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

ARIMA and improved Elman neural network combined wind power prediction method

A wind power forecasting and neural network technology, applied in neural learning methods, biological neural network models, forecasting, etc., to achieve simple modeling, improved forecasting accuracy, and good short-term wind power forecasting effects

Pending Publication Date: 2021-07-09
NANJING UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to propose a wind power forecasting method combining ARIMA and improved Elman neural network for the problems in the above-mentioned wind power forecasting field

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
  • ARIMA and improved Elman neural network combined wind power prediction method
  • ARIMA and improved Elman neural network combined wind power prediction method
  • ARIMA and improved Elman neural network combined wind power prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The invention proposes a wind power prediction method combining ARIMA and improved Elman neural network. The present invention will be described in further detail below in conjunction with specific embodiments and accompanying drawings, but the implementation manners of the present invention are not limited thereto.

[0046] refer to figure 1 As shown, it is a flow chart of a wind power prediction method combining ARIMA and improved Elman neural network, characterized in that the ARIMA model is combined with the improved Elman neural network model to predict wind power; firstly, the ARIMA model is used to predict wind power Make a preliminary prediction, then input the prediction results of the ARIMA model into the improved Elman model for prediction again, use the genetic algorithm (GA) to train and optimize the initial weight and threshold of the Elman network, output the final wind power prediction value, and complete the wind power analysis. Combined forecasting of...

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 an ARIMA and improved Elman neural network combined wind power prediction method, and the combined model combines an ARIMA model and an improved Elman neural network model for short-term wind power prediction, wherein the ARIMA model considers the linear behavior of wind power time sequence data, the Elman neural network model considers the nonlinear behavior of the wind power time sequence data, and the weight and threshold of the Elman network are trained and optimized by means of genetic algorithm (GA). Firstly, wind power data are input into an ARIMA model for preliminary prediction, then a prediction result of the ARIMA model is input into an improved Elman model for prediction again, and the error of a final prediction result of a combined model is smaller than the prediction error of each single model of the ARIMA model and the Elman model. The method provided by the invention is simple in modeling process, can quickly and effectively predict the wind power, and is of great significance to safety and dispatching operation of a power system under the condition of wind power integration.

Description

technical field [0001] The invention belongs to the technical field of wind power forecasting, in particular to a wind power forecasting method combining ARIMA and improved Elman neural network. Background technique [0002] While fossil fuels such as coal, oil, and natural gas are used in large quantities and are increasingly depleted worldwide, they have also brought serious environmental pollution problems such as smog, acid rain, and greenhouse effect to human life. The increasingly popular concept of sustainable development requires all countries to spare no effort to develop renewable energy power generation technologies. Wind power has become the fastest-growing and most mature renewable energy power generation technology. The installed capacity of wind power has increased rapidly, achieving large-scale parallelism network. [0003] However, due to the influence of natural wind, the output power of wind farms is fluctuating, random, and intermittent. After grid conne...

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): G06Q10/04G06Q50/06G06N3/04G06N3/08
CPCG06Q10/04G06Q50/06G06N3/086G06N3/044G06N3/045
Inventor 曹权李双明李岩刘辉曹树新
Owner NANJING UNIV OF SCI & TECH