Unlock instant, AI-driven research and patent intelligence for your innovation.

A Neural Network Wind Speed ​​Prediction Method Based on Time Series Data Analysis

A neural network and time series technology, which is applied in the field of neural network wind speed prediction based on time series data analysis, can solve problems such as grid disturbance, wind power fluctuation, and large peak-to-valley difference of wind power, so as to improve the accuracy.

Active Publication Date: 2021-06-29
NAT UNIV OF DEFENSE TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the process of wind power generation, wind energy is affected by natural factors in a complex manner, with very strong random fluctuations, and the output wind power energy also has strong fluctuations. In the process of utilizing wind power, two problems need to be solved , the first is the problem of wind power energy dispatching, the peak-to-valley difference of wind power power is large, and the energy regulation between peak and valley needs to be planned in advance, and the second is the stability of the transmission network. large disturbances, the carrying capacity and stability of the power grid must also be designed in advance

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
  • A Neural Network Wind Speed ​​Prediction Method Based on Time Series Data Analysis
  • A Neural Network Wind Speed ​​Prediction Method Based on Time Series Data Analysis
  • A Neural Network Wind Speed ​​Prediction Method Based on Time Series Data Analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further described below in conjunction with the accompanying drawings, but the present invention is not limited in any way. Any transformation or replacement based on the teaching of the present invention belongs to the protection scope of the present invention.

[0045] Using historical meteorological data to predict future wind speed, it is necessary to analyze the factors that may affect the wind speed. Research shows that the wind speed to be predicted is at least the same as the historical wind speed, wind direction, temperature, humidity, air pressure, wind speed difference, and wind speed standard deviation It is related to the 8 factors of wind direction and standard deviation, but historical meteorological data should be viewed with a dynamic perspective. Historical data is date-based time series data. Therefore, when dealing with meteorological attribute data of 8 factors, it is necessary to analyze A certain trend, using this tren...

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 neural network wind speed prediction method based on time series data analysis, which includes acquiring multiple sets of time series data of wind farms; establishing regression models of the meteorological data respectively, and recording meteorological attribute values ​​after regression; establishing BP neural network Network model, using differential operation and firefly hybrid algorithm to train the neural network model in groups first, and then conduct global training; through the latest historical meteorological data, calculate the latest meteorological attribute value after regression; input the latest meteorological attribute value into the neural network, Calculate the predicted wind speed value. The present invention adopts the trend data after the regression to replace the fixed data of a certain date to train the model, utilizes the difference algorithm and the firefly algorithm to improve the BP neural network, and adopts the method of combining group training and global training, so that the present invention is more traditional The prediction accuracy of the method is higher.

Description

technical field [0001] The invention belongs to the field of wind speed prediction of wind farms, and in particular relates to a neural network wind speed prediction method based on time series data analysis. Background technique [0002] Wind power is one of the most important ways that society utilizes renewable energy today. However, in the process of wind power generation, wind energy is affected by natural factors in a complex manner, with very strong random fluctuations, and the output wind power energy also has strong fluctuations. In the process of utilizing wind power, two problems need to be solved , the first is the problem of wind power energy dispatching, the peak-to-valley difference of wind power power is large, and the energy regulation between peak and valley needs to be planned in advance, and the second is the stability of the transmission network. If there is a large disturbance, the carrying capacity and stability of the power grid must also be designed...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/04G06Q50/06G06N3/00G06N3/04
Inventor 王锐廉振宇刘亚杰张涛黄生俊雷洪涛李洁明梦君李凯文
Owner NAT UNIV OF DEFENSE TECH