CN117578428A - Fan power recursion prediction method, device, computer equipment and storage medium - Google Patents
Fan power recursion prediction method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117578428A CN117578428A CN202311565839.5A CN202311565839A CN117578428A CN 117578428 A CN117578428 A CN 117578428A CN 202311565839 A CN202311565839 A CN 202311565839A CN 117578428 A CN117578428 A CN 117578428A
- Authority
- CN
- China
- Prior art keywords
- fan power
- time sequence
- prediction
- data
- model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000012417 linear regression Methods 0.000 claims abstract description 67
- 238000012549 training Methods 0.000 claims abstract description 55
- 238000004590 computer program Methods 0.000 claims description 24
- 239000010410 layer Substances 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 17
- 239000002356 single layer Substances 0.000 claims description 16
- 230000008859 change Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000007812 deficiency Effects 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000009514 concussion Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005429 filling process Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N3/08—Learning methods
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Power Engineering (AREA)
- Probability & Statistics with Applications (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)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application relates to a fan power recursion prediction method, a device, computer equipment and a storage medium. The method comprises the following steps: constructing a fan power time sequence according to fan power data of a historical period; obtaining the missing value data in the fan power time sequence, and filling the missing value data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence; training an initial fan power recursion prediction model according to the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in a target fan power time sequence; and predicting the fan power of the wind power plant in the time to be measured according to the fan power recursion prediction. The method and the device can improve accuracy and interpretability of the power prediction of the fan to be detected.
Description
Technical Field
The present disclosure relates to the field of fan power prediction technologies, and in particular, to a method, an apparatus, a computer device, and a storage medium for recursively predicting fan power.
Background
Wind energy is a clean energy source, but wind power generation faces challenges such as unstable wind speed, low fan efficiency, difficult power grid dispatching, poor safety and the like. In order to overcome the problems, the accuracy of fan power prediction is crucial, and the existing fan power prediction is divided into three prediction methods of physics, statistics and artificial intelligence.
However, the three prediction methods have certain defects, the physical method and the artificial intelligence method need a large amount of training data and calculation resources, and the statistical method ignores the rules and physical characteristics of the wind turbine. And with a small amount of available data, the prediction results of the above three prediction methods all lack interpretability. Therefore, the existing fan power prediction method has high requirements on data stability, and the difficulty in collecting data is high, so that the accuracy of fan power prediction is poor.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a blower power recursion prediction method, apparatus, computer device, computer-readable storage medium, and computer program product that can improve prediction accuracy and interpretability.
In a first aspect, the present application provides a method for recursively predicting fan power, including:
constructing a fan power time sequence according to fan power data of a historical period;
obtaining the missing value data in the fan power time sequence, and filling the missing value data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence;
training an initial fan power recursion prediction model according to the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in the target fan power time sequence;
predicting the fan power of the wind power plant in the time to be measured according to the fan power recursion prediction
In one embodiment, the obtaining the missing data in the fan power time sequence includes:
determining fan power data meeting default preset conditions in the fan power time sequence as default data; the default preset condition includes that the value of the fan power data is zero, and the change value of the fan power data relative to the fan power data of the previous time sequence is larger than a preset threshold.
In one embodiment, before the filling the missing data by the piecewise linear regression model, the method further includes:
interpolation filling is carried out on the default data to obtain a middle fan power time sequence;
and training an initial piecewise linear regression model according to the intermediate fan power time sequence to optimize parameters of the initial piecewise linear regression model until the piecewise linear regression model after training is obtained.
In one embodiment, the training an initial piecewise linear regression model from the intermediate fan power time series includes:
acquiring an exponential weighted moving average characteristic and a moving median characteristic of the intermediate fan power time sequence;
processing the intermediate fan power time sequence according to a BiLSTM model to obtain meta-characteristics of the intermediate fan power time sequence;
and training the initial piecewise linear regression model according to the meta-feature, the exponentially weighted moving average feature and the moving median feature to optimize parameters of the initial piecewise linear regression model until the piecewise linear regression model after training is obtained.
In one embodiment, the training the initial fan power recursion prediction model according to the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained includes:
Preprocessing to obtain a moving average sequence;
dividing the moving average sequence into a training set and a verification set, and training initial fan power recursion prediction to obtain the fan power recursion prediction model; the method comprises a single-layer BiLSTM model for processing a lightweight fan power prediction task and a double-layer BiLSTM model for processing a lightweight fan power prediction task.
In one embodiment, the predicting the fan power of the wind farm in the time to be measured according to the fan power recursion prediction includes:
respectively obtaining a first prediction result and a second prediction result of the single-layer BiLSTM model and the double-layer BiLSTM model;
and fusing the first prediction result and the second prediction result to obtain the fan power of the wind power plant in the time to be measured.
In a second aspect, the present application further provides a fan power recursion prediction apparatus, the apparatus comprising:
the sequence construction module is used for constructing a fan power time sequence according to the fan power data of the historical period;
the sequence updating module is used for acquiring the default data in the fan power time sequence, and filling the default data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence;
The model training module is used for carrying out fan power recursion prediction according to the target fan power time sequence so as to optimize parameters of the fan power recursion prediction until the fan power recursion prediction after training is completed is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in the target fan power time sequence;
and the data prediction module is used for predicting the fan power of the wind power plant in the time to be detected according to the fan power recursion prediction.
In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
constructing a fan power time sequence according to fan power data of a historical period;
obtaining the missing value data in the fan power time sequence, and filling the missing value data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence;
training an initial fan power recursion prediction model according to the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in the target fan power time sequence;
And predicting the fan power of the wind power plant in the time to be measured according to the fan power recursion prediction.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
constructing a fan power time sequence according to fan power data of a historical period;
obtaining the missing value data in the fan power time sequence, and filling the missing value data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence;
training an initial fan power recursion prediction model according to the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in the target fan power time sequence;
and predicting the fan power of the wind power plant in the time to be measured according to the fan power recursion prediction.
In a fifth aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:
Constructing a fan power time sequence according to fan power data of a historical period;
obtaining the missing value data in the fan power time sequence, and filling the missing value data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence;
training an initial fan power recursion prediction model according to the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in the target fan power time sequence;
and predicting the fan power of the wind power plant in the time to be measured according to the fan power recursion prediction.
The fan power recursion prediction method, the device, the computer equipment, the storage medium and the computer program product construct a fan power time sequence according to the fan power data of the historical period; obtaining the missing value data in the fan power time sequence, and filling the missing value data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence, so that the deficiency value data can be accurately filled according to the rules of fan power historical data, and the diversity of the data is improved; training an initial fan power recursion prediction model according to the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in a target fan power time sequence; according to the fan power recursion prediction, the fan power of the wind power plant in the time to be detected is predicted, so that the fan power can be accurately predicted based on a small amount of data through a fan power recursion prediction model according to the captured overall characteristics and rules, and the accuracy and the interpretability of the prediction are improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.
FIG. 1 is a diagram of an application environment for a method of recursive prediction of fan power in one embodiment;
FIG. 2 is a flow diagram of a method of recursive prediction of fan power in one embodiment;
FIG. 3 is a flow chart illustrating a step of generating a page packet in one embodiment;
FIG. 4 is another flow diagram of a method of recursive prediction of blower power in one embodiment;
FIG. 5 is a diagram of the result of searching for missing data of the wind farm A according to an embodiment;
FIG. 6 is a schematic diagram of a blower power recursion prediction of a wind farm A according to one embodiment;
FIG. 7 is a diagram of a missing data search result of a wind farm B according to an embodiment;
FIG. 8 is a schematic diagram of a blower power recursion prediction of a wind farm B according to one embodiment;
FIG. 9 is a block diagram of a blower power recursion prediction apparatus in one embodiment;
fig. 10 is an internal structural view of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
In the traditional technology, three main types of methods of physics, statistics and artificial intelligence are mainly adopted for fan power prediction, and each prediction method has some defects. Physical and artificial intelligence methods rely on a large amount of training data and high computational resources, while statistical methods tend to ignore the laws and physical characteristics of wind turbines. Furthermore, in the case of data scarcity, existing methods tend to be difficult to provide a predictive result that is highly interpretable. Therefore, the current fan power prediction method has higher requirements on the stability of data, and the acquisition of the data also faces a certain difficulty, which leads to the defect of the accuracy of fan power prediction. The fan power recursion prediction method can effectively solve the problems caused by the traditional technology.
The fan power recursion prediction method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In the application scenario of the present application, the terminal 102 constructs a fan power time sequence according to the fan power data of the historical period; obtaining the missing value data in the fan power time sequence, and filling the missing value data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence; training an initial fan power recursion prediction model according to the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in a target fan power time sequence; and predicting the fan power of the wind power plant in the time to be measured according to the fan power recursion prediction.
In an exemplary embodiment, as shown in fig. 2, a method for recursively predicting fan power is provided, which is illustrated by applying the method to the terminal 102 in fig. 1, and includes the following steps S202 to S208, where:
step S202, a fan power time sequence is constructed according to fan power data of a historical period.
The fan power data is the power generated by a fan of the wind power plant, and can be also called wind power output data. In some embodiments, during operation of the wind farm, the wind turbine collects wind turbine power data at preset time intervals, for example, wind turbine power data is collected every 15 minutes, so as to construct a wind turbine power time sequence.
In some embodiments, a fan power time series may be constructedRepresented as { P } 1 ,P 2 ,…,P n P is the power value and n represents the number of elements in the sequence, e.g., a fan power time sequence may be {100, 102, 98, 100, 98, … }. Because each fan power in the fan power time sequence is acquired according to a preset time interval, taking acquisition once every 15min as an example, the fan power time sequence can be a corresponding time feature sequence { T } 1 ,T 2 ,…,T n }，P n And T is n Corresponding, for example, {2021-01-0100:00, 2021-01-01 00:15, 2021-01-01 00:30, … }.
Step S204, obtaining the missing value data in the fan power time sequence, and filling the missing value data through a piecewise linear regression model to obtain a target fan power time sequence;
wherein, the missing data refers to data which is not collected at the time of collection. It can be understood that the acquisition process may be interfered by external factors, or abnormal conditions such as sudden power failure or shutdown may occur. Therefore, some missing data may exist in the fan power time sequence, automatic searching and complement are needed, and because the missing data is generally stored as 0 value, the missing data may be confused with the fan power data with the normal 0 value in the actual searching process, and accurate distinction is needed.
In some embodiments, a piecewise linear regression model may be used to capture local features and laws in the target fan power time series. It will be appreciated that the piecewise linear regression model not only simply performs linear regression on the entire fan power time series, but also may divide the time series into different segments according to the local nature of the data and perform linear regression within each segment. The processing mode enables the model to be more suitable for the change and fluctuation of data, and therefore the target fan power can be predicted more accurately.
By adopting the method, the segmented linear regression model is used for filling the missing value data, so that the complete target fan power time sequence is obtained, and the data filling process is beneficial to preserving local characteristics in the data, so that the accuracy of filling the missing value is improved, and the final time sequence is more complete and reliable.
And S206, training an initial fan power recursion prediction model according to the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained.
In some embodiments, the target fan power time series may be processed to extract training data, such as meta-features, weighted moving average features, moving median features, etc., for training the initial fan power recursion prediction model, and training the trained fan power recursion prediction model. The fan power recursion prediction model is used for capturing integral characteristics and rules in a target fan power time sequence.
It can be understood that by repeated training and parameter adjustment, the initial fan power recursion prediction model is gradually optimized, the fitting capacity of target data is improved, and the prediction result output by the trained fan power recursion prediction model is more accurate and reliable.
And step S208, predicting the fan power of the wind power plant in the time to be measured according to the fan power recursion prediction.
In some embodiments, multiple data may be used to predict a single data to enhance the prediction effect, as fan power and time have a relationship, so time characteristics are considered to assist in the prediction. When the calculation model is selected, a mode of combining a double-layer BiLSTM model and a single-layer BiLSTM model can be adopted to improve the prediction capability.
Wherein the BiLSTM model is modified based on the LSTM model, which introduces bi-directional information flow by using two LSTM cells at each time step. Thus, the hidden state of each time step is formed by combining two-way information, the improvement of the two-way information flow enables the BiLS to more comprehensively capture the context information of the input sequence, so that the BiLS model can better perform in a plurality of sequence modeling tasks, and the expression of the BiLSTM model can be as follows:
in conclusion, the wind power plant in the time to be tested is predicted through the trained fan power recursion prediction model, so that the power performance of the fan in the future time period can be estimated. The whole prediction process is based on analysis of historical data and model parameters, and aims to provide reasonable estimation of future fan power of the wind farm. The prediction mode can be used for guiding the operation plan of the power system, improving the stability of the power grid and reducing the dependence on non-renewable energy sources.
The fan power recursion prediction method, the device, the computer equipment, the storage medium and the computer program product construct a fan power time sequence according to the fan power data of the historical period; obtaining the missing value data in the fan power time sequence, and filling the missing value data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence, so that the deficiency value data can be accurately filled according to the rules of fan power historical data, and the diversity of the data is improved; training an initial fan power recursion prediction model according to the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in a target fan power time sequence; according to the fan power recursion prediction, the fan power of the wind power plant in the time to be detected is predicted, so that the fan power can be accurately predicted based on a small amount of data through a fan power recursion prediction model according to the captured overall characteristics and rules, and the accuracy and the interpretability of the prediction are improved.
In an exemplary embodiment, as shown in fig. 3, a flowchart illustrating a step of generating a page packet in one embodiment, before step S204, further includes the following steps:
and step S302, interpolation filling is carried out on the missing value data, and an intermediate fan power time sequence is obtained.
Referring to fig. 4, fig. 4 is another flow chart of a method for recursively predicting fan power according to one embodiment. As shown in FIG. 4, prior to training the piecewise linear regression model, simple linear padding may be performed on the deficiency data to obtain an intermediate fan power time series so that training features for training the initial piecewise linear regression model can be subsequently extracted from the intermediate fan power time series.
It can be understood that the intermediate fan power time sequence is obtained by interpolation filling, so that the continuity and the integrity of the fan power time sequence can be maintained. The missing power values can be filled in the fan power time sequence through interpolation filling, so that the data in the whole sequence becomes more complete, and a foundation is laid for accurately extracting training features for model training in the subsequent middle fan power time sequence. It also helps to ensure continuity and availability of the fan power time series over the entire time frame.
Step S304, training the initial piecewise linear regression model according to the intermediate fan power time sequence to optimize parameters of the initial piecewise linear regression model until a trained piecewise linear regression model is obtained.
It will be appreciated that optimizing the parameters of the initial piecewise linear regression model by the features extracted from the intermediate fan power time series enables a better fit to the local features and rules of the intermediate fan power time series. The segmented linear regression model is rendered more accurate and reliable across the time series by continuously adjusting and optimizing the parameters of the model. The piecewise linear regression model trained in this way can better capture local characteristics in the fan power time series, providing a more reliable basis for subsequent predictions and analyses.
In an exemplary embodiment, step S304 includes:
acquiring an exponential weighted moving average characteristic and a moving median characteristic of the intermediate fan power time sequence;
processing the intermediate fan power time sequence according to the BiLSTM model to obtain meta-characteristics of the intermediate fan power time sequence;
and training the initial piecewise linear regression model according to the meta-feature, the exponentially weighted moving average feature and the moving median feature to optimize parameters of the initial piecewise linear regression model until a trained piecewise linear regression model is obtained.
As shown in FIG. 4, in some embodiments, meta-features, such as overall trend, periodicity, anomaly pattern, etc., of fan power data may be extracted from the intermediate fan power time series via a BiLSTM model. The meta-feature is a predicted result, which can compensate for the missing value, but there is local distortion or local concussion. The weighted moving average feature and the moving median feature are features of the data itself, the former can adapt to data change more quickly, is more sensitive to recent change, and can extract main trend of the data; the latter can better preserve local features in the data and is not affected by extremes. But both cannot be directly compensated for in the face of a large number of missing values. The three characteristics are combined, and the segmented elastic network regression model is trained, so that the method can make up for the shortages, predict data more accurately and make up data.
It will be appreciated that by obtaining an exponentially weighted moving average feature and a moving median feature of the intermediate fan power time series, overall trends and local features in the intermediate fan power time series can be captured. The intermediate fan power time series is then processed using the BiLSTM model to obtain meta-features that can be used to represent higher level abstract properties of the series. The resulting meta-features, exponentially weighted moving average features, and moving median features are then combined for training an initial piecewise linear regression model. By continuously optimizing the parameters of the model, the model can be better fitted with various characteristics and rules of the intermediate fan power time sequence. This process continues until a trained piecewise linear regression model is obtained. Finally, the trained model can more accurately predict the missing value in the fan power time sequence, and provides a more reliable basis for subsequent data analysis and application.
In an exemplary embodiment, step S204 includes:
determining fan power data meeting default preset conditions in a fan power time sequence as default data; the default preset condition includes that the value of the fan power data is zero, and the change value of the fan power data relative to the fan power data of the previous time sequence is greater than a preset threshold.
For example only, assuming a preset threshold of 10 for the falling span, the fan power time series is {20,0,25,30,22,12,8,0,18}, due to P 2 The value of (2) is reduced from 20 to 0, the falling span is larger than the preset threshold value, P 2 Is the missing value data. Due to P 8 The value of (2) is reduced from 8 to 0, the falling span is smaller than the preset threshold value, P 8 Not the missing data.
In an exemplary embodiment, step S206 includes:
preprocessing to obtain a moving average sequence;
dividing the moving average sequence into a training set and a verification set, and training initial fan power recursion prediction to obtain a fan power recursion prediction model; the method comprises a single-layer BiLSTM model for processing a lightweight fan power prediction task and a double-layer BiLSTM model for processing a lightweight fan power prediction task.
In some embodiments, there is a large amount of fluctuation and noise in the target fan power time sequence after the value deficiency is supplemented, and the subsequent prediction is greatly influenced. By calculating the moving average, random noise or fluctuation in the data can be effectively removed, so that the data is smoother, the method is very helpful for identifying trends and modes, and long-term trends can be highlighted and short-term fluctuation can be restrained.
In some embodiments, the moving average sequence and performance may also be preprocessed, normalized to a sequence with zero mean and unit variance, and then a multi-step prediction step may be specified, the preparation time feature may be used to train a single-layer BiLSTM model and a double-layer BiLSTM model, and the adaptability to the lightweight and heavyweight fan power prediction tasks may be improved by training both models.
In an exemplary embodiment, step S208 includes:
respectively obtaining a single-layer BiLSTM model, a first prediction result and a second prediction result of double-layer BiLSTM model prediction;
and fusing the first prediction result and the second prediction result to obtain the fan power of the wind power plant in the time to be measured.
In some embodiments, the weighting is used to gradually transition from the single-layer BiLSTM result to the double-layer BiLSTM result when the first prediction result and the second prediction result of the single-layer BiLSTM model and the double-layer BiLSTM model are fused. This weighting may be achieved by setting a series of weights such that the results of a single layer of BiLSTM are more dependent in the initial phase, and then gradually increasing the dependence on the results of a double layer of BiLSTM until a comprehensive, balanced prediction results is ultimately formed. The advantages of the single-layer BiLSTM model and the double-layer BiLSTM model in different stages can be comprehensively utilized by the processing mode, so that the overall prediction performance is improved.
In the implementation process, referring to fig. 5 and 6, fan power data of the wind farm a in 2021, 1 to 7 months, with a data sampling interval of 15min, are selected, and power data of three hours in the future are predicted. Setting the threshold value of the model searching defect value point as 10, setting the hidden layer number of the BiLSTM model as 200, adopting Adam self-adaptive learning rate optimization algorithm, setting the maximum iteration number as 200, and carrying out recursion prediction according to a method for predicting 1 data by 30 data. In combining the single-layer and double-layer BiLSTM model results, the final predicted result will gradually transition from the single-layer BiLSTM result to the double-layer BiLSTM result in a weighted manner for both characteristics. The result of searching for missing values is shown in fig. 5, and it can be seen that the program automatically searches for data outliers according to the threshold and successfully distinguishes between normal zero values. The resulting model predictive evaluation index values are shown in table 1 below. The set prediction interval is predicted according to the trained model, the obtained result is shown in fig. 6, and as can be seen from fig. 6, the current model has certain credibility for predicting the future in a short time, and the trend prediction aspect is relatively fit.
| MAE | RMSE |
| 2.92 | 3.02 |
TABLE 1
Wherein, the average absolute error (Mean Absolute Error, abbreviated as MAE) MAE and root mean square error (Root Mean Square Error, abbreviated as RMSE) are very close to each other, which indicates that the prediction result has higher accuracy.
As shown in fig. 7 and 8, fan power data of the wind farm B from 2021 to 7 months are selected, the data sampling interval is 15min, and power data of three hours in the future are predicted. The model was set as before and the calculation results are shown in fig. 7, 8 and table 2.
| MAE | RMSE |
| 0.43 | 0.55 |
TABLE 2
As can be seen from fig. 5, 6 and table 2, the program has strong performance in both missing data identification and data recursive prediction. The result of combining the two examples can be obtained, and the program can be used for carrying out short-time fan power recursion prediction under the condition that the data resources are small and continuous deficiency exists.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a fan power recursion prediction device for realizing the above-mentioned fan power recursion prediction method. The implementation of the solution provided by the apparatus is similar to the implementation described in the above method, so the specific limitation in the embodiments of the apparatus for recursively predicting fan power provided below may be referred to the limitation of the method for recursively predicting fan power hereinabove, and will not be repeated herein.
In one exemplary embodiment, as shown in fig. 9, there is provided a blower power recursion prediction apparatus including: a sequence construction module 410, a sequence update module 420, a model training module 430, and a data prediction module 440, wherein:
a sequence construction module 410, configured to construct a fan power time sequence according to the fan power data of the historical period;
the sequence updating module 420 is configured to obtain the missing value data in the fan power time sequence, and fill the missing value data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence;
The model training module 430 is configured to train the initial fan power recursion prediction model according to the target fan power time sequence, so as to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in a target fan power time sequence;
the data prediction module 440 is configured to predict a fan power of the wind farm in the time to be measured according to the fan power recursion prediction.
In one embodiment, the sequence update module 420 is further specifically configured to:
determining fan power data meeting default preset conditions in a fan power time sequence as default data; the default preset condition includes that the value of the fan power data is zero, and the change value of the fan power data relative to the fan power data of the previous time sequence is greater than a preset threshold.
In one embodiment, the apparatus further comprises:
the intermediate sequence generating module is used for interpolating and filling the default data to obtain an intermediate fan power time sequence;
and the piecewise linear regression model generation module is used for training the initial piecewise linear regression model according to the intermediate fan power time sequence so as to optimize the parameters of the initial piecewise linear regression model until the trained piecewise linear regression model is obtained.
In one embodiment, a piecewise linear regression model generation module includes:
the characteristic acquisition sub-module is used for acquiring an exponential weighted moving average characteristic and a moving median characteristic of the intermediate fan power time sequence;
the meta-feature acquisition sub-module is used for processing the intermediate fan power time sequence according to the BiLSTM model to obtain meta-features of the intermediate fan power time sequence;
and training the initial piecewise linear regression model according to the meta-feature, the exponentially weighted moving average feature and the moving median feature to optimize parameters of the initial piecewise linear regression model until a trained piecewise linear regression model is obtained.
In one embodiment, model training module 430 is also specifically configured to:
preprocessing to obtain a moving average sequence;
dividing the moving average sequence into a training set and a verification set, and training initial fan power recursion prediction to obtain a fan power recursion prediction model; the method comprises a single-layer BiLSTM model for processing a lightweight fan power prediction task and a double-layer BiLSTM model for processing a lightweight fan power prediction task.
In one embodiment, the data prediction module 440 is further specifically configured to:
Respectively obtaining a single-layer BiLSTM model, a first prediction result and a second prediction result of double-layer BiLSTM model prediction;
and fusing the first prediction result and the second prediction result to obtain the fan power of the wind power plant in the time to be measured.
According to the fan power recursion prediction method, the missing value data can be accurately filled according to the rule of the fan power historical data, the diversity of the data is improved, the fan power can be accurately predicted based on a small amount of data through the fan power recursion prediction model according to the captured overall characteristics and rule, and therefore the accuracy and the interpretability of prediction are improved.
The respective modules in the fan power recursion prediction apparatus described above may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
Fig. 10 in an exemplary embodiment, a computer device, which may be a terminal, is provided, and an internal structure diagram thereof may be as shown in fig. 10. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a blower power recursion prediction method. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 10 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an exemplary embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor performing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use, and processing of the related data are required to meet the related regulations.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRA M), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Cha nge Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A method of blower power recursion prediction, the method comprising:
constructing a fan power time sequence according to fan power data of a historical period;
obtaining the missing value data in the fan power time sequence, and filling the missing value data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence;
Training an initial fan power recursion prediction model according to the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in the target fan power time sequence;
and predicting the fan power of the wind power plant in the time to be measured according to the fan power recursion prediction.
2. The method of claim 1, wherein the obtaining the missing data in the fan power time series comprises:
determining fan power data meeting default preset conditions in the fan power time sequence as default data; the default preset condition includes that the value of the fan power data is zero, and the change value of the fan power data relative to the fan power data of the previous time sequence is larger than a preset threshold.
3. The method of claim 1, further comprising, prior to said filling in said missing data by a piecewise linear regression model:
interpolation filling is carried out on the default data to obtain a middle fan power time sequence;
And training an initial piecewise linear regression model according to the intermediate fan power time sequence to optimize parameters of the initial piecewise linear regression model until the piecewise linear regression model after training is obtained.
4. The method of claim 3, wherein said training an initial piecewise linear regression model from the intermediate fan power time series comprises:
acquiring an exponential weighted moving average characteristic and a moving median characteristic of the intermediate fan power time sequence;
processing the intermediate fan power time sequence according to a BiLSTM model to obtain meta-characteristics of the intermediate fan power time sequence;
and training the initial piecewise linear regression model according to the meta-feature, the exponentially weighted moving average feature and the moving median feature to optimize parameters of the initial piecewise linear regression model until the piecewise linear regression model after training is obtained.
5. The method of claim 1, wherein training an initial fan power recursion prediction model based on the target fan power time sequence to optimize parameters of the initial fan power recursion prediction until a trained fan power recursion prediction model is obtained, comprises:
Preprocessing to obtain a moving average sequence;
dividing the moving average sequence into a training set and a verification set, and training initial fan power recursion prediction to obtain the fan power recursion prediction model; the method comprises a single-layer BiLSTM model for processing a lightweight fan power prediction task and a double-layer BiLSTM model for processing a lightweight fan power prediction task.
6. The method of claim 5, wherein predicting fan power of the wind farm during the time to be measured based on the fan power recursion prediction comprises:
respectively obtaining a first prediction result and a second prediction result of the single-layer BiLSTM model and the double-layer BiLSTM model;
and fusing the first prediction result and the second prediction result to obtain the fan power of the wind power plant in the time to be measured.
7. A fan power recursion prediction apparatus, the apparatus comprising:
the sequence construction module is used for constructing a fan power time sequence according to the fan power data of the historical period;
the sequence updating module is used for acquiring the default data in the fan power time sequence, and filling the default data through a piecewise linear regression model to obtain a target fan power time sequence; the piecewise linear regression model is used for capturing local characteristics and rules in the target fan power time sequence;
The model training module is used for training an initial fan power recursion prediction model according to the target fan power time sequence so as to optimize parameters of the initial fan power recursion prediction until a fan power recursion prediction model after training is obtained; the fan power recursion prediction model is used for capturing integral characteristics and rules in the target fan power time sequence;
and the data prediction module is used for predicting the fan power of the wind power plant in the time to be detected according to the fan power recursion prediction.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311565839.5A CN117578428A (en) | 2023-11-22 | 2023-11-22 | Fan power recursion prediction method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311565839.5A CN117578428A (en) | 2023-11-22 | 2023-11-22 | Fan power recursion prediction method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117578428A true CN117578428A (en) | 2024-02-20 |
Family
ID=89860274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311565839.5A Pending CN117578428A (en) | 2023-11-22 | 2023-11-22 | Fan power recursion prediction method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117578428A (en) |
-
2023
- 2023-11-22 CN CN202311565839.5A patent/CN117578428A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230128989A1 (en) | Systems and methods of data preprocessing and augmentation for neural network climate forecasting models | |
| CN111091233A (en) | Wind power plant short-term wind power prediction modeling method based on wavelet analysis and multi-model AdaBoost depth network | |
| US20230072708A1 (en) | Asymmetric Laplace-based wind power forecasting method and system | |
| WO2021129086A1 (en) | Traffic prediction method, device, and storage medium | |
| CN112766596B (en) | Construction method of building energy consumption prediction model, energy consumption prediction method and device | |
| CN112187554B (en) | Operation and maintenance system fault positioning method and system based on Monte Carlo tree search | |
| CN112215442A (en) | Method, system, device and medium for predicting short-term load of power system | |
| CN114330935A (en) | New energy power prediction method and system based on multiple combined strategy integrated learning | |
| US11197175B2 (en) | Forcasting time series data | |
| CN116021981A (en) | Method, device, equipment and storage medium for predicting ice coating faults of power distribution network line | |
| CN115600717A (en) | Federal learning-based industry-divided power load prediction method, equipment and storage medium | |
| CN116316617B (en) | Multi-station intelligent fusion new energy generation power region prediction method and system | |
| CN116523145B (en) | Photovoltaic power ultra-short-term prediction method and device, computer equipment and storage medium | |
| CN117674119A (en) | Power grid operation risk assessment method, device, computer equipment and storage medium | |
| CN117033039A (en) | Fault detection method, device, computer equipment and storage medium | |
| CN116522594A (en) | Time self-adaptive transient stability prediction method and device based on convolutional neural network | |
| CN117578428A (en) | Fan power recursion prediction method, device, computer equipment and storage medium | |
| CN116258923A (en) | Image recognition model training method, device, computer equipment and storage medium | |
| CN113408808A (en) | Training method, data generation method, device, electronic device and storage medium | |
| CN116881624B (en) | Composite extreme event forecasting method, device, computer equipment and storage medium | |
| CN113222276B (en) | Ice-covering condition prediction method, device, computer equipment and storage medium | |
| Plessis et al. | Unsupervised multi scale anomaly detection in streams of events | |
| CN117132154A (en) | Data processing method, apparatus, computer device, and computer readable storage medium | |
| CN115719083A (en) | Model training method and device, computer equipment and readable storage medium | |
| CN117613883A (en) | Method and device for predicting generated power, computer equipment and storage medium |
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 |