CN114626498B - Photovoltaic operation and maintenance data reconstruction method based on evolution optimization - Google Patents
Photovoltaic operation and maintenance data reconstruction method based on evolution optimization Download PDFInfo
- Publication number
- CN114626498B CN114626498B CN202210196364.6A CN202210196364A CN114626498B CN 114626498 B CN114626498 B CN 114626498B CN 202210196364 A CN202210196364 A CN 202210196364A CN 114626498 B CN114626498 B CN 114626498B
- Authority
- CN
- China
- Prior art keywords
- individual
- population
- lph
- observation matrix
- photovoltaic operation
- 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
- 238000012423 maintenance Methods 0.000 title claims abstract description 32
- 238000005457 optimization Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 title claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 47
- 238000009396 hybridization Methods 0.000 claims abstract description 12
- 230000006978 adaptation Effects 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 10
- 230000035772 mutation Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 238000007418 data mining Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003745 diagnosis Methods 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
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (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)
- Photovoltaic Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a photovoltaic operation and maintenance data reconstruction method based on evolution optimization. The invention applies an evolution optimization algorithm to optimally design an observation matrix in the reconstruction of photovoltaic operation data. In the optimization process, photovoltaic operation and maintenance data are input, parameters of an evolution optimization algorithm are set, populations are randomly generated, variation coefficients and hybridization rates are adjusted adaptively, mutation and hybridization operations are executed to generate new individuals, a combined reverse learning strategy is utilized to generate a reverse population, and the current population and the reverse population are subjected to competition to select a new generation population, so that an observation matrix for reconstructing the photovoltaic operation and maintenance data is optimized. The invention can improve the reconstruction efficiency of the photovoltaic operation and maintenance data.
Description
Technical Field
The invention relates to the field of data mining, in particular to a photovoltaic operation and maintenance data reconstruction method based on evolution optimization.
Background
With the rapid development of photovoltaic power generation technology, the operation and maintenance technology of photovoltaic power stations is also continuously enhanced. The operation and maintenance of photovoltaic power plants has gradually been digitalized. With the advancement of the digitizing process, the morphology of the photovoltaic operation and maintenance data is more and more abundant, and the capacity of the data is also more and more large. The photovoltaic operation and maintenance data reflects the dynamic state of the photovoltaic power plant at various levels during operation. Accordingly, technicians are increasingly focusing on the analysis of photovoltaic operation and maintenance data. In recent years, data mining techniques have penetrated deep into the analysis of photovoltaic operation and maintenance data. By utilizing the data mining technology, technicians can mine potential operation rules of the photovoltaic power station from the photovoltaic operation and maintenance data, so that decision support is provided for operation and maintenance of the photovoltaic power station.
The reconstruction of photovoltaic operation and maintenance data is a key technology in photovoltaic operation and maintenance data analysis, and has very important roles in compression and denoising of photovoltaic operation and maintenance data and fault diagnosis of photovoltaic equipment. In recent years, compressed sensing technology has achieved some viable results in the reconstruction of photovoltaic operational data. However, when reconstruction of photovoltaic operation and maintenance data is achieved using compressed sensing techniques, the optimal design of the observation matrix can greatly affect the reconstruction efficiency of the photovoltaic operation and maintenance data [ Cui Zhihua, zhang Chunmei, shi Zhentao, niu Yun ] the observation matrix optimization algorithm based on the bat algorithm [ J ]. Control and decision, 2018,33 (07): 1341-1344]. How to optimally design an effective observation matrix is a difficult problem in reconstruction of photovoltaic operation data. The defect of insufficient precision easily occurs when the traditional optimization design method of the observation matrix is applied to reconstruction of photovoltaic operation and maintenance data.
Disclosure of Invention
The invention provides a photovoltaic operation and maintenance data reconstruction method based on evolution optimization, which overcomes the defect that insufficient precision is easy to occur when the conventional optimization design method of an observation matrix is applied to the reconstruction of photovoltaic operation and maintenance data to a certain extent.
The technical scheme of the invention is as follows: a photovoltaic operation and maintenance data reconstruction method based on evolution optimization comprises the following steps:
step 1, inputting photovoltaic operation and maintenance data LData;
Step 2, inputting sparse transform basis (LPS);
Step 3, inputting the length LDM of the observed data;
Step 4, inputting population scale LPK, and enabling maximum iteration number to be LMaxT;
step 5, setting iteration times t=0;
Step 6, randomly generating a population LDP= { LX 1,LX2,...,LXki,...,LXLPK }, wherein LX ki represents a kth individual in the population, and DK optimal design parameters of an observation matrix LPH are stored in the individual LX ki; individual subscript ki=1, 2, LPK; the number dk=ldn×ldm of optimal design parameters of the observation matrix LPH; wherein, LDN is the length of photovoltaic operation data LData;
step 7, calculating the adaptation value of each individual in the population;
step 8, finding out the individual with the minimum adaptation value from the population and marking the individual as the optimal individual MinLX;
Step 9, setting a variation coefficient LF ki =rand (0, 1), and a hybridization rate LCR ki =rand (0, 1); wherein rand represents a function that generates random real numbers between [0,1 ];
Step 10, calculating a current sinusoidal variation amplitude value SinLF according to formula (1):
wherein sin represents a sine function, and pi represents a circumference ratio;
Step 11, calculating the current variation coefficient UF ki according to formula (2):
Wherein lpt is a random real number between [0,1 ]; sw1 is a random real number between [0,0.5 ];
step 12, calculating the current sine hybridization amplitude value SinCR according to formula (3):
Step 13, calculating the current hybridization rate UCR ki according to the formula (4):
Wherein upr is a random real number between [0,1 ]; sw2 is a random real number between [0,0.5 ];
Step 14, generating variant LM ki according to formula (5):
LMki＝LXr1+UFki×(LXr2-LXr3) (5)
Wherein LX r1,LXr2 and LX r3 represent three individuals randomly selected from a population;
step 15, generating hybrid LC ki according to formula (6):
Wherein LC ki,mj represents the mj-th parameter of the observation matrix LPH stored in hybrid LC ki; LM ki,mj represents the mj-th parameter of the observation matrix LPH stored in variant LM ki; LX ki,mj denotes the mj-th parameter of the observation matrix LPH stored in the individual LX ki; dimension subscript mj=1, 2,., DK;
Step 16, calculating the adaptation value of the hybrid LC ki;
Step 17, replacing individual LX ki with hybrid individual LC ki in the population if the fitness value of hybrid individual LC ki is less than the fitness value of individual LX ki, otherwise leaving individual LX ki unchanged;
Step 18, setting LF ki＝UFki if the fitness value of the hybrid individual LC ki is less than the fitness value of the individual LX ki, otherwise keeping LF ki unchanged;
Step 19, setting LCR ki＝UCRki if the fitness value of the hybrid individual LC ki is less than the fitness value of the individual LX ki, otherwise, keeping LCR ki unchanged;
step 20, calculating the reverse learning rate OLR according to formula (7):
step 21, sorting all individuals in the population from small to large according to the adaptation value, and putting the previous OLN individuals in the sorted population into a set PLO, wherein oln=ceil (olr×lpk), and ceil represents an upward rounding function;
step 22, generating a reverse population PEO according to equation (8):
Wherein OX ti represents the ti-th inverted individual in the inverted population of PEO; OX ti,mj represents the mj-th parameter of the observation matrix LPH stored in the inverse individual OX ti; minLX mj denotes the mj-th parameter of the observation matrix LPH stored in the optimal individual MinLX; LO ti,mj represents the mj-th parameter of the observation matrix LPH stored in the ti-th individual in the set PLO; PEA mj represents the lower bound of the individuals in the collection PLO; PEB mj represents the upper bound of the individuals in the collection PLO; OW represents a random real number between [0,1 ]; reverse individual subscript ti=1, 2,., OLN;
Step 23, selecting the previous LPK individuals with the minimum adaptation value from the union of the population LDP and the reverse population PEO to form a new generation population;
Step 24, finding out the individual with the minimum adaptation value from the new generation population and marking the individual as the optimal individual MinLX;
Step 25, setting the iteration times t=t+1; if the iteration number t is smaller than the maximum iteration number LMaxT, the step 10 is switched to, otherwise, the step 26 is switched to;
And 26, extracting DK parameters of an observation matrix LPH from the optimal individual MinLX, constructing the observation matrix LPH by using the obtained DK parameters, and reconstructing the photovoltaic operation data LData by using an orthogonal matching pursuit algorithm based on the sparse transform basis LPS and the obtained observation matrix LPH.
Aiming at the defect that insufficient precision easily occurs when the traditional optimization design method of the observation matrix is applied to the reconstruction of photovoltaic operation and maintenance data, the invention applies an evolution optimization algorithm to optimally design the observation matrix in the reconstruction of photovoltaic operation and maintenance data. In the evolution optimization algorithm, the periodicity of the sine function is utilized to adaptively adjust the variation coefficient and the hybridization rate, so that the balance of global search and local search is realized, and the optimization efficiency of the algorithm is improved. In addition, in the optimization process, a reverse population is generated by utilizing a combined reverse learning strategy, the current population and the reverse population are subjected to competition, a new generation of population is selected, the optimization performance of an algorithm is enhanced, and therefore the reconstruction accuracy of photovoltaic operation and maintenance data is improved.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further specifically described below through examples and with reference to the accompanying drawings.
Examples:
in this embodiment, with reference to the accompanying drawings, the following steps are implemented in the embodiment of the present invention:
step 1, inputting photovoltaic operation and maintenance data LData; the photovoltaic operation and maintenance data are photovoltaic power generation power data;
step2, inputting a sparse transform basis (LPS) as an identity matrix;
step 3, inputting the length ldm=64 of the observed data;
Step 4, inputting population scale lpk=50, and maximum iteration number LMaxT =3000;
step 5, setting iteration times t=0;
Step 6, randomly generating a population LDP= { LX 1,LX2,...,LXki,...,LXLPK }, wherein LX ki represents a kth individual in the population, and DK optimal design parameters of an observation matrix LPH are stored in the individual LX ki; individual subscript ki=1, 2, LPK; the number dk=ldn×ldm of optimal design parameters of the observation matrix LPH; wherein ldn=256 is the length of the photovoltaic operation data LData;
Step 7, calculating the adaptation value of each individual in the population; the adaptive value calculating method comprises the following steps: for the kth individual LX ki in the population, firstly extracting DK parameters of an observation matrix LPH from the individual LX ki, then constructing the observation matrix LPH by using the obtained DK parameters, compressing photovoltaic operation data LData into observation data GLD with the length of LDM by using a sparse transform basis LPS and the obtained observation matrix LPH, then reconstructing the observation data GLD into data YLD by using an orthogonal matching pursuit algorithm based on the observation matrix LPH and the sparse transform basis LPS, calculating an error Err between the data YLD and the photovoltaic operation data LData, and setting an adaptation value of the individual LX ki as Err;
step 8, finding out the individual with the minimum adaptation value from the population and marking the individual as the optimal individual MinLX;
Step 9, setting a variation coefficient LF ki =rand (0, 1), and a hybridization rate LCR ki =rand (0, 1); wherein rand represents a function that generates random real numbers between [0,1 ];
Step 10, calculating a current sinusoidal variation amplitude value SinLF according to formula (1):
wherein sin represents a sine function, and pi represents a circumference ratio;
Step 11, calculating the current variation coefficient UF ki according to formula (2):
Wherein lpt is a random real number between [0,1 ]; sw1 is a random real number between [0,0.5 ];
step 12, calculating the current sine hybridization amplitude value SinCR according to formula (3):
Step 13, calculating the current hybridization rate UCR ki according to the formula (4):
Wherein upr is a random real number between [0,1 ]; sw2 is a random real number between [0,0.5 ];
Step 14, generating variant LM ki according to formula (5):
LMki＝LXr1+UFki×(LXr2-LXr3) (5)
Wherein LX r1,LXr2 and LX r3 represent three individuals randomly selected from a population;
step 15, generating hybrid LC ki according to formula (6):
Wherein LC ki,mj represents the mj-th parameter of the observation matrix LPH stored in hybrid LC ki; LM ki,mj represents the mj-th parameter of the observation matrix LPH stored in variant LM ki; LX ki,mj denotes the mj-th parameter of the observation matrix LPH stored in the individual LX ki; dimension subscript mj=1, 2,., DK;
Step 16, calculating the adaptation value of the hybrid LC ki;
Step 17, replacing individual LX ki with hybrid individual LC ki in the population if the fitness value of hybrid individual LC ki is less than the fitness value of individual LX ki, otherwise leaving individual LX ki unchanged;
Step 18, setting LF ki＝UFki if the fitness value of the hybrid individual LC ki is less than the fitness value of the individual LX ki, otherwise keeping LF ki unchanged;
Step 19, setting LCR ki＝UCRki if the fitness value of the hybrid individual LC ki is less than the fitness value of the individual LX ki, otherwise, keeping LCR ki unchanged;
step 20, calculating the reverse learning rate OLR according to formula (7):
step 21, sorting all individuals in the population from small to large according to the adaptation value, and putting the previous OLN individuals in the sorted population into a set PLO, wherein oln=ceil (olr×lpk), and ceil represents an upward rounding function;
step 22, generating a reverse population PEO according to equation (8):
Wherein OX ti represents the ti-th inverted individual in the inverted population of PEO; OX ti,mj represents the mj-th parameter of the observation matrix LPH stored in the inverse individual OX ti; minLX mj denotes the mj-th parameter of the observation matrix LPH stored in the optimal individual MinLX; LO ti,mj represents the mj-th parameter of the observation matrix LPH stored in the ti-th individual in the set PLO; PEA mj represents the lower bound of the individuals in the collection PLO; PEB mj represents the upper bound of the individuals in the collection PLO; OW represents a random real number between [0,1 ]; reverse individual subscript ti=1, 2,., OLN;
Step 23, selecting the previous LPK individuals with the minimum adaptation value from the union of the population LDP and the reverse population PEO to form a new generation population;
Step 24, finding out the individual with the minimum adaptation value from the new generation population and marking the individual as the optimal individual MinLX;
Step 25, setting the iteration times t=t+1; if the iteration number t is smaller than the maximum iteration number LMaxT, the step 10 is switched to, otherwise, the step 26 is switched to;
And 26, extracting DK parameters of an observation matrix LPH from the optimal individual MinLX, constructing the observation matrix LPH by using the obtained DK parameters, and reconstructing the photovoltaic operation data LData by using an orthogonal matching pursuit algorithm based on the sparse transform basis LPS and the obtained observation matrix LPH.
Claims (1)
1. The photovoltaic operation and maintenance data reconstruction method based on evolution optimization is characterized by comprising the following steps of:
step 1, inputting photovoltaic operation and maintenance data LData;
Step 2, inputting sparse transform basis (LPS);
Step 3, inputting the length LDM of the observed data;
Step 4, inputting population scale LPK, and enabling maximum iteration number to be LMaxT;
step 5, setting iteration times t=0;
Step 6, randomly generating a population LDP= { LX 1,LX2,...,LXki,...,LXLPK }, wherein LX ki represents a kth individual in the population, and DK optimal design parameters of an observation matrix LPH are stored in the individual LX ki; individual subscript ki=1, 2, LPK; the number dk=ldn×ldm of optimal design parameters of the observation matrix LPH; wherein, LDN is the length of photovoltaic operation data LData;
step 7, calculating the adaptation value of each individual in the population;
step 8, finding out the individual with the minimum adaptation value from the population and marking the individual as the optimal individual MinLX;
Step 9, setting a variation coefficient LF ki =rand (0, 1), and a hybridization rate LCR ki =rand (0, 1); wherein rand represents a function that generates random real numbers between [0,1 ];
Step 10, calculating a current sinusoidal variation amplitude value SinLF according to formula (1):
wherein sin represents a sine function, and pi represents a circumference ratio;
Step 11, calculating the current variation coefficient UF ki according to formula (2):
Wherein lpt is a random real number between [0,1 ]; sw1 is a random real number between [0,0.5 ];
step 12, calculating the current sine hybridization amplitude value SinCR according to formula (3):
Step 13, calculating the current hybridization rate UCR ki according to the formula (4):
Wherein upr is a random real number between [0,1 ]; sw2 is a random real number between [0,0.5 ];
Step 14, generating variant LM ki according to formula (5):
LMki＝LXr1+UFki×(LXr2-LXr3) (5)
Wherein LX r1,LXr2 and LX r3 represent three individuals randomly selected from a population;
step 15, generating hybrid LC ki according to formula (6):
Wherein LC ki,mj represents the mj-th parameter of the observation matrix LPH stored in hybrid LC ki; LM ki,mj represents the mj-th parameter of the observation matrix LPH stored in variant LM ki; LX ki,mj denotes the mj-th parameter of the observation matrix LPH stored in the individual LX ki; dimension subscript mj=1, 2,., DK;
Step 16, calculating the adaptation value of the hybrid LC ki;
Step 17, replacing individual LX ki with hybrid individual LC ki in the population if the fitness value of hybrid individual LC ki is less than the fitness value of individual LX ki, otherwise leaving individual LX ki unchanged;
Step 18, setting LF ki＝UFki if the fitness value of the hybrid individual LC ki is less than the fitness value of the individual LX ki, otherwise keeping LF ki unchanged;
Step 19, setting LCR ki＝UCRki if the fitness value of the hybrid individual LC ki is less than the fitness value of the individual LX ki, otherwise, keeping LCR ki unchanged;
step 20, calculating the reverse learning rate OLR according to formula (7):
step 21, sorting all individuals in the population from small to large according to the adaptation value, and putting the previous OLN individuals in the sorted population into a set PLO, wherein oln=ceil (olr×lpk), and ceil represents an upward rounding function;
step 22, generating a reverse population PEO according to equation (8):
Wherein OX ti represents the ti-th inverted individual in the inverted population of PEO; OX ti,mj represents the mj-th parameter of the observation matrix LPH stored in the inverse individual OX ti; minLX mj denotes the mj-th parameter of the observation matrix LPH stored in the optimal individual MinLX; LO ti,mj represents the mj-th parameter of the observation matrix LPH stored in the ti-th individual in the set PLO; PEA mj represents the lower bound of the individuals in the collection PLO; PEB mj represents the upper bound of the individuals in the collection PLO; OW represents a random real number between [0,1 ]; reverse individual subscript ti=1, 2,., OLN;
Step 23, selecting the previous LPK individuals with the minimum adaptation value from the union of the population LDP and the reverse population PEO to form a new generation population;
Step 24, finding out the individual with the minimum adaptation value from the new generation population and marking the individual as the optimal individual MinLX;
Step 25, setting the iteration times t=t+1; if the iteration number t is smaller than the maximum iteration number LMaxT, the step 10 is switched to, otherwise, the step 26 is switched to;
And 26, extracting DK parameters of an observation matrix LPH from the optimal individual MinLX, constructing the observation matrix LPH by using the obtained DK parameters, and reconstructing the photovoltaic operation data LData by using an orthogonal matching pursuit algorithm based on the sparse transform basis LPS and the obtained observation matrix LPH.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210196364.6A CN114626498B (en) | 2022-03-02 | 2022-03-02 | Photovoltaic operation and maintenance data reconstruction method based on evolution optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210196364.6A CN114626498B (en) | 2022-03-02 | 2022-03-02 | Photovoltaic operation and maintenance data reconstruction method based on evolution optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114626498A CN114626498A (en) | 2022-06-14 |
| CN114626498B true CN114626498B (en) | 2024-05-28 |
Family
ID=81899169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210196364.6A Active CN114626498B (en) | 2022-03-02 | 2022-03-02 | Photovoltaic operation and maintenance data reconstruction method based on evolution optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114626498B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101221586A (en) * | 2007-12-11 | 2008-07-16 | 中山大学 | Power electronic circuit optimization method based on decoupling technology and genetic algorithm |
| WO2019109757A1 (en) * | 2017-12-06 | 2019-06-13 | 华南理工大学 | Method for using particle swarm algorithm to optimize power electronic circuit |
| CN111899286A (en) * | 2020-07-13 | 2020-11-06 | 江西理工大学 | Image registration method based on elite differential evolution |
| CN113919474A (en) * | 2021-09-13 | 2022-01-11 | 中国电建集团江西省电力建设有限公司 | Photovoltaic operation and maintenance data oriented reduction method |
| WO2022037164A1 (en) * | 2020-08-20 | 2022-02-24 | 广东奥博信息产业股份有限公司 | Labeled data storage server allocation method based on evolutionary optimization |
-
2022
- 2022-03-02 CN CN202210196364.6A patent/CN114626498B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101221586A (en) * | 2007-12-11 | 2008-07-16 | 中山大学 | Power electronic circuit optimization method based on decoupling technology and genetic algorithm |
| WO2019109757A1 (en) * | 2017-12-06 | 2019-06-13 | 华南理工大学 | Method for using particle swarm algorithm to optimize power electronic circuit |
| CN111899286A (en) * | 2020-07-13 | 2020-11-06 | 江西理工大学 | Image registration method based on elite differential evolution |
| WO2022037164A1 (en) * | 2020-08-20 | 2022-02-24 | 广东奥博信息产业股份有限公司 | Labeled data storage server allocation method based on evolutionary optimization |
| CN113919474A (en) * | 2021-09-13 | 2022-01-11 | 中国电建集团江西省电力建设有限公司 | Photovoltaic operation and maintenance data oriented reduction method |
Non-Patent Citations (1)
| Title |
|---|
| 实数编码最优子种群遗传算法及结构优化;黄隽;;淮阴师范学院学报(自然科学版);20080515(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114626498A (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110147760B (en) | Novel efficient electric energy quality disturbance image feature extraction and identification method | |
| CN1811367A (en) | Integrated supporting vector machine mixed intelligent diagnosing method for mechanical fault | |
| CN108710771B (en) | Based on the integrated mechanized equipment service reliability appraisal procedure extracted of depth characteristic | |
| CN108549962B (en) | Wind power prediction method based on historical segmented sequence search and time sequence sparsification | |
| Yadav et al. | An overview of genetic algorithm and modeling | |
| CN109886464A (en) | The low information loss short-term wind speed forecasting method of feature set is generated based on optimization singular value decomposition | |
| CN111832812A (en) | Wind power short-term prediction method based on deep learning | |
| CN108507789A (en) | The sparse diagnostic method of rolling bearing fault based on the weak orthogonal matching pursuit of mean random | |
| CN112731137A (en) | Cage type asynchronous motor stator and rotor fault joint diagnosis method based on stack type self-coding and light gradient elevator algorithm | |
| CN107679615B (en) | Transformer sample selection method based on improved genetic algorithm | |
| CN104881549B (en) | A kind of power consumption optimization method of the Reed Muller logic circuits comprising outlier | |
| CN114626498B (en) | Photovoltaic operation and maintenance data reconstruction method based on evolution optimization | |
| CN1879148A (en) | Assignment of semantic tags to phrases for grammar generation | |
| CN113282747B (en) | Text classification method based on automatic machine learning algorithm selection | |
| Zeng et al. | Self-adaptive mechanism for multi-objective evolutionary algorithms | |
| CN107609216B (en) | Mechanical fault diagnosis method based on probability box model correction | |
| CN114168782B (en) | Deep hash image retrieval method based on triplet network | |
| CN113128133B (en) | Genetic algorithm-based power consumption attack efficient screening method | |
| CN114281846B (en) | New energy power generation prediction method based on machine learning | |
| CN102043910B (en) | Remote protein homology detection and fold recognition method based on Top-n-gram | |
| CN106845799B (en) | Evaluation method for typical working condition of battery energy storage system | |
| CN114077924A (en) | Wind power prediction gale data enhancement method considering extreme gale weather | |
| CN113536508A (en) | Method and system for classifying manufacturing network nodes | |
| Ghimire et al. | Loss-aware automatic selection of structured pruning criteria for deep neural network acceleration | |
| CN111310788A (en) | Water body pH value prediction method based on parameter optimization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |