CN106897771A - A kind of new energy template processing machine site selecting method and system based on Chaos Genetic Algorithm - Google Patents
A kind of new energy template processing machine site selecting method and system based on Chaos Genetic Algorithm Download PDFInfo
- Publication number
- CN106897771A CN106897771A CN201710002219.9A CN201710002219A CN106897771A CN 106897771 A CN106897771 A CN 106897771A CN 201710002219 A CN201710002219 A CN 201710002219A CN 106897771 A CN106897771 A CN 106897771A
- Authority
- CN
- China
- Prior art keywords
- processing machine
- template processing
- blower fan
- group
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 119
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000002068 genetic effect Effects 0.000 title claims abstract description 22
- 230000008859 change Effects 0.000 claims abstract description 8
- 238000004393 prognosis Methods 0.000 claims abstract description 7
- 210000000349 chromosome Anatomy 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 10
- 230000035772 mutation Effects 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 230000000739 chaotic effect Effects 0.000 claims description 5
- 108090000623 proteins and genes Proteins 0.000 claims description 5
- 238000005728 strengthening Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 claims description 2
- 230000005684 electric field Effects 0.000 description 21
- 230000005611 electricity Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000004043 dyeing Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000009931 harmful effect Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
Classifications
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Control Of Positive-Displacement Air Blowers (AREA)
- Wind Motors (AREA)
Abstract
The invention provides a kind of new energy template processing machine site selecting method based on Chaos Genetic Algorithm and system, judge whether to need to change template processing machine, blower fan is divided into several big groups according to characteristic, template processing machine is recalculated using Chaos Genetic Algorithm;Accurate weather prognosis related data is obtained by new template processing machine, accurate active/idle prediction data is obtained.Shortcoming of the present invention for the subjective method for selecting of template processing machine tradition analyzes template processing machine performance using quantizating index, and template processing machine is changed by Chaos Genetic Algorithm in real time, the theoretical generated energy of other blower fans of wind power plant can be accurately estimated by suitable template processing machine, with abandon air quantity, with very important practical application meaning.
Description
Technical field
The invention belongs to wind-powered electricity generation field, especially relate to it is a kind of using quantizating index analysis wind power plant template processing machine performance,
And change the new method and system of template processing machine in real time by Chaos Genetic Algorithm.
Background technology
Increasing with installed capacity of wind-driven power, wind-powered electricity generation progressively becomes big in electricity market portion, and country increasingly sees
Again to wind power plant air quantity ASSOCIATE STATISTICS and wind power plant real-time control in terms of management.In extend out wind power plant template processing machine this
Concept, by combining blower fan treatment characteristic combination electric field model based on wind power plant template processing machine, can effectively estimate every typhoon
The approximation theory of machine is active, and wind power plant abandons air quantity, with very important Practical significance.
Country is made that some related requests to the selected of wind power plant template processing machine now, mainly includes template processing machine installed capacity
Without 10% more than electric field installed capacity, multiple template processing machines can not be selected in same cluster.In addition do not give
Go out the selection standard or method of more efficient property.Cause present wind power plant existing mainly by wind power plant in the method for selection mark post blower fan
The subjective determination of field operating personnel, or selected after correlation modeling software carries out Utopian modeling analysis, wind power plant reality
Border can not carry out the selection of objective modification template processing machine according to unit health status after putting into operation.
Whether existing blower fan template processing machine method for selecting causes seldom to go to investigate the template processing machine being capable of generation after template processing machine is selected
The practical operation situation of the whole wind power plant of table, while the actual condition of template processing machine is with using changing, and Various Seasonal
Influence of the wind to template processing machine is all inevitable variable quantity, and this will cause the changeless blower fan template processing machine can not be completely anti-
Should in the running status of the wind power plant under all wind states, cause wind power plant abandon air quantity be out of one's reckoning, wind power plant it is active/it is idle
Regulation and control error etc., and then cause electric field power prediction inaccurate, electric field is active/reactive power fluctuation impacts to power network, and these all can one
Determine pool regulation and control and the safe operation of power network of the influence power network in degree to wind power resources.
Especially when template processing machine is under inspecting state, the function of the template processing machine is even more in error condition, will be serious
Influence the estimation and the regulation and control of electric field fan of some electric field datas based on the template processing machine data.
The content of the invention
In view of this, the present invention proposes a kind of new energy template processing machine site selecting method and system based on Chaos Genetic Algorithm,
Shortcoming for the subjective method for selecting of template processing machine tradition analyzes template processing machine performance using quantizating index, and by Chaos-Genetic
Algorithm changes template processing machine in real time, and the theoretical hair of other blower fans of wind power plant can be accurately estimated by suitable template processing machine
Electricity, and air quantity is abandoned, with very important practical application meaning.
To reach above-mentioned purpose, the technical proposal of the invention is realized in this way:It is a kind of based on the new of Chaos Genetic Algorithm
Energy template processing machine site selecting method, including:
(1) judge whether to need to change template processing machine, if it is continue step (2);
(2) blower fan is divided into several big groups according to characteristic, the characteristic includes blower fan machine unit characteristic, unit distribution
Region, windage region;
(3) template processing machine is recalculated using Chaos Genetic Algorithm;
(4) accurate weather prognosis related data is obtained by new template processing machine, obtains accurate active/idle prediction number
According to.
Further, judge whether that the method for needing to change template processing machine is:
(11) judge whether template processing machine overhauls, be, carry out next step;
(12) whether wind power plant is judged in rationing the power supply state, is then return to step (101), otherwise carry out next step;
(13) judge that whether template processing machine is sent out active and matched with wind-force in fact, be then return to step (101), otherwise carry out next
Step;
(14) judge whether former state trigger meets calculating standard, be then return to step (101), otherwise carry out step (2).
Further, the process of step (3) described Chaos Genetic Algorithm is:
(31) encode:Each group respectively selects a template processing machine, and every template processing machine numbering collectively constitutes coding, used as dyeing
Body;
(32) initialization of population:Population number is defined as 2* blower fans total number/template processing machine number;
(33) fitness is calculated:It is theoretical active based on the template processing machine selected, calculate the fitness of chromosome;
(34) selection operation:Fitness size according to chromosome, by roulette algorithm filter out fitness it is big
Body is used as follow-on parent;
(35) crossover operation:Crossover operation is carried out using the method for chaos operator, realization is traveled through completely;
(36) mutation operation:Operation is interchangeable using two corresponding points are randomly selected on chromosome.
Further, the specific method of step (33) the calculating fitness is:
(331) calculating the respective theory of each group has work value and PjSumIf there is L platform units, P in j-th groupsIt is machine
Kludge capacity, PkFor the theory of template processing machine in the group has work value and PkallIt is the template processing machine installed capacity and λsIt is the machine
The correction factor of group, then
(332) calculating whole audience blower fan theory has work value and Ptheo, whole audience blower fan is allocated M group, then
(333) hair has work value and P in fact to calculate whole audience blower fanreal, whole audience blower fan number is N, PiFor the i-th Fans, hair has in fact
Work(, then
(334) fitness is calculated, formula is as follows:
Further, the specific method of step (35) described crossover operation is:
(351) crossover operation selected part matching Crossover Strategy, chooses two random crosspoints in two individualities, and will
Gene section, i.e. machine group # section in the middle of crosspoint are exchanged, if exchange part is identical, are reselected;
(352) when needing to carry out adding chaos operator to process, the individuality for choosing in population 10% is entered using chaos operator
Row treatment, i.e., add a chaotic disturbance, the diversity of strengthening system at random to blower fan numbering is upper.
x0=0.1
xn+1=βi*xn*(1-xn)
β in formulaiTo correspond to the number of certain group;
(353) each section to selected legal chromosome carries out addition xnIt is circulated at the method for counting
Reason.
Another aspect of the present invention, a kind of new energy template processing machine site selection system based on Chaos Genetic Algorithm, including:
Judge module, for judging whether to need to change template processing machine;
Group division module, for blower fan to be divided into several big groups according to characteristic, the characteristic includes blower fan machine
Group characteristic, unit distributed areas, windage region;
Template processing machine computing module, for recalculating template processing machine using Chaos Genetic Algorithm;
Prediction module, for obtaining accurate weather prognosis related data by new template processing machine, obtain accurately it is active/
Idle prediction data.
Further, the judge module includes:
Maintenance judging unit, for judging whether template processing machine overhauls;
Ration the power supply judging unit, for judging wind power plant whether in state of rationing the power supply;
Matching judgment unit, for judging that whether template processing machine is sent out active and matched with wind-force in fact;
Calculating standard judging unit, judges whether former state trigger meets calculating standard.
Further, template processing machine computing module includes:
Coding unit:Each group respectively selects a template processing machine, and every template processing machine numbering collectively constitutes coding, used as dyeing
Body;
Initialization of population unit:Population number is defined as 2* blower fans total number/template processing machine number;
Calculate fitness unit:It is theoretical active based on the template processing machine selected, calculate the fitness of chromosome;
Selection operation unit:Fitness size according to chromosome, by roulette algorithm filter out fitness it is big
Body is used as follow-on parent;
Crossover operation unit:Crossover operation is carried out using the method for chaos operator, realization is traveled through completely;
Mutation operation unit:Operation is interchangeable using two corresponding points are randomly selected on chromosome.
Further, the calculating fitness unit includes:
Group theory has work value and computation subunit, has work value and P for calculating the respective theory of each groupjSumIf,
There is L platform units, P in j-th groupsIt is unit installed capacity, PkFor the theory of template processing machine in the group has work value and PkallFor
The template processing machine installed capacity and λsIt is the correction factor of the unit, then
Whole audience blower fan theory has work value and computation subunit, has work value and P for calculating whole audience blower fan theorytheo, the whole audience
Blower fan is allocated M group, then
Hair has work value and computation subunit to whole audience blower fan in fact, and for calculating whole audience blower fan, hair has work value and P in factreal, the whole audience
Blower fan number is N, PiFor the i-th Fans are sent out active in fact, then
Fitness computation subunit, for calculating fitness, formula is as follows:
Further, crossover operation unit includes:
Selection subelement, Crossover Strategy is matched for crossover operation selected part, and two are chosen in two individualities at random
Crosspoint, and the gene section in the middle of crosspoint, i.e. machine group # section are exchanged, if exchange part is identical, reselect;
Chaos operator subelement, for when needing to carry out adding chaos operator to process, choosing in population 10% individuality
Processed using chaos operator, i.e., added a chaotic disturbance, the diversity of strengthening system at random to blower fan numbering is upper.
x0=0.1
xn+1=βi*xn*(1-xn)
β in formulaiTo correspond to the number of certain group;
Cycle count subelement, addition x is carried out for each section to selected legal chromosomenIt is circulated counting
Method processed.
Relative to prior art, a kind of new energy template processing machine site selecting method based on Chaos Genetic Algorithm of the present invention and
System has the beneficial effect that:
Present invention combination country has formulated a whole set of practicable template processing machine and has selected machine method to the relevant criterion of template processing machine
And related algorithm, the operation outlet quantified to the performance of template processing machine, the quality of template processing machine can objectively be commented
Valency.
The present invention is selected again to all blower fans of electric field again in wind-powered electricity generation stage of not rationing the power supply, selects the period wind-force
It is best able to that the template processing machine of electric field practical operation situation can be reflected under state, being capable of effective reflection wind-powered electricity generation objective to the full extent
The current ruuning situation in field, it is to avoid artificial subjective operation, effectively improves the representativeness of template processing machine, while by electric field blower fan
Real time electrical quantity is counted reversely to be verified the validity of template processing machine, is that reselecting for later stage template processing machine provides effective
Data supporting.
Can be preferably minimized for the harmful effect that conventional fixed blower fan template processing machine type selecting is caused by the present invention.Effectively improve and be based on
The operating reliability of the other systems of wind power plant template processing machine related data, be wind power prediction and wind power plant it is active/without power control
System provides more accurate data and supports.Wind-resources utilization rate and wind power plant operation level of security are improved to a certain extent.Improve
Wind power utilization rate, lifts electric field safety and stability rank.
Brief description of the drawings
Fig. 1 is schematic flow sheet of the invention.
Specific embodiment
It should be noted that in the case where not conflicting, the feature in embodiments of the invention and embodiment can be mutual
Combination.
As shown in figure 1, specific implementation flow of the invention is:
1. whether wind power plant is in inspecting state
When template processing machine be in inspecting state under when, the function of the template processing machine is even more in error condition, will have a strong impact on
The estimation and the regulation and control of electric field fan of some electric field datas based on the template processing machine data.Therefore need to recalculate model
Machine.
2. whether wind power plant is in state of rationing the power supply
It is currently theoretical whether the active desired value of the whole audience of wind power plant is more than the electric field obtained by template processing machine or other approach are calculated
There is work value.
When the active desired value of the whole audience>The current theory of electric field has work value, and system is in non-state of rationing the power supply.
When the active desired value of the whole audience<The current theory of electric field has work value, and system is in state of rationing the power supply.
Blower fan is in free generating state under non-state of rationing the power supply, and blower fan institute's generated energy receives wind-force and set state with main
Influence, without human intervention, the blower fan under the state can reflect electric field practical operation situation.
3. whether hair power matches template processing machine with wind-force in fact
Template processing machine is set to by own power generation mode, i.e. template processing machine by electric field active reactive control system and sends out active in fact
By wind-force and unit, state is influenceed in itself, not by human intervention.Active amount has the hysteresis quality of certain hour relative to wind-force simultaneously.
The lag time is determined by fan characteristic and wind speed.
The hair power and blower fan then template processing machine working condition that matches is good in fact for blower fan template processing machine.Otherwise template processing machine operating mode compared with
Difference, changes template processing machine.
4. whether original template processing machine meets calculating standard
Whether template processing machine is sent out active and meets the active correlation curve of wind-force under the wind state for collecting.The contrast is bent
Line has different performances with blower fan manufacturer, the difference of blower fan model, and the difference in blower fan machine age.
5. blower fan divides group
Blower fan point group refers to the unit distributed areas according to blower fan machine unit characteristic by blower fan, and the characteristic such as windage region will
All blower fans of this electric field are divided into several big groups.Each blower fan is sent out active and can be approximately seen as in the group of planes in fact in group
The approximation that mark post blower fan is sent out active in fact, can be by group of planes correction factor λkModification.
6. genetic algorithm
Genetic algorithm is a kind of process for simulating natural evolution search optimal solution, can by simulating fitness individuality high
The principle that heredity is gone down carries out screening of constantly evolving, with stronger search capability and robustness.
A) coding is encoded using integer combinations coded system.
N sections of chromosome point, n is selected template processing machine number, every section of numbering for representing blower fan.
Note electric field have 30 Fans, be divided into three groups (1-10 units be a group, 11-20 units be 2 groups,
21-30 units are 3 groups), choose 3 Fans exemplarily machine, then each group respectively selects one one 6 of numbering composition
Numeral is a legal chromosome.
B) initialization of population, initialization of population should not be too small, too small that algorithm can be caused to can not find globally optimal solution, also unsuitable
Too big, too conference causes the calculating time to increase, and evolutionary rate is excessively slow, and all chromosomes will include all blower fans.So planting here
Group's number is defined as 2* blower fans total number/template processing machine number.
C) fitness function is above-mentioned blower fan fitness function
Wherein PtheoFor current time whole audience blower fan theory has work value and PrealFor current time whole audience blower fan is sent out active in fact
Value and.
Note whole audience blower fan number is N, PiFor the i-th Fans are sent out active in fact, then
Note whole audience blower fan is allocated M group, and each group internal unit equipment state is similar to, PjSumFor the group is theoretical
Have work value and, then
Remember that j-th group has L platform units, PsIt is unit installed capacity, PkFor in the group of planes template processing machine it is theoretical active
With PkallIt is the template processing machine installed capacity and λsIt is the correction factor of the unit, then
The coefficient represents the theoretical active prediction accuracy based on the template processing machine, and coefficient is closer to 0, template processing machine effect
Fruit is better, when f < 3% then think that blower fan template processing machine selection is qualified.When wind power plant can in the wind-force unstable region coefficient
It is appropriate to expand.
The coefficient only in the case where electric field is in non-state of rationing the power supply effectively, send out active and be restricted in fact in the case of electric field is rationed the power supply by blower fan
So the coefficient can not reflect the quality of template processing machine selection.
D) selection operation
The fitness size of the chromosome in population is determined according to fitness function.It is suitable to be filtered out by roulette algorithm
The big individuality of response is used as follow-on parent.
E) crossover operation
Common crossover operation can not avoid the possibility of incomplete traversal.So being mixed in the use of genetic algorithm here
The method of ignorant operator carries out crossover operation to crossover operation.Ensure that genetic process can find globe optimum, it is to avoid part is most
Advantage.
Crossover operation selected part matches Crossover Strategy.Two random crosspoints are chosen first in two individualities, and will
Gene section (i.e. machine group #) in the middle of crosspoint is exchanged, if exchange part is identical, is reselected.
When need carry out add chaos operator process when, choose population in 10% individuality using chaos operator at
Reason, i.e., add a chaotic disturbance, the diversity of strengthening system at random to blower fan numbering is upper.
x0=0.1
xn+1=βi*xn*(1-xn)
β in formulaiTo correspond to the number of certain group of planes
Each section to selected legal chromosome carries out addition xnThe method for being circulated counting is processed.
F) mutation operation
Mutation operation can increase population diversity, create new individual, have certain to locally optimal solution to a certain extent
Rejection ability.Mutation operation is interchangeable operation using the company of randomly selecting on chromosome corresponding points.
7. accurate weather prognosis related data, accurate active/idle prediction data
The weather prognosis related data calculated by template processing machine is included:Air quantity, actual air volume etc. are abandoned, is calculated by template processing machine
Active/idle related data includes:The active amount of subsequent time, idle amount etc..
The information such as general principle of the invention, principal character and embodiment, but the present invention are the foregoing described not by upper
The limitation of implementation process is stated, on the premise of spirit and scope is not departed from, the present invention there can also be various changes and modifications.
Therefore, unless this changes and improvements are departing from the scope of the present invention, they should be counted as comprising in the present invention.
Claims (10)
1. a kind of new energy template processing machine site selecting method based on Chaos Genetic Algorithm, it is characterised in that including:
(1) judge whether to need to change template processing machine, if it is continue step (2);
(2) blower fan is divided into several big groups according to characteristic, the characteristic includes blower fan machine unit characteristic, unit distributed area
Domain, windage region;
(3) template processing machine is recalculated using Chaos Genetic Algorithm;
(4) accurate weather prognosis related data is obtained by new template processing machine, obtains accurate active/idle prediction data.
2. method according to claim 1, it is characterised in that step (1) judges whether the method for needing to change template processing machine
For:
(11) judge whether template processing machine overhauls, be, carry out next step;
(12) whether wind power plant is judged in rationing the power supply state, is then return to step (101), otherwise carry out next step;
(13) judge that whether template processing machine is sent out active and matched with wind-force in fact, be then return to step (101), otherwise carry out next step;
(14) judge whether former state trigger meets calculating standard, be then return to step (101), otherwise carry out step (2).
3. method according to claim 1, it is characterised in that the process of step (3) described Chaos Genetic Algorithm is:
(31) encode:Each group respectively selects a template processing machine, and every template processing machine numbering collectively constitutes coding, used as chromosome;
(32) initialization of population:Population number is defined as 2* blower fans total number/template processing machine number;
(33) fitness is calculated:It is theoretical active based on the template processing machine selected, calculate the fitness of chromosome;
(34) selection operation:Fitness size according to chromosome, the big individual work of fitness is filtered out by roulette algorithm
It is follow-on parent;
(35) crossover operation:Crossover operation is carried out using the method for chaos operator, realization is traveled through completely;
(36) mutation operation:Operation is interchangeable using two corresponding points are randomly selected on chromosome.
4. method according to claim 3, it is characterised in that the specific method that step (33) is described to calculate fitness is:
(331) calculating the respective theory of each group has work value and PjSumIf there is L platform units, P in j-th groupsFor machine is assembled
Machine capacity, PkFor the theory of template processing machine in the group has work value and PkallIt is the template processing machine installed capacity and λsIt is the unit
Correction factor, then
(332) calculating whole audience blower fan theory has work value and Ptheo, whole audience blower fan is allocated M group, then
(333) hair has work value and P in fact to calculate whole audience blower fanreal, whole audience blower fan number is N, PiFor the i-th Fans are sent out active in fact, then
(334) fitness is calculated, formula is as follows:
5. method according to claim 3, it is characterised in that the specific method of step (35) described crossover operation is:
(351) crossover operation selected part matching Crossover Strategy, chooses two random crosspoints, and will intersect in two individualities
Gene section, i.e. machine group # section in the middle of are exchanged, if exchange part is identical, are reselected;
(352) when need carry out add chaos operator process when, choose population in 10% individuality using chaos operator at
Reason, i.e., add a chaotic disturbance, the diversity of strengthening system at random to blower fan numbering is upper.
x0=0.1
xn+1=βi*xn*(1-xn)
β in formulaiTo correspond to the number of certain group;
(353) each section to selected legal chromosome carries out addition xnThe method for being circulated counting is processed.
6. a kind of new energy template processing machine site selection system based on Chaos Genetic Algorithm, it is characterised in that including:
Judge module, for judging whether to need to change template processing machine;
Group division module, for blower fan to be divided into several big groups according to characteristic, the characteristic includes that blower fan unit is special
Property, unit distributed areas, windage region;
Template processing machine computing module, for recalculating template processing machine using Chaos Genetic Algorithm;
Prediction module, for obtaining accurate weather prognosis related data by new template processing machine, obtains accurately active/idle
Prediction data.
7. system according to claim 6, it is characterised in that the judge module includes:
Maintenance judging unit, for judging whether template processing machine overhauls;
Ration the power supply judging unit, for judging wind power plant whether in state of rationing the power supply;
Matching judgment unit, for judging that whether template processing machine is sent out active and matched with wind-force in fact;
Calculating standard judging unit, judges whether former state trigger meets calculating standard.
8. system according to claim 6, it is characterised in that template processing machine computing module includes:
Coding unit:Each group respectively selects a template processing machine, and every template processing machine numbering collectively constitutes coding, used as chromosome;
Initialization of population unit:Population number is defined as 2* blower fans total number/template processing machine number;
Calculate fitness unit:It is theoretical active based on the template processing machine selected, calculate the fitness of chromosome;
Selection operation unit:Fitness size according to chromosome, the big individual work of fitness is filtered out by roulette algorithm
It is follow-on parent;
Crossover operation unit:Crossover operation is carried out using the method for chaos operator, realization is traveled through completely;
Mutation operation unit:Operation is interchangeable using two corresponding points are randomly selected on chromosome.
9. system according to claim 8, it is characterised in that the calculating fitness unit includes:
Group theory has work value and computation subunit, has work value and P for calculating the respective theory of each groupjSumIf, j-th
There is L platform units, P in groupsIt is unit installed capacity, PkFor the theory of template processing machine in the group has work value and PkallIt is the model
Machine installed capacity and λsIt is the correction factor of the unit, then
Whole audience blower fan theory has work value and computation subunit, has work value and P for calculating whole audience blower fan theorytheo, whole audience blower fan quilt
M group of distribution, then
Hair has work value and computation subunit to whole audience blower fan in fact, and for calculating whole audience blower fan, hair has work value and P in factreal, whole audience blower fan
Number is N, PiFor the i-th Fans are sent out active in fact, then
Fitness computation subunit, for calculating fitness, formula is as follows:
10. system according to claim 8, it is characterised in that crossover operation unit includes:
Selection subelement, Crossover Strategy is matched for crossover operation selected part, and two random intersections are chosen in two individualities
Point, and the gene section in the middle of crosspoint, i.e. machine group # section are exchanged, if exchange part is identical, reselect;
Chaos operator subelement, for when needing to carry out adding chaos operator to process, the individuality for choosing in population 10% to be used
Chaos operator is processed, i.e., add a chaotic disturbance, the diversity of strengthening system at random to blower fan numbering is upper.
x0=0.1
xn+1=βi*xn*(1-xn)
β in formulaiTo correspond to the number of certain group;
Cycle count subelement, addition x is carried out for each section to selected legal chromosomenIt is circulated the side of counting
Method is processed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710002219.9A CN106897771B (en) | 2017-01-03 | 2017-01-03 | New energy sample board machine selection method and system based on chaotic genetic algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710002219.9A CN106897771B (en) | 2017-01-03 | 2017-01-03 | New energy sample board machine selection method and system based on chaotic genetic algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106897771A true CN106897771A (en) | 2017-06-27 |
CN106897771B CN106897771B (en) | 2020-03-06 |
Family
ID=59198288
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710002219.9A Active CN106897771B (en) | 2017-01-03 | 2017-01-03 | New energy sample board machine selection method and system based on chaotic genetic algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106897771B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107766941A (en) * | 2017-10-31 | 2018-03-06 | 天津大学 | A kind of facility site selecting method based on genetic algorithm |
CN113987936A (en) * | 2021-10-27 | 2022-01-28 | 中国人民解放军32801部队 | Equipment test resource overall allocation method based on chaotic genetic algorithm |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103268573A (en) * | 2013-05-09 | 2013-08-28 | 国家电网公司 | Wind power plant marker post draught fan selection method based on principal component analysis |
CN104200001A (en) * | 2014-07-23 | 2014-12-10 | 清华大学 | Selection method of marker post fan |
CN104901340A (en) * | 2015-05-18 | 2015-09-09 | 北京四方继保自动化股份有限公司 | Sample machine-based photovoltaic power adjusting method |
US20160171401A1 (en) * | 2014-12-11 | 2016-06-16 | Hao Wu | Layout optimization for interactional objects in a constrained geographical area |
CN106056312A (en) * | 2016-06-23 | 2016-10-26 | 国电南瑞科技股份有限公司 | Dynamic selection method for sample fan |
-
2017
- 2017-01-03 CN CN201710002219.9A patent/CN106897771B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103268573A (en) * | 2013-05-09 | 2013-08-28 | 国家电网公司 | Wind power plant marker post draught fan selection method based on principal component analysis |
CN104200001A (en) * | 2014-07-23 | 2014-12-10 | 清华大学 | Selection method of marker post fan |
US20160171401A1 (en) * | 2014-12-11 | 2016-06-16 | Hao Wu | Layout optimization for interactional objects in a constrained geographical area |
CN104901340A (en) * | 2015-05-18 | 2015-09-09 | 北京四方继保自动化股份有限公司 | Sample machine-based photovoltaic power adjusting method |
CN106056312A (en) * | 2016-06-23 | 2016-10-26 | 国电南瑞科技股份有限公司 | Dynamic selection method for sample fan |
Non-Patent Citations (2)
Title |
---|
李耀华 等: "用于优化风电场理论出力计算精度的样本风机动态选取方法", 《计算机科学与探索》 * |
王勃 等: "用于弃风电量计算的样板风机选择方法", 《电力系统及其自动化学报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107766941A (en) * | 2017-10-31 | 2018-03-06 | 天津大学 | A kind of facility site selecting method based on genetic algorithm |
CN113987936A (en) * | 2021-10-27 | 2022-01-28 | 中国人民解放军32801部队 | Equipment test resource overall allocation method based on chaotic genetic algorithm |
CN113987936B (en) * | 2021-10-27 | 2022-04-08 | 中国人民解放军32801部队 | Equipment test resource overall allocation method based on chaotic genetic algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN106897771B (en) | 2020-03-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106385025B (en) | A kind of distributed generation resource and interconnection multistage collaborative planning method | |
CN106951983A (en) | Injector performance Forecasting Methodology based on the artificial neural network using many parent genetic algorithms | |
CN106230026A (en) | The power distribution network bilayer coordinated planning method containing distributed power source analyzed based on temporal characteristics | |
CN108428045A (en) | A kind of distribution network operation health state evaluation method | |
CN107528350B (en) | A kind of wind power output typical scene generation method adapting to long -- term generation expansion planning | |
CN102929942A (en) | Social network overlapping community finding method based on ensemble learning | |
CN107248029A (en) | A kind of multi-target improvement differential evolution model of Land use structure type | |
CN105279615A (en) | Active power distribution network frame planning method on the basis of bi-level planning | |
CN104392394B (en) | A kind of detection method of micro-capacitance sensor energy storage nargin | |
CN109146123A (en) | A kind of multiple-energy-source comprehensive coordination effect evaluation method and system | |
CN107681655A (en) | A kind of tidal current energy generating field coordinated planning method | |
CN107169655A (en) | A kind of method and device of preferred power distribution network project compatibility | |
CN103778573A (en) | Classification method for areas with power supplied by power distribution network | |
CN104036364A (en) | Evaluation method for network structure level of power distribution network | |
CN104318317A (en) | Black-start scheme optimization method based on distributive integrated energy supply system | |
CN106845626A (en) | It is a kind of that application process is distributed rationally based on the DG for mixing the population that leapfrogs | |
CN106897771A (en) | A kind of new energy template processing machine site selecting method and system based on Chaos Genetic Algorithm | |
CN105488589A (en) | Genetic simulated annealing algorithm based power grid line loss management evaluation method | |
CN111553608A (en) | Benefit evaluation method for urban distribution network comprehensive energy system | |
CN105633971B (en) | A kind of intelligent distribution network probabilistic loadflow method based on imperial competition algorithm | |
CN106779361A (en) | The multi-objective optimization design of power method of grid-connected mixing renewable energy system | |
CN107784442A (en) | A kind of Assessment method of power system comprehensive benefit | |
CN109802634A (en) | A kind of intelligent O&M method and operational system of the photovoltaic plant based on big data | |
CN109299752A (en) | A kind of preferred method based on cluster with the waste and old power battery coincident indicator of comentropy | |
CN105701717B (en) | Power distribution network interaction scheme compilation method based on improved genetic algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: No.227, 2f, building 1, building materials City, Xisanqi, Haidian District, Beijing 100091 Applicant after: New energy Polytron Technologies Inc Address before: 100081, No. 19, building 68, College Road, Haidian District, Beijing, four, 407 Applicant before: Beijing Guo Nengxin system control technique company limited |
|
GR01 | Patent grant | ||
GR01 | Patent grant |