CN114091317A - Photovoltaic power station power prediction method based on NWP irradiance correction and error prediction - Google Patents
Photovoltaic power station power prediction method based on NWP irradiance correction and error prediction Download PDFInfo
- Publication number
- CN114091317A CN114091317A CN202111354751.XA CN202111354751A CN114091317A CN 114091317 A CN114091317 A CN 114091317A CN 202111354751 A CN202111354751 A CN 202111354751A CN 114091317 A CN114091317 A CN 114091317A
- Authority
- CN
- China
- Prior art keywords
- irradiance
- nwp
- prediction
- power
- error
- 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
- 238000012937 correction Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 239000002245 particle Substances 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 3
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005096 rolling process Methods 0.000 claims description 3
- 238000010248 power generation Methods 0.000 abstract description 13
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000053 physical method Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/25—Design optimisation, verification or simulation using particle-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Mathematical Physics (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention relates to a photovoltaic power station power prediction method based on NWP irradiance correction and error prediction, which comprises the following steps: acquiring historical operating data of a photovoltaic power station and NWP numerical weather forecast; establishing an NWP irradiance correction model to realize multi-step correction of the NWP irradiance; thirdly, obtaining power prediction data by adopting the corrected irradiance based on the optimized power prediction model of the PSO-ELM; fourthly, calculating an error according to the power prediction data, and establishing an error prediction model based on a time sequence; and obtaining a plurality of error predicted values by a data iteration method, and combining the error predicted values with power predicted data to obtain a final photovoltaic power predicted value. The method has higher prediction precision, can effectively improve the reliability of photovoltaic power generation power prediction, and provides reference for a decision maker of a power system.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a photovoltaic power station power prediction method based on NWP irradiance correction and error prediction.
Background
In recent years, it has become a common consensus among countries to accelerate the development of new energy in order to solve the problem of fossil energy depletion and to realize energy transformation. Photovoltaic power generation is rapidly developing with its advantages of being clean and sustainable. However, photovoltaic power generation has strong randomness and intermittent periodicity. When photovoltaic power generation is connected to the grid in a large scale, impact can be generated on an electric power system, and safe and stable operation of the electric power system is seriously influenced. Because the photovoltaic short-term power prediction has important significance for the power generation planning of the power department, the accurate short-term power prediction can improve the reliability of the photovoltaic power generation connected to the power grid, reduce the influence of the photovoltaic power generation uncertainty on the power system, and is one of the key technologies for solving the grid-connected obstacle of the photovoltaic power generation.
At present, methods related to short-term power prediction of photovoltaic power generation can be roughly divided into two categories, namely physical methods and statistical methods. The physical method is based on a solar radiation transfer equation, a photovoltaic module operation equation and the like to establish a physical model so as to directly calculate the photovoltaic output power, but the modeling process is complex and the robustness is poor due to the involvement of various equations, and the method is difficult to realize; the statistical method is to train historical operating data of a photovoltaic power station to establish a prediction model through an intelligent algorithm according to the relation between the output power of photovoltaic power generation and meteorological factors, the model is relatively simple, but due to the limitation of the intelligent algorithm, a prediction result has a certain degree of error. Meanwhile, input data of power prediction is derived from numerical weather forecast, and the influence of the error of the numerical weather forecast on the power prediction is considered to be less in the prior art, so that the residual error of the conventional prediction method has negative influence on the power prediction precision, and the predicted data needs to be subjected to post-processing to reduce the influence.
Disclosure of Invention
The invention aims to provide a photovoltaic power station power prediction method based on NWP irradiance correction and error prediction, which improves prediction accuracy.
In order to solve the problems, the photovoltaic power station power prediction method based on NWP irradiance correction and error prediction comprises the following steps:
acquiring historical operating data of a photovoltaic power station and NWP numerical weather forecast;
establishing an NWP irradiance correction model to realize multi-step correction of the NWP irradiance;
thirdly, obtaining power prediction data by adopting the corrected irradiance based on the optimized power prediction model of the PSO-ELM;
fourthly, calculating an error according to the power prediction data, and establishing an error prediction model based on a time sequence; and obtaining a plurality of error predicted values by a data iteration method, and combining the error predicted values with power predicted data to obtain a final photovoltaic power predicted value.
The multi-step NWP irradiance correction method comprises the following steps:
determining data parameters of the corrected modelnWill bet-n+1 totThe actually measured irradiance at the moment is used as a correction variable so as to correct the NWP irradiance at the next moment;
selectingt-n+1,t-n+2…t-1, measured irradiance sum at time ttNWP forecast irradiance at +1 time is used as input to the model,tthe actually measured irradiance at the +1 moment is used as the output of the model, an ELM extreme learning machine algorithm is adopted to establish an irradiance correction model, and the aim of correcting the irradiance is achievedtCorrection of the predicted irradiance at time NWP + 1.
Thirdly, adopting a rolling iteration mode to performtThe NWP irradiance correction value at the +1 moment is used as input, and then the correction value is applied totCorrecting the NWP forecast irradiance at the +2 moment to realize multistep correction of the NWP forecast irradiance;
selecting a root mean square error RMSE, an average absolute error MAE and an average absolute percentage error MAPE to evaluate the NWP irradiance correction result, wherein the calculation formula is as follows:
in the formula:g a for the corrected irradiance/predicted power;g measured is the actual irradiance/measured power;nis the number of samples.
The power prediction data in the step three is obtained according to the following method:
establishing a photovoltaic power prediction model by adopting an ELM extreme learning machine algorithm;
classifying data according to months, taking actual measurement historical meteorological data as input, taking actual measurement historical power as output, and training a prediction model;
iii, optimizing the number of hidden layer nodes of the ELM by adopting a Particle Swarm Optimization (PSO), and searching the optimal number of hidden layer nodes by taking the minimum mean square error of a prediction result as an objective function of the PSO optimization to realize the optimization of the photovoltaic power prediction model;
iv, different prediction models are selected according to months, and the corrected NWP irradiance data and other meteorological information are input to obtain power prediction data.
Compared with the prior art, the invention has the following advantages:
1. the method and the device consider that a hybrid prediction model is established from three aspects of data preprocessing, model parameter optimization and data post-processing in different stages of the prediction process, so that the power prediction precision is improved.
2. The irradiance correction model is established, the NWP irradiance is corrected through actually measured irradiance, and errors of input data in the prediction model are reduced.
3. The invention establishes a power prediction model based on PSO-ELM, and adopts a PSO optimization prediction model to reduce the error of the model.
4. The method utilizes the error sequence to establish an error prediction model, combines the power prediction value and the error prediction value to obtain a final power prediction result, and further reduces the error of power prediction.
5. Compared with the traditional method, the method has higher prediction precision, can effectively improve the reliability of photovoltaic power generation power prediction, and provides reference for a decision maker of a power system.
Drawings
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a single step modification diagram of the present invention.
FIG. 3 is a schematic view of a multi-step modification of the present invention.
Fig. 4 is a schematic diagram of a photovoltaic power prediction model according to the present invention.
FIG. 5 is a schematic diagram of an error prediction model according to the present invention.
FIG. 6 is a graph of predicted power versus measured power according to the present invention.
Detailed Description
As shown in fig. 1, the photovoltaic power plant power prediction method based on NWP irradiance correction and error prediction includes the following steps:
acquiring historical operating data of a photovoltaic power station and NWP numerical weather forecast:
checking the integrity and reasonableness of the data, deleting error data, filling up missing data and the like. The collected raw data comprises historical power data and historical meteorological data (including environmental data such as irradiance, temperature and wind speed) of the photovoltaic power station and contemporaneous NWP numerical weather forecast data, and various data can be corresponded on a time scale.
And establishing a NWP irradiance correction model to realize multi-step correction of the NWP irradiance. The specific process is as follows:
determining data parameters of the corrected modelnWill bet-n+1 totThe measured irradiance at a time is used as a correction variable to correct for the next time (i.e., the time at which the measured irradiance is measured)t+1 time) is corrected, the correction process is as shown in fig. 2.
Selectingt-n+1,t-n+2…t-1, measured irradiance sum at time ttNWP forecast irradiance at +1 time is used as input to the model,tthe actually measured irradiance at the +1 moment is used as the output of the model, an ELM extreme learning machine algorithm is adopted to establish an irradiance correction model, and the aim of correcting the irradiance is achievedtCorrection of the predicted irradiance at time NWP + 1.
Given aNA plurality of different training samples (x i ,t i ) Wherein, in the step (A),x i =[x i1,x i2…x in ]Tfor the input value of the sample, the value of the sample,t i =[t i1,t i2…t in ]Tis the desired output value of the sample. Has the advantages ofLA hidden node andg(x) The mathematical model of the ELM as an excitation function can be expressed as:
in the formula:is to connect the input sample with the secondThe weight vector of each hidden node is calculated,is connected to the firstA weight vector of hidden nodes and output samples,b i is the firstAn offset of each hidden node;β i is the output weight;g(x) Is an excitation function;to representw i Andx j the inner product of (d).
As described aboveNThe matrix form of the equation can be written as:
wherein the content of the first and second substances,His the output of the hidden node;βis the output weight;Tis the desired output.
HTo (1) aiColumn is the firstiThe output vector of each hidden layer node. Connection weight between hidden layer and output layerβCan be obtained using a least squares solution of the following system of equations:
the solution can be expressed as:
in the formula:H +is the generalized inverse of Moore-Penrose of the hidden layer output matrix.
And thirdly, single-step correction of the NWP irradiance can be realized in the last step, the correction time is short, and sometimes the prediction time cannot meet the requirement of the prediction time.
Therefore, in a rolling iterative manner, willtThe NWP irradiance correction value at the +1 moment is used as input, and then the correction value is applied totAnd correcting the NWP predicted irradiance at the +2 moment to realize multi-step correction of the NWP predicted irradiance, and obtaining a correction result for a longer time as shown in figure 3. And selecting a proper iteration step number according to the predicted time length to adapt to the prediction requirements of different time scales.
Selecting a root mean square error RMSE, an average absolute error MAE and an average absolute percentage error MAPE to evaluate the NWP irradiance correction result, and evaluating the subsequent power prediction precision by adopting the three indexes, wherein the calculation formula is as follows:
in the formula:g a for the corrected irradiance/predicted power;g measured is the actual irradiance/measured power;nis the number of samples.
Thirdly, obtaining power prediction data by adopting the corrected irradiance based on the optimized power prediction model of the PSO-ELM. The specific process is as follows:
and i, establishing a photovoltaic power prediction model by adopting an ELM extreme learning machine algorithm, as shown in FIG. 4.
And ii, classifying the data according to the month, taking the actually measured historical meteorological data as input, taking the actually measured historical power as output, and training the prediction model.
And iii, optimizing the number of hidden layer nodes of the ELM by adopting a Particle Swarm Optimization (PSO), and searching the optimal number of hidden layer nodes by taking the minimum mean square error of the prediction result as an objective function of the PSO optimization so as to realize the optimization of the photovoltaic power prediction model.
Optimizing hidden layer node number in ELM algorithm according to fitness function by utilizing particle swarm optimizationL. By comparing the fitness function of each iteration particle, the particle speed and position are updated to obtain the optimal hidden layer node numberL best 。The velocity and position update formula for the particles is as follows:
in the formula:are particlesiIn the first placekFirst in +1 iterationsdVelocity in dimension;is the inertial weight;are particlesiIn the first placekIn the second iterationdVelocity in dimension;c 1、c 2is a learning factor;、random numbers which are uniformly distributed in the (0,1) interval;kis the iteration number;Pbest id i, the optimal position of the particle individual;are particlesiIn the first placekIn the second iterationdA position in a dimension;Gbest kd globally optimal position for the whole particle swarm;particlesiIn the first placekFirst in +1 iterationsdThe position in the dimension.
Iv, different prediction models are selected according to months, and the corrected NWP irradiance data and other meteorological information are input to obtain power prediction data.
Fourthly, calculating an error according to the power prediction data, and establishing an error prediction model based on a time sequence; and obtaining a plurality of error predicted values by a data iteration method, and combining the error predicted values with power predicted data to obtain a final photovoltaic power predicted value.
The embodiment takes annual data of a national key laboratory photovoltaic demonstration test power station of a new energy power system of North China Power university as an example, and the data sampling time is 15 minutes.
The photovoltaic power station power prediction method based on NWP irradiance correction and error prediction comprises the following steps:
the method includes the steps of obtaining historical operation data of the photovoltaic power station and NWP numerical weather forecast.
And establishing a NWP irradiance correction model to realize multi-step correction of the NWP irradiance.
Wherein: table 1 shows the results for different irradiance correction parameters. Comprehensively considering three error indexes and selecting parametersn=5 as parameter input for subsequent instance verification.
Table 1: different irradiance correction parameter results
Thirdly, obtaining power prediction data by adopting the corrected irradiance based on the optimized power prediction model of the PSO-ELM.
Fourthly, calculating an error according to the power prediction data, and establishing an error prediction model based on a time sequence; and obtaining a plurality of error predicted values by a data iteration method, and combining the error predicted values with power predicted data to obtain a final photovoltaic power predicted value.
The predictive model was built according to the data relationships shown in fig. 5.X 1-X 4In order to be an input, the user can select,X 5is an output;X 2-X 5in order to be an input, the user can select,X 6and so on for output. A plurality of error predictors are obtained according to a data iteration method similar to that of fig. 3. And combining the error prediction result and the power prediction to obtain the final photovoltaic prediction power.
FIG. 6 is a graph comparing power prediction and measured power for steps 1, 4 and 8; table 2 shows the prediction evaluation indexes of the conventional ELM power prediction algorithm, the PSO-optimized ELM power prediction algorithm and the error correction-based PSO-ELM power prediction algorithm. As can be seen from fig. 6 and table 2, the prediction accuracy of the PSO-optimized ELM algorithm is higher than that of the conventional ELM algorithm, and the accuracy of the photovoltaic power generation power prediction is further improved after the error prediction model is added. The longer the prediction step number is, the longer the prediction time is, and the prediction precision is reduced to some extent; the smaller the number of prediction steps is, the lower the corresponding evaluation indexes are, which indicates that the ultra-short-term prediction has better precision.
TABLE 2 Power prediction results for different step counts
Claims (3)
1. The photovoltaic power station power prediction method based on NWP irradiance correction and error prediction comprises the following steps:
acquiring historical operating data of a photovoltaic power station and NWP numerical weather forecast;
establishing an NWP irradiance correction model to realize multi-step correction of the NWP irradiance;
thirdly, obtaining power prediction data by adopting the corrected irradiance based on the optimized power prediction model of the PSO-ELM;
fourthly, calculating an error according to the power prediction data, and establishing an error prediction model based on a time sequence; and obtaining a plurality of error predicted values by a data iteration method, and combining the error predicted values with power predicted data to obtain a final photovoltaic power predicted value.
2. The photovoltaic power plant power prediction method based on NWP irradiance correction and error prediction as recited in claim 1, wherein: the multi-step NWP irradiance correction method comprises the following steps:
determining data parameters of the corrected modelnWill bet-n+1 totThe measured irradiance at a moment is used as a correction variable so as to carry out the NWP irradiance at the next momentCorrecting the lines;
selectingt-n+1,t-n+2…t-1, measured irradiance sum at time ttNWP forecast irradiance at +1 time is used as input to the model,tthe actually measured irradiance at the +1 moment is used as the output of the model, an ELM extreme learning machine algorithm is adopted to establish an irradiance correction model, and the aim of correcting the irradiance is achievedtCorrection of the predicted irradiance at time NWP + 1.
Thirdly, adopting a rolling iteration mode to performtThe NWP irradiance correction value at the +1 moment is used as input, and then the correction value is applied totCorrecting the NWP forecast irradiance at the +2 moment to realize multistep correction of the NWP forecast irradiance;
selecting a root mean square error RMSE, an average absolute error MAE and an average absolute percentage error MAPE to evaluate the NWP irradiance correction result, wherein the calculation formula is as follows:
in the formula:g a for the corrected irradiance/predicted power;g measured is the actual irradiance/measured power;nis the number of samples.
3. The photovoltaic power plant power prediction method based on NWP irradiance correction and error prediction as recited in claim 1, wherein: the power prediction data in the step three is obtained according to the following method:
establishing a photovoltaic power prediction model by adopting an ELM extreme learning machine algorithm;
classifying data according to months, taking actual measurement historical meteorological data as input, taking actual measurement historical power as output, and training a prediction model;
iii, optimizing the number of hidden layer nodes of the ELM by adopting a Particle Swarm Optimization (PSO), and searching the optimal number of hidden layer nodes by taking the minimum mean square error of a prediction result as an objective function of the PSO optimization to realize the optimization of the photovoltaic power prediction model;
iv, different prediction models are selected according to months, and the corrected NWP irradiance data and other meteorological information are input to obtain power prediction data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111354751.XA CN114091317A (en) | 2021-11-16 | 2021-11-16 | Photovoltaic power station power prediction method based on NWP irradiance correction and error prediction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111354751.XA CN114091317A (en) | 2021-11-16 | 2021-11-16 | Photovoltaic power station power prediction method based on NWP irradiance correction and error prediction |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114091317A true CN114091317A (en) | 2022-02-25 |
Family
ID=80300915
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111354751.XA Pending CN114091317A (en) | 2021-11-16 | 2021-11-16 | Photovoltaic power station power prediction method based on NWP irradiance correction and error prediction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114091317A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114676893A (en) * | 2022-03-11 | 2022-06-28 | 中国长江三峡集团有限公司 | Photovoltaic power station solar irradiance short-term prediction method based on optimal graph structure and storage medium |
CN115529002A (en) * | 2022-11-28 | 2022-12-27 | 天津海融科技有限公司 | Photovoltaic power generation power prediction method under various weather conditions |
CN116050187A (en) * | 2023-03-30 | 2023-05-02 | 国网安徽省电力有限公司电力科学研究院 | TS fuzzy outlier self-correction method and system for second-level photovoltaic power prediction |
-
2021
- 2021-11-16 CN CN202111354751.XA patent/CN114091317A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114676893A (en) * | 2022-03-11 | 2022-06-28 | 中国长江三峡集团有限公司 | Photovoltaic power station solar irradiance short-term prediction method based on optimal graph structure and storage medium |
CN114676893B (en) * | 2022-03-11 | 2024-02-02 | 中国长江三峡集团有限公司 | Photovoltaic power station solar irradiance short-term prediction method based on optimal graph structure and storage medium |
CN115529002A (en) * | 2022-11-28 | 2022-12-27 | 天津海融科技有限公司 | Photovoltaic power generation power prediction method under various weather conditions |
CN116050187A (en) * | 2023-03-30 | 2023-05-02 | 国网安徽省电力有限公司电力科学研究院 | TS fuzzy outlier self-correction method and system for second-level photovoltaic power prediction |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109117951B (en) | BP neural network-based probability load flow online calculation method | |
CN112949945B (en) | Wind power ultra-short-term prediction method for improving bidirectional long-term and short-term memory network | |
CN114091317A (en) | Photovoltaic power station power prediction method based on NWP irradiance correction and error prediction | |
CN110807554B (en) | Generation method and system based on wind power/photovoltaic classical scene set | |
WO2017054537A1 (en) | Long-time scale photovoltaic output time sequence modelling method and apparatus | |
CN112149879B (en) | New energy medium-and-long-term electric quantity prediction method considering macroscopic volatility classification | |
CN112348292A (en) | Short-term wind power prediction method and system based on deep learning network | |
CN107681685A (en) | A kind of Probabilistic Load computational methods for considering photovoltaic non-linear dependencies | |
Sogabe et al. | Optimization of decentralized renewable energy system by weather forecasting and deep machine learning techniques | |
CN112200377A (en) | Photovoltaic medium-long term power generation capacity forecasting method and device based on SARIMAX model | |
CN113269314A (en) | New energy power generation scene data migration method based on generation countermeasure network | |
CN115829126A (en) | Photovoltaic power generation power prediction method based on multi-view self-adaptive feature fusion | |
CN113991711B (en) | Capacity configuration method for energy storage system of photovoltaic power station | |
CN111259550A (en) | Grid search and improved NM simplex algorithm-based photovoltaic model updating method | |
CN117060407B (en) | Wind power cluster power prediction method and system based on similar day division | |
Dong et al. | Day-ahead prediction of wind power based on conditional generative adversarial network | |
CN110059972B (en) | Daily solar radiation resource assessment method based on functional deep belief network | |
CN112307672A (en) | BP neural network short-term wind power prediction method based on cuckoo algorithm optimization | |
CN111815051A (en) | GRNN photovoltaic power generation prediction method considering weather influence factors | |
CN116845875A (en) | WOA-BP-based short-term photovoltaic output prediction method and device | |
Fuselero et al. | Daily Solar Radiation Forecasting based on a Hybrid NARXGRU Network in Dumaguete, Philippines. | |
CN116485004A (en) | Wind power prediction method based on power heat map and convolutional neural network | |
CN111461297B (en) | Solar irradiation quantity optimization prediction algorithm based on MPC and ELM neural network | |
CN115577856A (en) | Method and system for predicting construction cost and controlling balance of power transformation project | |
CN112581311B (en) | Method and system for predicting long-term output fluctuation characteristics of aggregated multiple wind power plants |
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 |