CN112231976B - Method for establishing wind farm equivalent model - Google Patents
Method for establishing wind farm equivalent model Download PDFInfo
- Publication number
- CN112231976B CN112231976B CN202011099920.5A CN202011099920A CN112231976B CN 112231976 B CN112231976 B CN 112231976B CN 202011099920 A CN202011099920 A CN 202011099920A CN 112231976 B CN112231976 B CN 112231976B
- Authority
- CN
- China
- Prior art keywords
- fan
- wind
- area
- areas
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/06—Wind turbines or wind farms
Abstract
The invention discloses a method for establishing an equivalent model of a wind farm, which comprises the following steps: A. setting a partition distance threshold value of adjacent fans, and setting an area percentage threshold value of a single fan area accounting for the total area of the wind power plant; B. dividing the whole wind farm into a plurality of wind turbine sub-areas; C. dividing different fan areas by taking each fan as a center for each fan group partition, wherein each fan area is provided with only one fan, and the areas which do not belong to the fan areas are divided into an integral non-fan area; D. establishing a neural network prediction model of wind speed, wind direction and fan power in a fan area; E. establishing a first bidirectional association function set between a non-fan area and different fan areas; F. a second set of bi-directional correlation functions for non-fan regions in adjacent fan group partitions is established. The method can improve the defects of the prior art, simplify the equivalent model of the wind power plant and improve the timeliness of grid-connected power prediction of the wind power plant.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to a method for establishing an equivalent model of a wind power plant.
Background
Wind energy is a green renewable resource, and wind power generation is a major form of utilizing this green energy. Because a large wind farm needs to be integrated with a power grid for power transmission, in order to keep the load balance of the power grid, the grid-connected power of the wind farm needs to be predicted, and the premise of predicting the grid-connected power of the wind farm is to establish an equivalent model of the wind farm. In the prior art, the equivalent model of the wind power plant has the defects of more parameters, high complexity and large operand in the prediction process, and the grid-connected power generation power of the wind power plant cannot be predicted in time.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method for establishing a wind power plant equivalent model, which can solve the defects of the prior art, simplify the wind power plant equivalent model and improve the timeliness of wind power plant grid-connected power prediction.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows.
The method for establishing the wind farm equivalent model comprises the following steps:
A. setting a partition distance threshold value of adjacent fans, and setting an area percentage threshold value of a single fan area accounting for the total area of the wind power plant;
B. dividing the whole wind power plant into a plurality of wind power plant partitions, wherein the distance between all fans in the same wind power plant partition and the nearest fan is smaller than a partition distance threshold value, and the area ratio of all the wind power plant partitions to the wind power plant is smaller than an area percentage threshold value;
C. dividing different fan areas by taking each fan as a center for each fan group partition, wherein each fan area is provided with only one fan, and the areas which do not belong to the fan areas are divided into an integral non-fan area;
D. establishing a neural network prediction model of wind speed, wind direction and fan power in a fan area;
E. establishing a first bidirectional association function set between a non-fan area and different fan areas;
F. a second set of bi-directional correlation functions for non-fan regions in adjacent fan group partitions is established.
In the step D, the axial direction of the rotating shaft of the fan blade is taken as a central line, the fan area is divided into equal number of subareas at two sides of the central line, the wind speed and wind direction data of each subarea are used as a group of input data of the neural network prediction model, and the wind speed and wind direction data of different subareas are input into the neural network prediction model for training according to the sequence from far to near of the fan until the fan power result output by the neural network prediction model is stable.
Preferably, a transformation function of wind speed and wind direction between all subareas and adjacent subareas is established, when a neural network prediction model is used for predicting fan power, the subarea with the most stable wind field state is selected as a reference area, wind speed and wind direction data of other subareas are combined into the reference area by using the transformation function, and then the data of the reference area are directly input into the neural network prediction model for prediction operation.
Preferably, in step E, according to the fan distribution state, a three-dimensional trend graph of airflow disturbance caused by the existence of fans is built in a non-fan area, then airflow disturbance is decomposed into disturbance components corresponding to all sub-areas one by one, a first bi-directional correlation function is built according to each disturbance component, and then all the first bi-directional correlation functions form a first bi-directional correlation function set.
In the step F, preferably, an airflow transmission three-dimensional state diagram of the non-fan area in the adjacent fan group partition is established according to airflow disturbance three-dimensional trend diagrams of different non-fan areas, and then the airflow transmission three-dimensional state diagram is converted into a plurality of binary probability density functions of wind speed and wind direction, and all the binary probability density functions form a second bidirectional association function set.
The beneficial effects brought by adopting the technical scheme are as follows: according to the method, the wind power plant is partitioned, and then the fan power of each partition is predicted by adopting a neural network model. In order to simplify the operation amount of the prediction process of the neural network model, the fan area is reasonably partitioned according to the installation direction of the fan, and wind speed and wind direction data of different subareas are combined by utilizing a transformation function and used as input data of the neural network model, so that the repeated operation of the prediction process can be effectively reduced. In order to obtain a grid-connected power generation power predicted value of the whole wind power plant, the method establishes airflow flowing relations of fan areas in different fan group areas by using a non-fan area, and further obtains real-time output total power of all fans of the whole wind power plant.
Drawings
FIG. 1 is a flow chart of one embodiment of the present invention.
Detailed Description
Referring to fig. 1, one embodiment of the present invention includes the steps of:
A. setting a partition distance threshold value of adjacent fans, and setting an area percentage threshold value of a single fan area accounting for the total area of the wind power plant;
B. dividing the whole wind power plant into a plurality of wind power plant partitions, wherein the distance between all fans in the same wind power plant partition and the nearest fan is smaller than a partition distance threshold value, and the area ratio of all the wind power plant partitions to the wind power plant is smaller than an area percentage threshold value;
C. dividing different fan areas by taking each fan as a center for each fan group partition, wherein each fan area is provided with only one fan, and the areas which do not belong to the fan areas are divided into an integral non-fan area;
D. establishing a neural network prediction model of wind speed, wind direction and fan power in a fan area;
E. establishing a first bidirectional association function set between a non-fan area and different fan areas;
F. a second set of bi-directional correlation functions for non-fan regions in adjacent fan group partitions is established.
In the step D, the axial direction of the rotating shaft of the fan blade is taken as a central line, the fan area is divided into equal number of subareas at two sides of the central line, the wind speed and wind direction data of each subarea are taken as a group of input data of the neural network prediction model, and the wind speed and wind direction data of different subareas are input into the neural network prediction model for training according to the sequence from far to near of the fan until the fan power result output by the neural network prediction model is stable.
And establishing transformation functions of wind speeds and wind directions between all subareas and adjacent subareas, selecting the subarea with the most stable wind field state as a reference area when a neural network prediction model is used for predicting the power of the fan, merging the wind speed and wind direction data of other subareas into the reference area by using the transformation functions, and then directly inputting the data of the reference area into the neural network prediction model for prediction operation.
In the step E, according to the distribution state of the fans, a three-dimensional trend graph of air flow disturbance caused by the existence of the fans is built in a non-fan area, then the air flow disturbance is decomposed into disturbance components corresponding to all the subareas one by one, a first two-way correlation function is built according to each disturbance component, and then all the first two-way correlation functions form a first two-way correlation function set.
And F, establishing an airflow transmission three-dimensional state diagram of the non-fan area in the adjacent fan group partition according to the airflow disturbance three-dimensional trend diagrams of different non-fan areas, and converting the airflow transmission three-dimensional state diagram into a plurality of binary probability density functions of wind speed and wind direction, wherein all the binary probability density functions form a second bidirectional association function set.
After the equivalent model is built, only a small amount of wind speed and wind direction sensors are installed in the peripheral area of the wind power plant (without being installed in the wind power plant), the output power of the wind at the edge of the wind power plant is predicted according to wind speed and wind direction data of the periphery of the wind power plant, wind power plant parameters around the wind power plant adjacent to the predicted area are fitted according to functions corresponding to the first bidirectional correlation function set and the second bidirectional correlation function set, the output power of the wind power plant is predicted, and the like, so that grid-connected power of the whole wind power plant can be obtained.
In the description of the present invention, it should be understood that the terms "longitudinal," "transverse," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate or are based on the orientation or positional relationship shown in the drawings, merely to facilitate description of the present invention, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present invention.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (1)
1. The method for establishing the wind farm equivalent model is characterized by comprising the following steps of:
A. setting a partition distance threshold value of adjacent fans, and setting an area percentage threshold value of a single fan area accounting for the total area of the wind power plant;
B. dividing the whole wind power plant into a plurality of wind power plant partitions, wherein the distance between all fans in the same wind power plant partition and the nearest fan is smaller than a partition distance threshold value, and the area ratio of all the wind power plant partitions to the wind power plant is smaller than an area percentage threshold value;
C. dividing different fan areas by taking each fan as a center for each fan group partition, wherein each fan area is provided with only one fan, and the areas which do not belong to the fan areas are divided into an integral non-fan area;
D. establishing a neural network prediction model of wind speed, wind direction and fan power in a fan area; taking the axial direction of a rotating shaft of a fan blade as a central line, dividing the fan area into equal number of subareas at two sides of the central line, taking the wind speed and wind direction data of each subarea as a group of input data of a neural network prediction model, and inputting the wind speed and wind direction data of different subareas into the neural network prediction model for training according to the sequence from far to near of the fan until the fan power result output by the neural network prediction model is stable; establishing transformation functions of wind speeds and wind directions between all subareas and adjacent subareas, selecting the subarea with the most stable wind field state as a reference area when a neural network prediction model is used for predicting the power of a fan, merging the wind speed and wind direction data of other subareas into the reference area by using the transformation functions, and then directly inputting the data of the reference area into the neural network prediction model for prediction operation;
E. establishing a first bidirectional association function set between a non-fan area and different fan areas; according to the distribution state of the fans, a three-dimensional trend graph of air flow disturbance caused by the existence of the fans is built in a non-fan area, then the air flow disturbance is decomposed into disturbance components corresponding to all the subareas one by one, a first two-way correlation function is built according to each disturbance component, and then all the first two-way correlation functions form a first two-way correlation function set;
F. establishing a second set of bi-directional correlation functions for non-fan areas in adjacent fan group partitions; according to the airflow disturbance three-dimensional trend graphs of different non-fan areas, an airflow transmission three-dimensional state graph of the non-fan areas in adjacent fan group areas is established, then the airflow transmission three-dimensional state graph is converted into a plurality of binary probability density functions of wind speed and wind direction, and all the binary probability density functions form a second bidirectional association function set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011099920.5A CN112231976B (en) | 2020-10-15 | 2020-10-15 | Method for establishing wind farm equivalent model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011099920.5A CN112231976B (en) | 2020-10-15 | 2020-10-15 | Method for establishing wind farm equivalent model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112231976A CN112231976A (en) | 2021-01-15 |
| CN112231976B true CN112231976B (en) | 2023-06-13 |
Family
ID=74113599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011099920.5A Active CN112231976B (en) | 2020-10-15 | 2020-10-15 | Method for establishing wind farm equivalent model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112231976B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239646B (en) * | 2021-05-25 | 2023-08-22 | 华能新能源股份有限公司 | Wind farm modeling method, medium and device based on equivalent roughness |
| CN116819025B (en) * | 2023-07-03 | 2024-01-23 | 中国水利水电科学研究院 | Water quality monitoring system and method based on Internet of things |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268366A (en) * | 2013-03-06 | 2013-08-28 | 辽宁省电力有限公司电力科学研究院 | Combined wind power prediction method suitable for distributed wind power plant |
| CN106849066A (en) * | 2017-03-07 | 2017-06-13 | 云南电网有限责任公司电力科学研究院 | A kind of regional wind power prediction method |
| CN108616139A (en) * | 2016-12-12 | 2018-10-02 | 中国电力科学研究院 | A kind of wind power cluster prediction technique and device |
| CN111525552A (en) * | 2020-04-22 | 2020-08-11 | 大连理工大学 | Three-stage short-term wind power plant group power prediction method based on characteristic information |
-
2020
- 2020-10-15 CN CN202011099920.5A patent/CN112231976B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268366A (en) * | 2013-03-06 | 2013-08-28 | 辽宁省电力有限公司电力科学研究院 | Combined wind power prediction method suitable for distributed wind power plant |
| CN108616139A (en) * | 2016-12-12 | 2018-10-02 | 中国电力科学研究院 | A kind of wind power cluster prediction technique and device |
| CN106849066A (en) * | 2017-03-07 | 2017-06-13 | 云南电网有限责任公司电力科学研究院 | A kind of regional wind power prediction method |
| CN111525552A (en) * | 2020-04-22 | 2020-08-11 | 大连理工大学 | Three-stage short-term wind power plant group power prediction method based on characteristic information |
Non-Patent Citations (3)
| Title |
|---|
| Research on Frequency Fuzzy Adaptive Additional Inertial Control Strategy for D-PMSGWind Turbine;Mudan Li 等;《Sustainability》;第11卷(第15期);1-19 * |
| 基于ASW-FCM算法的风电场动态等效建模与仿真;李牡丹 等;《系统仿真学报》;第32卷(第8期);1606-1616 * |
| 基于特征影响因子和改进BP算法的直驱风机风电场建模方法;王增平 等;《中国电机工程学报》;第39卷(第9期);2604-2614 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112231976A (en) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112231976B (en) | Method for establishing wind farm equivalent model | |
| CN107039977B (en) | Robust scheduling uncertainty set construction method for power system | |
| CN110535174B (en) | Active power control method considering fatigue load distribution and productivity of wind power plant | |
| CN108599268B (en) | Day-ahead optimization scheduling method considering wind power plant space-time association constraint | |
| CN103996074A (en) | CFD and improved PSO based microscopic wind-farm site selection method of complex terrain | |
| CN106786763B (en) | The collector system network optimized approach of photovoltaic plant is built in a kind of wind power plant increasing | |
| CN104933483A (en) | Wind power forecasting method dividing based on weather process | |
| CN113255210B (en) | Method and system for diagnosing federal fault of wind turbine generator | |
| CN108092284B (en) | Three-phase unbalanced intelligent power distribution network reconstruction method based on linear model | |
| WO2021203738A1 (en) | Method for calculating reliability of power distribution system considering demand-side resource layered and decentralized control | |
| WO2023201552A1 (en) | County-wide photovoltaic prediction method based on cluster division and data enhancement | |
| CN106786669B (en) | A kind of active power of wind power field change rate control method and system | |
| CN114021382A (en) | Wind power plant layout optimization method based on mathematical programming | |
| CN114091265A (en) | Wind power plant layout optimization method and system based on local search strategy | |
| CN106845671A (en) | A kind of multipotency streaming system Multi-objective optimal power flow model and its method for solving | |
| CN103149840A (en) | Semanteme service combination method based on dynamic planning | |
| CN110909994A (en) | Small hydropower station power generation amount prediction method based on big data drive | |
| CN109274117A (en) | A kind of Unit Combination method of robust a few days ago of data-driven | |
| CN107370190B (en) | A kind of combined method solving Unit Commitment model | |
| CN115021246A (en) | Doubly-fed fan grid-connected system stability analysis method based on Gehr circle theorem | |
| CN109816184B (en) | Topology planning method and device for large wind farm | |
| CN108364071A (en) | A kind of adaptive modeling wind power prediction method based on genetic programming algorithm | |
| CN113688581A (en) | Method and device for optimal control of active power output of wind power plant, electronic equipment and medium | |
| CN104408531B (en) | A kind of uniform dynamic programming method of multidimensional multistage complicated decision-making problems | |
| CN102438325B (en) | Resource scheduling method based on cognitive radio terminal reconfiguration 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 |