CN110705099A - Method for verifying output correlation of wind power plant - Google Patents
Method for verifying output correlation of wind power plant Download PDFInfo
- Publication number
- CN110705099A CN110705099A CN201910943047.4A CN201910943047A CN110705099A CN 110705099 A CN110705099 A CN 110705099A CN 201910943047 A CN201910943047 A CN 201910943047A CN 110705099 A CN110705099 A CN 110705099A
- Authority
- CN
- China
- Prior art keywords
- wind power
- output
- function
- power plants
- power plant
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
A method for verifying wind power plant output correlation comprises the following steps: a. taking the historical output of the wind power plants as sample data, and respectively solving probability density functions of the output of the two wind power plants by adopting a non-parameter kernel density estimation method; b. calculating the cumulative distribution function values of the two wind power plants; d. solving a joint probability density function and a joint distribution function H (u) of two wind power plants by adopting multi-dimensional kernel density estimation1,u2) (ii) a e. Calculating Spearman rank correlation coefficients and Kendall rank correlation coefficients of output sequences among different wind power plants; f. and comparing the rank correlation coefficient with a set threshold value to obtain the conclusion whether the multi-wind power plant output has correlation and the magnitude of the correlation. The method can effectively reflect the correlation characteristics of the output of the wind power plant, shows the synchronization probability of the output of the multiple wind power plants, presents the output scene of the multiple wind power plants, and ensures the wind power integrationThe stable and economic operation of the power system is of great significance.
Description
Technical Field
The invention relates to a method for detecting output correlation of a wind power plant, belonging to the technical field of power generation.
Background
At present, wind power energy is developed and utilized on a large scale, and installed capacity of wind power is increased very rapidly. By the end of 2017, the installed wind power capacity in China reaches 188.3 GW. Due to the randomness and the volatility of wind power, the safe and stable operation of a power system is certainly influenced by large-scale wind power integration. With the continuous expansion of the scale of wind power plants, a plurality of wind power plants are often gathered in the same area, the wind power output of the wind power plants has certain correlation, and particularly, the wind power plants which are close to each other are generally positioned on the same wind speed band, so that the output of each wind power plant not only has randomness in time, but also has strong correlation in space. The wind power resources in China are extremely unevenly distributed, a mode of centralized development and base construction is often adopted, and the correlation and the influence of a wind power plant are serious. The detection and determination of the relevant structure of the output of the multi-wind power plant and the change rule thereof have important significance for safe, stable and economic operation of large-scale wind power after being merged into a power grid.
The wind power plant output under the relevant wind speed has certain synchronism, the sample particle space distribution is denser, the fluctuation of the wind power is superposed, the safe operation of a power grid is threatened, and the probability of the power grid losing stability is increased along with the enhancement of the wind speed relevance. Therefore, it is necessary to perform output correlation verification for multiple wind farms within a certain range.
The wind power output correlation of the large wind power plant is very difficult to accurately verify and involves many factors; only if the wind power output correlation of the multiple wind power plants is accurately described, the wind power plant output can be objectively analyzed or predicted. The invention relates to a method for determining a kernel Copula function of output correlation of a wind power plant, calculating a rank correlation coefficient representing the correlation by using the function and verifying the output correlation of the wind power plant, thereby effectively reflecting the output characteristics of the wind power plant under the wind speed of the correlation and improving the stability and the economy of grid-connected operation of the wind power plant, and belongs to the technical field of power generation.
At present, in the analysis and determination of the output correlation of the wind farm, one or more Copula functions are widely selected from a Copula function family to describe the relevant structure of the output of the wind farm, and the selection criterion is based on the minimum Euclidean distance method between the candidate Copula and the empirical Copula function, and the Copula function corresponding to the minimum Euclidean distance is used for describing the relevant characteristics of the output of the wind farm. In fact, the empirical Copula function is discontinuous, the Copula function determined based on the empirical method may not be unique, and the empirical Copula function distribution is only an approximation of the true distribution, and there will always be a certain gap between the two no matter how large the sample capacity is. In addition, the empirical Copula function has no analytic expression, and when the data information amount is large, the method for reasonably selecting the Copula function consumes long time and even falls into a dilemma. Until now, how to establish an accurate wind power plant output correlation model for correlation determination is still a big difficulty.
Disclosure of Invention
The invention aims to provide a method for verifying the output correlation of a wind power plant aiming at the defects of the prior art, so that the probability of the output consistency of multiple wind power plants is determined, the precision of analyzing or predicting the output of the wind power plant is improved, and the stability of grid-connected operation of the wind power plant is further improved.
The problems of the invention are realized by the following technical scheme.
A method for verifying wind power plant output correlation comprises the following steps:
a. taking the historical output of the wind power plant as sample data, and respectively solving probability density functions of the output of the two wind power plants by adopting a non-parameter kernel density estimation method:
let two wind power plant output sample sequences be omega1r,ω2r,L,ωnr(r 1,2), wherein r is the serial number of the wind power plant, n is the sample capacity, and the following optimization model is established by adopting a Gauss kernel function:
thus, the window width h of the two wind power plant output sample sequences is calculated1,h2；
Selecting Gauss function as kernel function, and using probability density function for two wind power plant output sequences
Carrying out engraving:
in the formula (I), the compound is shown in the specification,
respectively taking the probability density functions of the output of the first wind power plant and the second wind power plant; k (g) is a kernel function; omega1Outputting power for the first wind power plant; omega2Outputting power for a second wind power plant;
b. calculating probability distribution function F (omega) of output of two wind power plantsr) (r ═ 1,2), calculated specifically as follows:
in the formula, phi is a standard normal distribution function;
c. historical output sequences omega of two wind power plants1r,ω2r,L,ωnr(r ═ 1,2) into the cumulative distribution function F (ω) of the wind farm outputr) (r is 1,2), and calculating the cumulative distribution function value U of the two wind power plantsr＝(u1r,u2r,L,unr)T，(r＝1,2)；
d. Let ur＝F(ωr) (r ═ 1,2), the cumulative distributions of the two wind farms are regarded as random variables, and a joint probability density function h (u) of the two wind farms is obtained by using multidimensional kernel density estimation1,u2) And a joint distribution function H (u)1,u2) Wherein the edge distribution of H (g, g) is uniform;
wherein the probability density function h (u) is combined1,u2) And a joint distribution function H (u)1,u2) The specific treatment process is as follows:
① determining a uniform sequence u11,u21,L,un1；u12,u22,L,un2The optimal window width matrix H:
taking H as positive definite diagonal matrix, i.e. H ═ diag (H)1,h2) H is obtained by solving the following optimization model:
② determining a multidimensional kernel function K (g) as:
wherein x and y are variables of a function;
③ substituting the optimal window width matrix H and the two-dimensional kernel function K (x, y) into the random variable u1,u2Obtaining a joint probability density function h (u) of the two wind power plants by using the joint probability density expression1,u2)：
Binary random variable u1,u2The kernel Copula density function of (a) is expressed as follows:
joint distribution function H (u) of two wind farms1,u2) Then it is:
e. jointly distribute function H (u)1,u2) As a function of kernel Copula and is denoted as
Spearman rank correlation coefficient for calculating output sequences between different wind power plants
And Kendall rank correlation coefficient
f. Comparing the two rank correlation coefficients with a set threshold value to obtain a similarity degree representing the output fluctuation rule among the wind power plants; if the value is equal to zero, no correlation is indicated; when the output values of the multiple wind power plants are more than a set threshold value, the output values of the multiple wind power plants have considerable correlation, and correlation influence among the wind power plants must be considered when forecasting the output values of the multiple wind power plants in the region or carrying out load flow calculation, stability analysis and scheduling on the power system so as to ensure the reliable operation of the wind power grid-connected power system; the threshold value ranges from greater than 0 to less than 1, and generally ranges from 0.4 to 0.6.
According to the method, a kernel Copula function suitable for detecting and determining the output correlation of the wind power plant is constructed based on nonparametric kernel density estimation and a Copula function theory, an algorithm model for detecting the output correlation of the wind power plant is directly established according to the kernel Copula function, and two difficulties of Copula function selection and parameter determination are avoided. The Spearman rank correlation coefficient of the output sequence between the wind power plants obtained in the technical scheme
And Kendall rank correlation coefficient
Can effectively reflect the correlation characteristics of the output of the wind power plant, and shows thatThe synchronicity probability of the output of the multi-wind power plant presents a multi-wind power plant output scene, and has important significance for ensuring the stable and economic operation of a wind power grid-connected power system.
Drawings
The present invention will be described in further detail with reference to the accompanying drawings.
FIG. 1 is a schematic flow diagram of an embodiment of the present invention;
FIG. 2 is a nuclear density estimation curve of a first wind farm output profile;
FIG. 3 is a nuclear density estimation curve of a second wind farm output profile;
FIG. 4 is a frequency histogram of the cumulative distribution function of two wind farm outputs;
FIG. 5 is a graphical illustration of a kernel Copula density function of a cumulative distribution function of two wind farm outputs.
Fig. 4 illustrates that the output of the first wind farm and the second wind farm has tail correlation (regularly described by the data curves of fig. 2 and fig. 3), and the lower tail correlation is stronger, and the upper tail correlation is weaker, that is, the wind power output has a smaller probability and the wind power output has a smaller probability.
Figure 5 illustrates the effectiveness of the present solution.
The symbols used herein are respectively represented as: r is the wind farm serial number; n is the sample volume; h is1,h2Window widths of output sample sequences of the two wind power plants;
respectively taking the probability density functions of the output of the first wind power plant and the second wind power plant; k (g) is a kernel function; omega1Outputting power for the first wind power plant; omega2Outputting power for a second wind power plant; f (omega)r) (r ═ 1,2) is the probability distribution function of the two wind farm outputs; u shaper＝(u1r,u2r,L,unr)T(r is 1,2) is the cumulative distribution function value of the two wind power plants; h (u)1,u2) A joint probability density function for two wind farms; h (u)1,u2) A joint distribution function for two wind farms;
spearman rank correlation coefficients for the power sequences between different wind farms;
kendall rank correlation coefficients of output sequences among different wind power plants; h is the optimal window width matrix.
Detailed Description
The invention provides a method for verifying output correlation of a wind power plant, which aims to solve the problems of difficulty in selection, trouble in parameter determination and the like of a conventional Copula function in output prediction and can more accurately and conveniently determine the relevant characteristics of the output of the wind power plant.
The technical scheme of the invention comprises the following steps:
(1) in order to accurately obtain the probability density function of the wind power plant output, a non-parameter kernel density estimation method is adopted to calculate a window width value influencing the fitting precision of the wind power output sequence. The process is as follows:
let two wind power plant output sample sequences be omega1r,ω2r,L,ωnr(r ═ 1,2), the following optimization model was established using Gauss kernel function
The model can be used for accurately calculating the window width h of two wind power plant output sample sequences1,h2。
Selecting Gauss function as kernel function, and using probability density function for two wind power plant output sequences
The method comprises the following steps:
in the formula, n is the sample capacity; k (g) is a kernel function.
(2) Calculating probability distribution function F (omega) of output of two wind power plantsr) (r ═ 1,2), calculated specifically as follows:
(3) in order to eliminate the difference caused by wind power plants with different capacities, a distribution function F (omega) is adopted1),F(ω2) Two wind power plant output samples w1＝(ω11,ω21,L,ωn1)T，w2＝(ω12,ω22,L,ωn2)TCarrying out normalization processing to obtain a normalized sample U1＝(u11,u21,L,un1)T,U2＝(u12,u22,L,un2)TAnd has uir:U[0,1](i＝1,2,L,n；r＝1,2)。
(4) Let u1＝F(ω1),u2＝F(ω2) Solving a joint probability density function h (u) for describing internal relation of output of two wind power plants by adopting multi-dimensional kernel density estimation1,u2) And a joint distribution function H (u)1,u2) The specific process is as follows:
1) determination of a uniform sequence u11,u21,L,un1；u12,u22,L,un2The optimal window width matrix H. Since H is a positive definite symmetric matrix, H is usually taken as a positive definite diagonal matrix, i.e., H ═ diag (H)1,h2). H can be obtained by solving the following optimization model:
2) a multidimensional kernel function k (g) is determined. For simplicity of calculation, K (g) may take two mononuclear Ki(g) The product of (i), i.e. K (g) ═ K1(g)K2(g)
Mononuclear Ki(g) Taking the Gauss function, K (g) can be expressed as:
3) substituting the determined window width matrix H and the two-dimensional kernel function K (x, y) into a random variable u1,u2Combined probability density expression of
Obtaining binary random variable u1,u2The kernel Copula density function expression of (a), as follows:
accordingly, a binary random variable u1,u2The kernel function expression of
The kernel Copula function has a flexible expression form and has stronger adaptability to various types of samples. In addition, the kernel Copula function also has similar mathematical properties to the conventional Copula function.
(5) By utilizing the obtained kernel Copula function, a Spearman rank correlation coefficient and a Kendall rank correlation coefficient of the multi-wind power field output are calculated, and specific expressions are as follows:
1) spearman rank correlation coefficient:
2) kendall rank correlation coefficient:
(6) and comparing the rank correlation coefficient with a set threshold value to obtain the conclusion whether the multi-wind power plant output has correlation and the magnitude of the correlation.
The invention provides a function construction method for verifying the output correlation of a wind power plant, which reduces the difficulty of verifying the output correlation of a multi-wind power plant at present and improves the application range of verifying the output correlation of the multi-wind power plant. When the kernel Copula function is adopted to calculate the rank correlation coefficient, the Copula function which can accurately fit sample data does not need to be selected from a Copula function family, the edge distribution of the sample is not limited, a model for detecting and determining the output correlation of the wind power plant can be directly established according to the function, and the two difficulties of Copula function selection and parameter determination are avoided. The technical scheme can accurately reflect the nonlinear and asymmetric related structures among variables, and provides favorable information for analyzing the influence of the grid connection of the wind power plant on the power system. The method has the advantages that the correlation of the output of the wind power plant is verified, the probability of consistency of the output of the multiple wind power plants is determined, and the method has important significance for improving the prediction precision of the output of the wind power plant and further improving the stability and the economic operation of a power system.
To further illustrate the method for verifying the wind farm output correlation provided by the present invention, the following description is made with reference to specific examples:
16068 output samples of two adjacent wind power plants in the North China within a period of time are selected, and the basic information of the two wind power plants is as follows: (the output sample can be wind speed and power monitored by the wind power plant)
| Wind farm | Mean value (m/s) | Variance (m/s) | Capacity (MW) |
| First wind farm | 9.23 | 3.37 | 24 |
| Second wind farm | 8.81 | 3.28 | 15 |
(1) And determining the probability density function of the output of each wind power plant.
By adopting the technical scheme provided by the invention, the nuclear density estimation of the output distribution of the two wind power plants can be obtained as shown in fig. 2 and 3. As can be seen from the graph, the kernel density estimation curve of the wind power plant output almost completely coincides with the empirical curve.
(2) Cumulative frequency histograms of the two wind farm outputs are plotted, as shown in fig. 4. As can be seen from fig. 4, the outputs of the two wind farms have an asymmetric tail-related structure.
(3) And estimating the output nuclear distribution function of the wind power plants according to the output nuclear density of the wind power plants, and converting the output sequences of the two wind power plants into uniform distribution on [0,1] according to the nuclear distribution function.
(4) The optimal window width matrix H of the transformed wind field output sequence is obtained by using the scheme of the invention, and the result is as follows:
(5) substituting the optimal window width matrix H into a kernel Copula function expression to obtain a joint distribution function of the output of the first wind power plant and the second wind power plant:
(6) according to the method, the Spearman rank correlation coefficient and the Kendall rank correlation coefficient for describing the output correlation of the multi-wind power plant are calculated as follows:
namely: the wind power plant output correlation value obtained by adopting the technical scheme disclosed by the invention is as follows: spearman rank correlation coefficient 0.7392 and Kendall rank correlation coefficient 0.5489. The two quantities represent the similarity degree of output fluctuation rules among wind power plants. When the value (the range is greater than or equal to 0, less than or equal to 1, and equal to 0 represents irrelevance) is greater than a set threshold (the specific threshold can be determined according to application scenes, and usually can be 0.5 or 0.4), the output of the multiple wind power plants is quite relevant, and the output values of the multiple wind power plants in the area are predicted or power flow calculation, stability analysis and economic dispatching of the power system are carried out, the relevant influence among the wind power plants must be considered, so that the reliable operation of the wind power grid-connected power system can be guaranteed.
Claims (2)
1. A method for verifying wind farm output correlation, comprising the steps of:
a. taking the historical output of the wind power plant as sample data, and respectively solving probability density functions of the output of the two wind power plants by adopting a non-parameter kernel density estimation method:
let two wind power plant output sample sequences be omega1r,ω2r,L,ωnr(r 1,2), wherein r is the serial number of the wind power plant, n is the sample capacity, and the following optimization model is established by adopting a Gauss kernel function:
thus, the window width h of the two wind power plant output sample sequences is calculated1,h2；
Selecting Gauss function as kernel function, and using probability density function for two wind power plant output sequences
Carrying out engraving:
in the formula (I), the compound is shown in the specification,
respectively taking the probability density functions of the output of the first wind power plant and the second wind power plant; k (g) is a kernel function; omega1Outputting power for the first wind power plant; omega2Outputting power for a second wind power plant;
b. calculating probability distribution function F (omega) of output of two wind power plantsr) (r ═ 1,2), calculated specifically as follows:
where Φ is a normal distribution function
c. Historical output sequences omega of two wind power plants1r,ω2r,L,ωnr(r ═ 1,2) into the cumulative distribution function F (ω) of the wind farm outputr) (r is 1,2), and calculating the cumulative distribution function value U of the two wind power plantsr＝(u1r,u2r,L,unr)T，(r＝1,2)；
d. Let ur＝F(ωr) (r ═ 1,2), the cumulative distributions of the two wind farms are regarded as random variables, and a joint probability density function h (u) of the two wind farms is obtained by using multidimensional kernel density estimation1,u2) And a joint distribution function H (u)1,u2) Wherein the edge distribution of H (g, g) is uniform;
e. jointly distribute function H (u)1,u2) As a function of kernel Copula and is denoted as
Spearman rank correlation coefficient for calculating output sequences between different wind power plants
And Kendall rank correlation coefficient
f. Comparing the two rank correlation coefficients with a set threshold value to obtain a similarity degree representing the output fluctuation rule among the wind power plants; if the value is equal to zero, no correlation is indicated; when the output values of the multiple wind power plants are more than a set threshold value, the output values of the multiple wind power plants have considerable correlation, and correlation influence among the wind power plants must be considered when forecasting the output values of the multiple wind power plants in the region or carrying out load flow calculation, stability analysis and scheduling on the power system so as to ensure the reliable operation of the wind power grid-connected power system; the threshold value ranges from greater than 0 to less than 1, and generally ranges from 0.4 to 0.6.
2. According to the claimsThe method for detecting the output correlation of the wind power plants in the 1 is characterized in that a combined probability density function h (u) of two wind power plants is obtained by adopting multi-dimensional nuclear density estimation1,u2) And a joint distribution function H (u)1,u2) The specific process is as follows:
① determining a uniform sequence u11,u21,L,un1；u12,u22,L,un2The optimal window width matrix H:
taking H as positive definite diagonal matrix, i.e. H ═ diag (H)1,h2) H is obtained by solving the following optimization model:
② determining a multidimensional kernel function K (g) as:
wherein x and y are variables of a function;
③ substituting the optimal window width matrix H and the two-dimensional kernel function K (x, y) into the random variable u1,u2Obtaining a joint probability density function h (u) of the two wind power plants by using the joint probability density expression1,u2)：
Binary random variable u1,u2The kernel Copula density function of (a) is expressed as follows:
joint distribution function H (u) of two wind farms1,u2) Comprises the following steps:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910943047.4A CN110705099B (en) | 2019-09-30 | 2019-09-30 | Method for verifying output correlation of wind power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910943047.4A CN110705099B (en) | 2019-09-30 | 2019-09-30 | Method for verifying output correlation of wind power plant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110705099A true CN110705099A (en) | 2020-01-17 |
| CN110705099B CN110705099B (en) | 2021-06-11 |
Family
ID=69197399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910943047.4A Active CN110705099B (en) | 2019-09-30 | 2019-09-30 | Method for verifying output correlation of wind power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110705099B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112711864A (en) * | 2021-01-18 | 2021-04-27 | 国网浙江省电力有限公司电力科学研究院 | Distribution network cable quality index correlation model construction and data expansion method |
| CN113761706A (en) * | 2021-07-19 | 2021-12-07 | 国网新疆电力有限公司经济技术研究院 | Method for obtaining wind power output fluctuation correlation |
| CN115455772A (en) * | 2022-09-15 | 2022-12-09 | 长安大学 | Microcosmic reservoir rock conductivity prediction method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020423A (en) * | 2012-11-21 | 2013-04-03 | 华中科技大学 | Copula-function-based method for acquiring relevant characteristic of wind power plant capacity |
| US20150160373A1 (en) * | 2013-12-07 | 2015-06-11 | Cardinal Wind, Inc. | Computer-implemented data analysis methods and systems for wind energy assessments |
| CN107038292A (en) * | 2017-04-01 | 2017-08-11 | 三峡大学 | A kind of many output of wind electric field correlation modeling methods based on adaptive multivariable nonparametric probability |
| CN107274028A (en) * | 2017-06-23 | 2017-10-20 | 国网山东省电力公司经济技术研究院 | A kind of many wind fields based on mixing Copula functions are exerted oneself Forecasting Methodology |
| 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 |
-
2019
- 2019-09-30 CN CN201910943047.4A patent/CN110705099B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020423A (en) * | 2012-11-21 | 2013-04-03 | 华中科技大学 | Copula-function-based method for acquiring relevant characteristic of wind power plant capacity |
| US20150160373A1 (en) * | 2013-12-07 | 2015-06-11 | Cardinal Wind, Inc. | Computer-implemented data analysis methods and systems for wind energy assessments |
| CN107038292A (en) * | 2017-04-01 | 2017-08-11 | 三峡大学 | A kind of many output of wind electric field correlation modeling methods based on adaptive multivariable nonparametric probability |
| CN107274028A (en) * | 2017-06-23 | 2017-10-20 | 国网山东省电力公司经济技术研究院 | A kind of many wind fields based on mixing Copula functions are exerted oneself Forecasting Methodology |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 徐玉琴，等: "Copula函数与核估计理论相结合分析风电场出力相关性的一种新方法", 《电工技术学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112711864A (en) * | 2021-01-18 | 2021-04-27 | 国网浙江省电力有限公司电力科学研究院 | Distribution network cable quality index correlation model construction and data expansion method |
| CN113761706A (en) * | 2021-07-19 | 2021-12-07 | 国网新疆电力有限公司经济技术研究院 | Method for obtaining wind power output fluctuation correlation |
| CN115455772A (en) * | 2022-09-15 | 2022-12-09 | 长安大学 | Microcosmic reservoir rock conductivity prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110705099B (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110705099B (en) | Method for verifying output correlation of wind power plant | |
| CN110336534B (en) | Fault diagnosis method based on photovoltaic array electrical parameter time series feature extraction | |
| CN107038292B (en) | Multi-wind-field output correlation modeling method based on self-adaptive multivariate nonparametric kernel density estimation | |
| CN111241755A (en) | Power load prediction method | |
| Wang et al. | Wind power curve modeling with asymmetric error distribution | |
| CN111709454B (en) | Multi-wind-field output clustering evaluation method based on optimal copula model | |
| CN112001441A (en) | Power distribution network line loss anomaly detection method based on Kmeans-AHC hybrid clustering algorithm | |
| CN110212592B (en) | Thermal power generating unit load regulation maximum rate estimation method and system based on piecewise linear expression | |
| CN111160772A (en) | Large power grid risk rapid assessment method | |
| CN110879927A (en) | Sea clutter amplitude statistical distribution field modeling method for sea target detection | |
| CN112765746B (en) | Turbine blade top gas-thermal performance uncertainty quantification system based on polynomial chaos | |
| CN113359435B (en) | Correction method for dynamic working condition data of thermal power generating unit | |
| CN111984906B (en) | Probability power flow rapid calculation method considering correlation of photovoltaic and load time sequence | |
| Zhang et al. | An improved association rule mining-based method for discovering abnormal operation patterns of HVAC systems | |
| CN108009963A (en) | Economic transition development and energy demand relevance assessment system based on gray theory | |
| CN117273195A (en) | Steam heating system demand load prediction method | |
| CN112990603B (en) | Air conditioner cold load prediction method and system considering frequency domain decomposed data characteristics | |
| CN110555566A (en) | b-spline quantile regression-based photoelectric probability density prediction method | |
| CN116249186A (en) | Data processing method and device of wireless network equipment, storage medium and electronic equipment | |
| CN106816871B (en) | State similarity analysis method for power system | |
| CN113052398A (en) | Power consumption prediction method and system based on variational modal decomposition | |
| Elkantassi et al. | INFERENCE AND SENSITIVITY IN STOCHASTIC WIND POWER FORECAST MODELS. | |
| Huang et al. | A piecewise linear representation method of hydrological time series based on curve feature | |
| CN111199014A (en) | Time sequence based seq2point NILM method and device | |
| Liu et al. | Hidden Markov Models Based Appliance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |