 A CN202010939289 A CN 202010939289A CN 112163695 A CN112163695 A CN 112163695A
- Authority
- CN
- China
- Prior art keywords
- wind power
- copula
- dynamic
- correlation
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 241000039077 Copula Species 0.000 title claims abstract description 111
- 238000010248 power generation Methods 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000005315 distribution function Methods 0.000 claims abstract description 67
- 238000011160 research Methods 0.000 claims abstract description 40
- 239000012634 fragment Substances 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000011218 segmentation Effects 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 97
- 238000012843 least square support vector machine Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 description 6
- 230000005622 photoelectricity Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a copula function-based wind power photovoltaic power generation prediction method, a system and a medium, wherein the method comprises the following steps: acquiring basic data; acquiring an empirical distribution function value of wind power and photoelectric data; taking the empirical distribution function value as an edge distribution function of the empirical distribution function value, establishing a plurality of dynamic copula correlation research models according to the edge distribution function, and evaluating the advantages and disadvantages of the dynamic copula correlation research models according to the empirical copula function; calculating a wind power-photoelectric dynamic correlation coefficient, performing segmentation processing on a wind power and photoelectric time sequence to obtain a sample fragment, obtaining an average value of the dynamic correlation coefficient of the sample fragment, and judging the correlation degree of wind power generation and photovoltaic power generation according to the average value; and predicting the data of the wind power generation and the photovoltaic power generation according to the degree of the correlation. The method can reflect the change trend of the wind-light correlation in a specific time period, and can be widely applied to the technical field of wind power-photovoltaic power generation.
Description
Technical Field
The invention relates to the technical field of wind power-photovoltaic power generation, in particular to a copula function-based wind power photovoltaic power generation prediction method, a copula function-based wind power photovoltaic power generation prediction system and a copula function-based wind power photovoltaic power generation prediction medium.
Background
The development and application of new energy is a hot spot in the global energy topic in recent years. With the advancement of energy technology, renewable energy has become an important role in energy revolution. At present, wind energy, solar energy and the like are widely applied, and the wind energy, the solar energy and the like have a large number of research results in the field of power generation. At present, wind power plants and photovoltaic power stations are gradually connected into a power grid, and due to the particularity of new energy power generation, the new energy power generation is connected into a power grid structure in a large scale, so that the influence on power planning and power grid planning is gradually increased, and researchers are required to deeply solve the problem of new energy planning.
At present, the national requirements for renewable energy power generation are that they need to be consumed in the power grid first, which requires that the generated energy information of new energy needs to be mastered in advance when power supply planning and power grid planning are performed, which is wind power prediction and photovoltaic power generation prediction. However, the prediction of wind power generation and photovoltaic power generation is greatly influenced by natural factors, such as wind speed, illumination intensity and the like, so that the wind power generation and the photovoltaic power generation have characteristics of high randomness, volatility and the like, and certain difficulty is brought to the power generation prediction. In the existing research results, wind power prediction and photoelectric prediction reach a better level, but the rising space still exists. In power generation prediction, research on correlation is an important subject, and by analyzing sample information correlation among a plurality of wind power plants or photovoltaic power plants in the same region, a data characteristic rule of wind energy or solar energy can be extracted to better construct a prediction model. However, most of the current correlation researches are limited among a plurality of wind power plants or photovoltaic power plants, and the correlation between wind power-photovoltaic data in the same region is not deeply researched.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a copula function-based wind power photovoltaic power generation prediction method, a copula function-based wind power photovoltaic power generation prediction system and a copula function-based wind power photovoltaic power generation prediction medium.
The technical scheme adopted by the invention is as follows:
a wind power photovoltaic power generation prediction method based on copula function comprises the following steps:
acquiring basic data, wherein the basic data comprises wind power and photoelectric data of a plurality of regions;
acquiring an empirical distribution function value of the wind power and photoelectric data, and acquiring an edge distribution function of the wind power and photoelectric data according to the empirical distribution function value (namely acquiring the edge distribution function of the wind power data according to the empirical distribution function value of the wind power data and acquiring the edge distribution function of the photoelectric data according to the empirical distribution function value of the photoelectric data);
establishing various dynamic copula correlation research models according to the edge distribution function, establishing an empirical copula function, and evaluating the advantages and disadvantages of the dynamic copula correlation research models according to the empirical copula function;
calculating a wind power-photoelectric dynamic correlation coefficient by adopting the dynamic copula correlation research model, performing segmentation processing on a wind power and photoelectric time sequence to obtain a sample fragment, obtaining an average value of the dynamic correlation coefficient of the sample fragment, and judging the correlation degree of wind power generation and photovoltaic power generation according to the average value;
and predicting the data of the wind power generation and the photovoltaic power generation by adopting a least square support vector machine model according to the correlation degree so as to improve the prediction precision.
Further, the wind power and photoelectric data comprise wind power historical data and photoelectric historical data in the same region and the same time span.
Further, the acquiring an empirical distribution function value of the wind power and the photoelectric data includes:
establishing an experience distribution function of the wind power and photoelectric data according to the wind power and photoelectric data;
sorting the data points of the wind power and photoelectric data time sequence according to an empirical distribution function to obtain an empirical distribution function value of each sorted data point;
and carrying out spline interpolation on the sorted data points and the empirical distribution function values corresponding to the data points to obtain the empirical distribution functions of the wind power channel and the photoelectric channel of the original data so as to obtain the empirical distribution function values corresponding to the original sample observation values which are not sorted.
Further, the establishing a plurality of dynamic copula correlation research models according to the edge distribution function, establishing an empirical copula function, and evaluating the quality of the dynamic copula correlation research models according to the empirical copula function includes:
constructing a plurality of dynamic copula correlation research models by adopting a plurality of dynamic copula function constructors according to an edge distribution function;
solving the dynamic correlation coefficients of the various dynamic copula functions by adopting a semi-parameter estimation method;
constructing an empirical copula function according to the dynamic correlation coefficient, and calculating the squared Euclidean distance between each dynamic copula correlation research model and the empirical copula function;
and evaluating the quality of the copula correlation research model according to the squared Euclidean distance.
Further, the plurality of dynamic copula functions include at least two of a dynamic N-copula function, a dynamic t-copula function, and a dynamic clavyton-copula function.
Further, the calculating a wind power-photoelectric dynamic correlation coefficient by using the dynamic copula correlation research model, performing segmentation processing on the wind power and photoelectric time series to obtain sample fragments, obtaining an average value of the dynamic correlation coefficient of the sample fragments, and judging the correlation degree of wind power generation and photovoltaic power generation according to the average value includes:
fitting different dynamic copula correlation research models, calculating to obtain a wind power-photoelectric dynamic correlation coefficient sequence, and preliminarily judging the wind power-photoelectric correlation;
according to the change condition of the correlation coefficient of the sample, carrying out segmentation processing on the sample, dividing data at a group of adjacent sampling points with the related coefficient change trend and the close change range into the same segment, and obtaining sample segments;
calculating an average value of the dynamic correlation coefficients of the sample segments;
and setting a correlation coefficient threshold value, and comparing the average value of the correlation coefficients with the correlation coefficient threshold value to judge the degree of correlation between the wind power generation and the photovoltaic power generation.
Further, the formula of the least squares support vector machine model is as follows:
wherein alpha isi(i ═ 1,2, …, l) is the regression coefficient, b is the deviation; k (-) is a kernel function, which is an arbitrary symmetric function that satisfies the Mercer condition; k (-) has two key parameters: hyper-and nuclear parameters gamma and sigma2γ reflects the magnitude of the training error, σ2And reflecting the distribution condition of the training samples.
The other technical scheme adopted by the invention is as follows:
a wind power photovoltaic power generation prediction system based on copula function comprises:
the data acquisition module is used for acquiring basic data, wherein the basic data comprises wind power and photoelectric data of a plurality of regions;
the data sorting module is used for acquiring an empirical distribution function value of the wind power and photoelectric data and acquiring an edge distribution function of the wind power and photoelectric data according to the empirical distribution function value;
the model establishing module is used for establishing various dynamic copula correlation research models according to the edge distribution function, establishing an empirical copula function and evaluating the quality of the dynamic copula correlation research models according to the empirical copula function;
the correlation calculation module is used for calculating a wind power-photoelectric dynamic correlation coefficient by adopting the dynamic copula correlation research model, carrying out segmentation processing on a wind power and photoelectric time sequence to obtain a sample fragment, obtaining an average value of the dynamic correlation coefficient of the sample fragment, and judging the correlation degree of wind power generation and photovoltaic power generation according to the average value;
and the prediction optimization module is used for predicting the data of the wind power generation and the photovoltaic power generation by adopting a least square support vector machine model according to the correlation degree so as to improve the prediction precision.
The other technical scheme adopted by the invention is as follows:
a wind power photovoltaic power generation prediction system based on copula function comprises:
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 processor-executable instructions for performing the method as described above when executed by a processor.
The invention has the beneficial effects that: the method applies the dynamic copula function model to the research of the wind power-photoelectric correlation, simultaneously calculates the wind-light correlation coefficient by using various different dynamic copula functions, obtains the wind power-photoelectric correlation coefficient sequence which changes along with time, intuitively reflects the change trend of the wind-light correlation in a specific time period, and has higher reference function on the characteristic analysis of the wind power data with high randomness.
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 schematic flow chart of a wind-photovoltaic power generation prediction method based on dynamic Copula wind-light correlation research in an embodiment of the present invention;
FIG. 2 is a schematic diagram of an empirical distribution function of wind power and photoelectric data in the embodiment of the invention;
FIG. 3 is a schematic diagram of an empirical copula function constructed in an 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.
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 wind-photovoltaic power generation prediction method based on dynamic Copula wind-light correlation study, including but not limited to the following steps:
and S1, acquiring basic data, wherein the basic data comprises wind power and photoelectric data of a plurality of regions.
Wind power and photoelectric data are actual data acquired in an open database or acquired by connecting related units, and the data cover different seasons, time periods and regions. In addition, in order to compare wind power data with photoelectric data, each region needs to acquire wind power and photoelectric historical data within the same time span at the same time.
And S2, obtaining an empirical distribution function value of the wind power and photoelectric data by combining a non-parameter method based on empirical distribution with a spline interpolation method, and taking the empirical distribution function value as an approximate overall distribution function of the sample. The 'it' refers to the acquired wind power and photoelectric experience distribution function value; namely, the wind power and photoelectric empirical distribution function obtained by calculation is used for approximately describing the overall distribution of the whole wind power and photoelectric sample.
Wherein, the step S2 specifically includes the following steps S21-S22:
and S21, setting the wind power and photoelectric random variables as X and Y respectively, and constructing an empirical distribution function of the wind power and photoelectric random variables. Taking wind power as an example, let (x)1,x2,...,xn) Arranging a group of observed values of the wind power data into a small observed value and a large observed value in sequence
x(1)<x(2)<…<x(n)
Wherein x is(i)The frequency of occurrence of (i ═ 1, 2.., r) is ni(n1+n2+…nrN). Then for the observed values arranged in sequence, there are
See FIG. 2, Fn(x) Namely an empirical distribution function of the wind power data X.
S22, when the code is used for implementation, the wind power data time sequence X and the photoelectric data time sequence Y are sequenced, and an empirical distribution function value of each data point after sequencing is obtained. In order to obtain an empirical distribution function value corresponding to the original sample observation value which is not sequenced, spline interpolation is carried out on the sequenced data points and the empirical distribution function value thereof to obtain the wind power and photoelectric empirical distribution function of the original data.
S3, establishing various dynamic copula correlation research models, constructing an empirical copula function, calculating the squared Euclidean distance between each copula model and the empirical copula function, and judging the quality of the models according to the magnitude of the squared Euclidean distance.
Wherein, the step S3 specifically includes steps S31-S32:
s31, first, determining the edge distribution of two random variables X, Y (representing wind power data and photoelectric data, respectively).
And constructing an empirical distribution function of the wind power and photoelectric original time sequence, and taking the empirical distribution function as an overall distribution function of the sample, namely the edge distribution of random variables X and Y.
And S32, constructing a wind power-photoelectric data correlation research model by using various dynamic copula functions. Step S32 specifically includes S321-S323:
s321, building a wind-light correlation model by using three dynamic copula functions respectively: dynamic N-copula functions, dynamic t-copula functions, and dynamic clavyton-copula functions, as follows:
constructing a wind-light correlation model by using a dynamic N-copula function:
wherein u and v are respectively the edge distribution function of random variables X and Y, phi-1An inverse function of a distribution function representing a standard normal distribution. RhotThe Copula model is a parameter to be solved and is a dynamic correlation coefficient which changes along with time.
Dynamic Clayton-copula function:
also, the parameter θtAlso time-varying, is the correlation coefficient between two variables.
Dynamic t-copula function:
wherein rho and v are parameters to be solved by the model, v is the degree of freedom of the function, and rho is a dynamic correlation coefficient changing along with time.
S322, solving the dynamic correlation coefficients of the three dynamic copula functions by using a half-parameter estimation method:
when using the sample empirical distribution function F of the random variables X and Yn(x) And Gn(Y) As the edge distribution functions F (X) and G (Y) of X and Y, respectively, the parameter ρ in the dynamic copula function can be estimated by a semi-parameter estimation methodtI.e. the dynamic correlation coefficient.
For dynamic N-copula function and dynamic Clayton-copula function, there are
For dynamic t-copula function, there are
Wherein u isi＝Fn(xi)，vi＝Cn(yi) (ii) a i is 1,2, …, n. c (u, v; p) is copula density function
S323, referring to fig. 3, an empirical copula function is constructed, the squared euclidean distance between each copula model and the empirical copula function is calculated, and the quality of the model is determined by the magnitude of the squared euclidean distance.
For empirical distribution function of Fn(x) And Gn(y) random variables, the empirical copula function is constructed as follows
Wherein, I[·]For an illustrative function, when Fn(xi) When the content is less than or equal to u,
otherwise
Dynamic copula function to be investigated
Calculate its squared Euclidean distance from the empirical copula function
Wherein u isi＝Fn(xi)，vi＝Gn(yi) (i ═ 1,2, …, n). Squared Euclidean distance d2Reflecting the fitting condition of the dynamic copula model to the original data, d2Smaller indicates better fit.
S4, calculating a wind power-photoelectric dynamic correlation coefficient by using a copula model, carrying out segmentation processing on a wind power and photoelectric time sequence to obtain a sample segment, setting a correlation coefficient threshold value, and judging the correlation degree of the wind power-photoelectric dynamic correlation coefficient and the photoelectric time sequence by using the size relation between the average value of the correlation coefficient of the sample segment and the threshold value.
Wherein, the step S4 specifically includes steps S41-S42:
and S41, preliminarily judging the wind power-photoelectric correlation condition by combining the fitting combination of different dynamic copula function models and the dynamic correlation coefficient sequence obtained by calculation.
And S41, segmenting the samples according to the change condition of the correlation coefficients of the samples, and dividing the data at a group of adjacent sampling points with the change trend of the correlation coefficients and the close change range into the same segment. Setting a correlation coefficient threshold, calculating the average value of the correlation coefficient of the wind power-photoelectric data of each sample segment with the close correlation condition, comparing the average value with the threshold, and judging the correlation.
I.e., on a sample sequence fragment [ (x)1,y1),(x2,y2),...,(xk,yk)]The corresponding correlation coefficient sequence is (rho)1,ρ2,...,ρk) Then the average value of the correlation coefficient
Let the sample correlation coefficient threshold be ρMWhen is coming into contact with
Then (c) is performed. The wind power-photoelectricity of the section is considered to have correlation when
When the wind power-photoelectric conversion is carried out, the wind power-photoelectric conversion of the section is not related.
And S5, combining the wind-light correlation, and performing data prediction of wind power generation and photovoltaic power generation by using a least square support vector machine model to improve the prediction precision.
Wherein, the step S5 specifically includes steps S51-S52:
s51, respectively constructing a Least Square Support Vector Machine (LSSVM) prediction model for the wind power data and the photoelectric data:
wherein alpha isi(i＝1,2, …, l) are regression coefficients and b is the deviation. K (-) is a kernel function, which is an arbitrary symmetric function that satisfies the Mercer condition. K (-) has two key parameters: hyper-and nuclear parameters gamma and sigma2The former can reflect the size of the training error, the latter reflects the distribution of the training samples, gamma and sigma2Can be obtained by an optimization algorithm.
S52, carrying out wind power and photoelectric data prediction by using a least square support vector machine model, wherein the characteristics of the prediction are as follows: according to the correlation research condition of the sample, a targeted training scheme is adopted for the prediction model.
Step S52 specifically includes steps S521-S523:
s521, firstly, selecting one or more sample segments adjacent to a certain point to be predicted, and judging whether the selected sample segments have wind-electricity-light correlation or not based on the calculation result in the step S4.
And S522, if the selected sample segment has wind power-photoelectric correlation, selecting sampling points with the relation number larger than a threshold value in the sample segment to form training data. And for the least square support vector machine models of wind power and photoelectricity, simultaneously using wind power data and photoelectricity data at sampling points as historical data, training the models, and obtaining the trained prediction models. When wind power or photoelectricity is predicted, historical wind power data and photoelectricity data are used as input, a value to be predicted is finally obtained, and prediction accuracy is improved.
And S523, if the selected sample segment has no wind power-photoelectric correlation, respectively training a wind power and photoelectric least square support vector machine model. When the wind power prediction model is trained, the model is trained only by using the historical wind power data, and the wind power historical data is also used as the model input to obtain the value to be predicted. The same is true for the prediction model of photovoltaics.
In summary, compared with the prior art, the prediction method based on the dynamic copula wind-light correlation study in the embodiment has the following beneficial effects:
(1) and correlation research is carried out on the wind power-photoelectric data, which is beneficial to deep analysis of the data characteristics of the wind power-photoelectric data and the photoelectric data.
(2) Compared with the traditional model only considering wind power or photoelectric historical data, the wind power and photoelectric historical data model has more data factors, and provides a new angle for improving the model prediction precision.
(3) In the embodiment, a dynamic copula function model is applied to the research of wind power-photoelectric correlation, and wind-light correlation coefficients are calculated by using three different dynamic copula functions to obtain a wind power-photoelectric correlation coefficient sequence changing along with time, so that the change trend of the wind-light correlation in a specific time period is reflected visually, and a higher reference effect is provided for the characteristic analysis of wind power data with high randomness.
(4) In the embodiment, the judgment threshold is set for the wind power-photoelectric correlation coefficient, and the data points with the correlation coefficient larger than the threshold are used as the training data set, so that the prediction accuracy of the local prediction model is improved.
The embodiment also provides a wind power photovoltaic power generation prediction system based on copula function, which includes:
the data acquisition module is used for acquiring basic data, wherein the basic data comprises wind power and photoelectric data of a plurality of regions;
the data sorting module is used for acquiring an empirical distribution function value of the wind power and photoelectric data and acquiring an edge distribution function of the wind power and photoelectric data according to the empirical distribution function value;
the model establishing module is used for establishing various dynamic copula correlation research models according to the edge distribution function, establishing an empirical copula function and evaluating the quality of the dynamic copula correlation research models according to the empirical copula function;
the correlation calculation module is used for calculating a wind power-photoelectric dynamic correlation coefficient by adopting the dynamic copula correlation research model, carrying out segmentation processing on a wind power and photoelectric time sequence to obtain a sample fragment, obtaining an average value of the dynamic correlation coefficient of the sample fragment, and judging the correlation degree of wind power generation and photovoltaic power generation according to the average value;
and the prediction optimization module is used for predicting the data of the wind power generation and the photovoltaic power generation by adopting a least square support vector machine model according to the correlation degree so as to improve the prediction precision.
The copula function-based wind power photovoltaic power generation prediction system can execute the copula function-based wind power photovoltaic power generation prediction method provided by the method embodiment of the invention, can execute any combination of the implementation steps of the method embodiment, and has corresponding functions and beneficial effects of the method.
A wind power photovoltaic power generation prediction system based on copula function comprises:
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 copula function-based wind power photovoltaic power generation prediction system can execute the copula function-based wind power photovoltaic power generation prediction method provided by the method embodiment of the invention, can execute any combination of the implementation steps of the method embodiment, and has corresponding functions and beneficial effects of the method.
A storage medium having stored therein processor-executable instructions for performing the method as described above when executed by a processor.
The embodiment also provides a storage medium, which stores an instruction or a program capable of executing the wind power photovoltaic power generation prediction method based on copula function provided by the embodiment of the method of the invention, and when the instruction or the program is executed, the method can be executed by any combination of the embodiment of the method, and the method has corresponding functions and beneficial effects.
It will be understood that all or some of the steps, systems of methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (10)
1. A wind power photovoltaic power generation prediction method based on copula function is characterized by comprising the following steps:
acquiring basic data, wherein the basic data comprises wind power and photoelectric data of a plurality of regions;
acquiring an empirical distribution function value of the wind power and photoelectric data, and acquiring an edge distribution function of the wind power and photoelectric data according to the empirical distribution function value;
establishing various dynamic copula correlation research models according to the edge distribution function, establishing an empirical copula function, and evaluating the advantages and disadvantages of the dynamic copula correlation research models according to the empirical copula function;
calculating a wind power-photoelectric dynamic correlation coefficient by adopting the dynamic copula correlation research model, performing segmentation processing on a wind power and photoelectric time sequence to obtain a sample fragment, obtaining an average value of the dynamic correlation coefficient of the sample fragment, and judging the correlation degree of wind power generation and photovoltaic power generation according to the average value;
and predicting the data of the wind power generation and the photovoltaic power generation by adopting a least square support vector machine model according to the correlation degree so as to improve the prediction precision.
2. The copula function-based wind power photovoltaic power generation prediction method according to claim 1, wherein the wind power and photovoltaic data comprise wind power historical data and photovoltaic historical data in the same region and the same time span.
3. The copula function-based wind power photovoltaic power generation prediction method according to claim 1, wherein the obtaining of the empirical distribution function value of the wind power and photovoltaic data comprises:
establishing an experience distribution function of the wind power and photoelectric data according to the wind power and photoelectric data;
sorting the data points of the wind power and photoelectric data time sequence according to an empirical distribution function to obtain an empirical distribution function value of each sorted data point;
and carrying out spline interpolation on the sorted data points and the empirical distribution function values corresponding to the data points to obtain the empirical distribution functions of the wind power channel and the photoelectric channel of the original data so as to obtain the empirical distribution function values corresponding to the original sample observation values which are not sorted.
4. The copula function-based wind photovoltaic power generation prediction method according to claim 1, wherein the establishing of multiple dynamic copula correlation study models according to the edge distribution function and the establishing of an empirical copula function according to which the advantages and disadvantages of the dynamic copula correlation study models are evaluated comprises:
constructing a plurality of dynamic copula correlation research models by adopting a plurality of dynamic copula function constructors according to an edge distribution function;
solving the dynamic correlation coefficients of the various dynamic copula functions by adopting a semi-parameter estimation method;
constructing an empirical copula function according to the dynamic correlation coefficient, and calculating the squared Euclidean distance between each dynamic copula correlation research model and the empirical copula function;
and evaluating the quality of the copula correlation research model according to the squared Euclidean distance.
5. The copula function-based wind power photovoltaic generation prediction method according to claim 4, wherein the plurality of dynamic copula functions comprise at least two of a dynamic N-copula function, a dynamic t-copula function and a dynamic clavyton-copula function.
6. The copula function-based wind power and photovoltaic power generation prediction method according to claim 1, wherein the method comprises the steps of calculating a wind power-photoelectric dynamic correlation coefficient by using the dynamic copula correlation research model, performing segmentation processing on a wind power and photoelectric time sequence to obtain a sample segment, obtaining an average value of the dynamic correlation coefficient of the sample segment, and judging the correlation degree of wind power generation and photovoltaic power generation according to the average value, and comprises the following steps:
fitting different dynamic copula correlation research models, calculating to obtain a wind power-photoelectric dynamic correlation coefficient sequence, and preliminarily judging the wind power-photoelectric correlation;
according to the change condition of the correlation coefficient of the sample, carrying out segmentation processing on the sample, dividing data at a group of adjacent sampling points with the related coefficient change trend and the close change range into the same segment, and obtaining sample segments;
calculating an average value of the dynamic correlation coefficients of the sample segments;
and setting a correlation coefficient threshold value, and comparing the average value of the correlation coefficients with the correlation coefficient threshold value to judge the degree of correlation between the wind power generation and the photovoltaic power generation.
7. The copula function-based wind power photovoltaic power generation prediction method according to claim 1, wherein the formula of the least squares support vector machine model is as follows:
wherein alpha isi(i ═ 1,2, …, l) is the regression coefficient, b is the deviation; k (-) is a kernel function, which is an arbitrary symmetric function that satisfies the Mercer condition; k (-) has two key parameters: hyper-and nuclear parameters gamma and sigma2γ reflects the magnitude of the training error, σ2And reflecting the distribution condition of the training samples.
8. A wind power photovoltaic power generation prediction system based on copula function is characterized by comprising:
the data acquisition module is used for acquiring basic data, wherein the basic data comprises wind power and photoelectric data of a plurality of regions;
the data sorting module is used for acquiring an empirical distribution function value of the wind power and photoelectric data and acquiring an edge distribution function of the wind power and photoelectric data according to the empirical distribution function value;
the model establishing module is used for establishing various dynamic copula correlation research models according to the edge distribution function, establishing an empirical copula function and evaluating the quality of the dynamic copula correlation research models according to the empirical copula function;
the correlation calculation module is used for calculating a wind power-photoelectric dynamic correlation coefficient by adopting the dynamic copula correlation research model, carrying out segmentation processing on a wind power and photoelectric time sequence to obtain a sample fragment, obtaining an average value of the dynamic correlation coefficient of the sample fragment, and judging the correlation degree of wind power generation and photovoltaic power generation according to the average value;
and the prediction optimization module is used for predicting the data of the wind power generation and the photovoltaic power generation by adopting a least square support vector machine model according to the correlation degree so as to improve the prediction precision.
9. A wind power photovoltaic power generation prediction system based on copula function is characterized by comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, the at least one program causes the at least one processor to implement a copula function-based wind photovoltaic power generation prediction method according to any one of claims 1 to 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.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010939289.9A CN112163695A (en) | 2020-09-09 | 2020-09-09 | Copula function-based wind power photovoltaic power generation prediction method, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010939289.9A CN112163695A (en) | 2020-09-09 | 2020-09-09 | Copula function-based wind power photovoltaic power generation prediction method, system and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112163695A true CN112163695A (en) | 2021-01-01 |
Family
ID=73858599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010939289.9A Pending CN112163695A (en) | 2020-09-09 | 2020-09-09 | Copula function-based wind power photovoltaic power generation prediction method, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112163695A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115659672A (en) * | 2022-11-02 | 2023-01-31 | 中国长江三峡集团有限公司 | Basin water, wind and light resource combined random simulation method and device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104252649A (en) * | 2014-09-25 | 2014-12-31 | 东南大学 | Regional wind power output prediction method based on correlation between multiple wind power plants |
| CN107918920A (en) * | 2017-12-13 | 2018-04-17 | 上海交通大学 | The output correlation analysis method of more photovoltaic plants |
| CN109038648A (en) * | 2018-07-10 | 2018-12-18 | 华中科技大学 | A kind of scene joint power output modeling method based on Copula function |
| CN110188964A (en) * | 2019-06-06 | 2019-08-30 | 河北工业大学 | A kind of photovoltaic power generation output forecasting method based on correlation |
-
2020
- 2020-09-09 CN CN202010939289.9A patent/CN112163695A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104252649A (en) * | 2014-09-25 | 2014-12-31 | 东南大学 | Regional wind power output prediction method based on correlation between multiple wind power plants |
| CN107918920A (en) * | 2017-12-13 | 2018-04-17 | 上海交通大学 | The output correlation analysis method of more photovoltaic plants |
| CN109038648A (en) * | 2018-07-10 | 2018-12-18 | 华中科技大学 | A kind of scene joint power output modeling method based on Copula function |
| CN110188964A (en) * | 2019-06-06 | 2019-08-30 | 河北工业大学 | A kind of photovoltaic power generation output forecasting method based on correlation |
Non-Patent Citations (1)
| Title |
|---|
| 宋帅: "《桥梁系统地震易损性研究》", 31 August 2019 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115659672A (en) * | 2022-11-02 | 2023-01-31 | 中国长江三峡集团有限公司 | Basin water, wind and light resource combined random simulation method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779223B (en) | Photovoltaic system power generation real-time prediction method and device | |
| CN114118640B (en) | Long-term precipitation prediction model construction method, long-term precipitation prediction method and device | |
| CN104657791B (en) | A kind of wind farm group wind speed profile prediction technique based on correlation analysis | |
| CN112862630B (en) | Photovoltaic power prediction method, terminal and medium based on weather type index interval | |
| CN108763713B (en) | Mathematical model calculation method and system | |
| CN111126662A (en) | Irrigation decision making method, device, server and medium based on big data | |
| CN113988477A (en) | Photovoltaic power short-term prediction method and device based on machine learning and storage medium | |
| CN114006369A (en) | Regional wind and light station power joint prediction method and device, electronic equipment and storage medium | |
| CN115730755A (en) | Method, device, terminal equipment and medium for realizing path planning of double-carbon target | |
| CN115271253A (en) | Water-wind power generation power prediction model construction method and device and storage medium | |
| CN115239105A (en) | Method and device for evaluating wind resources of in-service wind power plant | |
| CN115759365A (en) | Photovoltaic power generation power prediction method and related equipment | |
| CN111179108A (en) | Method and device for predicting power consumption | |
| CN114819374A (en) | Regional new energy ultra-short term power prediction method and system | |
| CN116796141A (en) | GBDT regression model-based office building energy consumption prediction method | |
| CN112163695A (en) | Copula function-based wind power photovoltaic power generation prediction method, system and medium | |
| CN114118401A (en) | Neural network-based power distribution network flow prediction method, system, device and storage medium | |
| CN116739172B (en) | Method and device for ultra-short-term prediction of offshore wind power based on climbing identification | |
| CN115983478A (en) | Distributed photovoltaic power generation power prediction analysis method, system, terminal and medium | |
| US20220243347A1 (en) | Determination method and determination apparatus for conversion efficiency of hydrogen production by wind-solar hybrid electrolysis of water | |
| CN112016744B (en) | Forest fire prediction method and device based on soil moisture and storage medium | |
| Gerards et al. | Pv predictions made easy: Flexibility through simplicity | |
| Huang et al. | Hybrid Intra-hour Solar PV Power Forecasting using Statistical and Skycam-based Methods | |
| CN110210657B (en) | Fan power prediction method and system based on single machine model and computer storage medium | |
| CN114778795B (en) | Soil quality grade determination method and device based on urban layout |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210101 |
|
| RJ01 | Rejection of invention patent application after publication |