SHORT-TERM WIND SPEED PREDICTION METHOD BASED ON COMPLEX-VALUED ACCELERATION ALGORITHM

Title:

SHORT-TERM WIND SPEED PREDICTION METHOD BASED ON COMPLEX-VALUED ACCELERATION ALGORITHM

Document Type and Number:

WIPO Patent Application WO/2023/236260

Kind Code:

A1

Abstract:

The present invention relates to a short-term wind speed prediction method based on a complex-valued acceleration algorithm. The method comprises: acquiring sample data comprising wind speeds and wind directions, preprocessing the sample data to obtain a data set, and dividing the data set into a training set and a test set; constructing and initializing a complex-valued forward neural network model comprising an error threshold value e0 and an adaptive window length N; training an initialized complex-valued forward neural network by using a complex-valued acceleration LM algorithm, so as to obtain a trained complex-valued forward neural network; and inputting the test set into the trained complex-valued neural network, so as to obtain a prediction result. In the present invention, the error threshold value and the adaptive window length are introduced, and the complex-valued forward neural network is trained by using the complex-valued acceleration LM algorithm, such that calculation costs during the early, middle and late stages of training are effectively reduced, a training speed is increased, and the calculation complexity is effectively reduced on the basis that a short-term wind speed prediction result is ensured.

More Like This:

WO/2021/050130	CONVOLUTIONAL NEURAL NETWORK WITH PHONETIC ATTENTION FOR SPEAKER VERIFICATION
WO/2022/069498	COMPUTER SYSTEM AND METHOD PROVIDING OPERATING INSTRUCTIONS FOR THERMAL CONTROL OF A BLAST FURNACE
WO/2017/149971	ARITHMETIC PROCESSING DEVICE

Inventors:

HUANG HE (CN)
WANG ZHIDONG (CN)
CAO HONGLONG (CN)

Application Number:

PCT/CN2022/101006

Publication Date:

December 14, 2023

Filing Date:

June 24, 2022

Export Citation:

Click for automatic bibliography generation Help

Assignee:

UNIV SOOCHOW (CN)

International Classes:

G06N3/04; G06F17/16; G06N3/08

Foreign References:

CN113158582A	2021-07-23
CN102102626A	2011-06-22
CN112613657A	2021-04-06
US20200063710A1	2020-02-27

Other References:

MULTAZAM TEUKU; PUTRI RATNA IKA; PUJIANTARA MARGO; LYSTIANINGRUM VITA; PRIYADI ARDYONO; HERYP MAURIDHI: "Short-Term Wind Speed Prediction Base on Backpropagation Levenberg-Marquardt Algorithm; Case Study Area Nganjuk", 2017 5TH INTERNATIONAL CONFERENCE ON INSTRUMENTATION, COMMUNICATIONS, INFORMATION TECHNOLOGY, AND BIOMEDICAL ENGINEERING (ICICI-BME), IEEE, 6 November 2017 (2017-11-06), pages 163 - 166, XP033449192, DOI: 10.1109/ICICI-BME.2017.8537769

Attorney, Agent or Firm:

CENTRAL SOUTH WELL INTELLECTUAL PROPERTY OFFICE (CN)

Download PDF:

View/Download PDF PDF Help

Previous Patent: REFRIGERATION DEVICE

Next Patent: SEMICONDUCTOR STRUCTURE AND MANUFACTURING METHOD THEREFOR