Wind power ultra-short-term probability prediction method based on conditional quantile regression model
A technology of quantile regression and wind power, applied in forecasting, neural learning methods, biological neural network models, etc., can solve problems such as long training time, time-consuming and computing resources, falling into local minimum, etc., and achieve good reliability , the effect of improving the credibility of predictions
Active Publication Date: 2021-08-13
HOHAI UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, this method takes a long time to train and is inefficient
The extreme learning machine is an efficient and concise feedforward neural network. Different from the traditional feedback neural network, it needs to repeatedly optimize the calculation parameters, which consumes time and computing resources and is easy to fall into a 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 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
[0065] The invention provides a wind power ultra-short-term probability prediction method based on a conditional quantile regression model, which is based on clustering theory and a conditional quantile regression model to perform ultra-short-term prediction of wind power non-parametric probability intervals. It can be applied to other ranges and fields such as load, wind power / photovoltaic output, etc.
[0066] The prediction model flow chart of the present invention is as figure 1 Shown, its embodiment step is mainly as follows:
[0067] (1) Preprocess the data, that is, initialize the coefficients from the input layer to the hidden layer of the extreme learning machine model and the threshold value of the hidden layer, predict the rated confidence interval, import the normalized historical wind power time series, and construct sample;
[0068] (2) Construct multiple time series motifs, respectively calculate the differences based on static characteristics, dynamic charact...
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 a wind power ultra-short-term probability prediction method based on a conditional quantile regression model, and the method comprises the following steps: firstly analyzing the characteristics of a wind power time sequence, researching a hierarchical clustering method based on a multivariate time sequence motif, comprehensively considering static characteristics, dynamic characteristics and meteorological characteristics, then calculating a sample multiplication coefficient based on a clustering result, carrying out quantile regression on each sample class to train a model and complete parameter optimization on the basis of the sample multiplication coefficient, and finally inputting a wind power time sequence to realize ultra-short-term probability prediction. The prediction interval performance of the invention is obviously superior to that of a traditional prediction model based on a quantile regression model, the invention has good reliability, and the reliability of wind power prediction is greatly improved.
Description
technical field [0001] The invention relates to the technical fields of new energy power generation and smart grid, in particular to an ultra-short-term probability prediction method of wind power based on a conditional quantile regression model. Background technique [0002] In recent years, with the continuous increase of wind power installed capacity, wind energy has become one of the most important renewable energy sources. However, wind power has uncertainty and randomness, which limits its application and development. Traditional wind power forecasting focuses on deterministic forecasting, that is, point forecasting, and lacks a description of uncertainty, making it impossible to give more objective and comprehensive information to the grid dispatching department. In view of this, more and more technicians pay attention to the method of probability interval forecasting. Unlike the point forecasting method that directly predicts a certain value, the probability interv...
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 IPC IPC(8): G06Q10/04G06Q10/06G06F17/18G06K9/62G06N3/04G06N3/06G06N3/08
CPCG06Q10/04G06F17/18G06Q10/06393G06N3/061G06N3/08G06N3/048G06F18/23Y04S10/50
Inventor 孙永辉周衍王森侯栋宸王建喜张林闯
Owner HOHAI UNIV