CN107291927A - A kind of air speed data cleaning method for Wind turbines wind speed correlation analysis - Google Patents
A kind of air speed data cleaning method for Wind turbines wind speed correlation analysis Download PDFInfo
- Publication number
- CN107291927A CN107291927A CN201710516600.7A CN201710516600A CN107291927A CN 107291927 A CN107291927 A CN 107291927A CN 201710516600 A CN201710516600 A CN 201710516600A CN 107291927 A CN107291927 A CN 107291927A
- Authority
- CN
- China
- Prior art keywords
- mrow
- mtd
- wind turbines
- wind
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Quality & Reliability (AREA)
- Wind Motors (AREA)
Abstract
The present invention relates to a kind of air speed data cleaning method for Wind turbines wind speed correlation analysis, the cleaning of each Wind turbines air speed data during for multiple Wind turbines wind speed correlation analysis, this method comprises the following steps：(1) each original wind speed time series data of Wind turbines and corresponding generating power output time series data are obtained；(2) search matrix that retrieval mark obtains each Wind turbines is carried out according to the retrieval mark rule of setting to generating power output time series data；(3) comprehensive modification is carried out to each Wind turbines search matrix to obtain correcting search matrix；(4) data rejecting is carried out to the original air speed data of each Wind turbines according to amendment search matrix and obtains the wind speed time series data after each Wind turbines cleaning.Compared with prior art, the inventive method is simple and reliable, improves the availability of Wind turbines air speed data, it is ensured that the accuracy of correlation analysis result.
Description
Technical field
The present invention relates to a kind of air speed data cleaning method, it is used for Wind turbines wind speed correlation point more particularly, to one kind
The air speed data cleaning method of analysis.
Background technology
With the fast development of wind-power electricity generation, the research of wind-power electricity generation is perfect for development of clean energy and power grid architecture
Significant, the information excavating of wherein wind power plant operation data is increasingly becoming the focus studied in the industry.Wind power plant was run
The wind-powered electricity generation data volume produced in journey exponentially increases, and contains in huge database between each Wind turbines in connection
System.Wind turbines field operational data includes time, wind speed, wind angle, wind power, propeller pitch angle, frequency, generator voltage etc.
Unit major parameter.
In wind power plant actual moving process, due to wind energy stochastic volatility, sensor fault, Wind turbines shut down,
Situations such as wind power plant exception and human factor, inherently there are a series of dirty datas in running of wind generating set data or data lack
Situations such as mistake, it is impossible to the input-output characteristic reflected authentic and validly between running of wind generating set state and each unit.Entering line number
Before excavation and analysis, it is necessary to pre-process original coarse wind-powered electricity generation data, that is, need to carry out clearly wind-powered electricity generation data
Wash.
The content of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind is used for Wind turbines
The air speed data cleaning method of wind speed correlation analysis.
The purpose of the present invention can be achieved through the following technical solutions：
A kind of air speed data cleaning method for Wind turbines wind speed correlation analysis, for multiple Wind turbines wind speed
The cleaning of each Wind turbines air speed data during correlation analysis, this method comprises the following steps：
(1) each original wind speed time series data of Wind turbines and corresponding generating power output time series data are obtained；
(2) retrieval mark is carried out according to the retrieval mark rule of setting to generating power output time series data and obtains each wind-powered electricity generation
The search matrix of unit；
(3) comprehensive modification is carried out to each Wind turbines search matrix to obtain correcting search matrix；
(4) data rejecting is carried out to the original air speed data of each Wind turbines according to amendment search matrix and obtains each Wind turbines
Wind speed time series data after cleaning.
The retrieval mark rule set in step (2) as：
When generating power output is more than 0, corresponding retrieval tag value is 1, when generated output is less than or equal to 0, correspondence
Retrieval tag value be 0.
Step (2) is specially：
The power output time series data P=[p of the i-th typhoon group of motors are extracted successively1i p2i ... pji ... pmi]TIn
J-th of element pji, corresponding retrieval tag value b is determined according to the retrieval mark of setting ruleji, and then obtain the i-th typhoon motor
The search matrix B of groupi=[b1i b2i ... bji ... bmi]T, wherein pjiRepresent the i-th typhoon group of motors jth sampling instant
Power output, bjiRepresent the retrieval tag value of the i-th typhoon group of motors jth sampling instant, i=1,2 ... n, j=1,2 ... m, n
Total number of units of the Wind turbines of pending wind speed correlation analysis is represented, m is sampling instant total number.
Step (3) is specially：
For the search matrix B of all Wind turbinesi, i=1,2 ... n obtain correcting search matrix using following computing
B：
Wherein, П represents quadrature computing, bjRepresent the retrieval mark correction value of jth sampling instant, j=1,2 ... m.
Step (4) is specially：
(41) sampling instant that retrieval mark correction value is 0 in amendment search matrix B is obtained；
(42) respectively by the wind of the sampling instant corresponded in the original wind speed time series data of each Wind turbines in step (41)
Fast data are rejected；
(43) sampling instant augment direction is defined as sampling instant axle negative direction, for each Wind turbines by step
(42) the remaining air speed data after air speed data rejecting is carried out to obtain after cleaning along the translation of sampling instant axle negative direction and polishing
Wind speed time series data.
Compared with prior art, the invention has the advantages that：
(1) present invention is determined each by the use of generating power output as the abnormal foundation of mark by the way of being marked using 0 and 1
The search matrix of Wind turbines, at the same in order to multiple Wind turbines wind speed correlation analysis, search matrix is modified into
Row obtains integrating the amendment search matrix of all Wind turbines, and the cleaning of air speed data is carried out using the amendment search matrix, is kept away
Exempt to carry out data analysis under the premise of non-justice, rejected error and abnormal air speed data, selection unit is continuously normally run
Data are used as research sample, it is ensured that the correctness and validity of follow-up Wind turbines wind speed correlation analysis result；
(2) the inventive method is simple and easy to apply, is easy to implement.
Brief description of the drawings
FB(flow block)s of the Fig. 1 for the present invention for the air speed data cleaning method of Wind turbines wind speed correlation analysis；
Fig. 2 is the original wind speed time series data distribution map of 2 typhoon group of motors in the present embodiment；
Fig. 3 is the wind speed time series data distribution map after 2 typhoon group of motors cleaning in the present embodiment.
Embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.
Embodiment
As shown in figure 1, a kind of air speed data cleaning method for Wind turbines wind speed correlation analysis, for multiple wind
The cleaning of each Wind turbines air speed data during group of motors wind speed correlation analysis, this method comprises the following steps：
(1) each original wind speed time series data of Wind turbines and corresponding generating power output time series data are obtained；
(2) retrieval mark is carried out according to the retrieval mark rule of setting to generating power output time series data and obtains each wind-powered electricity generation
The search matrix of unit；
(3) comprehensive modification is carried out to each Wind turbines search matrix to obtain correcting search matrix；
(4) data rejecting is carried out to the original air speed data of each Wind turbines according to amendment search matrix and obtains each Wind turbines
Wind speed time series data after cleaning.
Understood according to Wind turbines operation principle and wind power plant O＆M code, when the input wind speed of Wind turbines it is smaller (or
It is larger) when, Wind turbines are not up to incision wind speed (or reaching cut-out wind speed), and Wind turbines generating power output is zero；Wind-powered electricity generation
When unit breaks down or shut down according to repair schedule, power output is also zero；And when Wind turbines are in power generation operation shape
During state, its electromotive power output is more than zero.Researcher thinks the wind speed correlation statistics point of the Wind turbines under normal power generation state
Analyse has actual construction value to electricity net safety stable for wind power plant cluster control, reduction grid connected wind power power.Therefore, walk
Suddenly the retrieval mark rule set in (2) as：
When generating power output is more than 0, corresponding retrieval tag value is 1, when generated output is less than or equal to 0, correspondence
Retrieval tag value be 0.
Step (2) is specially：
The power output time series data P=[p of the i-th typhoon group of motors are extracted successively1i p2i ... pji ... pmi]TIn
J-th of element pji, corresponding retrieval tag value b is determined according to the retrieval mark of setting ruleji, and then obtain the i-th typhoon motor
The search matrix B of groupi=[b1i b2i ... bji ... bmi]T, wherein pjiRepresent the i-th typhoon group of motors jth sampling instant
Power output, bjiRepresent the retrieval tag value of the i-th typhoon group of motors jth sampling instant, i=1,2 ... n, j=1,2 ... m, n
Total number of units of the Wind turbines of pending wind speed correlation analysis is represented, m is sampling instant total number.
Step (3) is specially：
For the search matrix B of all Wind turbinesi, i=1,2 ... n obtain correcting search matrix using following computing
B：
Wherein, П represents quadrature computing, bjRepresent the retrieval mark correction value of jth sampling instant, j=1,2 ... m.
Step (4) is specially：
(41) sampling instant that retrieval mark correction value is 0 in amendment search matrix B is obtained；
(42) respectively by the wind of the sampling instant corresponded in the original wind speed time series data of each Wind turbines in step (41)
Fast data are rejected；
(43) sampling instant augment direction is defined as sampling instant axle negative direction, for each Wind turbines by step
(42) the remaining air speed data after air speed data rejecting is carried out to obtain after cleaning along the translation of sampling instant axle negative direction and polishing
Wind speed time series data.
Above-mentioned steps (42) realize the cleaning of data, and step (43) realizes pair of data on a timeline after cleaning
It is neat fixed, can simply it be interpreted as above-mentioned steps (43)：Such as original wind speed time series data includes the wind of 10 sampled points
Fast data, amendment search matrix B=[1,1,1,0,0,1,0,1,1,1]T, then step (42) by the 4th, 5 and 7 three sampling instants
Air speed data reject after, the air speed data of the sampling instant of the original 6th, 8,9 and 10 is translated forward along time shaft and made successively
For the air speed data of the 4th~7 sampling instant, so as to realize described polishing.
The actual operating data of the present embodiment using Zhangbei County's wind power base wind power plant T32 and T33 Wind turbines is entered as sample
Row analysis.Construction data shows that T32 and the typhoon group of motors of T33 two are SE8215-L3/1500kW type Wind turbines, cuts/cuts
It is respectively 3m/s, 25m/s to go out wind speed；Geographically T32 and T33 is located at same latitude, and T32 units are located at T33 units upstream, two machines
Air line distance is 700m between group.
Fig. 2 is the original wind speed before the 1000 data sample points cleaning of T32 and T33 Wind turbines in June, 2013 operation
Time series data distribution map, Fig. 3 is the time series data distribution map after being cleaned to data in Fig. 2.Primary data analysis result is sent out
Now, the wind speed coefficient correlation after cleaning is adjusted is produced better than the preceding wind speed coefficient correlation of cleaning main reason is that low wind speed area wind
Group of motors does not put into operation, and wind speed record accuracy is not so good as high speed.
Comparison diagram 2 and Fig. 3 are understood, after being cleaned using the data cleaning method of the present invention, and wind speed is less than 3m/s sample
This point is cleaned to be eliminated, and the sampled point for being zeroed out in coarse wind speed time series, and passage time alignment is avoided
The interference from human factor that data correlation statistics are analyzed.The wind series cleaning method and flow that of the invention can be built are effective
Property, objective, accurate basic data can be provided for statistical analysis.
Claims (5)
1. a kind of air speed data cleaning method for Wind turbines wind speed correlation analysis, for multiple Wind turbines wind speed phases
The cleaning of each Wind turbines air speed data during the analysis of closing property, it is characterised in that this method comprises the following steps：
(1) each original wind speed time series data of Wind turbines and corresponding generating power output time series data are obtained；
(2) retrieval mark is carried out according to the retrieval mark rule of setting to generating power output time series data and obtains each Wind turbines
Search matrix；
(3) comprehensive modification is carried out to each Wind turbines search matrix to obtain correcting search matrix；
(4) data rejecting is carried out to the original air speed data of each Wind turbines according to amendment search matrix and obtains each Wind turbines cleaning
Wind speed time series data afterwards.
2. a kind of air speed data cleaning method for Wind turbines wind speed correlation analysis according to claim 1, its
Be characterised by, the retrieval mark rule set in step (2) as：
When generating power output is more than 0, corresponding retrieval tag value is 1, when generated output is less than or equal to 0, corresponding inspection
Rope mark value is 0.
3. a kind of air speed data cleaning method for Wind turbines wind speed correlation analysis according to claim 2, its
It is characterised by, step (2) is specially：
The power output time series data P=[p of the i-th typhoon group of motors are extracted successively1i p2i ... pji ... pmi]TIn jth
Individual element pji, corresponding retrieval tag value b is determined according to the retrieval mark of setting ruleji, and then obtain the i-th typhoon group of motors
Search matrix Bi=[b1i b2i ... bji ... bmi]T, wherein pjiRepresent the defeated of the i-th typhoon group of motors jth sampling instant
Go out power, bjiRepresent the retrieval tag value of the i-th typhoon group of motors jth sampling instant, i=1,2 ... n, j=1,2 ... m, n tables
Show total number of units of the Wind turbines of pending wind speed correlation analysis, m is sampling instant total number.
4. a kind of air speed data cleaning method for Wind turbines wind speed correlation analysis according to claim 3, its
It is characterised by, step (3) is specially：
For the search matrix B of all Wind turbinesi, i=1,2 ... n obtain amendment search matrix B using following computing：
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<mi>B</mi>
<mo>=</mo>
<msup>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msub>
<mi>b</mi>
<mn>1</mn>
</msub>
</mtd>
<mtd>
<msub>
<mi>b</mi>
<mn>2</mn>
</msub>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<msub>
<mi>b</mi>
<mi>m</mi>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
<mi>T</mi>
</msup>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<msup>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mrow>
<munderover>
<mo>&Pi;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>b</mi>
<mrow>
<mn>1</mn>
<mi>i</mi>
</mrow>
</msub>
</mrow>
</mtd>
<mtd>
<mrow>
<munderover>
<mo>&Pi;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>b</mi>
<mrow>
<mn>2</mn>
<mi>i</mi>
</mrow>
</msub>
</mrow>
</mtd>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mrow>
<munderover>
<mo>&Pi;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>b</mi>
<mrow>
<mi>m</mi>
<mi>i</mi>
</mrow>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mi>T</mi>
</msup>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>,</mo>
</mrow>
Wherein, П represents quadrature computing, bjRepresent the retrieval mark correction value of jth sampling instant, j=1,2 ... m.
5. a kind of air speed data cleaning method for Wind turbines wind speed correlation analysis according to claim 4, its
It is characterised by, step (4) is specially：
(41) sampling instant that retrieval mark correction value is 0 in amendment search matrix B is obtained；
(42) respectively by the wind speed number of the sampling instant corresponded in the original wind speed time series data of each Wind turbines in step (41)
According to rejecting；
(43) sampling instant augment direction is defined as sampling instant axle negative direction, entered step (42) for each Wind turbines
Row air speed data reject after remaining air speed data along sampling instant axle negative direction translate and polishing cleaned after wind speed
Time series data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710516600.7A CN107291927B (en) | 2017-06-29 | 2017-06-29 | A kind of air speed data cleaning method for Wind turbines wind speed correlation analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710516600.7A CN107291927B (en) | 2017-06-29 | 2017-06-29 | A kind of air speed data cleaning method for Wind turbines wind speed correlation analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107291927A true CN107291927A (en) | 2017-10-24 |
| CN107291927B CN107291927B (en) | 2019-11-05 |
Family
ID=60098673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710516600.7A Active CN107291927B (en) | 2017-06-29 | 2017-06-29 | A kind of air speed data cleaning method for Wind turbines wind speed correlation analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107291927B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108549689A (en) * | 2018-04-12 | 2018-09-18 | 华北电力大学 | A kind of running of wind generating set data cleaning method |
| CN109991888A (en) * | 2017-12-29 | 2019-07-09 | 北京金风科创风电设备有限公司 | Fan data processing method and system, fan controller and fan farm group controller |
| WO2021027011A1 (en) * | 2019-08-14 | 2021-02-18 | 北京天泽智云科技有限公司 | Method and apparatus for improving data quality of wind power system |
| CN113777351A (en) * | 2021-08-26 | 2021-12-10 | 同济大学 | Fault diagnosis method and device for wind speed sensor of wind power plant |
| CN115062879A (en) * | 2022-08-19 | 2022-09-16 | 昆仑智汇数据科技(北京)有限公司 | Method, device and equipment for acquiring index parameters of wind turbine generator |
| CN115063252A (en) * | 2022-06-08 | 2022-09-16 | 山东省农业科学院 | Crop fertilizer accurate application method and system based on neural network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4819343B2 (en) * | 2004-11-09 | 2011-11-24 | Ｎｅｃエンジニアリング株式会社 | Wind profiler system |
| CN105224733A (en) * | 2015-09-19 | 2016-01-06 | 东北电力大学 | Wind power is abandoned wind data feature and is known method for distinguishing |
| CN105868165A (en) * | 2016-04-15 | 2016-08-17 | 华中科技大学 | Method for cleaning operation data of power station boiler |
-
2017
- 2017-06-29 CN CN201710516600.7A patent/CN107291927B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4819343B2 (en) * | 2004-11-09 | 2011-11-24 | Ｎｅｃエンジニアリング株式会社 | Wind profiler system |
| CN105224733A (en) * | 2015-09-19 | 2016-01-06 | 东北电力大学 | Wind power is abandoned wind data feature and is known method for distinguishing |
| CN105868165A (en) * | 2016-04-15 | 2016-08-17 | 华中科技大学 | Method for cleaning operation data of power station boiler |
Non-Patent Citations (1)
| Title |
|---|
| 娄建楼等: "基于功率曲线的风电机组数据清洗算法", 《电力系统自动化》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109991888A (en) * | 2017-12-29 | 2019-07-09 | 北京金风科创风电设备有限公司 | Fan data processing method and system, fan controller and fan farm group controller |
| CN108549689A (en) * | 2018-04-12 | 2018-09-18 | 华北电力大学 | A kind of running of wind generating set data cleaning method |
| CN108549689B (en) * | 2018-04-12 | 2021-04-02 | 华北电力大学 | Method for cleaning operation data of wind turbine generator |
| WO2021027011A1 (en) * | 2019-08-14 | 2021-02-18 | 北京天泽智云科技有限公司 | Method and apparatus for improving data quality of wind power system |
| CN113777351A (en) * | 2021-08-26 | 2021-12-10 | 同济大学 | Fault diagnosis method and device for wind speed sensor of wind power plant |
| CN115063252A (en) * | 2022-06-08 | 2022-09-16 | 山东省农业科学院 | Crop fertilizer accurate application method and system based on neural network |
| CN115062879A (en) * | 2022-08-19 | 2022-09-16 | 昆仑智汇数据科技(北京)有限公司 | Method, device and equipment for acquiring index parameters of wind turbine generator |
| CN115062879B (en) * | 2022-08-19 | 2022-10-28 | 昆仑智汇数据科技(北京)有限公司 | Method, device and equipment for acquiring index parameters of wind turbine generator |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107291927B (en) | 2019-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107291927B (en) | A kind of air speed data cleaning method for Wind turbines wind speed correlation analysis | |
| Qu et al. | Prediction of electricity generation from a combined cycle power plant based on a stacking ensemble and its hyperparameter optimization with a grid-search method | |
| Zhang et al. | Weather prediction with multiclass support vector machines in the fault detection of photovoltaic system | |
| Zeng et al. | Short-term wind power prediction using a wavelet support vector machine | |
| CN101750210B (en) | Fault diagnosis method based on OLPP feature reduction | |
| CN103631681B (en) | A kind of method of online reparation abnormal data of wind power plant | |
| CN111426950B (en) | Wind driven generator fault diagnosis method of multi-scale space-time convolution depth belief network | |
| CN106762452B (en) | Fan master control system fault diagnosis and on-line monitoring method based on data-driven | |
| CN104978608A (en) | Wind power prediction apparatus and prediction method | |
| CN107392304A (en) | A kind of Wind turbines disorder data recognition method and device | |
| CN103401236A (en) | Wind power farm generator unit grouping method based on flow correlation of wind power farm | |
| CN107609697A (en) | A kind of Wind power forecasting method | |
| CN105512766A (en) | Wind power plant power predication method | |
| CN108985490A (en) | Wind-driven generator power curve modification method based on the fitting of sliding window characteristic | |
| CN104333048A (en) | Thermal power generating unit dispatching method and system | |
| CN110991701A (en) | Wind power plant fan wind speed prediction method and system based on data fusion | |
| CN104574221B9 (en) | A kind of photovoltaic plant running status discrimination method based on loss electricity characteristic parameter | |
| Wang et al. | A compressed sensing and CNN‐based method for fault diagnosis of photovoltaic inverters in edge computing scenarios | |
| CN114399081A (en) | Photovoltaic power generation power prediction method based on weather classification | |
| Roy | Optimal planning of wind energy conversion systems over an energy scenario | |
| CN103364723A (en) | Running state analysis method for aerogenerator based on voltage and current balance | |
| Malakouti | Prediction of wind speed and power with LightGBM and grid search: case study based on Scada system in Turkey | |
| Yang et al. | Fast simulation modeling and multiple-PS fault diagnosis of the PV array based on I–V curve conversion | |
| CN117559560A (en) | Multi-type power supply adjusting method based on phyllus network decision | |
| CN116660678A (en) | Evaluation system for power transmission network fault distance measurement and fault |
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 |