Method for constructing photovoltaic power station generation capacity short-term prediction model based on multiple neural network combinational algorithms

A neural network algorithm and neural network technology, applied in the forecast of solar photovoltaic power generation, photovoltaic power generation and grid-connected technology, can solve problems such as single algorithm, poor applicability in different weather, large measurement error of prediction model, etc., to improve prediction accuracy, Practicality guarantee, effect of reducing prediction error

Inactive Publication Date: 2015-12-23
QIQIHAR UNIVERSITY
View PDF3 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention solves the problem that the existing photovoltaic power plant power generation prediction model uses a single algorithm, has

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for constructing photovoltaic power station generation capacity short-term prediction model based on multiple neural network combinational algorithms
  • Method for constructing photovoltaic power station generation capacity short-term prediction model based on multiple neural network combinational algorithms
  • Method for constructing photovoltaic power station generation capacity short-term prediction model based on multiple neural network combinational algorithms

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0039] Specific embodiment one: see figure 1 To explain this embodiment, the method for constructing a short-term prediction model of photovoltaic power generation capacity based on multiple neural network combination algorithms described in this embodiment is as follows:

[0040] Step 1: Selection of neural network algorithm;

[0041] The four neural network algorithms of BP, Elman, RBF and GRNN are used to construct neural network prediction sub-models A, B, C and D respectively, and the ambient temperature T at different time points during the daily power station working period i , Daily average solar radiation intensity Average daily wind speed As the input data of the short-term prediction model of photovoltaic power generation, to predict the photovoltaic output power P at the corresponding time point of the day i As the output data of each neural network prediction sub-model A, B, C and D;

[0042] Step 2: Selection of sample data;

[0043] Through the photovoltaic data collec...

Example Embodiment

[0048] Embodiment 2: The difference between this embodiment and the method for constructing a short-term prediction model of photovoltaic power generation capacity based on multiple neural network combination algorithms described in the first embodiment is that the method also includes step four: short-term photovoltaic power generation Revision of the forecast model;

[0049] a) First, normalize the sample data in step two,

[0050] b) Secondly, genetic algorithm and particle swarm algorithm are used.

[0051] In this embodiment, first, the sample data in step 2 is normalized to further reduce the prediction error of the prediction sub-model. Secondly, using genetic algorithm and particle swarm algorithm, two methods are used to optimize all neural network predictive sub-models, which can avoid the problem of neural network algorithm easily falling into local optimality, and further reduce the prediction error of neural network predictive sub-model.

[0052] In this embodiment, the ...

Example Embodiment

[0059] Embodiment 3: The difference between this embodiment and the method for constructing a short-term prediction model of photovoltaic power generation capacity based on multiple neural network combination algorithms described in the first or second embodiment is that the method also includes step five: Quantitative short-term forecasting model evaluation;

[0060] Two error evaluation methods of average absolute percentage error MAPE and root mean square error RMSE are used to evaluate the error of the short-term prediction model of photovoltaic power generation.

[0061] M A P E = 1 N X i = 1 N | P p i - P a i P a i | X 100 % ,

[0062] R M S E = X i = 1 N ( P p i - P a i ) N 2 ,

[0063] Among them, N represents the total amount of data, i is a positive integer, Represents the predicted value of the i-th data point, Represents the actual...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a method for constructing a photovoltaic power station generation capacity short-term prediction model based on multiple neural network combinational algorithms and belongs to the technical field of photovoltaic power generation, power grid connection technology and solar energy photovoltaic forecasting. The method overcomes the problem that a usually-used algorithm for constructing the photovoltaic power station generation capacity short-term prediction model is single and is likely to fall into local optimization, further resulting in big measurement error of the prediction model. The technical construction method of the invention is realized as follows: firstly using four different neural network algorithms to construct sub-models for neural network prediction; secondly screening and classifying weather information and analyzing the suitability of the various sub-models for neural network prediction; giving weighted parameter values of the sub-models in a combined model according to the suitability to further make the combined neural network model for prediction suitable for different weather conditions and then completing the construction of the photovoltaic power station generation capacity short-term prediction model. The method is mainly used for photovoltaic power station grid connection short-term prediction.

Description

technical field [0001] The invention belongs to the fields of photovoltaic power generation and grid-connected technology, and solar photovoltaic power generation forecast. Background technique [0002] With the rapid development of the world economy, the demand for energy is increasing day by day, and the traditional non-renewable energy sources (coal, oil, natural gas, etc.) The advantages of large size, renewability, and wide distribution range have become research hotspots all over the world. In my country, solar photovoltaic power generation has become an important way of solar energy application, and the scale and quantity of grid-connected photovoltaic power plants are constantly increasing. The output of photovoltaic power generation system is affected by factors such as weather and solar radiation intensity, which is fluctuating and intermittent. It is an uncontrollable factor for grid connection and will affect the safety and stability of the power system. Theref...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06Q50/06G06N3/02
CPCY04S10/50
Inventor 姚仲敏潘飞吴金秋都文和李梦瑶张鹏
Owner QIQIHAR UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap