CN108960588A - A kind of integrated evaluating method for Wind turbines standby redundancy - Google Patents
A kind of integrated evaluating method for Wind turbines standby redundancy Download PDFInfo
- Publication number
- CN108960588A CN108960588A CN201810619115.7A CN201810619115A CN108960588A CN 108960588 A CN108960588 A CN 108960588A CN 201810619115 A CN201810619115 A CN 201810619115A CN 108960588 A CN108960588 A CN 108960588A
- Authority
- CN
- China
- Prior art keywords
- standby redundancy
- layer
- neural network
- wind turbines
- evaluating method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a kind of integrated evaluating method for Wind turbines standby redundancy, which specifically includes 4 steps: Appreciation gist: factor in need of consideration includes the life cycle of spare unit, accounting period, ambient operating temperatures and the purchase cost of standby redundancy;Data prediction: data prediction includes the deletion of abnormal data, the deletion of incomplete data, the processing of database data integrality and input quantity normalized totally 4 contents;It establishes fuzzy neural network: determining network size and each initial connection weight, threshold value and scale of neural network, using life cycle, accounting period, ambient operating temperatures and this 4 parameters of purchase cost of standby redundancy as 4 input nodes of fuzzy neural network, exporting result is exactly a comprehensive performance evaluation index.The present invention obtains comprehensive performance evaluation index with the method based on fuzzy neural network, to predict that the demand of standby redundancy provides condition, improves blower overall economic benefit.
Description
Technical field
The invention belongs to the Comprehensive Assessment Technology fields of Wind turbines standby redundancy, particularly relate to a kind of for wind
The integrated evaluating method of motor group standby redundancy.
Background technique
Currently, overall evaluation system of the China in fields such as finance, machine-building and automobile parts is relatively mature,
But the overall evaluation system in Wind turbines standby redundancy field is not still overripened.With nearly more than ten years, wind-power electricity generation row
Flourishing for industry, proposes the evaluation index of Wind turbines standby redundancy, establishes the synthesis of perfect Wind turbines standby redundancy
Evaluation system becomes extremely urgent.And now the evaluation method for being used in other industry mainly has expert system, level point
Analysis method and AHP spare part candidate's method etc..Currently, lacking the method and hand of a kind of overall merit in Wind turbines standby redundancy market
Section, most of wind power plants are all the hobby or the buying side in former years depending on policymaker most of when selecting standby redundancy brand
Case.China is all mainly that expert system binding hierarchy analytic approach uses in the overall merit field of standby redundancy, Zhuan Jiaping
The disadvantages of valence system is horizontal different different with expert individual's preference there are expertise.
Nowadays, analytic hierarchy process (AHP) being often used in finance and new energy field, overall merit, level point are carried out to standby redundancy
Analysis method is to be picked out spare part according to the importance of each factor, to form reasonable standby redundancy Candidate Set, although level
Analytic approach carries out decision using research object as a system, according to the mode of thinking of decomposition, multilevel iudge, synthesis, become after
The important tool of the network analysis to grow up after Analysis on Mechanism, statistical analysis, but analytic hierarchy process (AHP) is from alternative
In preferentially choose, the new departure solved the problems, such as can not be provided, and the quantitative data that analytic hierarchy process (AHP) uses is less, it is qualitative at
Live apart more, and combine expert system, more there is the risk of personal preference, it is as a result not convincing.
Summary of the invention
The present invention provides a kind of synthesis for Wind turbines standby redundancy and comments to overcome the shortcomings of the prior art
Valence method, the integrated evaluating method are not only able to provide pre- data for the requirement forecasting of standby redundancy, additionally it is possible to be procurement scheme
The foundation of optimum selecting is provided.
The present invention is achieved by the following technical solutions: a kind of overall merit side for Wind turbines standby redundancy
Method, the integrated evaluating method specifically comprise the following steps:
Step 1. Appreciation gist: factor in need of consideration includes the life cycle of spare unit, the accounting period of standby redundancy, ring
Border running temperature and purchase cost;
Step 2. data prediction: data prediction includes the deletion of abnormal data, the deletion of incomplete data, database number
According to the processing of integrality and input quantity normalized totally 4 contents;
Step 3. establishes fuzzy neural network: determining network size and each initial connection weight, threshold value and neural network rule
Mould, using life cycle, accounting period, ambient operating temperatures and the purchase cost of standby redundancy this 4 parameters as fuzzy neural
4 input nodes of network, output result is exactly a comprehensive performance evaluation index.
The system structure of fuzzy neural network of the present invention is divided into 4 layers:
1st layer: being known as input layer, each node respectively indicates the linguistic variable of an input;
2nd layer: being known as membership function layer, each node respectively represents a membership function, which is with as follows
Gaussian function indicate:
Wherein, μijIt is xiJ-th of membership function, cijIt is xiJ-th of Gauss member function center, σjIt is xiJth
The width of a Gauss member function, r are input variable numbers, and μ is the quantity of membership function, also represent the total regular number of system;
3rd layer: it is known as T- norm layer, each node respectively represents the part IF- in a possible fuzzy rule, because
This, which reflects number of fuzzy rules, j-th of rule RjOutput are as follows:
Wherein, It is j-th of RBF unit
Center, each node of this layer represents a RBF unit;
4th layer: referred to as normalization layer, these nodes are referred to as N node, it is clear that N number of nodes is equal with fuzzy rule number of nodes,
J-th of node NjOutput are as follows:
Wherein, y is the output of variable, ωkIt is the connection weight of THEN- partial results parameter or k-th of rule, for
TSK model:
ωk=αi0+αk1χ1+…+αkrχrK=1,2 ..., μ (3.5);
When result parameter is real constant:
ωk=αkK=1,2 ..., μ (3.6);
Wushu (3.2), formula (3.3), formula (3.5) and formula (3.6) substitute into formula (3.4) respectively, then respectively obtain:
TSK model:
S model:
According to the parameter that above-mentioned model exports, the purpose evaluated Wind turbines standby redundancy is realized.
The object of classification of integrated evaluating method of the present invention be the generators of Wind turbines, blade, gear-box, electric variable pitch,
Motor, capacitor, automatically controlled, sensor, frequency converter, IGBT or PLC etc..
Firstly, the present invention is mainly the research by the standby redundancy integrated evaluating method to existing other field, find out
At present to Wind turbines spare parts management and the existing larger problem of buying, and with certain the classification of the repair piece and
Integrated evaluating method is analyzed and is improved, and target is to be carried out systematically by reasonable new evaluation method to blower spare unit
Evaluation, then provides condition for the requirement forecasting of standby redundancy, the procurement scheme for blower standby redundancy provides optimum selecting
Foundation, and then improve blower overall economic benefit;Secondly, being by reasonable integrated evaluating method and corresponding inventory's basic management
Implementation, establish a kind of long-term, effectively evaluating method, improve previous supply chains process, to make wind field spare parts purchasing
Manage further normalization, scientific.
Integrated evaluating method in the present invention be with reference to traditional industry and the common expert system of commercial field and
Analytic hierarchy process (AHP) is mainly technically characterized by innovatively proposing the integrated evaluating method based on fuzzy neural network, followed by not
Again simply using expert opinion as unique conditional, or according to each conditions standby redundancy is simply sorted.
The beneficial effects of the present invention are: the method for the present invention is with the integrated evaluating method based on fuzzy neural network to wind-powered electricity generation
The standby redundancy of unit is systematically evaluated, and is obtained comprehensive performance evaluation index, is preferentially sorted, for the need for predicting standby redundancy
The amount of asking provides condition, provides the foundation of optimum selecting for procurement scheme, improves blower overall economic benefit.And the present invention passes through
The implementation of reasonable evaluation management method and corresponding inventory's basic management is established a kind of long-term, effectively evaluating system, is improved
Previous supply chains process provides various reasonable and the high buying alternative of cost performance, thus make wind field spare part buying and
Manage further normalization, scientific.
The invention belongs to a kind of new application fields: evaluation method being used in Wind turbines standby redundancy evaluation pipe for the first time
Reason, demand analysis prediction and standby redundancy area of procurement.The present invention provides a kind of new Appreciation gists: for the first time not only will be economical
It is optimal to be used as unique foundation, but the combined factors such as the life cycle of spare part, the accounting period of spare part and running environment are examined
Consider.Present invention employs a kind of new evaluation models: using the comprehensive evaluation model based on fuzzy neural network, fuzznet
Network can carry out data analysis to standby redundancy in the case where comprehensively considering multifactor, obtain a fuzzy comprehensive performance and comment
Valence index.
The novelty of the present invention compared with the existing technology is: the method for the present invention is to apply to comment in Wind turbines standby redundancy
It is more extensively and comprehensive with field in valence management, demand analysis prediction and area of procurement, system can either be carried out to blower spare unit
Ground evaluation, and can provide condition for the requirement forecasting of standby redundancy, moreover it is possible to provide and select for the procurement scheme of blower standby redundancy
It is preferred that the foundation selected.The present invention for the first time applies to fuzzy neural network in the overall evaluation system of Wind turbines standby redundancy,
Thus be not only using economic optimum as unique foundation, but by the life cycle of spare part, spare part the accounting period and
The combined factors such as running environment consider.The present invention, which is also not, unilaterally evaluates wind power generating set control performance, theoretical
On can infinitely expand factor of evaluation, obtain last comprehensive performance evaluation index.
The degree of association is not present between each influence factor that traditional analytic hierarchy process (AHP) differentiates in the prior art, between factor
It does not influence mutually, once influence factor or discriminant criterion are excessive, this method can only just carry out single layer sequence, and different sequences can shadow
Ring final result.But the integrated evaluating method disclosed in the present invention based on fuzzy neural network can well solve this
Problem, and discriminant criterion theoretically can infinitely expand, and present example has only selected four discriminant criterions to be illustrated.
The present invention is a kind of base for being used in Wind turbines standby redundancy evaluation management, demand analysis prediction and area of procurement
In the integrated evaluating method of fuzzy neural network.It is common that integrated evaluating method in the present invention is different from nowadays other field
Analytic hierarchy process (AHP), reasonably to consider various wind-powered electricity generation fields peculiar for the integrated evaluating method based on fuzzy neural network in the present invention
Factor as distinguishing rule, and be not only only consider an economic factor, scientifically Wind turbines standby redundancy is integrated
Performance evaluation, and preferentially sort, reasonable buying prescheme is formd, present invention application fuzzy neural network is standby in Wind turbines
It is flexibly used in terms of the comprehensive performance evaluation metrics evaluation of product spare part.
Detailed description of the invention
Fig. 1 is the comprehensive performance evaluation index curve graph of blade in the embodiment of the present invention;
Fig. 2 is fuzzy neural network topological model figure of the invention;
Fig. 3 is fuzzy neural network algorithm flow chart of the invention.
Specific embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.
As shown in Figure 1 to Figure 3, the invention discloses a kind of integrated evaluating methods for Wind turbines standby redundancy, should
Integrated evaluating method specifically comprises the following steps:
Step 1: Appreciation gist: factor in need of consideration includes the life cycle (type, component projected life), standby of spare unit
Accounting period, ambient operating temperatures and the purchase cost of product;
Step 2: data prediction: mainly including four contents, the deletion of abnormal data, the deletion of incomplete data, data
The processing and input quantity normalized of library data integrity.
Step 3: establishing fuzzy neural network: determining network size and each initial connection weight, threshold value and neural network rule
Mould, using four life cycle, the accounting period of spare unit, ambient operating temperatures and purchase cost parameters as fuzzy neural network
4 input nodes, output node number take 1, export the result is that a comprehensive performance evaluation index, the structure chart of fuzzy neural network
As shown in Fig. 2, the system structure is divided into 4 layers:
(1) the 1st layer: being known as input layer, each node respectively indicates the linguistic variable of an input;
(2) the 2nd layers: being known as membership function layer, each node respectively represents a membership function, which is with such as
Under Gaussian function indicate:
Wherein, μijIt is xiJ-th of membership function, cijIt is xiJ-th of Gauss member function center, σjIt is xiJth
The width of a Gauss member function, r are input variable numbers, and μ is the quantity of membership function, also represent the total regular number of system;
(3) the 3rd layers: it is known as T- norm layer, each node respectively represents the part IF- in a possible fuzzy rule,
Therefore, which reflects number of fuzzy rules, j-th of rule RjOutput are as follows:
Wherein, It is j-th of RBF unit
Center, it can be seen that, each node of this layer represents a RBF unit by formula (3.2);In the following discussion, mould
Pasting regular number will be used alternatingly with RBF number of nodes without laying down a definition;
(4) the 4th layers: referred to as normalization layer, these nodes are referred to as N node, it is clear that N number of nodes and fuzzy rule number of nodes
It is equal, j-th of node NjOutput are as follows:
Wherein, y is the output of variable, ωkIt is the connection weight of THEN- partial results parameter or k-th of rule, for
TSK model:
ωk=αi0+αk1χ1+…+αkrχrK=1,2 ..., μ (3.5);
When result parameter is real constant:
ωk=αkK=1,2 ..., μ (3.6);
Wushu (3.2), formula (3.3), formula (3.5) and formula (3.6) substitute into formula (3.4) respectively, then respectively obtain:
TSK model:
S model:
The flow chart of fuzzy neural network is as shown in Figure 3.In conclusion being realized according to the parameter that model exports by wind-powered electricity generation
The purpose of unit standby redundancy evaluation.
The object of classification of integrated evaluating method of the present invention is the crucial standby redundancy of Wind turbines, such as generator, blade, tooth
Roller box, electric variable pitch, motor, capacitor, automatically controlled, sensor, frequency converter, driver, IGBT and PLC etc..
Embodiment: the data after the blade normalized of the same type of certain brand are as shown in table 1:
Data after the normalized of certain the same type of brand blade of table 1
Step 1: by these data Input Fuzzy Neural Networks, the comprehensive performance evaluation for obtaining the brand same type machine blade refers to
Mark, is fitted to a comprehensive performance evaluation index curve graph as shown in Figure 1, as shown in Figure 1, the comprehensive performance evaluation of the blade
Index levels off to 3, that is, thinks that the comprehensive performance evaluation index of the blade is 3.
Step 2: repeating the above steps 1, the data after all kinds of standby redundancy normalizeds of Wind turbines are inputted fuzzy
Neural network obtains their comprehensive performance evaluation index, analyzes data and carries out height sequence, table is made, such as 2 institute of table
Show:
The comprehensive performance evaluation index of the 2 different brands standby redundancy of table
In conclusion obtaining simulation curve according to the parameter that model exports, Wind turbines standby redundancy is commented to realize
The purpose of valence.
Finally it should be noted that the above content is merely illustrative of the technical solution of the present invention, rather than the present invention is protected
The limitation of range, the simple modification or equivalent replacement that those skilled in the art carry out technical solution of the present invention,
All without departing from the spirit and scope of technical solution of the present invention.
Claims (3)
1. a kind of integrated evaluating method for Wind turbines standby redundancy, it is characterised in that: the integrated evaluating method is specific
Include the following steps:
Step 1. Appreciation gist: factor in need of consideration includes the life cycle of spare unit, the accounting period of standby redundancy, environment fortune
Trip temperature and purchase cost;
Step 2. data prediction: data prediction is complete comprising the deletion of abnormal data, the deletion of incomplete data, database data
The processing of whole property and input quantity normalized totally 4 contents;
Step 3. establishes fuzzy neural network: determine network size and each initial connection weight, threshold value and scale of neural network,
Life cycle, accounting period, ambient operating temperatures and the purchase cost of standby redundancy this 4 parameters are as fuzzy neural network
4 input nodes, output result is exactly a comprehensive performance evaluation index.
2. a kind of integrated evaluating method for Wind turbines standby redundancy according to claim 1, it is characterised in that: institute
The system structure for stating fuzzy neural network is divided into 4 layers:
1st layer: being known as input layer, each node respectively indicates the linguistic variable of an input;
2nd layer: being known as membership function layer, each node respectively represents a membership function, which is with following height
This function representation:
Wherein, μijIt is xiJ-th of membership function, cijIt is xiJ-th of Gauss member function center, σjIt is xiIt is j-th high
The width of this membership function, r are input variable numbers, and μ is the quantity of membership function, also represent the total regular number of system;
3rd layer: being known as T- norm layer, each node respectively represents the part IF- in a possible fuzzy rule, therefore, should
Node layer number reflects number of fuzzy rules, j-th of rule RjOutput are as follows:
Wherein,It is j-th of RBF unit
Each node at center, this layer represents a RBF unit;
4th layer: referred to as normalization layer, these nodes are referred to as N node, it is clear that N number of nodes is equal with fuzzy rule number of nodes, jth
A node NjOutput are as follows:
Wherein, y is the output of variable, ωkIt is the connection weight of THEN- partial results parameter or k-th of rule, for TSK mould
Type:
ωk=αi0+αk1χ1+…+αkrχrK=1,2 ..., μ (3.5);
When result parameter is real constant:
ωk=αkK=1,2 ..., μ (3.6);
Wushu (3.2), formula (3.3), formula (3.5) and formula (3.6) substitute into formula (3.4) respectively, then respectively obtain:
TSK model:
S model:
According to the parameter that above-mentioned model exports, the purpose evaluated Wind turbines standby redundancy is realized.
3. a kind of integrated evaluating method for Wind turbines standby redundancy according to claim 1 or 2, feature exist
In: the object of classification of the integrated evaluating method is that generator, blade, gear-box, electric variable pitch, the electricity of Wind turbines are mechanical, electrical
Appearance, automatically controlled, sensor, frequency converter, IGBT or PLC.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810619115.7A CN108960588A (en) | 2018-06-15 | 2018-06-15 | A kind of integrated evaluating method for Wind turbines standby redundancy |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810619115.7A CN108960588A (en) | 2018-06-15 | 2018-06-15 | A kind of integrated evaluating method for Wind turbines standby redundancy |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108960588A true CN108960588A (en) | 2018-12-07 |
Family
ID=64489678
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810619115.7A Pending CN108960588A (en) | 2018-06-15 | 2018-06-15 | A kind of integrated evaluating method for Wind turbines standby redundancy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108960588A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113127538A (en) * | 2021-04-16 | 2021-07-16 | 北京交通大学 | High-precision spare part demand prediction method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120197605A1 (en) * | 2011-01-30 | 2012-08-02 | Sinovel Wind Group Co., Ltd. | Comprehensive assessment system and assessment method for vibration and load of wind generating set |
CN107423904A (en) * | 2017-07-28 | 2017-12-01 | 中国能源建设集团浙江省电力设计院有限公司 | A kind of Wind turbines evaluation method based on Life cycle cost analysis |
-
2018
- 2018-06-15 CN CN201810619115.7A patent/CN108960588A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120197605A1 (en) * | 2011-01-30 | 2012-08-02 | Sinovel Wind Group Co., Ltd. | Comprehensive assessment system and assessment method for vibration and load of wind generating set |
CN107423904A (en) * | 2017-07-28 | 2017-12-01 | 中国能源建设集团浙江省电力设计院有限公司 | A kind of Wind turbines evaluation method based on Life cycle cost analysis |
Non-Patent Citations (2)
Title |
---|
田启华等: "基于模糊神经网络的机械产品性能评价 ", 《中国制造业信息化》 * |
马莉等: "基于动态模糊神经网络的生物工程算法研究 ", 《计算机工程与科学》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113127538A (en) * | 2021-04-16 | 2021-07-16 | 北京交通大学 | High-precision spare part demand prediction method |
CN113127538B (en) * | 2021-04-16 | 2024-02-09 | 北京交通大学 | High-precision spare part demand prediction method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yang et al. | Reinforcement learning in sustainable energy and electric systems: A survey | |
CN110685857B (en) | Mountain wind turbine generator behavior prediction model based on ensemble learning | |
CN104392269B (en) | Microgrid distributed energy source bidding method based on artificial immunity | |
CN107341349A (en) | Method, system, memory and the controller of blower fan health evaluating | |
CN109272405A (en) | Carbon transaction in assets method and system | |
CN108876002B (en) | Method for optimizing inventory of spare parts of wind generating set | |
Chuentawat et al. | The comparison of PM2. 5 forecasting methods in the form of multivariate and univariate time series based on support vector machine and genetic algorithm | |
Kaboli et al. | An expression-driven approach for long-term electric power consumption forecasting | |
Yuan et al. | Conditional style-based generative adversarial networks for renewable scenario generation | |
Wang et al. | Automated machine learning for short-term electric load forecasting | |
CN107092989A (en) | The Forecasting Methodology and equipment of short-term wind-electricity power | |
CN110717610A (en) | Wind power prediction method based on data mining | |
CN112952807B (en) | Multi-objective optimization scheduling method considering wind power uncertainty and demand response | |
Reche-López et al. | Comparison of metaheuristic techniques to determine optimal placement of biomass power plants | |
CN114021483A (en) | Ultra-short-term wind power prediction method based on time domain characteristics and XGboost | |
CN107145968A (en) | Photovoltaic apparatus life cycle cost Forecasting Methodology and system based on BP neural network | |
KR102583858B1 (en) | Method and apparatus for managing a renewable energy based on an artificial intelligence | |
CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
CN108960588A (en) | A kind of integrated evaluating method for Wind turbines standby redundancy | |
Abasi et al. | A novel metaheuristic approach to solve unit commitment problem in the presence of wind farms | |
CN116307028A (en) | Short-term power load prediction method and system based on improved decision tree | |
Jimenez et al. | The role of artificial intelligence in Latin Americas energy transition | |
Zha et al. | An improved reinforcement learning for security-constrained economic dispatch of battery energy storage in microgrids | |
Yuan et al. | A novel hybrid short-term wind power prediction framework based on singular spectrum analysis and deep belief network utilized improved adaptive genetic algorithm | |
CN111967689A (en) | Model and method for wind power generation prediction by combining multivariate and stepwise linear regression and artificial neural network |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181207 |
|
RJ01 | Rejection of invention patent application after publication |