Short-term wind power forecasting method based on improved afsa and optimized elm

A technology for wind power prediction and wind speed, applied in the direction of prediction, electrical components, circuit devices, etc., can solve problems such as easy to fall into local minimum, increase calculation time cost, low prediction accuracy, etc., to achieve favorable prediction data and error probability Concentrated distribution and high prediction accuracy

Active Publication Date: 2019-07-02
NANJING UNIV OF INFORMATION SCI & TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the short-term wind power prediction based on ELM in the prior art, the prediction accuracy is low, the cost of calculation time increases, and it is easy to fall into the problem of local minimum

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 power forecasting method based on improved afsa and optimized elm
  • Short-term wind power forecasting method based on improved afsa and optimized elm
  • Short-term wind power forecasting method based on improved afsa and optimized elm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings.

[0034] The short-term wind power prediction method based on the improved AFSA optimized ELM of the present invention uses the improved fish swarm algorithm to optimize the weight and threshold of the extreme learning machine, and uses the improved artificial fish swarm optimization extreme learning machine to perform short-term wind power prediction, which has fast convergence speed , has the characteristics of strong generalization ability and high prediction accuracy, and is more suitable for short-term wind power prediction, including the following steps,

[0035] Step (A), determine the input vector and output vector of extreme learning machine network: adopt single wind speed as the input vector of limited learning machine network, input vector is I=[I 1 ,I 2 ,...,I M ], the output vector is y=F (I), wherein, I is wind speed, M is the wind speed number of input;...

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 present invention discloses a short-period wind power prediction method for optimizing an ELM based on an improved AFSA (Artificial Fish Swarm Algorithm). The method comprises the following steps: randomly generating an artificial fish initial group, taking the weight and the threshold value of an extreme learning machine (ELM) network as the position vector of the artificial fish school, determining the food concentration of the artificial fish school through the root-mean-square error function of the ELM, solving the optimal position vector through adoption of an improved fish school method, and taking the position vector as the initial weight and the threshold value of the ELM network to perform prediction of the short-period wind power. The short-period wind power prediction method is fast in convergence rate, high in generalization ability and high in prediction accuracy, and has a good application prospect.

Description

technical field [0001] The invention relates to the technical field of short-term wind power forecasting, in particular to a short-term wind power forecasting method based on improved AFSA optimized ELM. Background technique [0002] With the global warming and the depletion of non-renewable resources such as oil and natural gas, the development and utilization of clean and renewable energy has been increasingly attached great importance to by countries all over the world. Since the early 1990s in foreign countries, the research on short-term wind power forecasting methods has started. Due to the late start of wind power forecasting, there are still many deficiencies in forecasting accuracy, reliability and adaptability to different wind fields. [0003] The extreme learning machine ELM is a new learning method in the single hidden layer feedforward neural network SLFN. The training process does not need to be adjusted, and the optimal solution can be obtained by setting the...

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): H02J3/00G06N3/00G06Q10/04G06Q50/06
CPCG06N3/006G06Q10/04G06Q50/06H02J3/00
Inventor 张颖超邓华王雅晨熊雄顾荣黄飞
Owner NANJING UNIV OF INFORMATION SCI & TECH
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