Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Photovoltaic probability prediction method and system based on Bayesian neural network

A neural network and probabilistic prediction technology, applied in biological neural network model, prediction, neural architecture, etc., can solve the large gap between power output and expected, the frequency and voltage of the distribution network exceeds the limit, and the fluctuation of photovoltaic power cannot be judged. To achieve the effect of improving data density, small average interval width, and improving information extraction ability

Pending Publication Date: 2020-06-05
CHINA ELECTRIC POWER RES INST +1
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This prediction method can provide a certain reference for the dispatching system to calculate the day-ahead dispatching plan, but the dispatching system still cannot judge the possible fluctuation of photovoltaic power in a short time scale
When the power grid load is large and the weather changes suddenly, dispatching based on deterministic forecast results may cause a large gap between power output and expectations, which will cause problems such as frequency limit and voltage limit in the distribution network

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
  • Photovoltaic probability prediction method and system based on Bayesian neural network
  • Photovoltaic probability prediction method and system based on Bayesian neural network
  • Photovoltaic probability prediction method and system based on Bayesian neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Such as figure 1 As shown, a photovoltaic probability prediction method based on Bayesian neural network provided by the present invention includes:

[0068] S1 Obtain weather forecast data of the point to be predicted and historical output data of photovoltaic equipment;

[0069] S2 performs dimensionality reduction processing on the weather forecast data, and obtains characteristic data based on the weather forecast data after the dimensionality reduction processing and historical output data of the photovoltaic equipment;

[0070] S3 brings the characteristic data into the pre-built improved Bayesian neural network model to obtain the photovoltaic output distribution of the points to be predicted.

[0071] The photovoltaic probability prediction method provided by the present invention requires the construction of an improved Bayesian neural network model. The model can be constructed and trained in advance for the same photovoltaic device. After the training is completed, t...

Embodiment 2

[0141] Based on the same inventive concept, the present invention also provides a photovoltaic probability prediction system based on Bayesian neural network, including:

[0142] The acquisition module is used to acquire weather forecast data of the point to be predicted and historical output data of photovoltaic equipment;

[0143] The dimensionality reduction processing module is used to perform dimensionality reduction processing on the weather forecast data, and obtain characteristic data based on the weather forecast data after the dimensionality reduction processing and the historical output data of the photovoltaic equipment;

[0144] The prediction module is used to bring the characteristic data into a pre-built improved Bayesian neural network model to obtain the photovoltaic output distribution of the points to be predicted.

[0145] In an embodiment, the prediction module includes:

[0146] The prediction unit is used to bring the characteristic data into the pre-built improv...

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 discloses a photovoltaic probability prediction method and system based on a Bayesian neural network. The method comprises the steps of obtaining weather forecast data of a to-be-predicted point and historical output data of photovoltaic equipment; carrying out dimension reduction processing on the weather forecast data, and obtaining feature data based on the weather forecast data after dimension reduction processing and historical output data of photovoltaic equipment; and substituting the feature data into a pre-constructed improved Bayesian neural network model to obtain photovoltaic output distribution of the to-be-predicted point. According to the method, the photovoltaic output distribution of the to-be-predicted point is obtained, compared with a deterministic prediction mode, the photovoltaic probability prediction method provided by the invention has a smaller average interval width when the same prediction accuracy is achieved, the prediction precision is improved, and the method has important significance for improving the safety and stability of a power grid.

Description

Technical field [0001] The invention relates to the field of new energy power prediction, in particular to a photovoltaic probability prediction method and system based on Bayesian neural network. Background technique [0002] In recent years, with the advent of the energy crisis, the utilization rate of new energy sources has increased year by year. Taking China as an example in 2018, the installed capacity of distributed photovoltaics increased by 20.96 million kilowatts compared with 2017, a year-on-year increase of 71%. Since the output of distributed power sources is highly dependent on the external weather conditions, which makes its overall randomness strong, the time and space correlation between the power source and the environment is also relatively large. Compared with traditional power sources, distributed power sources are more susceptible to the influence of factors inside and outside the system, and it is difficult to directly reflect the characteristics of changes...

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): G06Q10/04G06Q50/06G06K9/62G06N3/04
CPCG06Q10/04G06Q50/06G06N3/045G06F18/24155
Inventor 蒲天骄赵康宁王新迎李烨黄越辉
Owner CHINA ELECTRIC POWER RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products