Wind power prediction error estimation method based on data feature extraction
A technology for wind power prediction and error estimation, which is applied in the fields of electrical digital data processing, special data processing applications, and calculations, and can solve problems such as a large amount of calculation, and achieve the effects of easy acquisition, guaranteed executable, and reliable data sources.
Inactive Publication Date: 2016-06-15
SOUTHEAST UNIV +1
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At present, in terms of wind power forecasting error estimation at home and abroad, it is proposed to determine the wind power forecasting error by comparing the forecasting results provided by several different wind power forecasting tools. source of data, and may bring a large amount of calculation
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
[0032] The present invention will be further described below in conjunction with the accompanying drawings.
[0033] Such as figure 1 As shown, the wind power prediction error estimation method based on data feature extraction of the present invention statistically analyzes the historical data of wind power operation in the past year, calculates the wind power amplitude, the fluctuation degree of the predicted output in the past day, the fluctuation degree of the wind power output in the past 3 days and the forecast The weight coefficient of the influence of accuracy on the wind power forecast error, combined with the wind power forecast output and the wind power operation data of the past 3 days to calculate the wind power forecast amplitude and fluctuation degree, the wind power output fluctuation degree and forecast accuracy in the past 3 days, and finally estimate the wind power. Power prediction errors, such as figure 1 shown, including several major steps
[0034] Step...
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 method for estimating a wind power prediction error based on data feature extraction. The method comprises the following steps: (1) summarizing and analyzing historical data about wind power running in the latest one year, and analyzing and calculating a wind power amplitude, the fluctuating degree of day-ahead predicted output, the fluctuating degree of wind power output in the latest three days and the influence weight coefficients of prediction accuracy on the wind power prediction error; (2) according to the weight coefficients obtained in step (1), utilizing the day-ahead predicted output and the wind power running data in the latest three days to calculate the day-ahead prediction amplitude and fluctuation degree of wind power, and the fluctuation degree and the prediction accuracy of the wind power output in the latest three days, and then estimating the wind power prediction error. The historical data features about wind power running are summarized, analyzed and extracted, and the wind power running data in the latest three days are utilized to estimate the wind power prediction error. The method has the characteristics of low online calculation intensity, reliable data resource and easiness in data acquisition and has a high engineering practical value.
Description
technical field [0001] The invention belongs to the technical field of power system scheduling automation in new energy power generation technology, and in particular relates to a wind power prediction error estimation method based on data feature extraction. Background technique [0002] In recent years, the penetration rate of new energy represented by wind power in the power grid has increased sharply due to its inherent characteristics of non-polluting, renewable, and no greenhouse gas emissions, and has become an important direction of energy development. As one of the most mature new energy utilization methods, wind power has achieved rapid growth with the strong support of government departments. However, with the integration of large-scale wind power into the grid, due to the inherent randomness, intermittency and uncertainty of wind power, the uncertainty factors in the operation of the power system continue to increase, which brings great challenges to the safe, st...
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): G06F19/00H02J3/38
CPCY02E10/76
Inventor 张凯锋丁恰杨国强王颖陈汉一
Owner SOUTHEAST UNIV