CN106897771B - New energy sample board machine selection method and system based on chaotic genetic algorithm - Google Patents
New energy sample board machine selection method and system based on chaotic genetic algorithm Download PDFInfo
- Publication number
- CN106897771B CN106897771B CN201710002219.9A CN201710002219A CN106897771B CN 106897771 B CN106897771 B CN 106897771B CN 201710002219 A CN201710002219 A CN 201710002219A CN 106897771 B CN106897771 B CN 106897771B
- Authority
- CN
- China
- Prior art keywords
- unit
- sample
- fan
- sample board
- calculating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000000739 chaotic effect Effects 0.000 title claims abstract description 30
- 230000002068 genetic effect Effects 0.000 title claims abstract description 24
- 238000010187 selection method Methods 0.000 title claims abstract description 11
- 238000000034 method Methods 0.000 claims description 34
- 210000000349 chromosome Anatomy 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 13
- 238000010248 power generation Methods 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 6
- 230000035772 mutation Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 claims description 5
- 108090000623 proteins and genes Proteins 0.000 claims description 5
- 230000007547 defect Effects 0.000 abstract description 2
- 230000005684 electric field Effects 0.000 description 20
- 230000006870 function Effects 0.000 description 5
- 230000033228 biological regulation Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
Images
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)
- Wind Motors (AREA)
- Control Of Positive-Displacement Air Blowers (AREA)
Abstract
The invention provides a new energy sample board machine selection method and system based on a chaotic genetic algorithm, which are used for judging whether a sample board machine needs to be replaced or not, dividing a fan into a plurality of large groups according to characteristics, and recalculating the sample board machine by using the chaotic genetic algorithm; and obtaining accurate meteorological prediction related data through a new sample board machine to obtain accurate active/reactive prediction data. The invention adopts the quantitative index to analyze the performance of the sample board machine aiming at the defects of the traditional subjective selection method of the sample board machine, and the sample board machine is replaced in real time through the chaotic genetic algorithm, so that the theoretical generated energy and the air abandoning amount of other fans of the wind power plant can be more accurately estimated through the proper sample board machine, and the invention has very important practical application significance.
Description
Technical Field
The invention belongs to the field of wind power, and particularly relates to a novel method and a system for analyzing the performance of a sample board machine of a wind power plant by adopting quantitative indexes and replacing the sample board machine in real time through a chaotic genetic algorithm.
Background
With the increasing installed capacity of wind power, the share of wind power in the power market gradually increases, and the state increasingly pays more attention to the management of wind power plant air volume related statistics and real-time control of the wind power plant. Therefore, the concept of a wind power plant sample machine is extended, the wind power plant sample machine is used as a basis, the fan processing characteristics are combined with an electric field model, the approximate theoretical active power of each fan and the wind power plant wind abandoning amount can be effectively estimated, and the method has very important practical significance.
At present, some relevant requirements are made on selection of a sample board machine of a wind power plant in China, and the method mainly comprises that the installed capacity of the sample board machine does not exceed 10% of the installed capacity of the wind power plant, and a plurality of sample board machines cannot be selected from the same cluster. In addition to this no more effective selection criteria or methods are given. The method for selecting the benchmark fan of the existing wind power plant mainly depends on subjective judgment of field operators of the wind power plant, or is selected after idealized modeling analysis is carried out through relevant modeling software, and the selection of a sample board machine cannot be objectively modified according to the health condition of a unit after the wind power plant is actually put into operation.
The existing fan sample board machine selection method leads the sample board machine to be selected and then rarely examines whether the sample board machine can represent the actual operation condition of the whole wind power plant, meanwhile, the actual working condition of the sample board machine changes along with use, and the influence of wind on the sample board machine in different seasons is inevitable variable quantity, so that the fixed fan sample board machine cannot completely reflect the operation state of the wind power plant in all wind power states, the estimation error of wind abandoning quantity of the wind power plant, the active/reactive regulation and control error of the wind power plant and the like are caused, further, the prediction of the power of the electric field is inaccurate, the active/reactive fluctuation of the electric field impacts the power grid, and the overall regulation and control of the power grid on wind power resources and the safe operation of the power grid.
Particularly, when the sample plate machine is in a maintenance state, the function of the sample plate machine is in an error state, which seriously affects the estimation of some electric field data and the regulation and control of an electric field fan based on the sample plate machine data.
Disclosure of Invention
In view of the above, the invention provides a new energy panel computer selection method and system based on a chaotic genetic algorithm, which are used for analyzing the performance of a panel computer by adopting a quantitative index aiming at the defects of the traditional subjective selection method of the panel computer, replacing the panel computer in real time through the chaotic genetic algorithm, and accurately estimating the theoretical generated energy and the air abandoning amount of other fans of a wind power plant through a proper panel computer, thereby having very important practical application significance.
In order to achieve the purpose, the technical scheme of the invention is realized as follows: a new energy sample plate machine selection method based on a chaotic genetic algorithm comprises the following steps:
(1) judging whether the sample plate machine needs to be replaced, if so, continuing the step (2);
(2) dividing the fans into a plurality of large groups according to characteristics, wherein the characteristics comprise fan unit characteristics, unit distribution areas and wind power influence areas;
(3) recalculating the sample plate machine by using a chaotic genetic algorithm;
(4) and obtaining accurate meteorological prediction related data through a new sample board machine to obtain accurate active/reactive prediction data.
Further, the method for judging whether the sample plate machine needs to be replaced comprises the following steps:
(11) judging whether the sample plate machine is overhauled, if so, carrying out the next step;
(12) judging whether the wind power plant is in a power limiting state, if so, returning to the step (11), and if not, performing the next step;
(13) judging whether the real active power of the sample board computer is matched with the wind power, if so, returning to the step (11), otherwise, performing the next step;
(14) and (5) judging whether the original sample board machine meets the calculation standard, if so, returning to the step (11), and otherwise, performing the step (2).
Further, the chaotic genetic algorithm in the step (3) comprises the following steps:
(31) and (3) encoding: selecting a sample plate machine for each group, wherein the serial numbers of the sample plate machines jointly form codes which are used as chromosomes;
(32) population initialization: the number of the clusters is defined as 2 total number of fans/number of the sample plates;
(33) calculating the fitness: calculating the fitness of the chromosome by using a selected sample plate machine as a basic theoretical activity;
(34) selecting operation: screening out individuals with high fitness as parents of the next generation by a roulette algorithm according to the fitness of the chromosome;
(35) and (3) cross operation: performing cross operation by using a chaos operator method to realize complete traversal;
(36) mutation operation: and (4) randomly selecting two corresponding points on the chromosome to carry out interchange operation.
Further, the specific method for calculating the fitness in step (33) is as follows:
(331) calculating the respective theoretical effective value and P of each groupjSumLet the jth group exist in L sets, PsFor the installed capacity of the unit, PkIs the sum of the theoretical effective values, P, of the plate formers in the groupkallFor the prototype machine, the sum of the installed capacities, lambdasIs the correction factor of the unit, then
(332) Calculating the theoretical active value and P of the whole field fantheoIf the whole fan is distributed with M groups
(333) Calculating the actual power value and P of the whole fanrealThe number of the whole fans is N and PiIf the ith fan actually generates active power, the method
(334) And calculating the fitness according to the following formula:
furthermore, the specific method of the interleaving operation in step (35) is as follows:
(351) the cross operation selection part matches with a cross strategy, two random cross points are selected from the two individuals, gene segments in the middle of the cross points, namely the unit number segments, are exchanged, and if the exchange parts are the same, the two random cross points are reselected;
(352) when the chaos operator is required to be added for processing, 10% of individuals in the population are selected to be processed by the chaos operator, namely, a chaos disturbance is randomly added to the fan number, and the diversity of the system is enhanced.
x0＝0.1
xn+1＝βi*xn*(1-xn)
Formula (III) βiThe number of the corresponding groups;
(353) adding x to each segment of the selected legal chromosomenAnd processing by a method of cycle counting.
In another aspect of the present invention, a new energy panel selecting system based on a chaotic genetic algorithm includes:
the judging module is used for judging whether the sample plate machine needs to be replaced or not;
the system comprises a group division module, a wind power generation module and a wind power generation module, wherein the group division module is used for dividing the wind power generation module into a plurality of large groups according to characteristics, and the characteristics comprise characteristics of a wind power generation unit, a unit distribution area and a wind power influence area;
the sample plate computer computing module is used for recalculating the sample plate computer by using a chaotic genetic algorithm;
and the prediction module is used for obtaining accurate meteorological prediction related data through a new sample board machine to obtain accurate active/reactive prediction data.
Further, the judging module includes:
the maintenance judging unit is used for judging whether the sample plate machine is maintained or not;
the power limiting judgment unit is used for judging whether the wind power plant is in a power limiting state;
the matching judgment unit is used for judging whether the real active power of the sample board machine is matched with the wind power;
and the calculation standard judging unit is used for judging whether the original sample plate machine meets the calculation standard.
Further, the sample board computer calculating module comprises:
an encoding unit: selecting a sample plate machine for each group, wherein the serial numbers of the sample plate machines jointly form codes which are used as chromosomes;
a population initialization unit: the number of the clusters is defined as 2 total number of fans/number of the sample plates;
a fitness calculating unit: calculating the fitness of the chromosome by using a selected sample plate machine as a basic theoretical activity;
a selection operation unit: screening out individuals with high fitness as parents of the next generation by a roulette algorithm according to the fitness of the chromosome;
a cross operation unit: performing cross operation by using a chaos operator method to realize complete traversal;
a mutation operation unit: and (4) randomly selecting two corresponding points on the chromosome to carry out interchange operation.
Still further, the calculating fitness unit includes:
a group theoretical active value and calculation subunit for calculating the respective theoretical active value and P of each groupjSumLet the jth group exist in L sets, PsFor the installed capacity of the unit, PkIs the sum of the theoretical effective values, P, of the plate formers in the groupkallFor the prototype machine, the sum of the installed capacities, lambdasIs the correction factor of the unit, then
A whole field fan theoretical active value and calculation subunit for calculating the whole field fan theoretical active value and PtheoIf the whole fan is distributed with M groups
The actual power value and calculation subunit of the whole-field fan is used for calculating the actual power value and P of the whole-field fanrealThe number of the whole fans is N and PiIf the ith fan actually generates active power, the method
The fitness meter operator unit is used for calculating the fitness, and the formula is as follows:
further, the interleaving operation unit includes:
the selection subunit is used for selecting a partial matching crossing strategy through crossing operation, selecting two random crossing points from the two individuals, interchanging gene segments in the middle of the crossing points, namely the unit number segments, and reselecting if the interchanging parts are the same;
and the chaotic operator subunit is used for selecting 10% of individuals in the population to use the chaotic operator for processing when the chaotic operator needs to be added for processing, namely, randomly adding a chaotic disturbance to the fan number, so that the diversity of the system is enhanced.
x0＝0.1
xn+1＝βi*xn*(1-xn)
Formula (III) βiThe number of the corresponding groups;
a cycle count subunit for adding x to each segment of the selected legal chromosomenAnd processing by a method of cycle counting.
Compared with the prior art, the new energy sample board machine selection method and system based on the chaotic genetic algorithm have the beneficial effects that:
the invention combines the related national standards of the sample plate machine to establish a set of feasible sample plate machine selection method and related algorithms, quantificationally operates the performance of the sample plate machine to get out of the way, and can objectively evaluate the quality of the sample plate machine.
According to the invention, all fans of the electric field are reselected at the stage of unlimited electricity of wind power, the sample board machine which can best reflect the actual operation condition of the electric field in the wind power state in the period of time is selected, the current operation condition of the wind power plant can be objectively and effectively reflected to the greatest extent, artificial subjective operation is avoided, the representativeness of the sample board machine is effectively improved, meanwhile, the effectiveness of the sample board machine is reversely verified by counting the real-time electric quantity of each fan of the electric field, and effective data support is provided for the reselection of the sample board machine in the later period.
The invention can minimize the adverse effect caused by the selection of the prior fan fixing sample plate machine. The operation reliability of other systems based on the relevant data of the wind power plant sample board computer is effectively improved, and more accurate data support is provided for wind power prediction and active/reactive control of the wind power plant. The wind resource utilization rate and the wind farm operation safety level are improved to a certain extent. The wind power utilization rate is improved, and the safety and stability level of the electric field is improved.
Drawings
FIG. 1 is a schematic flow diagram of the present invention.
Detailed Description
It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.
As shown in fig. 1, the specific implementation process of the present invention is:
1. whether the sample plate machine is in a maintenance state
When the sample plate machine is in a maintenance state, the function of the sample plate machine is in an error state, and the estimation of some electric field data and the regulation and control of an electric field fan based on the sample plate machine data are seriously influenced. Thus requiring recalculation of the template machine.
2. Whether the wind power plant is in a power limiting state
And whether the full-field active target value of the wind power plant is larger than the current theoretical active value of the electric field calculated by a sample board computer or other ways.
When the full-field active target value is larger than the current theoretical active value of the electric field, the system is in a non-power-limiting state.
And when the full-field active target value is less than the current theoretical active value of the electric field, the system is in a power limiting state.
The fans are in a free power generation state in an unlimited power state, the generated energy of the fans is mainly influenced by wind power and the state of a unit, no human intervention exists, and the fans in the state can reflect the actual operation condition of an electric field.
3. Whether the actual power of the sample plate machine is matched with the wind power
The sample board machine is set to be in an own power generation mode through the electric field active and reactive control system, namely the sample board machine is only influenced by wind power and the state of the unit, and is not manually interfered. Meanwhile, the active power has certain time lag relative to the wind power. The lag time is determined by the fan characteristics and the wind speed.
The actual power of the fan sample machine is matched with the fan, and then the working state of the sample machine is good. Otherwise, the sample plate machine is replaced due to poor working condition.
4. Whether the original sample plate machine meets the calculation standard
And whether the active power generated by the sample board machine in the acquired wind power state accords with a wind power active comparison curve or not. The comparison curve can show different performances along with different fan manufacturers, different fan models and different fan ages.
5. Grouping of fans
The fan grouping means that all fans of the electric field are divided into a plurality of large groups according to characteristics of fan units, unit distribution areas, wind power influence areas and the like. The actual power generation of each fan in the cluster can be approximately regarded as an approximate value of the actual power generation of the benchmark fan in the cluster, and the cluster can correct the coefficient lambdakAnd (5) modifying.
6. Genetic algorithm
The genetic algorithm is a process for searching an optimal solution by simulating natural evolution, continuous evolution screening is carried out by simulating the principle that an individual with high fitness can inherit, and the genetic algorithm has strong searching capability and robustness.
a) The coding adopts an integer combination coding mode for coding.
The chromosome is divided into n sections, wherein n is the number of the selected sample plate machines, and each section represents the number of the fan.
The electric field is provided with 30 fans which are divided into three groups (the No. 1-10 machine set is a group, the No. 11-20 machine set is a group 2, and the No. 21-30 machine set is a group 3), 3 fans are selected as sample boards, and a 6-digit number formed by one serial number is selected from each group to be a legal chromosome.
b) And (3) population initialization, wherein the population initialization is not too small, the too small population initialization can cause the algorithm to not find the global optimal solution, the too large population initialization can cause the increase of the calculation time and the slow evolution speed, and all chromosomes contain all fans. The population number here is defined as 2 × total number of fans/number of sample plates.
c) The fitness function is the fitness function of the fan
Wherein P istheoFor the sum of theoretical active values, P, of the full-field fan at the current momentrealAnd the sum of the actual power values of the whole wind turbine at the current moment is generated.
Memory cardThe number of the field fans is N and PiIf the ith fan actually generates active power, the method
Recording that the full-field fan is distributed with M groups, the equipment state in each group is similar, PjSumFor the theoretical sum of merit for this group, then
Noting that the jth group exists in L sets, PsFor the installed capacity of the unit, PkFor theoretical active summation of the plate formers in the cluster, PkallFor the prototype machine, the sum of the installed capacities, lambdasIs the correction factor of the unit, then
The coefficient represents the theoretical active power prediction accuracy based on the sample plate machine, the closer the coefficient is to 0, the better the effect of the sample plate machine is, and when f is less than 3%, the fan sample plate machine is considered to be qualified in selection. The coefficient can be properly expanded when the wind power plant is in an unstable wind area.
The coefficient is effective only when the electric field is in a non-electricity-limiting state, and the real active power of the fan is limited under the electricity-limiting condition of the electric field, so the coefficient cannot reflect the advantages and disadvantages selected by the sample plate machine.
d) Selection operation
And determining the fitness of the chromosome in the population according to the fitness function. And screening out the individuals with high fitness as parents of the next generation by a roulette algorithm.
e) Crossover operation
Ordinary interleaving operations cannot avoid the possibility of incomplete traversal. Therefore, the method of the genetic algorithm adopting the chaos operator carries out the cross operation on the cross operation. And the genetic process is ensured to find the global optimum point, and the local optimum point is avoided.
And the cross operation selection part matches with a cross strategy. Firstly, two random cross points are selected from two individuals, gene segments (namely unit numbers) in the middle of the cross points are exchanged, and if the exchange parts are the same, the two random cross points are reselected.
When the chaos operator is required to be added for processing, 10% of individuals in the population are selected to be processed by the chaos operator, namely, a chaos disturbance is randomly added to the fan number, and the diversity of the system is enhanced.
x0＝0.1
xn+1＝βi*xn*(1-xn)
Formula (III) βiTo correspond to the number of a certain cluster
Adding x to each segment of the selected legal chromosomenAnd processing by a method of cycle counting.
f) Mutation operation
The variation operation can increase the population diversity, create new individuals and have certain inhibition capacity on the local optimal solution to a certain extent. The mutation operation adopts the method of randomly selecting and exchanging corresponding points on the chromosome.
7. Accurate weather prediction related data and accurate active/reactive power prediction data
The meteorological prediction related data calculated by the sample plate computer comprise: abandon the amount of wind, actual amount of wind etc. calculate active/reactive relevant data through the proof board machine and include: active amount, passive amount, etc. at the next moment.
The basic principles, main features, and embodiments of the present invention have been described above, but the present invention is not limited to the above-described implementation process, and various changes and modifications can be made without departing from the spirit and scope of the present invention. Therefore, unless such changes and modifications depart from the scope of the present invention, they should be construed as being included therein.
Claims (6)
1. A new energy sample plate machine selection method based on a chaotic genetic algorithm is characterized by comprising the following steps:
(1) judging whether the sample plate machine needs to be replaced, if so, continuing the step (2);
(2) dividing the fans into a plurality of large groups according to characteristics, wherein the characteristics comprise fan unit characteristics, unit distribution areas and wind power influence areas;
(3) recalculating the sample board machine by using a chaotic genetic algorithm according to the group division;
(4) obtaining accurate meteorological prediction related data through a new sample board machine to obtain accurate active/reactive prediction data;
the chaotic genetic algorithm in the step (3) comprises the following processes:
(31) and (3) encoding: selecting a sample plate machine for each group, wherein the serial numbers of the sample plate machines jointly form codes which are used as chromosomes;
(32) population initialization: the number of the clusters is defined as 2 total number of fans/number of the sample plates;
(33) calculating the fitness: calculating the fitness of the chromosome by using a selected sample plate machine as a basic theoretical activity;
(34) selecting operation: screening out individuals with high fitness as parents of the next generation by a roulette algorithm according to the fitness of the chromosome;
(35) and (3) cross operation: performing cross operation by using a chaos operator method to realize complete traversal;
(36) mutation operation: randomly selecting two corresponding points on a chromosome to carry out interchange operation;
the specific method for calculating the fitness in the step (33) is as follows:
(331) calculating the respective theoretical effective value and P of each groupjSumLet the jth group exist in L sets, PsFor the installed capacity of the unit, PkIs the sum of the theoretical effective values, P, of the plate formers in the groupkallFor the prototype machine, the sum of the installed capacities, lambdasIs the correction factor of the unit, then
(332) Calculating the theoretical active value and P of the whole field fantheoIf the whole fan is distributed with M groups
(333) Calculating the actual power value and P of the whole fanrealThe number of the whole fans is N and PiIf the ith fan actually generates active power, the method
(334) And calculating the fitness according to the following formula:
2. the method of claim 1, wherein the step (1) of determining whether the sample plate replacing process is required is performed by:
(11) judging whether the sample plate machine is overhauled, if so, carrying out the next step;
(12) judging whether the wind power plant is in a power limiting state, if so, returning to the step (11), and if not, performing the next step;
(13) judging whether the real active power of the sample board computer is matched with the wind power, if so, returning to the step (11), otherwise, performing the next step;
(14) and (5) judging whether the original sample board machine meets the calculation standard, if so, returning to the step (11), and otherwise, performing the step (2).
3. The method of claim 1, wherein the specific method of the interleaving operation of step (35) is as follows:
(351) the cross operation selection part matches with a cross strategy, two random cross points are selected from the two individuals, gene segments in the middle of the cross points, namely the unit number segments, are exchanged, and if the exchange parts are the same, the two random cross points are reselected;
(352) when the chaotic operator is required to be added for processing, 10% of individuals in the population are selected to be processed by the chaotic operator, namely, a chaotic disturbance is randomly added to the fan number, so that the diversity of the system is enhanced;
x0＝0.1
xn+1＝βi*xn*(1-xn)
formula (III) βiThe number of the corresponding groups;
(353) adding x to each segment of the selected legal chromosomenAnd processing by a method of cycle counting.
4. A new energy sample board machine selection system based on a chaotic genetic algorithm is characterized by comprising:
the judging module is used for judging whether the sample plate machine needs to be replaced or not;
the system comprises a group division module, a wind power generation module and a wind power generation module, wherein the group division module is used for dividing the wind power generation module into a plurality of large groups according to characteristics, and the characteristics comprise characteristics of a wind power generation unit, a unit distribution area and a wind power influence area;
the sample board computer calculation module is used for recalculating the sample board computer by using a chaotic genetic algorithm according to the group division;
the forecasting module is used for obtaining accurate meteorological forecasting related data through a new sample board machine to obtain accurate active/reactive forecasting data;
the sample board computer calculation module comprises:
an encoding unit: selecting a sample plate machine for each group, wherein the serial numbers of the sample plate machines jointly form codes which are used as chromosomes;
a population initialization unit: the number of the clusters is defined as 2 total number of fans/number of the sample plates;
a fitness calculating unit: calculating the fitness of the chromosome by using a selected sample plate machine as a basic theoretical activity;
a selection operation unit: screening out individuals with high fitness as parents of the next generation by a roulette algorithm according to the fitness of the chromosome;
a cross operation unit: performing cross operation by using a chaos operator method to realize complete traversal;
a mutation operation unit: randomly selecting two corresponding points on a chromosome to carry out interchange operation;
the calculating fitness unit comprises:
a group theoretical active value and calculation subunit for calculating the respective theoretical active value and P of each groupjSumLet the jth group exist in L sets, PsFor the installed capacity of the unit, PkIs the sum of the theoretical effective values, P, of the plate formers in the groupkallFor the prototype machine, the sum of the installed capacities, lambdasIs the correction factor of the unit, then
A whole field fan theoretical active value and calculation subunit for calculating the whole field fan theoretical active value and PtheoIf the whole fan is distributed with M groups
The actual power value and calculation subunit of the whole-field fan is used for calculating the actual power value and P of the whole-field fanrealThe number of the whole fans is N and PiIf the ith fan actually generates active power, the method
The fitness meter operator unit is used for calculating the fitness, and the formula is as follows:
5. the system of claim 4, wherein the determining module comprises:
the maintenance judging unit is used for judging whether the sample plate machine is maintained or not;
the power limiting judgment unit is used for judging whether the wind power plant is in a power limiting state;
the matching judgment unit is used for judging whether the real active power of the sample board machine is matched with the wind power;
and the calculation standard judging unit is used for judging whether the original sample plate machine meets the calculation standard.
6. The system of claim 4, wherein the interleaving unit comprises:
the selection subunit is used for selecting a partial matching crossing strategy through crossing operation, selecting two random crossing points from the two individuals, interchanging gene segments in the middle of the crossing points, namely the unit number segments, and reselecting if the interchanging parts are the same;
the chaotic operator subunit is used for selecting 10% of individuals in the population to use the chaotic operator for processing when the chaotic operator needs to be added for processing, namely, randomly adding a chaotic disturbance to the fan number to enhance the diversity of the system;
x0＝0.1
xn+1＝βi*xn*(1-xn)
formula (III) βiThe number of the corresponding groups;
a cycle count subunit for adding x to each segment of the selected legal chromosomenAnd processing by a method of cycle counting.
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 CN106897771A (en) | 2017-06-27 |
| CN106897771B true 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) |
Families Citing this family (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 |
| 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 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268573B (en) * | 2013-05-09 | 2016-02-24 | 国家电网公司 | A kind of wind energy turbine set mark post ventilator selection method based on principal component analysis (PCA) |
| CN104200001B (en) * | 2014-07-23 | 2017-09-22 | 清华大学 | The choosing method of mark post blower 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 |
| CN106056312B (en) * | 2016-06-23 | 2019-08-16 | 国电南瑞科技股份有限公司 | A kind of sample blower choice of dynamical method |
-
2017
- 2017-01-03 CN CN201710002219.9A patent/CN106897771B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106897771A (en) | 2017-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106529731A (en) | Regional power grid photovoltaic power station cluster division method | |
| CN108428017A (en) | Wind power interval prediction method based on core extreme learning machine quantile estimate | |
| CN112186761B (en) | Wind power scene generation method and system based on probability distribution | |
| CN113205210B (en) | Wind power plant wind speed and power prediction method, system and equipment for complex terrain and storage medium | |
| CN115796393B (en) | Energy management optimization method, system and storage medium based on multi-energy interaction | |
| CN107679687A (en) | A kind of photovoltaic output modeling method and Generation System Reliability appraisal procedure | |
| CN106875037A (en) | Wind-force Forecasting Methodology and device | |
| CN106684885A (en) | Multi-scene analysis-based reactive power optimization method for power distribution network of wind power generation set | |
| CN112307672A (en) | BP neural network short-term wind power prediction method based on cuckoo algorithm optimization | |
| CN111709569A (en) | Method and device for predicting and correcting output power of wind power plant | |
| CN110009181A (en) | Distribution network transform measure and mistake load figureofmerit relevance method for digging and device | |
| CN110263998A (en) | Multi-source numerical weather forecast set bilayer modification method | |
| CN106897771B (en) | New energy sample board machine selection method and system based on chaotic genetic algorithm | |
| CN109886560A (en) | Distribution network transform measure and rate of qualified voltage index relevance method for digging and device | |
| CN115759467A (en) | Time-division integrated learning photovoltaic prediction method for error correction | |
| CN117195449A (en) | Wind farm arrangement optimization method, device, equipment and medium | |
| CN111612227A (en) | Load prediction method based on K-means clustering and bat optimization neural network | |
| CN113610285A (en) | Power prediction method for distributed wind power | |
| CN111950131B (en) | Wind power plant output equivalent aggregation model construction method considering electricity limiting factors | |
| CN109615142A (en) | A kind of wind farm wind velocity combination forecasting method based on wavelet analysis | |
| CN102539823A (en) | Method for forecasting wind speed distribution of WTG (wind turbine generator) | |
| CN117371581A (en) | New energy generated power prediction method, device and storage medium | |
| CN110400233A (en) | A kind of power distribution network loss electricity calculating method and device neural network based | |
| CN112994079A (en) | Wind power plant output sequence generation method and system | |
| CN106251035A (en) | The data processing method calculated for the project indicator and device |
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 |