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

A Wind Power Prediction Method Based on the Combination Model of VMD and BLS

A wind power prediction and combination model technology, applied in the field of wind power, can solve problems such as endpoint effect, decomposition data mode aliasing, and affect the accuracy of prediction, so as to reduce mode aliasing, reduce endpoint effect phenomenon, and improve prediction effect of effect

Active Publication Date: 2022-06-03
SHANGHAI DIANJI UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the above method, SVM and ANN are not accurate in predicting wind power. It is difficult to select the wavelet base and determine the decomposition scale in wavelet transform. Empirical mode decomposition is easy to make the decomposition data modal aliasing and the phenomenon of endpoint effect, which affects the prediction. the accuracy of

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 Wind Power Prediction Method Based on the Combination Model of VMD and BLS
  • A Wind Power Prediction Method Based on the Combination Model of VMD and BLS
  • A Wind Power Prediction Method Based on the Combination Model of VMD and BLS

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0060] A BLS regression prediction model is established for each sub-modal respectively to predict.

[0062] Superimpose each sub-modal prediction value to obtain the final wind power prediction result.

[0068]

[0070] Introduce the Lagrange multiplier λ and the penalty factor α to the constraint problem in the above formula (1), and change it into

[0071]

[0072] In the formula, α represents the penalty factor, and λ represents the Lagrange multiplier.

[0074]

[0075]

[0076]

[0077] In the formula, the superscript ∧ represents the Fourier transform, n is the number of iterations, and o represents the update factor.

[0079]

[0080] In the formula, ∈ represents the discrimination accuracy.

[0081] III, predict through the improved BLS model.

[0084] for sample X

[0086] Z

[0087] And m groups of enhanced nodes are expressed as:

[0088] Q

[0090] The improved BLS is a Gaussian kernel function instead of the activation function of the enhanced node, which maps the inpu...

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 relates to a wind power prediction method based on a combined model of VMD and BLS. The method comprises the following steps: Step 1: collecting wind power data, and selecting training samples and test samples; Step 2: analyzing the collected wind power The data is subjected to VMD variational modal decomposition to obtain the VMD decomposed wind power sequence; Step 3: Input each modal component in the VMD decomposed wind power sequence into the BLS model for prediction, and obtain the BLS model output corresponding to each modal component ; Step 4: superimpose and sum the BLS model outputs corresponding to all modal components to obtain the final wind power result predicted by the combined model, and perform error calculation. Compared with the prior art, the present invention has the advantages of being able to complement each other compared with a single forecasting model, improving the forecasting accuracy and enhancing the robustness of the model, and the like.

Description

A wind power prediction method based on the combined model of VMD and BLS technical field The present invention relates to the technical field of wind power, especially relate to a kind of wind power prediction based on VMD and BLS combined model. measurement method. Background technique [0002] At present, the methods of wind power prediction include physical methods, time series methods and artificial intelligence methods. artificial intelligence Energy methods include artificial neural network (ANN) and support vector machine (SVM), etc. [0003] At present, most models are combined with other algorithms on the basis of support vector machines or neural networks. Predict to get predicted power. Such as empirical mode decomposition (ELM) or the combination of wavelet transform and support vector machine for wind power Prediction, prediction effect is not very good. In the above-mentioned method, SVM and ANN carry out prediction accuracy to wind power power is no...

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): G06Q10/04G06F30/27G06N3/08G06F111/04G06F113/06G06F119/06
CPCG06Q10/04G06F30/27G06N3/08G06F2111/04G06F2113/06G06F2119/06Y04S10/50
Inventor 赵阳文传博曹山秀
Owner SHANGHAI DIANJI UNIV