A short-term wind speed prediction method for wind farms
A technology for wind speed forecasting and wind farms, which is applied in the field of short-term wind speed forecasting for wind farms. It can solve the problems of increasing the total error of wind speed forecasting, and achieve the effects of reducing excessive overall forecasting errors, improving forecasting accuracy, and accurate forecasting of wind speed random fluctuations.
Active Publication Date: 2022-07-19
HEBEI UNIV OF TECH
View PDF14 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, because there must be prediction errors in wind speed prediction, this method predicts multiple wind speed components separately, resulting in the superposition of prediction errors of multiple components, increasing the total error of wind speed prediction
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 1
[0091] Select the historical wind speed data of a wind farm in Zhangbei for a certain year, select the wind speed data from January to November as the training set, and apply the prediction method of the present invention to predict the wind speed on the first day of December; The actual measured wind speed data of 1 is used as the standard to test the reliability of the prediction method; the interval between wind speed time points is 10min or 15min, which is 10min in this embodiment, that is, the wind speed at 145 time points needs to be predicted.
[0092] The invention provides a short-term wind speed prediction method for a wind farm, the method comprising the following steps:
[0093] Step 1: Apply the EMD algorithm to convert the original wind speed time series V in the training set ori (see figure 1 ) is decomposed into 8 wind speed component time series V IMF , as in formula (1);
[0094] V ori =V IMF1 +V IMF2 +V IMF3 …+V IMF8 (1)
[0095] Step 2: Calculate ...
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 short-term wind speed prediction method for a wind farm. The prediction method recombines the decomposed wind speed components to obtain two wind speed components, thereby reducing the excessively large overall prediction error caused by the accumulation of prediction errors of multiple wind speed components, and The random fluctuation of wind speed that affects the effect of wind speed prediction is extracted to improve the prediction accuracy of another wind speed component. In addition, the application of artificial fish swarm algorithm to optimize the RBF neural network improves the prediction accuracy and computational efficiency of the neural network. For the random fluctuations that affect wind speed prediction, a probability model of dependence of wind speed fluctuations on trend quantities is established, which makes the wind speed random fluctuation prediction more accurate and improves the wind speed prediction accuracy.
Description
technical field [0001] The invention belongs to the technical field of wind speed prediction, and in particular relates to a short-term wind speed prediction method for a wind farm. Background technique [0002] Wind power generation has become an important part of China's energy system. Today, wind power technology is mature enough. For wind farms, accurate wind speed prediction is crucial to the operation of wind farms. The power grid formulates dispatch plans and adjusts grid frequency according to the wind speed forecast results. , to ensure the stability of the power grid and the quality of power supply. For wind farms, accurate wind speed prediction can improve the efficiency of power generation. [0003] Wind is a phenomenon in nature, and wind speed is uncertain and affected by many factors, so it is difficult to predict wind speed. Wind speed will fluctuate in a short period of time. This type of fluctuation is the main factor affecting wind speed prediction. Extra...
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): G06F30/27G06Q10/04G06Q50/06G06N3/04G01P5/00G06F111/08G06F113/08
CPCG06F30/27G06Q10/04G06Q50/06G01P5/00G06F2111/08G06F2113/08G06N3/045Y04S10/50
Inventor 张家安刘东王军燕郭翔宇
Owner HEBEI UNIV OF TECH