The optimization method and system of a kind of wind-driven generator arrangement type selecting
Technical field
The present invention relates to wind-driven generator microcosmic structure field, more particularly to a kind of optimization of wind-driven generator arrangement type selecting
Method and system.
Background technology
Wind energy is a kind of pollution-free, reproducible new energy, serious in energy scarcity and traditional energy environmental pollution
Modern society, Wind Power Generation Industry is as one of New Energy Industry greatly developed.Wind power plant microcosmic structure is that Wind Power Generation Industry is rationally advised
The steps necessary drawn.The wind power plant microcosmic structure built before wind power plant can effectively improve wind energy utilization efficiency, and improving blower fan makes
With the life-span, wind power plant O&M cost and cost of wind power generation are reduced, so as to realize Rational Decision and the scientific development of Wind Power Generation Industry.
Wind farm siting includes macroscopical addressing and microcosmic structure, and macroscopical addressing is intended to selection wind power plant site, and microcosmic structure emphasis exists
In Fan Selection and installation site.Long-term record and analysis to local wind-resources are the major premise of wind farm siting, microcosmic choosing
Anemometer tower is installed in location after macroscopical addressing completion, detection and the record of more than a year is carried out to wind regime at site, with reference to locality
Long-range meteorological record etc., comprehensively carries out wind-resources analysis and assessment.In wind-resources assessment, the base of site topography and geomorphology comprehensive analysis
On plinth, blower fan quantity and model are selected, determine assembling position, annual production maximum or expected wind-force are expected to reach wind power plant
Generating degree electricity cost is minimum, makes the wind power plant under conditions of society, economy and environmental index meet, and reaches economic benefit maximum
Change.
The optimization of wind power plant microcosmic structure is a kind of non-linear close coupling problem, need to consider local meteorology landform, environment
The factors such as index, land price, road distribution and construction feasibility, are related to many factors such as fluid, meteorology, electromechanics, it is impossible to
Optimal solution is drawn using traditional optimal method.Therefore, at present worldwide, the achievement in research of the direction all makes mostly
Decision-making is optimized to particular problem with the heuritic approach based on search to calculate.The main method of optimization be genetic algorithm, with
Machine algorithm, particle swarm optimization algorithm etc..Increase because wind speed profile increases with height above sea level, each model blower fan is in different wind
Each advantageous and inferior position under energy distribution situation.In wind power plant microcosmic structure, Multiple Type, height assembling same
Individual wind power plant, can effectively improve wind energy utilization and whole field generating efficiency, and then reduce the cost of wind power generation.
In the document and patent related to the application, document Castro Mora, J etc. are published in 2007 years
In the paper " An evolutive algorithm for wind farm optimal design " of Neurocomputing,
Propose the problem of polytypic blower fan arrangement optimization and give a kind of solution, but between not considering blower fan in optimization
Wake effect.Patent《A kind of wind power plant polytypic blower fan optimization arrangement based on genetic algorithm》(application publication number:CN
103793566 A) propose using genetic algorithm to solve the problems, such as that polytypic wind-driven generator is arranged, but the blower fan for using
Model chooses optimized algorithm and does not consider the of overall importance of optimized algorithm, relative coarseness, not enough precisely.
The content of the invention
The invention provides the optimization method and system of a kind of wind-driven generator arrangement type selecting, above-described skill is solved
Art problem.
The technical scheme that the present invention solves above-mentioned technical problem is as follows:
It is according to one aspect of the present invention, there is provided a kind of optimization method of wind-driven generator arrangement type selecting including following
Step:
Step 1, obtains at least one blower fan arrangement, and using each blower fan arrangement as one of genetic algorithm
Chromosome;
Step 2, according to default point of group's formula particle cluster algorithm, generates the corresponding optimal Fan Selection scheme of each chromosome
Fitness corresponding with the optimal Fan Selection scheme, and using fitness as the chromosome fitness;
Step 3, according to the genetic algorithm and the fitness of all chromosomes, calculates the first global optimum of genetic algorithm
Fitness, and the corresponding target chromosome of first global optimum fitness is obtained, then export the target chromosome pair
The blower fan arrangement answered exports the corresponding optimal Fan Selection scheme conduct of the target chromosome as target arrangement
Target selecting type scheme.
The beneficial effects of the invention are as follows:Optimization method of the invention makes genetic algorithm with point group's formula particle cluster algorithm is nested
With first by genetic algorithm selection blower fan arrangement position, after every generation population generation of genetic algorithm, with when former generation blower fan position
Put as blower fan arrangement position, the optimal solution of type selecting when then drawing blower fan arrangement position using point group's formula particle cluster algorithm,
I.e. optimal Fan Selection scheme, so as on the basis of, raising position arrangement precision continuous to wind power plant range searching, fully examine
The of overall importance of type selecting algorithm is considered, Lectotype Optimization can be prevented effectively from and be absorbed in local optimum, of overall importance more preferable, performance indications are more
Good, selecting type scheme is more accurate, and practicality is stronger.
On the basis of above-mentioned technical proposal, the present invention can also do following improvement.
Further, the step 1 is specially:
S101, obtains the transverse and longitudinal coordinate scope and at least one blower fan arrangement of wind-powered electricity generation field areas;
S102, the initial position of the wind-powered electricity generation field areas inner blower is generated according to blower fan arrangement and transverse and longitudinal coordinate scope
Matrix;
S103, each row to the initial position matrix carries out binary coding, and by the initial position matrix
Often capable coding result as genetic algorithm a chromosome;
The often row of the initial position matrix represents a blower fan arrangement.
Beneficial effect using above-mentioned further scheme is:This further technical scheme is directly compiled to blower fan position coordinates
Code, rather than to being selected gridiron pattern after wind power plant region division gridiron pattern, therefore can be connected in the range of wind power plant
Continuous search such that it is able to effectively carry out the selection of blower fan position and optimization for actual wind-powered electricity generation field areas.Simultaneously can also be by losing
Propagation algorithm coded system changes location finding density, so as to improve optimal speed.
Further, the step 2 is specially:
S201, obtains the initial type selecting result of blower fan;
S202, determines the search space of point group's formula particle cluster algorithm according to the initial type selecting result, and by the search
Space is divided at least one independent subspace;
S203, the chromosome corresponding at least one described in initial position matrix according to the initial type selecting prediction of result
Individual Fan Selection scheme, and the Fan Selection scheme is assigned in corresponding subspace as the particle of the chromosome,
One particle represents a Fan Selection scheme;
S204, speed and particle to particle in the subspace carry out random initializtion in the position of subspace, then
Function is calculated according to default fitness and calculates each particle using corresponding blower fan arrangement and in the present bit of subspace
The fitness put, and the second global optimum of the individual adaptive optimal control degree and all particles in subspace for obtaining each particle adapts to
Degree, using the corresponding particle position of second global optimum fitness as the subspace current group optimal location;
S205, according to the individual adaptive optimal control degree, second global optimum fitness and default evolutionary rule, antithetical phrase
The speed of each particle and position are constantly evolved in space, pre- until reaching to optimize the current group optimal location
If evolution end condition, then perform S206;
S206, the current group optimal location of relatively more all subspaces, and obtained from all of current group optimal location
Take target optimal location of the chromosome in the search space, and using the corresponding fitness of the target optimal location as
The fitness of the chromosome, the target optimal location is the corresponding optimal Fan Selection scheme of the chromosome.
Beneficial effect using above-mentioned further scheme is:This further technical scheme has used point group's formula particle cluster algorithm
Obtain genetic algorithm in each chromosome optimal selecting type scheme, not only ensure that for Multiple Type wind-driven generator parameter compared with
Type selecting solution can be quickly sought obtaining in the case of many, can guarantee that two kinds of algorithm nestings are used again, and during the excessive situation of iterations, meter
Evaluation time will not be long, while having more preferable Global Optimality.
Further, the step 3 is specially:
S301, obtains the fitness and target optimal location of all chromosomes in the initial position matrix;
S302, the fitness according to all chromosomes calculates first global optimum's fitness of the genetic algorithm, and obtains
Take the corresponding target chromosome of first global optimum's fitness of iterations and the genetic algorithm of genetic algorithm;
S303, judges whether iterations reaches default iterations threshold value, if so, then exporting the target chromosome
Corresponding blower fan arrangement exports the corresponding target optimal location conduct of the target chromosome as target arrangement
Target selecting type scheme, if it is not, then performing S304;
S304, all chromosomes that step 1 is generated as parent chromosome group intersect and life after mutation operation
Into child chromosome, the initial position matrix is updated according to the child chromosome then, and be back to step
S203。
Beneficial effect using above-mentioned further scheme is:Genetic algorithm has been used to obtain most in this further technical scheme
Excellent arrangement and corresponding optimal selecting type scheme, not only algorithm is advanced, and ensure that for non-linear close coupling optimization ask
Topic can still obtain feasible solution, strong applicability.
Further, in step S203, the cabin altitude prediction Fan Selection scheme according to blower fan model and assembling, and
By blower fan model is identical and cabin altitude is different, blower fan model is different and cabin altitude is identical different with blower fan model and cabin is high
The different scheme of degree regards as different Fan Selection schemes.
Beneficial effect using above-mentioned further scheme is:This further technical scheme has taken into full account actual wind field region
The characteristics of and the characteristics of utilize wind energy using polytypic blower fan, may extend to complicated landform three-dimensional blower fan addressing and polytypic blower fan
Situation about loading in mixture.
Further, in step S204, the fitness is that the particle uses corresponding blower fan arrangement and type selecting side
The inverse of the electric cost of degree that case is calculated, it is as follows that the fitness calculates function:
Wherein, CoE is a year cost of electricity-generating, and AEP is wind power plant average annual energy output, CiBe every Fans purchase it is average annual into
This, CO&MIt is the annual O&M cost of wind power plant, ClandIt is wind power plant soil annual cost of possession, CotherBe wind power plant other
The annual mean of expense, PiIt is the average annual energy output of every Fans, N is the total number of units of wind electric field blower.
In order to solve technical problem of the invention, a kind of optimization system of wind-driven generator arrangement type selecting, bag are additionally provided
Include:
First generation module, for obtaining at least one blower fan arrangement, and using each blower fan arrangement as something lost
One chromosome of propagation algorithm;
Second generation module, for according to default point of group's formula particle cluster algorithm, generating each chromosome corresponding optimal
Fan Selection scheme and the corresponding fitness of the optimal Fan Selection scheme, and using the fitness as chromosome adaptation
Degree;
Output module, for the fitness according to the genetic algorithm and all chromosomes, calculates the first of genetic algorithm
Global optimum's fitness, and obtain first global optimum fitness and answer corresponding target chromosome, then export the mesh
The corresponding blower fan arrangement of mark chromosome exports the corresponding optimal blower fan choosing of the target chromosome as target arrangement
Type scheme is used as target selecting type scheme.
The beneficial effects of the invention are as follows:Optimization system of the invention makes genetic algorithm with point group's formula particle cluster algorithm is nested
With first by genetic algorithm selection blower fan arrangement position, after every generation population generation of genetic algorithm, with when former generation blower fan position
Put as blower fan arrangement position, the optimal solution of type selecting when then drawing blower fan arrangement position using point group's formula particle cluster algorithm,
I.e. optimal Fan Selection scheme, on the basis of arranging precision in, raising position continuous to wind power plant range searching, Neng Gouyou
Effect avoids Lectotype Optimization from being absorbed in local optimum, and of overall importance more preferable, more preferably, selecting type scheme is more accurate, and practicality is more for performance indications
By force.
Further, first generation module includes:
First acquisition unit, transverse and longitudinal coordinate scope and at least one blower fan arrangement for obtaining wind-powered electricity generation field areas;
First generation unit, for generating wind in the wind-powered electricity generation field areas according to blower fan arrangement and transverse and longitudinal coordinate scope
The initial position matrix of machine;
Second generation unit, binary coding is carried out for each row to the initial position matrix, and will be described first
In beginning location matrix often capable coding result as genetic algorithm a chromosome;The often row of the initial position matrix is represented
One blower fan arrangement.
Further, second generation module includes:
Second acquisition unit, the initial type selecting result for obtaining blower fan;
Division unit, the search space for determining point group's formula particle cluster algorithm according to the initial type selecting result, and will
The search space partition is at least one independent subspace;
3rd generation unit, for the chromosome described in initial position matrix according to the initial type selecting prediction of result
Corresponding at least one Fan Selection scheme, and it is assigned to correspondence using the Fan Selection scheme as the particle of the chromosome
Subspace in, a particle represents a Fan Selection scheme;
4th generation unit, is carried out at random for the speed and particle to particle in the subspace in the position of subspace
Initialization, then calculates function and calculates each particle using corresponding blower fan arrangement and sub empty according to default fitness
Between current location fitness, and obtain each particle individual adaptive optimal control degree and all particles in subspace it is second complete
Office adaptive optimal control degree, using the corresponding particle position of second global optimum fitness as the subspace current group most
Excellent position;
First evolution unit, for according to the individual adaptive optimal control degree, second global optimum fitness and default
Evolutionary rule, speed and position to each particle in subspace are constantly evolved, to optimize the optimal position of the current group
Put, until reaching default evolution end condition, then drive the 5th generation unit;
5th generation unit, the current group optimal location for comparing all subspaces, and from all of current group
Target optimal location of the chromosome in the search space is obtained in optimal location, and the target optimal location is corresponding
Fitness as the chromosome fitness, the target optimal location is the corresponding optimal blower fan choosing of the chromosome
Type scheme.
Further, the output module includes:
3rd acquiring unit, fitness and the optimal position of target for obtaining all chromosomes in the initial position matrix
Put;
6th generation unit, the first global optimum for calculating the genetic algorithm according to the fitness of all chromosomes
Fitness, and obtain the corresponding target dye of first global optimum's fitness of iterations and the genetic algorithm of genetic algorithm
Colour solid;
Judging unit, for judging whether iterations reaches default iterations threshold value, if so, then exporting the mesh
The corresponding blower fan arrangement of mark chromosome is used as target arrangement, and it is optimal to export the corresponding target of the target chromosome
Position is used as target selecting type scheme, if it is not, then driving the second evolution unit;
Second evolution unit, for all chromosomes for generating the first generation module as parent chromosome group, goes forward side by side
Child chromosome is generated after row intersection and mutation operation, the initial position matrix is carried out according to the child chromosome then
Update, and drive the 3rd generation unit.
The advantage of the additional aspect of the present invention will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by present invention practice.
Brief description of the drawings
Fig. 1 is a kind of schematic flow sheet of the optimization method of wind-driven generator arrangement type selecting provided in an embodiment of the present invention;
Fig. 2 is a kind of structural representation of the optimization system of wind-driven generator arrangement type selecting provided in an embodiment of the present invention;
First generation module in the optimization system of the wind-driven generator arrangement type selecting that Fig. 3 is provided for another embodiment of the present invention
Structural representation;
Second generation module in the optimization system of the wind-driven generator arrangement type selecting that Fig. 4 is provided for another embodiment of the present invention
Structural representation;
The knot of output module in the optimization system of the wind-driven generator arrangement type selecting that Fig. 5 is provided for another embodiment of the present invention
Structure schematic diagram.
Specific embodiment
Principle of the invention and feature are described below in conjunction with accompanying drawing, example is served only for explaining the present invention, and
It is non-for limiting the scope of the present invention.
A kind of flow of the optimization method of wind-driven generator arrangement type selecting that Fig. 1 is provided for one embodiment of the invention is illustrated
Figure, as shown in figure 1, comprising the following steps:
Step 1, obtains at least one blower fan arrangement, and using each blower fan arrangement as one of genetic algorithm
Chromosome;
Step 2, according to default point of group's formula particle cluster algorithm, generates the corresponding optimal Fan Selection scheme of each chromosome
Fitness corresponding with the optimal Fan Selection scheme, and using fitness as the chromosome fitness;
Step 3, according to the genetic algorithm and the fitness of all chromosomes, calculates the first global optimum of genetic algorithm
Fitness, and the corresponding target chromosome of first global optimum fitness is obtained, then export the target chromosome pair
The blower fan arrangement answered exports the corresponding optimal Fan Selection scheme conduct of the target chromosome as target arrangement
Target selecting type scheme.
The optimization method of the present embodiment uses genetic algorithm with point group's formula particle cluster algorithm is nested, is calculated first by heredity
Method chooses blower fan arrangement position, after every generation population generation of genetic algorithm, using when former generation blower fan position as blower fan arrangement position
Put, the optimal solution of type selecting, i.e., optimal Fan Selection side when then drawing blower fan arrangement position using point group's formula particle cluster algorithm
Case, so as on the basis of, raising position arrangement precision continuous to wind power plant range searching, Lectotype Optimization is prevented effectively from and fallen into
Enter local optimum, of overall importance more preferable, more preferably, selecting type scheme is more accurate, and practicality is stronger for performance indications.
In a preferred embodiment, the step 1 is specially:
S101, obtains the transverse and longitudinal coordinate scope and at least one blower fan arrangement of wind-powered electricity generation field areas;
S102, the initial position of the wind-powered electricity generation field areas inner blower is generated according to blower fan arrangement and transverse and longitudinal coordinate scope
Matrix;
S103, each row to the initial position matrix carries out binary coding, and by the initial position matrix
Often capable coding result as genetic algorithm a chromosome;The often row of the initial position matrix represents a blower fan arrangement
Scheme.
This preferred embodiment to blower fan position coordinates direct coding, rather than to after wind power plant region division gridiron pattern to chess
Disk lattice are selected, therefore can continuously be searched in the range of wind power plant such that it is able to be effectively directed to actual wind-powered electricity generation field areas
Carry out the selection of blower fan position and optimization.Location finding density can also be changed by genetic algorithm encoding mode simultaneously, so that
Improve optimal speed.
In another preferred embodiment, the step 2 is specially:
S201, obtains the initial type selecting result of blower fan, specifically can be according to wind-resources assessment result and wind power plant landform
Meteorological features, initial type selecting is carried out to wind-driven generator, determines several alternative models for Lectotype Optimization;
S202, determines the search space of point group's formula particle cluster algorithm according to the initial type selecting result, and by the search
Space is divided at least one independent subspace;
S203, the chromosome corresponding at least one described in initial position matrix according to the initial type selecting prediction of result
Individual Fan Selection scheme, and the Fan Selection scheme is assigned in corresponding subspace as the particle of the chromosome,
One particle represents a Fan Selection scheme;In specific embodiment, the population per sub-spaces is more than 3;
S204, speed and particle to particle in the subspace carry out random initializtion in the position of subspace, then
Function is calculated according to default fitness and calculates each particle using corresponding blower fan arrangement and in the present bit of subspace
The fitness put, and the second global optimum of the individual adaptive optimal control degree and all particles in subspace for obtaining each particle adapts to
Degree, using the corresponding particle position of second global optimum fitness as the subspace current group optimal location;
S205, according to the individual adaptive optimal control degree, second global optimum fitness and default evolutionary rule, antithetical phrase
The speed of each particle and position are constantly evolved in space, pre- until reaching to optimize the current group optimal location
If evolution end condition, then perform S206;
S206, the current group optimal location of relatively more all subspaces, and obtained from all of current group optimal location
Take target optimal location of the chromosome in the search space, and using the corresponding fitness of the target optimal location as
The fitness of the chromosome, the target optimal location is the corresponding optimal Fan Selection scheme of the chromosome.
In the step S205, it is default that the evolution end condition is that a point iterations for group's formula particle cluster algorithm has reached
Iterations threshold value, certainly in other embodiments can be using other evolution end conditions, such as the second global optimum
The increment of fitness is evolved when being less than preset increments threshold value and is terminated, and above-mentioned these schemes are within protection scope of the present invention.
Point group's formula particle cluster algorithm has been used to obtain the optimal of each chromosome in genetic algorithm in above preferred embodiment
Selecting type scheme, not only ensure that for Multiple Type wind-driven generator parameter it is more in the case of can quickly seek obtaining type selecting solution, and
Can guarantee that two kinds of algorithm nestings are used, and during the excessive situation of iterations, the time of calculating will not be long, while having preferably
Global Optimality.
In another preferred embodiment, the step 3 is specially:
S301, obtains the fitness and target optimal location of all chromosomes in the initial position matrix;
S302, the fitness according to all chromosomes calculates first global optimum's fitness of the genetic algorithm, and obtains
Take the corresponding target chromosome of first global optimum's fitness of iterations and the genetic algorithm of genetic algorithm;
S303, judges whether iterations reaches default iterations threshold value, if so, then exporting the target chromosome
Corresponding blower fan arrangement exports the corresponding target optimal location conduct of the target chromosome as target arrangement
Target selecting type scheme, if it is not, then performing S304;
S304, all chromosomes that step 1 is generated as parent chromosome group intersect and life after mutation operation
Into child chromosome, the initial position matrix is updated according to the child chromosome then, and be back to step
S203。
The preferred embodiment has used genetic algorithm to obtain optimal arrangement and corresponding optimal selecting type scheme, not only calculates
Method is advanced, and to ensure that and can still obtain feasible solution, strong applicability for non-linear close coupling optimization problem.
In another specific embodiment, the cabin altitude prediction Fan Selection scheme according to blower fan model and assembling,
And by blower fan model is identical and cabin altitude is different, blower fan model is different and the identical and cabin different with blower fan model of cabin altitude
Highly different schemes regards as different Fan Selection schemes.Such as alternative blower fan is two kinds of model A (rated power that dispatch from the factory
It is 1.5MW) and B (rated power is 2MW), the cabin altitude of the assembling of every kind of model of dispatching from the factory has two kinds, and (1.5MW has 65 meters
With 80 meters of two kinds of height, 2MW has 80 meters and 90 meters of two kinds of height), i.e., blower fan model has 4 kinds.The preferred embodiment takes into full account
The characteristics of actual wind field region and the characteristics of utilize wind energy using polytypic blower fan, may extend to complicated landform three-dimensional blower fan choosing
The situation that location and polytypic blower fan are loaded in mixture.
Preferably, fitness described in step S204 is that the particle uses corresponding blower fan arrangement and selecting type scheme
The inverse of the electric cost of degree for calculating, it is as follows that the fitness calculates function:
Wherein, CoE is a year cost of electricity-generating, and AEP is wind power plant average annual energy output, CiBe every Fans purchase it is average annual into
This, CO&MIt is the annual O&M cost of wind power plant, ClandIt is wind power plant soil annual cost of possession, CotherBe wind power plant other
The annual mean of expense, PiIt is the average annual energy output of every Fans, N is the total number of units of wind electric field blower.The preferred embodiment is led to
Excessively electricity weighs fitness into original, not only calculates simple, optimal speed block, and optimum results are accurate.
A kind of structural representation of the optimization system of wind-driven generator arrangement type selecting that Fig. 2 is provided for another embodiment, such as
Shown in Fig. 2, including:
First generation module, for obtaining at least one blower fan arrangement, and using each blower fan arrangement as something lost
One chromosome of propagation algorithm;
Second generation module, for according to default point of group's formula particle cluster algorithm, generating each chromosome corresponding optimal
Fan Selection scheme and the corresponding fitness of the optimal Fan Selection scheme, and using the fitness as chromosome adaptation
Degree;
Output module, for the fitness according to the genetic algorithm and all chromosomes, calculates the first of genetic algorithm
Global optimum's fitness, and obtain first global optimum fitness and answer corresponding target chromosome, then export the mesh
The corresponding blower fan arrangement of mark chromosome exports the corresponding optimal blower fan choosing of the target chromosome as target arrangement
Type scheme is used as target selecting type scheme.
Optimization system of the invention uses genetic algorithm with point group's formula particle cluster algorithm is nested, first by genetic algorithm
Choose blower fan arrangement position, genetic algorithm an every generation population generation after, using when former generation blower fan position as blower fan arrangement position,
The optimal solution of type selecting when then drawing blower fan arrangement position using point group's formula particle cluster algorithm, i.e., optimal Fan Selection scheme,
So as on the basis of, raising position arrangement precision continuous to wind power plant range searching, Lectotype Optimization is prevented effectively from and be absorbed in
Local optimum, of overall importance more preferable, more preferably, selecting type scheme is more accurate, and practicality is stronger for performance indications.
Fig. 3 be a preferred embodiment in, the structural representation of first generation module, as shown in figure 3, it is described first life
Include into module:
First acquisition unit, transverse and longitudinal coordinate scope and at least one blower fan arrangement for obtaining wind-powered electricity generation field areas;
First generation unit, for generating wind in the wind-powered electricity generation field areas according to blower fan arrangement and transverse and longitudinal coordinate scope
The initial position matrix of machine;
Second generation unit, binary coding is carried out for each row to the initial position matrix, and will be described first
In beginning location matrix often capable coding result as genetic algorithm a chromosome;The often row of the initial position matrix is represented
One blower fan arrangement.
First generation module of the preferred embodiment is drawn to blower fan position coordinates direct coding rather than to wind-powered electricity generation field areas
Gridiron pattern is selected after dividing gridiron pattern, therefore can continuously be searched in the range of wind power plant such that it is able to be effectively directed to
Actual wind-powered electricity generation field areas carries out the selection of blower fan position and optimization.Position can also be changed by genetic algorithm encoding mode simultaneously
Search density, so as to improve optimal speed.
Fig. 4 be another preferred embodiment in, the structural representation of second generation module, as shown in figure 4, described second
Generation module includes:
Second acquisition unit, the initial type selecting result for obtaining blower fan;
Division unit, the search space for determining point group's formula particle cluster algorithm according to the initial type selecting result, and will
The search space partition is at least one independent subspace;
3rd generation unit, for the chromosome described in initial position matrix according to the initial type selecting prediction of result
Corresponding at least one Fan Selection scheme, and it is assigned to correspondence using the Fan Selection scheme as the particle of the chromosome
Subspace in, a particle represents a Fan Selection scheme;
4th generation unit, is carried out at random for the speed and particle to particle in the subspace in the position of subspace
Initialization, then calculates function and calculates each particle using corresponding blower fan arrangement and sub empty according to default fitness
Between current location fitness, and obtain each particle individual adaptive optimal control degree and all particles in subspace it is second complete
Office adaptive optimal control degree, using the corresponding particle position of second global optimum fitness as the subspace current group most
Excellent position;
First evolution unit, for according to the individual adaptive optimal control degree, second global optimum fitness and default
Evolutionary rule, speed and position to each particle in subspace are constantly evolved, to optimize the optimal position of the current group
Put, until reaching default evolution end condition, then drive the 5th generation unit;
5th generation unit, the current group optimal location for comparing all subspaces, and from all of current group
Target optimal location of the chromosome in the search space is obtained in optimal location, and the target optimal location is corresponding
Fitness as the chromosome fitness, the target optimal location is the corresponding optimal blower fan choosing of the chromosome
Type scheme.
Second generation module of above preferred embodiment has used point group's formula particle cluster algorithm to obtain each in genetic algorithm
The optimal selecting type scheme of chromosome, not only ensure that for Multiple Type wind-driven generator parameter it is more in the case of can quickly seek
Type selecting solution, can guarantee that two kinds of algorithm nestings are used again, and during the excessive situation of iterations, the time of calculating will not be long, together
When there is more preferable Global Optimality.
Fig. 5 be another preferred embodiment in, the structural representation of the output module, as shown in figure 5, the output module
Including:
3rd acquiring unit, fitness and the optimal position of target for obtaining all chromosomes in the initial position matrix
Put;
6th generation unit, the first global optimum for calculating the genetic algorithm according to the fitness of all chromosomes
Fitness, and obtain the corresponding target dye of first global optimum's fitness of iterations and the genetic algorithm of genetic algorithm
Colour solid;
Judging unit, for judging whether iterations reaches default iterations threshold value, if so, then exporting the mesh
The corresponding blower fan arrangement of mark chromosome is used as target arrangement, and it is optimal to export the corresponding target of the target chromosome
Position is used as target selecting type scheme, if it is not, then driving the second evolution unit;
Second evolution unit, for all chromosomes for generating the first generation module as parent chromosome group, goes forward side by side
Child chromosome is generated after row intersection and mutation operation, the initial position matrix is carried out according to the child chromosome then
Update, and drive the 3rd generation unit.
The output module of above preferred embodiment used genetic algorithm obtain optimal arrangement and it is corresponding most preferably
Type scheme, not only algorithm is advanced, and to ensure that and can still obtain feasible solution, applicability for non-linear close coupling optimization problem
By force.
In another preferred embodiment, the 3rd generation unit is pre- according to the cabin altitude of blower fan model and assembling
Fan Selection scheme is surveyed, and by blower fan model is identical and cabin altitude is different, blower fan model is different and cabin altitude is identical and wind
The type difference and different scheme of cabin altitude regards as different Fan Selection schemes.So as to take into full account actual wind
The characteristics of field areas and the characteristics of utilize wind energy using polytypic blower fan, may extend to complicated landform three-dimensional blower fan addressing and many types of
The situation that number blower fan is loaded in mixture.
In the description of the invention, it is to be understood that term " first ", " second " are only used for describing purpose, and can not
It is interpreted as indicating or implying relative importance or the implicit quantity for indicating indicated technical characteristic.Thus, define " the
One ", at least one this feature can be expressed or be implicitly included to the feature of " second ".In the description of the invention, " multiple "
It is meant that at least two, such as two, three etc., unless otherwise expressly limited specifically.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means to combine specific features, structure, material or spy that the embodiment or example are described
Point is contained at least one embodiment of the invention or example.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be with office
Combined in an appropriate manner in one or more embodiments or example.Additionally, in the case of not conflicting, the skill of this area
Art personnel can be tied the feature of the different embodiments or example described in this specification and different embodiments or example
Close and combine.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all it is of the invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc. should be included within the scope of the present invention.