CN115345073A - Grid-coordinated genetic algorithm-based wind power plant position optimization method - Google Patents
Grid-coordinated genetic algorithm-based wind power plant position optimization method Download PDFInfo
- Publication number
- CN115345073A CN115345073A CN202210975919.7A CN202210975919A CN115345073A CN 115345073 A CN115345073 A CN 115345073A CN 202210975919 A CN202210975919 A CN 202210975919A CN 115345073 A CN115345073 A CN 115345073A
- Authority
- CN
- China
- Prior art keywords
- wind
- wind turbine
- genetic algorithm
- power plant
- turbine generator
- 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
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- 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 grid-coordinated genetic algorithm-based wind power plant position optimization method, which specifically comprises the following steps: predicting the wake flow speed of the wind turbine generator by using a Jensen wake flow model, obtaining the total kinetic energy loss in the wake flow of the wind turbine generator by using a square superposition model of the wake flow effect of the wind turbine generator, and minimizing the cost of generated energy according to an optimization objective function; the grid genetic algorithm and the coordinated genetic algorithm are combined, the number and the layout of the wind generation sets of the wind power plant are optimized initially through the grid genetic algorithm, and then the layout initial value of the wind generation sets is further optimized through the coordinated genetic algorithm, so that the total generated energy of the wind power plant is further increased. The method solves the problems of optimization of the number of wind generation sets and high calculation cost in wind power plant layout optimization, and avoids the limitation of a grid genetic algorithm on the position flexibility of the wind generation sets; a feasible method is provided for layout optimization of the wind power plant, and the efficiency of the wind power plant is greatly improved.
Description
Technical Field
The invention belongs to the technical field of wind power plant planning, and particularly relates to a grid-coordinated genetic algorithm-based wind power plant position optimization method.
Background
Wind energy is mainly obtained by the wind turbine generator, but due to the wake effect, the speed of airflow flowing through the wind turbine generator is reduced at the rear of the wind turbine generator, so that the power generation efficiency of the rear wind turbine generator is reduced. Although the wake effect can be reduced by increasing the distance between the wind turbines, the field of the wind power plant in practical application is limited, and the increase of the distance between the wind turbines can reduce the number of the mountable wind turbines and reduce the total generated energy of the wind power plant, thereby influencing the economic benefit of the wind power plant. Therefore, the layout of the wind turbine generator is optimized, the influence of the wake effect on the whole power generation amount of the wind power plant is reduced, and therefore the improvement of the power generation amount of the whole wind power plant becomes an important research subject.
In 1994, mosetti et al [1] first proposed using genetic algorithms to determine the number and location of wind turbines to obtain maximum energy extraction with minimum installed cost. Grady et al [2] use larger population size and iteration number to optimize on this basis, and are further promoted. Mittal [3] finds that grid density plays a critical role in optimizing a wind power plant through further research, and a high-density grid obtains a better optimization result but needs high calculation cost, so that Hassoine and other [4] adopt real number coding to optimize. Chen 5 considers the cost of optimizing the generating efficiency and unit generating capacity of the wind field at the same time on the basis of the researches, and proposes a genetic algorithm adopting multiple targets. To improve the efficiency of the algorithm, liu et al [6] introduce an adaptive genetic algorithm with interchangeable positions. Yang et al [7] discovered that population diversity can be increased by changing the fixed probability in the initial population and variation probability generated by genetic algorithm into dynamic probability, further optimizing the result, and proposed an improved algorithm. In addition to genetic algorithms, researchers have also studied various other optimization algorithms. In recent years, eroglu et al [8] studied the WELOP algorithm based on particle filtering, optimized three different situations by using the particle filtering method, and the results compare favorably with the genetic algorithm. Bilbao et al [9] realized the maximum power generation of the wind power plant by adopting a simulated annealing method. Beatriz et al [10] firstly sets an initial random layout through a heuristic algorithm, and then performs local optimization by using a nonlinear mathematical programming technology to maximize the power generation amount of a wind power plant, thereby obviously improving the power generation amount. There are also modified firefly algorithm, sequential conflex programming algorithm, modified particle swarm algorithm, etc. [11-13]. However, in consideration of accuracy and high efficiency of optimization, the genetic algorithm is still the most frequently used optimization algorithm in the wind power plant layout optimization problem.
The genetic algorithm of the existing research is divided into gridding and coordinatization, when the wind power plant layout is optimized by the gridding genetic algorithm, the wind turbine generator can only be placed in the center of a grid, the flexibility and the precision of the arrangement position of the wind turbine generator are greatly limited, and the calculation cost investment is large along with the increase of grid density. The coordinated genetic algorithm can only determine the number of the wind turbines under the condition that the number of the wind turbines is determined, and one very important research content is to determine the number of the wind turbines.
Reference documents:
[1]MOSETTI G，POLONI C，DIVIACCO B.Optimization of wind turbine positioning in large wind farms by means of a genetic algorithm[J].Journal of wind engineering&industrial aerodynamics，1994，51(1)：105-116.
[2]GRADY S A，HUSSAINI M Y，ABDULLAH M.Placement of wind turbines using genetic algorithms[J].Renew energy，2005，30(1)：259-270.
[3]MITTAL A.Optimization of the layout of large wind farms using a genetic algorithm[C]//International Mechanical Engineering Congress&Exposition,Vol.7.Texas,USA,20 12.
[4]HASSOINE M A，LAHLOU F，ADDAIM A，et al.Wind farm layout optimization using real coded multi-population genetic algorithm[C]//International Conference on Wireless Technologies，Embedded and Intelligent Systems,USMBA Univ,ESNA Fez,ERSI&IPI Lab,Fez,MOROCCO,2019.
[5]CHEN Y，LI H，HE B，et al.Multi-objective genetic algorithm based innovative wind farm layout optimization method[J].Energy conversion&management，2015，105(NOV)：1318-1327.
[6]LIU F，WANG Z F.Offshore wind farm layout optimization using adapted genetic algorithm：a different perspective[J].Electrical and Computer Engineering，2014，103(3)：917-922.
[7]YANG Q S，HU J X，LAW S.Optimization of wind farm layout with modified genetic algorithm based on boolean code[J].Journal of wind engineering and industrial aerodynamics，2018，181：61-68.
[8]EROGLU Y，SECKINER S U.Design of wind farm layout using ant colony algorithm[J].Renewable energy，2012，44：53-62.
[9]BILBAO M，ALBA E.Simulated annealing for optimization of wind farm annual profit[C]//International Symposium on Logistics&Industrial Informatics，IEEE，Linz，Austria，2009.
[10]BEATRIZ P，ROBERTO M，RAUL G.Offshore wind farm layout optimization using mathematical programming techniques[J].Renewable energy，2013，53(MAY)：389-399.
[11] liu Yong, shaoyizhou, yanlingwei and the like, a wind power plant micro site selection optimization research based on an improved binary firefly algorithm [ J ] renewable energy source, 2019, 37 (1): 112-119.
[12] Zwei. Complex terrain wind power plant optimization arrangement method [ J ] based on improved particle swarm optimization algorithm and wind speed distribution regression function method, hydroelectric energy science, 2016, 34 (1): 190-194.
[13]PARK J，LAW K H.Layout optimization for maximizing wind farm power production using sequential convex programming[J].Applied energy，2015，151(aug1)：320-334.
Disclosure of Invention
In order to overcome the problems and further improve the generated energy of the wind power plant, the invention provides a grid-coordinated genetic algorithm-based wind power plant position optimization method.
The invention relates to a grid-coordinated genetic algorithm-based wind power plant machine position optimization method, which comprises the following steps of:
step 1: predicting the wake flow speed of the wind turbine generator by using a Jensen wake flow model, and obtaining the total kinetic energy loss in the wake flow of the wind turbine generator by using a square superposition model of the wake flow effect of the wind turbine generator; the superposition model is divided into 4 working conditions (including full-overlapping, non-overlapping and partially overlapping) according to the influence degree of the wake flow of the wind turbine generator on the downstream wind turbine generator, and the cost of the generated energy is minimized according to an optimization objective function.
Step 2: the gridding genetic algorithm and the coordinated genetic algorithm are combined, and the adopted method comprises the following two steps:
(1) The number of wind turbines and the optimal layout for minimizing the objective function are optimized by a gridding 0-1 coding genetic algorithm.
Under the given parameters of a wind field and a wind turbine generator, considering that no wind turbine generator is placed in a specified range among the wind turbine generators, dividing a region into grids with specified size, wherein the number of the grids obtained in the given region is m, the number of the grids obtained when the wind turbine generators are placed in the grids is 1, and the number of the grids obtained when the wind turbine generators are not placed is 0, so that the arrangement mode of the wind turbine generators is converted into a binary code with the length of m to be represented.
Generating an initial population in a random mode, updating and iterating through crossing and variation, calculating the fitness of population individuals by taking a target function as a fitness function, selecting an optimal individual by combining a roulette method and an individual optimal retention method, and decoding the optimal individual to obtain the initial optimal layout of the wind turbine generator system; the position of the gene 1 in the individual code is the mounting position of the wind turbine generator, and the total number of the gene 1 is the number of the wind turbine generator.
(2) And finally optimizing the coordinated genetic algorithm, and based on the obtained number and layout of the wind generation sets, optimizing the positions of the wind generation sets again by using the genetic algorithm of real number coding, so as to further improve the generated energy.
Setting the optimal number of the wind generation sets obtained in the step (1) of the wind power plant as n sets, representing the positions of the wind generation sets by using vector coordinates, and recording as (x) i ,y i ) And i =1,.. N, analyzing the wind power plant in a plane coordinate axis, setting the wind direction of the incoming flow to be in the negative direction along the y axis, reordering the wind power generation sets according to the ordinate y from large to small, and if the ordinate y is equal, ordering according to the abscissa x from small to large, wherein the ith unit after being newly ordered is only influenced by the wake flow of the previous i-1 units.
The method comprises the steps of further optimizing and converting the layout of the wind turbine generator optimized by a grid genetic algorithm into the optimization of coordinates of the wind turbine generator, directly coding the coordinates by adopting the coordinate genetic algorithm, selecting individuals by taking a target function as an individual fitness calculation method, and obtaining optimal individuals, namely the optimal layout of the wind power plant through population updating iteration, thereby obtaining the optimal power generation capacity and the target function.
Furthermore, no wind turbine generator is arranged in a specified range between the wind turbine generators, the distance is set to be 5D, and D is the diameter of the wind turbine blade; the constraint is also applicable when coordinating genetic algorithms.
The beneficial technical effects of the invention are as follows:
the method solves the problems of optimization of the number of wind generating sets and high calculation cost in wind power plant layout optimization, and avoids the limitation of grid genetic algorithm on the position flexibility of the wind generating sets. More importantly, a feasible method can be provided for layout optimization of the wind power plant, so that the efficiency of the wind power plant is greatly increased.
Drawings
FIG. 1 is a flow chart of optimization of a wind farm location according to the present invention.
FIG. 2 is a Jensen wake model.
FIG. 3 shows 4 wake overlap area conditions.
FIG. 4 is a schematic diagram of wind turbine generator sequencing.
Fig. 5 shows three wind field wind conditions.
FIG. 6 is a wind speed probability distribution for wind condition three.
FIG. 7 is an optimized wind farm layout for wind condition one (a is gridded and b is coordinated).
Fig. 8 is a schematic diagram of coordinate transformation of the second wind condition.
Fig. 9 shows an optimized wind field layout for wind condition two (a is gridded and b is coordinated).
Fig. 10 shows an optimized wind field layout for wind condition three (a is gridded and b is coordinated).
Fig. 11 is a power curve adopted by the wind turbine generator under the third wind condition.
FIG. 12 is a wind speed probability distribution for wind condition three after improvement.
Fig. 13 shows the optimized wind field layout for wind condition three after improvement (a is gridded and b is coordinated).
Detailed Description
The invention is described in further detail below with reference to the figures and specific embodiments.
The method comprises the steps of firstly, optimizing the number and the layout of the wind generation sets of the wind power plant through a gridding genetic algorithm, and then further optimizing the layout initial value of the wind generation sets through a coordinate genetic algorithm, so that the total generated energy of the wind power plant is further increased.
The grid-coordinated genetic algorithm-based wind power plant position optimization method is shown in figure 1, and specifically comprises the following steps:
step 1: predicting the wind turbine generator wake flow speed by using a Jensen wake flow model (as shown in figure 2), and obtaining the total kinetic energy loss in the wind turbine generator wake flow by using a square superposition model of the wake flow effect of the wind turbine generator; the superposition model is divided into 4 working conditions (including full-overlapping, non-overlapping and partially overlapping) according to the influence degree of the wake flow of the wind turbine generator on the downstream wind turbine generator, and the cost of the generated energy is minimized according to an optimization objective function.
And 2, step: the gridding genetic algorithm and the coordinated genetic algorithm are combined, and the adopted method comprises the following two steps:
(1) The number of wind turbines and the optimal layout for minimizing the objective function are optimized by a gridding 0-1 coding genetic algorithm.
Under the given wind field and wind turbine generator parameters, considering that no wind turbine generator is arranged in the designated range among the wind turbine generators (the number of the grids is set to be 5D), dividing the region into grids with designated sizes, wherein the number of the grids arranged in the designated region is m, the number of the grids arranged in the grid is 1 if the wind turbine generators are arranged in the grids, and the number of the grids is not 0 if the wind turbine generators are arranged in the grids, the arrangement mode of the wind turbine generators is converted into a binary code with the length of m.
The initial population is generated in a random mode, updating iteration is carried out through crossing and variation, and different from the traditional genetic algorithm, the improved genetic algorithm changes the generation probability of 0 and 1 in the initial population and the variation process from fixed probability to dynamic probability so as to increase the population diversity. Calculating the fitness of population individuals by taking the target function as a fitness function, selecting the population individuals by combining a roulette method and an individual optimal reservation method, selecting the optimal individuals, and decoding the optimal individuals to obtain the initial optimal layout of the wind generating set; the position of the gene 1 in the individual code is the mounting position of the wind turbine generator, and the total number of the gene 1 is the number of the wind turbine generator.
(2) And finally optimizing the coordinated genetic algorithm, and based on the obtained number and layout of the wind generation sets, re-optimizing the positions of the wind generation sets by using the real number encoded genetic algorithm to further improve the generated energy.
Setting n sets of optimal wind turbine generators obtained by the wind power plant in the step (1), representing the positions of the wind turbine generators by using vector coordinates, and recording as (x) i ,y i ) I =1,.. N, the wind farm is analyzed in a plane coordinate axis, as shown in fig. 4, the incoming wind direction is set to be in the negative direction along the y axis, the wind turbines are reordered from large to small according to the ordinate y, and if the ordinate y is equal, the wind turbines are ordered from small to large according to the abscissa x, the i-th turbine after being newly ordered is only influenced by the wake flow of the previous i-1 turbine.
The method comprises the steps of further optimizing and converting the layout of the wind turbine generator optimized by a grid genetic algorithm into the optimization of the coordinates of the wind turbine generator, directly coding the coordinates by adopting the coordinate genetic algorithm, selecting individuals by taking a target function as an individual fitness calculation method, wherein the optimization of the target function needs to be combined with the wind field boundary and the constraint condition that the wind turbine generator is not placed in the 5D range between the wind turbine generators. And obtaining the optimal individual, namely the optimal layout of the wind power plant, through the updating iteration of the population, thereby obtaining the optimal power generation capacity and the target function.
Example (b):
according to the wind power plant of the 2km multiplied by 2km classical case, the optimal power generation amount of the wind power plant for one hour under unit cost is considered for carrying out layout optimization, and the power generation power is determined by the formula (1). The wind turbine generator and wind farm information are shown in table 1.
The calculation formula of the generated power is as follows:
in the formula: c P -efficiency of the wind turbine, C P ＝4a(1-a) 2 (ii) a Rho is the air density, and is determined by the power curve of the wind turbine generator.
TABLE 1 wind turbine and wind farm information
Consider 3 wind conditions, see fig. 5 for details. The specific wind speed and wind direction conditions are as follows:
wind conditions I: fixing wind direction and wind speed (12 m/s);
wind conditions II: 36 wind directions have the same frequency and the fixed wind speed (12 m/s);
and (3) wind conditions are as follows: 36 wind directions, variable wind speed (8, 12, 17 m/s), distribution probability of each wind direction as shown in fig. 6.
Wind conditions one case:
the optimization results are shown in table 2, and the layout is shown in fig. 7.
TABLE 2 wind conditions-case optimization results
Under the condition of the same number of wind turbine generators, the positions of the coordinates of the wind turbine generators are further optimized, the positions of the newly optimized wind turbine generators are distributed at the upper end and the lower end more intensively, the middle is dispersed properly, the wake effect is reduced to a greater extent, and the total generated energy of the wind turbine generators is improved. Compared with the best result, the power generation amount is improved by 7.70%, and the objective function is obviously improved.
Wind conditions two cases:
for the optimized layout of multiple wind directions, the layout needs to be further processed. When the incoming flow wind direction is not over against the wind turbine, the angle between the incoming flow wind direction and the wind turbine set is recorded as theta, the wind turbine set coordinates (x, y) are converted into (x ', y') through Cartesian coordinate conversion, as shown in FIG. 8, the converted wind direction is over against the wind turbine set, and the converted coordinates are substituted into an objective function for optimization, wherein the Cartesian coordinate conversion formula and the process are as follows:
the results are shown in Table 3 and the layout is shown in FIG. 9.
TABLE 3 wind two case optimization results
According to the analysis of fig. 9, since the 36 wind direction probabilities of the constant speed are equal, the wind turbine generators tend to be distributed symmetrically and more uniformly, but because of no limitation of the grid, the layout of the wind turbine generators placed in a wrong direction is more selected, so that the total power generation amount of the same number of the wind turbine generators is increased by 1.68%, and the objective function is further reduced.
Three cases of wind conditions:
for the third wind condition, since the wind direction is also from 36 wind directions, the cartesian coordinate transformation is first performed in the same manner as in the second wind condition, but the wind direction probabilities of different wind speeds are different from those in the second wind condition, so that the wind direction probabilities are classified and discussed, and then the classification is summed, and the calculation formula is:
in the formula: n is the number of wind turbine generators; n is a radical of hydrogen m The number of wind directions; n is a radical of s Is the wind speed number; v. of j Is the incoming flow wind speed; theta k The deviation angle is the deviation angle corresponding to the incoming flow wind direction and the wind turbine generator; q (v) j ,θ k ) Wind direction angle of theta k And the wind speed is v j Probability of (1 is the sum of the probabilities of the occurrence of wind speed under each wind direction); p i,j,k The wind speed of the i-th wind turbine generator set corresponding to the incoming flow is v j And the wind direction angle is theta k The amount of electricity generated.
The results of the three wind conditions are shown in table 4, and the layout of the wind field is shown in fig. 10.
TABLE 4 wind conditions three case optimization results
For wind conditions with variable wind speed and variable wind direction and different wind speed and wind direction probabilities, the wind direction frequency between 270 degrees and 350 degrees is high, the wind turbine generators arranged on the periphery of the wind field are large in number and uniform in distribution, and the wind turbine generators in the center are small in number and dispersed. After further optimization, the total power generation of the wind power plant is increased by 2.26% on the basis of the existing result.
Case-based analysis shows that the method provided by the invention is remarkably improved. However, the three-case wind condition (multi-wind speed and multi-wind direction) setting results in the average wind speed reaching 14m/s, which is higher and has larger difference with the actual wind condition of the wind field (the average wind speed is 5-8 m/s). In addition, the cut-in and cut-out wind speed of the wind turbine generator is not considered when the formula (1) is used for calculating the power, and the small wind turbine generator used in the formula is difficult to represent the large wind turbine generator adopted at present. Therefore, from the practical engineering application, the annual generating capacity of the wind power plant at unit cost is optimized by using the wind turbine set with the rated power of 3 MW. The information of the wind turbine is shown in table 5, and the adopted power curve is shown in fig. 11.
TABLE 5 wind turbine generator and wind farm information
The wind farm area is determined by giving longitude and latitude coordinates A (117.27 degrees, 23.42 degrees), B (117.3 degrees, 23.43 degrees), C (117.33 degrees, 23.39 degrees), D (117.33 degrees, 23.38 degrees), E (117.3 degrees, 23.36 degrees) and F (117.24 degrees and 23.4 degrees) of 6 points, and firstly converting the longitude and latitude into XY plane coordinates through arcgis to obtain the wind farm area projected on the plane coordinates. Considering that the placed wind turbine generator cannot exceed the boundary, the distance of one wind turbine generator diameter is reserved for the boundary, and the region where the wind turbine generator can be placed is obtained as shown in fig. 13. The constraint condition that no wind turbines are arranged in specified intervals among the wind turbines is required to be met, the constraint condition is set to be 5D, the wind power plant area is divided into grids with the side length being the specified length, meanwhile, some incomplete grids at the boundary of the wind field are removed, and therefore all complete grids where the wind turbines can be arranged are obtained.
Similar to the layout optimization of a classical wind power plant, the number and the initial layout of wind power generation sets are optimized by adopting a gridding genetic algorithm. Further, a coordinated genetic algorithm is used for re-optimization, constraint conditions of boundaries and wind turbine generator intervals need to be considered during optimization, and the constraint conditions specifically comprise:
and (4) further optimizing the position of the wind turbine generator by utilizing a coordinated genetic algorithm based on the constraint condition shown in the formula (4) to obtain an optimal layout and an objective function.
The three cases of the wind conditions are improved, so that the wind conditions are closer to an actual wind field. Similarly, the wind field still uses 36 wind directions (the difference between adjacent wind directions), but the wind speed and the wind speed frequency are adjusted, as shown in fig. 12. The average wind speed of the improved wind field was 7.48m/s.
The improved wind conditions three case results are shown in table 6, and the wind field layout is shown in fig. 13.
TABLE 6 improved wind conditions three case optimization results
Under the working conditions of multiple wind speeds and multiple wind directions, the annual energy production is improved by 1.77 percent compared with the gridding genetic algorithm, and the annual energy production is improved by 7963MWh. The layout after further optimization enables the wind generation sets to be more dispersed near the boundary line, the wind power plant area is maximally utilized to reduce the wake effect, and the total power generation amount of the wind power plant is improved to further optimize the objective function.
Claims (3)
1. A grid-coordinated genetic algorithm-based wind power plant position optimization method is characterized by comprising the following steps:
step 1: predicting the wake flow speed of the wind turbine generator by using a Jensen wake flow model, and obtaining the total kinetic energy loss in the wake flow of the wind turbine generator by using a square superposition model of the wake flow effect of the wind turbine generator; the superposition model is divided into 4 working conditions according to the influence degree of the wake flow of the wind turbine generator on the downstream wind turbine generator, and the cost of generating capacity is minimized according to an optimized objective function;
and 2, step: the gridding genetic algorithm and the coordinated genetic algorithm are combined, and the adopted method comprises the following two steps:
(1) Optimizing the number and the optimal layout of the wind turbine generators for enabling the objective function to reach the minimum through a gridding 0-1 coding genetic algorithm;
under the given parameters of a wind field and a wind turbine generator, considering that no wind turbine generator is placed in a specified range among the wind turbine generators, dividing a region into grids with specified size, wherein the number of the grids obtained in the given region is m, the number of the grids is 1 when the wind turbine generators are placed in the grids, and the number of the grids is 0 when the wind turbine generators are not placed in the grids, and the arrangement mode of the wind turbine generators is converted into a binary code with the length of m;
generating an initial population in a random mode, carrying out updating iteration through crossing and variation, calculating the fitness of population individuals by taking an objective function as a fitness function, selecting the optimal individuals by combining a roulette method and an individual optimal preservation method, and decoding the optimal individuals to obtain the initial optimal layout of the wind turbine generator system; the position of the gene 1 in the individual code is the mounting position of the wind turbine generator, and the sum of the number of the genes 1 is the number of the wind turbine generator;
(2) Finally optimizing a coordinated genetic algorithm, and based on the obtained number and layout of the wind turbine generators, re-optimizing the positions of the wind turbine generators by using a real number coded genetic algorithm to further improve the generated energy;
setting the optimal number of the wind generation sets obtained in the step (1) of the wind power plant as n sets, representing the positions of the wind generation sets by using vector coordinates, and recording as (x) i ,y i ) I =1, a, n, analyzing a wind power plant in a plane coordinate axis, setting the wind direction of incoming flow to be along the negative direction of a y axis, reordering the wind power generation units according to the longitudinal coordinate y from large to small, and if the longitudinal coordinate y is equal, ordering the wind power generation units according to the horizontal coordinate x from small to large, wherein the ith unit after new ordering is only influenced by the wake flow of the previous i-1 units;
the method comprises the steps of further optimizing and converting the layout of the wind turbine generator optimized by a gridding genetic algorithm into the optimization of coordinates of the wind turbine generator, adopting the coordinated genetic algorithm, directly coding the coordinates, selecting individuals by taking a target function as an individual fitness calculation method, and obtaining optimal individuals, namely the optimal layout of the wind power plant through population updating iteration, so that the optimal power generation capacity and the target function are obtained.
2. The grid-coordinated genetic algorithm-based wind power plant position optimization method according to claim 1, wherein no wind power plant is arranged within a specified range among the wind power plants, the distance is set to be 5D, and D is the diameter of a wind power plant blade; the constraint is also applicable when coordinating genetic algorithms.
3. The grid-coordinated genetic algorithm-based wind farm machine position optimization method according to claim 1, wherein the 4 working conditions specifically comprise full overlap, no overlap and two partial overlap.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210975919.7A CN115345073A (en) | 2022-08-15 | 2022-08-15 | Grid-coordinated genetic algorithm-based wind power plant position optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210975919.7A CN115345073A (en) | 2022-08-15 | 2022-08-15 | Grid-coordinated genetic algorithm-based wind power plant position optimization method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115345073A true CN115345073A (en) | 2022-11-15 |
Family
ID=83952677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210975919.7A Pending CN115345073A (en) | 2022-08-15 | 2022-08-15 | Grid-coordinated genetic algorithm-based wind power plant position optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115345073A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116151430A (en) * | 2022-12-12 | 2023-05-23 | 中广核风电有限公司 | Method and device for optimally arranging offshore wind power plant |
-
2022
- 2022-08-15 CN CN202210975919.7A patent/CN115345073A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116151430A (en) * | 2022-12-12 | 2023-05-23 | 中广核风电有限公司 | Method and device for optimally arranging offshore wind power plant |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hong et al. | Optimal sizing of hybrid wind/PV/diesel generation in a stand-alone power system using Markov-based genetic algorithm | |
| Negnevitsky et al. | Innovative short-term wind generation prediction techniques | |
| Tao et al. | Nonuniform wind farm layout optimization: A state-of-the-art review | |
| Song et al. | Three-dimensional wind turbine positioning using Gaussian particle swarm optimization with differential evolution | |
| CN106886833A (en) | A kind of wind-driven generator addressing Lectotype Optimization method suitable for Complex Constraints condition | |
| Ramli et al. | Wind farm layout optimization considering obstacles using a binary most valuable player algorithm | |
| CN115345073A (en) | Grid-coordinated genetic algorithm-based wind power plant position optimization method | |
| CN115618540A (en) | Wind generating set optimal layout method based on three-level dynamic variation rate | |
| Hakli | A new approach for wind turbine placement problem using modified differential evolution algorithm | |
| CN112052544A (en) | Wind power plant current collection network design method and system, storage medium and computing device | |
| Prabhu et al. | Optimal placement of off-shore wind turbines and subsequent micro-siting using Intelligently Tuned Harmony Search algorithm | |
| Duan et al. | Modified genetic algorithm for layout optimization of multi-type wind turbines | |
| CN108736472B (en) | Tidal current energy power generation field planning method considering reef influence | |
| Liu et al. | Offshore wind farm layout optimization using adapted genetic algorithm: A different perspective | |
| Qureshi et al. | Wind farm layout optimization through optimal wind turbine placement using a hybrid particle swarm optimization and genetic algorithm | |
| Zhang et al. | Joint optimization of the number, type and layout of wind turbines for a new offshore wind farm | |
| Hidayat et al. | Design of 3D wind farm layout using an improved electric charge particles optimization with hub-height variety | |
| Sood et al. | Optimal placement of wind turbines: A Monte Carlo approach with large historical data set | |
| Yang et al. | Optimal wind turbines micrositing in onshore wind farms using fuzzy genetic algorithm | |
| KR102439311B1 (en) | Coordinated optimization method for optimiztion of wind farm using sparsified wake digraph and apparatus performing the same | |
| Bellat et al. | Optimization of Wind Farms by the Particle Swarm Algorithm Considering Gaussian Wake Model | |
| CN116341226A (en) | Multi-objective optimization method for layout and wiring of offshore wind farm in consideration of noise | |
| KR102406851B1 (en) | Coordinated optimization method for maximizing the power of wind farm using scalable wake digraph and apparatus performing the same | |
| Niu et al. | A novel binary negatively correlated search for wind farm layout optimization | |
| Tao et al. | Optimal layout of a Co-Located wind/tidal current farm considering forbidden zones |
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 |