CN106570790B - Wind power plant output data restoration method considering wind speed data segmentation characteristics - Google Patents
Wind power plant output data restoration method considering wind speed data segmentation characteristics Download PDFInfo
- Publication number
- CN106570790B CN106570790B CN201610989785.9A CN201610989785A CN106570790B CN 106570790 B CN106570790 B CN 106570790B CN 201610989785 A CN201610989785 A CN 201610989785A CN 106570790 B CN106570790 B CN 106570790B
- Authority
- CN
- China
- Prior art keywords
- data
- abnormal
- output
- wind
- wind speed
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000011218 segmentation Effects 0.000 title claims description 30
- 230000002159 abnormal effect Effects 0.000 claims abstract description 100
- 241001123248 Arma Species 0.000 claims 4
- 238000012216 screening Methods 0.000 abstract description 9
- 238000012567 pattern recognition method Methods 0.000 abstract 1
- 238000009826 distribution Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000001276 Kolmogorov–Smirnov test Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000009827 uniform distribution Methods 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
- 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
Landscapes
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Wind Motors (AREA)
Abstract
本发明公开了一种计及风速数据分段特性的风电场出力数据修复方法，包括以下步骤：S1，从得到的数据中筛选重复、缺乏和不合理的异常数据，并根据异常数据所对应连续时间序列的长度，分为连续异常型和局部异常型两类；S2，对于局部异常型数据，采用插值方法得到修复的风电场出力数据；S3，对于连续异常型数据，基于最大后验概率，利用异常数据前后的正常数据判断异常数据是否含有分段点，然后基于每段的风速特性由正常数据或模式识别方法得到，基于该风速特性，采用ARMA模型生成修复的风速，进一步得到修复的风电场出力数据；S4，验证修复数据的有效性，输出修复报告；提高了电网中辅助服务的决策精度，减少了不必要的系统备用。
The invention discloses a wind farm output data restoration method taking into account the segmental characteristics of wind speed data. The method includes the following steps: S1, screening repeated, lacking and unreasonable abnormal data from the obtained data, and according to the continuous data corresponding to the abnormal data The length of the time series is divided into two types: continuous anomaly type and local anomaly type; S2, for local anomaly type data, use interpolation method to obtain the restored wind farm output data; S3, for continuous anomaly type data, based on the maximum posterior probability, Use the normal data before and after the abnormal data to determine whether the abnormal data contains segment points, and then obtain the normal data or pattern recognition method based on the wind speed characteristics of each segment. Field output data; S4, verify the validity of the repair data, and output the repair report; improve the decision-making accuracy of auxiliary services in the power grid, and reduce unnecessary system backup.
Description
Technical Field
The invention belongs to the field of new energy power station output data restoration, and particularly relates to a wind power plant output data restoration method considering wind speed data segmentation characteristics.
Background
Because of huge wind energy accumulation, wide distribution, cleanness and no pollution, wind power generation is rapidly developed in the global scope at present. However, due to the characteristics of randomness, volatility and intermittence of wind energy, large-scale wind power access has great influence on a power system, so that analysis on historical wind power plant output data of the access system is necessary to extract the output characteristics of the wind power plant, and an important decision basis is provided for scheduling of power grid operation.
However, the general position of the wind power plant is far away, the communication condition is poor, the real-time communication between the detection data and the data center is not stable enough, the problems of data loss, data repetition, errors and the like often occur, the quality of the output data of the wind power plant is seriously influenced, and the application of the data is limited. Therefore, it is important to repair such abnormal data as missing, overlapping, and error data.
The existing data restoration technology mostly obtains a correction value of abnormal data by extracting the characteristics of data from a wind power plant and then utilizing interpolation or prediction and other modes. The data restoration technology can better ensure the consistency of the statistical characteristics of the wind power plant output data and eliminate the influence of abnormal data items on the wind power plant output data characteristics.
Although the method can eliminate the interference of abnormal data on the output statistical characteristics of the wind power plant to a great extent, the repairing technology can only ensure that the repaired data keeps the consistent statistical characteristics with the normal data in a longer time period. Even if the difference of wind power statistical characteristics in different seasons or day and night is considered in some repairing technologies, characteristics such as a big wind day and a small wind day determined by real-time weather information cannot be effectively described, the day number and distribution characteristics of the big wind day and the small wind day are very important for planning and running of a power system, and the characteristics cannot be repaired, so that the application of wind power plant output data with a large abnormal proportion is seriously influenced.
Therefore, a new wind farm output data restoration technology is needed to avoid the above-mentioned defects.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a wind power plant output data restoration method considering wind speed data segmentation characteristics, which takes the restoration of wind speed as a core, and realizes the wind power plant output data restoration technology considering short-term wind speed statistical characteristic difference by determining the segmentation point of a wind speed sequence and determining the statistical characteristics corresponding to abnormal data, so that the data restoration method not only plays a role in 'eliminating bad' but also can introduce valuable effective information and has very significant significance for improving the application of the wind power plant output data in the planning and operation of a power system.
A wind power plant output data restoration method considering wind speed data segmentation characteristics comprises the following steps:
s1, screening repeated, lacked and unreasonable abnormal data from the obtained data, and dividing the abnormal data into a continuous abnormal type and a local abnormal type according to the length of a continuous time sequence corresponding to the abnormal data;
s2, for the local abnormal data, obtaining the repaired wind power plant output data by adopting an interpolation method;
s3, for continuous abnormal data, based on the maximum posterior probability, judging whether the abnormal data contains segmentation points by using normal data before and after the abnormal data, then obtaining the wind speed characteristics of each segment by a normal data or mode recognition method, and based on the wind speed characteristics, generating a restored wind speed by using an ARMA model, and further obtaining restored wind power plant output data;
and S4, verifying the validity of the repair data and outputting a repair report.
Preferably, the S1 is specifically:
searching data records corresponding to a plurality of data outputs at the same time point, wherein the data records are repeated data; searching time points without output data in a data restoration time window, wherein the time points correspond to missing data, screening data records with the same data of more than 4 continuous time points in the output data of the wind power plant, data records with output data larger than the starting capacity and data records with output at night, and recording the data records as unreasonable data; if the data records corresponding to not less than 5 continuous time points are all abnormal data, the data records corresponding to the time points are continuous abnormal data records, and the rest abnormal data records are local abnormal data records.
Preferably, the S2 is specifically:
the number of the local abnormal data is recorded as N, the data [ N/2] item before the local abnormal data and the data [ N/2] item after the local abnormal data are taken, and the abscissa values corresponding to the data are respectively marked as 1, 2, …, [ N/2], N + [ N/2], N + [ N/2] +1, … and 2N; fitting the N points to obtain an N-order polynomial fitting function; and calculating values of the fitting function at [ N/2] +1, [ N/2] +2, …, [ N/2] + N to serve as output data of the repair.
Preferably, the S3 specifically includes the following steps:
selecting normal data before and after the abnormal data, wherein the length of the normal data before and after the abnormal data is 1 day; judging whether the abnormal data contain segmentation points or not by using normal data before and after the abnormal data based on KS detection; if the abnormal data group contains the segmentation point, sampling the position of the segmentation point, respectively obtaining an ARMA model by using the normal data of the segment before and after the segmentation point, and then obtaining the wind speed of the time sequence corresponding to the abnormal data by using the ARMA model; if the group of abnormal data does not contain the segmentation point, normal data before and after the abnormal data are directly utilized to obtain an ARMA model, and then the ARMA model is utilized to obtain the wind speed of the time sequence corresponding to the abnormal data; based on a fan output characteristic formula, obtaining output sequences of various types of fans of the wind power plant according to wind speed; and solving the output sequence of the started fans in the wind power plant to obtain the restored wind power plant output data.
The technical scheme of the invention has the following beneficial effects:
according to the wind power plant output data restoration method considering the wind speed data segmentation characteristics, the non-stationary characteristic of the wind speed in a short period can be considered, and the accuracy of wind power plant output data restoration is improved through segmentation in the short period. The method can more effectively correct the abnormal record in the output data of the wind power plant and improve the quality of the output data of the wind power plant; the method is beneficial to improving the decision level of power grid planning and operation, improving the decision precision of auxiliary service in the power grid and reducing unnecessary system standby, thereby improving the economy of power grid construction and operation.
Drawings
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
FIG. 1 is an overall flowchart of a wind farm output data restoration method taking wind speed data segmentation characteristics into consideration according to the present invention;
fig. 2 is a schematic diagram of the commutation voltage area at the time of an ac side fault in the wind farm output data restoration method considering the wind speed data segment characteristics.
Detailed Description
In order to clearly understand the technical solution of the present invention, a detailed structure thereof will be set forth in the following description. It is apparent that the specific implementation of the embodiments of the present invention is not limited to the specific details familiar to those skilled in the art. The preferred embodiments of the present invention are described in detail below, and other embodiments are possible in addition to the embodiments described in detail.
The present invention will be described in further detail with reference to the accompanying drawings and examples.
Referring to fig. 1, the overall flow chart of the wind power plant output data restoration method considering the segmented characteristics of wind speed data includes the main steps of abnormal data screening and classification, weather information and photovoltaic output parameter feature extraction, abnormal data group restoration and the like, and specifically includes the following steps:
1) screening to obtain repeated, lacking and unreasonable abnormal data in the data, and classifying the abnormal data into a continuous abnormal type and a local abnormal type according to the length of a continuous time sequence corresponding to the abnormal data;
2) for the local abnormal data, obtaining restored wind power plant output data by adopting an interpolation method;
3) for continuous abnormal data, judging whether the abnormal data contain segmentation points or not by using normal data before and after the abnormal data based on the maximum posterior probability, then obtaining the wind speed characteristics of each segment by a normal data or mode recognition method, and generating the restored wind speed by adopting an ARMA (autoregressive moving average) model based on the wind speed characteristics to further obtain the restored wind power plant output data;
4) and verifying the validity of the repair data and outputting a repair report.
The step 1) specifically comprises the following steps: searching data records corresponding to a plurality of data outputs at the same time point, wherein the data records are repeated data; searching time points without output data in a data restoration time window, wherein the time points correspond to missing data, screening data records with the same data of more than 4 continuous time points in the output data of the wind power plant, data records with output data larger than the starting capacity and data records with output at night, and recording the data records as unreasonable data; if the data records corresponding to not less than 5 continuous time points are all abnormal data, the data records corresponding to the time points are continuous abnormal data records, and the rest abnormal data records are local abnormal data records.
The step 2) specifically comprises the following steps: the number of the local abnormal data is recorded as N, the data [ N/2] item before the local abnormal data and the data [ N/2] item after the local abnormal data are taken, and the abscissa values corresponding to the data are respectively marked as 1, 2, …, [ N/2], N + [ N/2], N + [ N/2] +1, … and 2N; fitting the N points to obtain an N-order polynomial fitting function; and calculating values of the fitting function at [ N/2] +1, [ N/2] +2, …, [ N/2] + N to serve as output data of the repair.
The step 3) specifically comprises the following steps: selecting normal data before and after the abnormal data, wherein the length of the normal data before and after the abnormal data is 1 day; judging whether the abnormal data contain segmentation points or not by using normal data before and after the abnormal data based on KS detection; if the abnormal data group contains the segmentation point, sampling the position of the segmentation point, respectively obtaining an ARMA model by using the normal data of the segment before and after the segmentation point, and then obtaining the wind speed of the time sequence corresponding to the abnormal data by using the ARMA model; if the group of abnormal data does not contain the segmentation point, normal data before and after the abnormal data are directly utilized to obtain an ARMA model, and then the ARMA model is utilized to obtain the wind speed of the time sequence corresponding to the abnormal data; based on a fan output characteristic formula, obtaining output sequences of various types of fans of the wind power plant according to wind speed; and solving the output sequence of the started fans in the wind power plant to obtain the restored wind power plant output data.
Wherein, the screening and classification of abnormal data: the abnormal data mainly refers to three types of repeated data, missing data and unreasonable data. As shown in fig. 2, the repeated data refers to output data records of a plurality of different photovoltaic power stations corresponding to a certain time; the missing data refers to incomplete photovoltaic power station output data records corresponding to a certain moment, wherein the incomplete data means that all data items stored in the output data records are not enough to be mutually deduced from the physical meanings of the data items; unreasonable data refers to photovoltaic power plant output data records which do not conform to physical reality.
According to the classification, three types of abnormal data are searched and screened in sequence: searching data records corresponding to a plurality of data outputs at the same time point, wherein the data records are repeated data; and searching time points without output data in the data restoration time window, wherein the time points correspond to missing data, screening data records with the same data of more than 4 continuous time points in the output data of the photovoltaic power station, data records with output data larger than the starting capacity and data records with output data existing at night, and recording the data records as unreasonable data.
When screening unreasonable data, should consider numberAccording to the accuracy and error of the record. When the boot capacity is PonIn time, the output of the photovoltaic power station can be controlled to be [ -alpha P ]on,(1+α)Pon]The starting capacity of the photovoltaic power station is not exceeded in the interval, and alpha can be selected to be 0.03-0.1 according to data quality.
And merging the abnormal data adjacent to the time point into an abnormal data group, wherein if the number of elements of the abnormal data group is not less than 5, the data in the abnormal data group is recorded as a continuous abnormal data record, and otherwise, the data is recorded as a local abnormal data record.
Repairing local abnormal data: the local abnormal data and the continuous abnormal data are different in property, the time interval corresponding to the local abnormal data and the continuous abnormal data is short, the change of the meteorological data in the time interval is not obvious, and the main factor influencing the photovoltaic output is the characteristic of a local area and does not need to be repaired by the meteorological data. Therefore, the present invention adopts different repair methods for the local abnormality type data and the continuous abnormality type data.
And for local abnormal data, directly repairing the local abnormal data by using a polynomial interpolation method. If the number of the local abnormal data is N, taking a data [ N/2] item before the local abnormal data and a data [ N/2] item after the local abnormal data, and respectively marking the abscissa values corresponding to the data as 1, 2, …, [ N/2], N + [ N/2], N + [ N/2] +1, … and 2N; fitting the N points to obtain an N-order polynomial fitting function; and calculating values of the fitting function at [ N/2] +1, [ N/2] +2, …, [ N/2] + N to serve as output data of the repair.
Segmentation point judgment based on KS test: wind speed data of the adjacent day before and after the abnormal data group are respectively recorded as S1 and S2. The KS test (Kolmogorov-Similnov test) is used for testing whether the distribution is the same or not by S1 and S2, and the steps are as follows:
1) assume that S1 and S2 obey the same distribution;
2) and counting the cumulative probability of two groups of wind speed data, namely F1, n (x) and F1, n (x), wherein n is the data quantity of S1 and S2, and the cumulative probability is defined as follows:
wherein I < - ∞, x (Xi) is an indicator function, that is, Xi < x is 1, otherwise 0;
3) calculating KS statistics:
wherein sup is the supremum operation;
4) checking whether to reject a hypothesis
If the following is satisfied, then (at the 0.05 level) the assumption is rejected, S1 and S2 obey different distributions, i.e., there are segmentation points for the set of outlier data, otherwise there are no segmentation points.
And if the abnormal data has segment points, sampling the positions of the segment points by utilizing uniform distribution.
Parameter estimation of ARMA model
The ARMA model (autoregressive moving average model) is a typical method of a wind speed model, and the ARMA (3,3) model is adopted to simulate the wind speed, namely, a 3-order model is adopted for both an autoregressive component and a moving average component. The time series form of ARMA (3,3) is as follows:
where c is a constant,. epsilon.t is white noise (i.e., a random variable that follows a Gaussian distribution with an expected 0 variance of δ 2), and φ i and θ i are parameters of the model.
The invention utilizes an autoregressive approximation method to carry out parameter estimation. The normal wind speed sequence used for parameter estimation is recorded as X, the length is n, and the parameters needing to be estimated are phi, theta, delta 2 and c.
1) From the expected estimated constant c of the wind speed sequence
2) Estimating a parameter phi of the wind speed sequence corresponding to the AR (3) model
Note the book
To s (phi) minimum
I.e. a least squares estimate of phi. If remember
S (phi) can be written as
Then the least squares estimate of phi is
3) Calculating wind speed sequence residual error
Based on step 2) to obtain
The residual error of the wind speed sequence is calculated as
4) Calculating parameters phi, theta and delta 2 in ARMA (3,3)
Note the book
Then a minimum value of Q (phi, theta) is reached
And
i.e., a least squares estimate of phi and theta.
Least squares estimation of δ 2 as
According to the wind power plant output data restoration method considering the wind speed data segmentation characteristics, the non-stationary characteristic of the wind speed in a short period can be considered, and the accuracy of wind power plant output data restoration is improved through segmentation in the short period. The method can more effectively correct the abnormal record in the output data of the wind power plant and improve the quality of the output data of the wind power plant; the method is beneficial to improving the decision level of power grid planning and operation, improving the decision precision of auxiliary service in the power grid and reducing unnecessary system standby, thereby improving the economy of power grid construction and operation.
Finally, it should be noted that: although the present invention has been described in detail with reference to the above embodiments, those skilled in the art can make modifications and equivalents to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is set forth in the claims appended hereto.
Claims (2)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610989785.9A CN106570790B (en) | 2016-11-10 | 2016-11-10 | Wind power plant output data restoration method considering wind speed data segmentation characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610989785.9A CN106570790B (en) | 2016-11-10 | 2016-11-10 | Wind power plant output data restoration method considering wind speed data segmentation characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106570790A CN106570790A (en) | 2017-04-19 |
| CN106570790B true CN106570790B (en) | 2021-05-07 |
Family
ID=58541185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610989785.9A Active CN106570790B (en) | 2016-11-10 | 2016-11-10 | Wind power plant output data restoration method considering wind speed data segmentation characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106570790B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392304A (en) * | 2017-08-04 | 2017-11-24 | 中国电力科学研究院 | A kind of Wind turbines disorder data recognition method and device |
| CN109740630A (en) * | 2018-12-06 | 2019-05-10 | 中科恒运股份有限公司 | Method for processing abnormal data and device |
| CN109800217B (en) * | 2018-12-28 | 2023-06-06 | 南京天溯自动化控制系统有限公司 | Method and device for repairing continuous abnormal energy consumption data and electronic equipment |
| CN110083804B (en) * | 2019-04-24 | 2022-10-28 | 华中科技大学无锡研究院 | Wind power plant SCADA data missing intelligent repairing method based on condition distribution regression |
| CN112310997A (en) * | 2019-07-29 | 2021-02-02 | 中国电力科学研究院有限公司 | Method and system for judging influence of wind power plant group output on power system service |
| CN110513252B (en) * | 2019-08-30 | 2020-11-24 | 湘电风能有限公司 | A wind farm SCADA system data abnormal alarm repair system and method |
| CN111177114A (en) * | 2019-12-09 | 2020-05-19 | 国网甘肃省电力公司电力科学研究院 | Wind power plant output data restoration method based on ARMA model |
| CN112067908B (en) * | 2020-08-20 | 2023-06-16 | 国网山东省电力公司电力科学研究院 | Fitting method and system for distorted electric field when substation robot measures power frequency electric field |
| CN118604717B (en) * | 2024-08-07 | 2024-11-29 | 保定市兆微软件科技有限公司 | A method and system for monitoring operation error of electric energy meter |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766175A (en) * | 2015-04-16 | 2015-07-08 | 东南大学 | Power system abnormal data identifying and correcting method based on time series analysis |
Family Cites Families (2)
| 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 |
| CN105160181B (en) * | 2015-09-02 | 2018-02-23 | 华中科技大学 | A kind of digital control system domain of instruction sequence variation data detection method |
-
2016
- 2016-11-10 CN CN201610989785.9A patent/CN106570790B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766175A (en) * | 2015-04-16 | 2015-07-08 | 东南大学 | Power system abnormal data identifying and correcting method based on time series analysis |
Non-Patent Citations (1)
| Title |
|---|
| ARMA 模型在振动信号分析中的应用;李社新;《机械科学与技术》;20101130;第29卷(第11期);第1586-1588页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106570790A (en) | 2017-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106570790B (en) | Wind power plant output data restoration method considering wind speed data segmentation characteristics | |
| CN109667727B (en) | Wind turbine generator yaw error inherent deviation identification and compensation method based on power curve analysis | |
| CN110362045B (en) | A fault discrimination method for offshore doubly-fed wind turbines considering marine meteorological factors | |
| CN103631681B (en) | A kind of method of online reparation abnormal data of wind power plant | |
| CN111522808B (en) | Abnormal operation data processing method for wind turbine generator | |
| CN112231361B (en) | A wind power project generation evaluation method based on wind turbine operation data | |
| CN106355512A (en) | Power curve fitting method of wind turbine generator based on optimizing maximum value of probability density | |
| CN111260503B (en) | Wind turbine generator power curve outlier detection method based on cluster center optimization | |
| CN103324980A (en) | Wind power station wind speed prediction method | |
| CN111322205A (en) | Identification method and correction method of wind vane zero position error of wind turbine | |
| CN111275570A (en) | A wind turbine power outlier detection method based on iterative statistics and hypothesis testing | |
| CN110674864B (en) | Wind power abnormal data identification method comprising synchronous phasor measurement device | |
| CN107728059A (en) | A kind of pitch-controlled system state evaluating method | |
| CN115578084A (en) | Wind Turbine Frequency Converter Fault Early Warning Method Based on Deep Convolutional Autoencoder | |
| CN117592799A (en) | A post-resource evaluation system for in-service wind power projects | |
| CN117195136A (en) | Power grid new energy abnormal data monitoring method | |
| CN110334951A (en) | An intelligent evaluation method and system for high temperature derating status of wind turbines | |
| CN104574221B9 (en) | A kind of photovoltaic plant running status discrimination method based on loss electricity characteristic parameter | |
| CN114912807A (en) | Method and system for evaluating generated energy improving effect of technically improved wind turbine generator | |
| CN112347655B (en) | Wind power plant theoretical power calculation method based on unit operation performance evaluation | |
| CN114971313A (en) | Wind turbine generator power curve fitting method | |
| CN114510815A (en) | A method and system for evaluating power characteristics of wind turbines | |
| CN117333325A (en) | Photovoltaic power station missing power restoration method based on correlation coefficient spline interpolation | |
| CN114281846B (en) | New energy power generation prediction method based on machine learning | |
| McKinnon et al. | Comparison of novel SCADA data cleaning technique for wind turbine electric pitch system |
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 |