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

Short-term wind speed prediction method based on EEMD and LSTM

A wind speed prediction, short-term technology, applied in the field of atmospheric science, can solve the problems of long time consumption, poor big data support, inaccurate prediction, etc., and achieve the effect of improving lag, small error, and high application value

Inactive Publication Date: 2019-12-10
南京信大气象科学技术研究院有限公司
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above method of predicting wind speed has poor support for big data, takes a long time, and the prediction is not accurate enough

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
  • Short-term wind speed prediction method based on EEMD and LSTM
  • Short-term wind speed prediction method based on EEMD and LSTM
  • Short-term wind speed prediction method based on EEMD and LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The present invention is described in further detail now in conjunction with accompanying drawing.

[0052] Such as figure 1 A short-term wind speed prediction method based on EEMD and LSTM is shown, which specifically includes the following steps:

[0053] 1. Preprocess the second-by-second wind speed measured by a regional meteorological observation station into a wind speed sequence with a time interval of τ, τ∈[1, 86400]s.

[0054] 2. Equipment failure and noise interference are unavoidable during the collection process of wind speed observation data, which is prone to modal aliasing during the EMD decomposition process, thereby reducing the prediction accuracy. At present, a better way to solve this problem is EEMD, and the decomposition flow chart is as follows image 3 As shown, the improvement steps are as follows:

[0055] 1) Add white noise such as from a normal distribution to the sequence N(t);

[0056] 2) EMD decomposition is performed on the newly form...

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 short-term wind speed prediction method based on EEMD and LSTM. Based on a wind speed prediction model combining ensemble empirical mode decomposition (EEMD) and a long short-term memory (LSTM) neural network, the method decomposes a wind speed sequence through EEMD to acquire a stable subsequence is obtained. The property of original data is well reserved. Errors causedby traditional empirical mode EMD mode aliasing are optimized. The method is combined with an LSTM prediction model, the hysteresis quality of the LSTM prediction model is improved, the efficiency ishigher compared with a traditional method, and meanwhile prediction errors can be effectively reduced.

Description

technical field [0001] The invention belongs to the field of atmospheric science, and in particular relates to a short-term wind speed prediction method based on EEMD and LSTM. Background technique [0002] Wind speed is the speed of airflow generated by air movement, and wind is the result of the joint action of the earth's surface atmosphere on solar radiation and surface long-wave radiation. Wind speed is characterized by uncertainty and volatility, and is one of the most difficult elements to predict in meteorological elements. Wind speed prediction is of great significance for improving the accuracy of weather forecast, predicting short-term strong wind disasters, the diffusion speed of air pollutants, and the safe operation of wind turbines. In terms of weather forecasting, wind speed is a basic element in weather forecasting, and its prediction accuracy affects the accuracy of weather forecasting; wind speed also affects the migration and diffusion speed of air pollu...

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 Applications(China)
IPC IPC(8): G06N3/04G06N3/08G06Q10/04G06Q50/06
CPCG06N3/08G06Q10/04G06Q50/06G06N3/044G06N3/045
Inventor 陆冰鉴周鹏王兴薛丰昌苗春生周可詹少伟张越
Owner 南京信大气象科学技术研究院有限公司
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