CN117473442A - Method for fitting power curve based on real-time historical data of wind turbine generator - Google Patents
Method for fitting power curve based on real-time historical data of wind turbine generator Download PDFInfo
- Publication number
- CN117473442A CN117473442A CN202311506239.1A CN202311506239A CN117473442A CN 117473442 A CN117473442 A CN 117473442A CN 202311506239 A CN202311506239 A CN 202311506239A CN 117473442 A CN117473442 A CN 117473442A
- Authority
- CN
- China
- Prior art keywords
- power
- fitting
- data
- real
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012935 Averaging Methods 0.000 claims abstract description 6
- 230000002159 abnormal effect Effects 0.000 claims abstract description 5
- 238000010248 power generation Methods 0.000 claims description 9
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Probability & Statistics with Applications (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)
- General Business, Economics & Management (AREA)
- Wind Motors (AREA)
Abstract
The invention provides a method for fitting a power curve based on real-time historical data of a wind turbine, which comprises the following steps: selecting a reference wind speed point, filling a fitting power curve by using an initial power curve of the wind turbine, and acquiring effective real-time data of the power curve; calculating whether fitting conditions are met according to the effective real-time data, if the fitting conditions are met, filling the real power corresponding to the wind speed section to a power cache data pool of the corresponding wind speed section, and if the fitting conditions are not met, continuing to monitor the effective data of the next time; judging whether the power cache data pool is full, if so, fluidizing the new data cache pool; removing abnormal values of a power buffer data pool by using a local outlier factor method, averaging other non-removed values, and obtaining fitting power of the wind speed section at the moment based on the averaged data; and updating the fitting power curve of the corresponding wind speed section by using the calculated fitting power. The power prediction can be effectively improved, and the operation and power output of the generator set are optimized.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to a method for fitting a power curve based on real-time historical data of a wind turbine generator.
Background
With the increase of the ratio of wind power in new energy, wind power generation plays an important role in the power system of China under the situation of rapid development of new energy. The wind farm power curve describes the output power of the wind generating set at different wind speeds. The wind farm power curve may vary depending on the model, design, and environmental conditions of the wind turbine. Furthermore, the power profile of a wind farm may also fluctuate due to changes in wind speed. The accuracy of the power curve of the wind power plant relates to assessment indexes such as available power and theoretical power of the wind power plant and influences the operation and power output of a generator set, so that obtaining an accurate power curve of the wind power plant is particularly important.
Disclosure of Invention
In view of the above, the invention aims to provide a method for fitting a power curve based on real-time historical data of a wind turbine, by which power prediction is effectively improved, and operation and power output of the wind turbine are optimized.
The invention solves the technical problems by the following technical means: the invention provides a method for fitting a power curve based on real-time historical data of a wind turbine, which comprises the following steps:
selecting a reference wind speed point, filling a fitting power curve by using an initial power curve of the wind turbine, and acquiring effective real-time data of the power curve;
calculating whether fitting conditions are met according to the effective real-time data, if the fitting conditions are met, filling the real power corresponding to the wind speed section to a power cache data pool of the corresponding wind speed section, and if the fitting conditions are not met, continuing to monitor the effective data of the next time;
judging whether the power cache data pool is full, if so, fluidizing the new data cache pool;
removing abnormal values of a power buffer data pool by using a local outlier factor method, averaging other non-removed values, and obtaining fitting power of the wind speed section at the moment based on the averaged data;
and updating the fitting power curve of the corresponding wind speed section by using the calculated fitting power.
Further, the acquiring the power effective real-time data includes acquiring wind speed and real power.
Further, the streaming and new data cache pool further comprises the step of starting calculation after the updated data pool quantity meets the set occupation ratio of the total data pool quantity; if the set duty ratio is not reached, the next effective data is continuously monitored.
Further, the set ratio is 10%.
Further, whether the fitting condition is met or not is calculated according to the effective real-time data, whether the wind speed section unit is in a power limiting power generation state at the moment or not is obtained according to the unit working mode, the pitch angle and the power limiting zone bit information, and if the wind speed section unit is in the power limiting power generation state, the fitting condition is not met.
According to the technical scheme, the beneficial effects of the invention are as follows: the invention provides a method for fitting a power curve based on real-time historical data of a wind turbine, which comprises the following steps: selecting a reference wind speed point, filling a fitting power curve by using an initial power curve of the wind turbine, and acquiring effective real-time data of the power curve; calculating whether fitting conditions are met according to the effective real-time data, if the fitting conditions are met, filling the real power corresponding to the wind speed section to a power cache data pool of the corresponding wind speed section, and if the fitting conditions are not met, continuing to monitor the effective data of the next time; judging whether the power cache data pool is full, if so, fluidizing the new data cache pool; removing abnormal values of a power buffer data pool by using a local outlier factor method, averaging other non-removed values, and obtaining fitting power of the wind speed section at the moment based on the averaged data; and updating the fitting power curve of the corresponding wind speed section by using the calculated fitting power. The power prediction can be effectively improved, and the operation and power output of the generator set are optimized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
FIG. 1 is a flow chart of a method for fitting a power curve based on real-time historical data of a wind turbine.
Description of the embodiments
Embodiments of the technical scheme of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and thus are merely examples, and are not intended to limit the scope of the present invention.
Referring to fig. 1, the invention provides a method for fitting a power curve based on real-time historical data of a wind turbine, which comprises the following steps:
selecting a reference wind speed point, filling a fitting power curve by using an initial power curve of the wind turbine, and acquiring effective real-time data of the power curve; by acquiring data such as wind speed and power.
Calculating whether fitting conditions are met according to the effective real-time data, if the fitting conditions are met, filling the real power corresponding to the wind speed section to a power cache data pool of the corresponding wind speed section, and if the fitting conditions are not met, continuing to monitor the effective data of the next time;
specifically, whether the fitting condition is met is calculated according to the effective real-time data, the calculating mode is that whether the wind speed section unit is in a power limiting power generation state at the moment is obtained according to the information such as the working mode of the unit, the pitch angle, the power limiting zone bit and the like, if the wind speed section unit is in the power limiting power generation state, the fitting condition is not met, and if the wind speed section unit is not in the power limiting power generation state, the fitting condition is met. If the fitting condition is met, filling the actual power corresponding to the wind speed section to a corresponding wind speed section power cache data pool, and if the fitting condition is not met, continuing to monitor the next effective data; by introducing fitting conditions, the main purpose of the introduction is to filter out data which are inconsistent in the power curve and influence the accuracy of the power curve due to the conditions of power grid limiting unit power, unit self limiting power and the like.
Judging whether the power buffer data pool is full, if not, jumping back to the first step, and re-selecting a reference wind speed point;
if the data is full, streaming the new data cache pool; and if the updated data pool amount occupies the total data pool amount and the above duty ratio is not achieved, returning to the step one to perform from the newly selected reference wind speed point.
When the updated data pool amount occupies a certain proportion of the total data pool amount, starting to calculate; specifically, this certain ratio is set to 10%; the selected duty ratio is too small, the data amount of the updated data pool is small, the updated data pool has no great significance on the updated result, the selected duty ratio is slightly large, the calculation is needed to be started after waiting for a long time, the timeliness is low, and the duty ratio of about 10% is selected.
Removing abnormal values of a power buffer data pool by using a local outlier factor method, averaging other non-removed values, and obtaining fitting power of the wind speed section at the moment based on the averaged data;
and updating the fitting power curve of the corresponding wind speed section by using the calculated fitting power.
According to the method, a reference wind speed point is selected according to real-time historical data, effective data of a power curve is obtained, whether fitting conditions are met or not is calculated according to the effective data, corresponding data are stored in a power buffer data pool, fitting power for a wind speed section is obtained according to the power buffer data pool by using a local outlier factor and an averaging method, and finally the fitting power curve is updated by using the fitting power of the wind speed section.
Because the accuracy of the power curve of the wind power plant relates to the available power, theoretical power and other assessment indexes of the wind power plant and influences the operation and power output of the generator set, the method effectively improves the power prediction and optimizes the operation and power output of the generator set.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (5)
1. A method for fitting a power curve based on real-time historical data of a wind turbine is characterized by comprising the following steps: the method comprises the following steps:
selecting a reference wind speed point, filling a fitting power curve by using an initial power curve of the wind turbine, and acquiring effective real-time data of the power curve;
calculating whether fitting conditions are met according to the effective real-time data, if the fitting conditions are met, filling the real power corresponding to the wind speed section to a power cache data pool of the corresponding wind speed section, and if the fitting conditions are not met, continuing to monitor the effective data of the next time;
judging whether the power cache data pool is full, if so, fluidizing the new data cache pool;
removing abnormal values of a power buffer data pool by using a local outlier factor method, averaging other non-removed values, and obtaining fitting power of the wind speed section at the moment based on the averaged data;
and updating the fitting power curve of the corresponding wind speed section by using the calculated fitting power.
2. The method for fitting a power curve based on real-time historical data of a wind turbine according to claim 1, wherein the obtaining power-efficient real-time data comprises obtaining wind speed and real power.
3. The method for fitting a power curve based on real-time historical data of a wind turbine generator set according to claim 1, wherein the step of streaming the data into a new data buffer pool further comprises the step of starting calculation when the updated data pool quantity meets a set ratio of the total data pool quantity; if the set duty ratio is not reached, the next effective data is continuously monitored.
4. A method for fitting a power curve based on real-time historical data of a wind turbine according to claim 3, wherein the set duty cycle is 10%.
5. The method for fitting a power curve based on real-time historical data of a wind turbine generator set according to claim 3 is characterized in that the method for calculating whether fitting conditions are met according to effective real-time data further comprises obtaining whether the wind speed section turbine generator set is in a power limiting power generation state at the moment according to a turbine generator set working mode, a pitch angle and power limiting zone bit information, and if the wind speed section turbine generator set is in the power limiting power generation state, the fitting conditions are not met.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311506239.1A CN117473442A (en) | 2023-11-13 | 2023-11-13 | Method for fitting power curve based on real-time historical data of wind turbine generator |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311506239.1A CN117473442A (en) | 2023-11-13 | 2023-11-13 | Method for fitting power curve based on real-time historical data of wind turbine generator |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117473442A true CN117473442A (en) | 2024-01-30 |
Family
ID=89627323
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311506239.1A Pending CN117473442A (en) | 2023-11-13 | 2023-11-13 | Method for fitting power curve based on real-time historical data of wind turbine generator |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117473442A (en) |
-
2023
- 2023-11-13 CN CN202311506239.1A patent/CN117473442A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101425686B (en) | Electrical power system on-line safety and stability evaluation forecast failure collection adaptive selection method | |
CN109767078B (en) | Multi-type power supply maintenance arrangement method based on mixed integer programming | |
CN110648249B (en) | Annual power balance measuring and calculating method, device and equipment | |
KR102286672B1 (en) | Method and system for power generation predict day-ahead of wind farm based on mixed physics and data model | |
CN108471137B (en) | Wind power prediction wind speed power probabilistic mapping method | |
CN117473442A (en) | Method for fitting power curve based on real-time historical data of wind turbine generator | |
CN104657786A (en) | Short-term wind power mixed predicting method based on Boosting algorithm | |
CN107221933A (en) | A kind of probability load flow calculation method | |
US20180328338A1 (en) | Control method, master controller system, and central controller for wind turbines | |
CN111799798A (en) | Method and system for improving accuracy of future state load flow calculation result | |
CN104239979A (en) | Ultra-short-term forecasting method of wind power plant generated power | |
CN114738212B (en) | Wind turbine generator set maintenance method and device considering multi-attribute meteorological characteristics | |
WO2023103448A1 (en) | Customized design method for wind turbine generator set | |
CN114825467A (en) | Thermal power generating unit annual maintenance plan standby adequacy evaluation method and system | |
CN115898787A (en) | Method and device for dynamically identifying static yaw error of wind turbine generator | |
CN104657787A (en) | Wind power time series combined prediction method | |
CN110808614B (en) | New energy consumption capacity calculation method, system and storage medium | |
CN111160653B (en) | Distributed energy storage system wind power consumption capability monitoring method based on cloud computing | |
CN117411081B (en) | Green energy consumption control method, device, equipment and storage medium | |
CN114564815B (en) | Power system reliability and economy modeling method based on Brazier paradox effect | |
CN115660249A (en) | Comprehensive evaluation method for wind power prediction error | |
Yi et al. | Potential Maximum Power Estimation for Wind Farms Based on LSTM Neural Network | |
CN113919718A (en) | Method and system for calculating power generation flow of reservoir hydropower station unit | |
CN118279083A (en) | Power grid engineering carbon emission reduction potential evaluation method | |
CN117498337A (en) | Operation standby optimal scheduling method considering influence of multidimensional prediction information on prediction error |
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 |