An ultra-short-term wind power prediction method based on small-wavelength short-term memory network
A technology of wind power prediction and long-term and short-term memory, applied in prediction, data processing applications, instruments, etc., can solve problems such as reduced training efficiency and complicated model structure, and achieve good prediction and easy processing effects
Active Publication Date: 2021-08-31
HOHAI UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in actual operation, if there are too many selected features or influencing factors, the structure of the predicted model may be complicated and the training efficiency will be reduced. The prediction accuracy is very important
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0017] Below in conjunction with specific embodiment, further illustrate the present invention, should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various equivalent forms of the present invention All modifications fall within the scope defined by the appended claims of the present application.
[0018] Such as figure 1 As shown, the ultra-short-term wind power prediction method based on the small-wavelength short-term memory network of the present invention comprises the following steps:
[0019] 1) Analyze and study wind power data, extract features closely related to wind power data, collect historical data of wind farms, and obtain a training sample set; wherein, the extracted feature information includes: 20 wind power values x before the current moment 1 ,x 2 ...,x 20 As the inp...
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
Login to View More Abstract
The invention discloses an ultra-short-term wind power prediction method based on a small-wavelength short-term memory network. Input variables are generated according to historical data, and the corresponding wind power historical data is used as an output to obtain training samples; the training samples are analyzed by wavelet analysis. The three-level wavelet decomposition obtains four wavelet samples, and uses the long-term short-term memory network model to train the four wavelet samples respectively, and obtains the small-wavelength short-term memory network prediction model after training; according to the actual data at the time to be predicted of the four wavelet samples Generate test input data and input it into the prediction model, and its output is the ultra-short-term wind power forecast value at the moment to be predicted. The invention combines the wavelet analysis method with the long-short-term memory deep network, can simultaneously realize data stabilization processing and deep learning, improves prediction accuracy, and enhances the generalization ability of the model.
Description
technical field [0001] The invention belongs to the technical field of new energy consumption, and in particular relates to an ultra-short-term wind power prediction method for predicting wind power. Background technique [0002] Nowadays, the decrease of fossil energy and the gradual increase of human demand for energy have become the main contradiction in the energy field. In order to solve the energy problem, human beings need to vigorously develop renewable energy, such as clean wind resources and solar energy resources. Due to the strong randomness, intermittency and volatility of resources, wind and light curtailment of renewable energy is still very serious. The forecasting research of renewable energy has become one of the key technologies for new energy consumption. With the advent of the era of artificial intelligence, more and more fields have successfully introduced advanced intelligent algorithms. For new energy forecasting research, it is even more necessary t...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/04G06Q50/06G06K9/62
CPCG06Q10/04G06Q50/06G06F18/214
Inventor 孙永辉王朋翟苏巍候栋宸武小鹏王义吕欣欣周衍张宇航钟永洁陈凯夏响张闪铭
Owner HOHAI UNIV