Wind power cluster power prediction and parameter optimization method

Abstract

The invention discloses a wind power cluster power prediction and parameter optimization method, which comprises the steps of dividing historical NWP data and historical power data into two independent data sets, and optimizing parameters in three stages; carrying out principal component analysis of the original wind speed vector, taking a principal component analysis result as input of a wind power cluster power prediction model, and respectively dividing two independent data sets into a to-be-predicted data set and a historical data set; calculating an Euclidean characteristic distance between the input data matrix of the prediction point and the historical data set; comparing the Euclidean characteristic distance with a threshold value delta to obtain a data set with the highest matching degree and a prediction data set, judging whether optimization is finished or not, and otherwise, setting a parameter value by using a variable-scale network search method to continue to optimize toobtain four parameters with the minimum overall prediction error; and controlling the three parameter values to be unchanged according to the obtained initial optimization values of the four parameters, and changing the remaining parameter value until an optimal four-parameter combination is obtained. The method is high in prediction precision and has popularization value.

Description

technical field [0001] The invention relates to a method for wind power cluster power forecasting and parameter optimization, which belongs to the field of new energy power forecasting. Background technique [0002] Wind energy is mainly affected by natural factors, and has the characteristics of randomness, volatility, and intermittency. As a result, after large-scale wind power is connected to the grid, there may be deviations in voltage and frequency, voltage fluctuations, and even off-grid. The scale is growing rapidly, and the uncertainty of wind power has more and more obvious impact on the stability, adequacy and economy of the power system and power market, which has attracted extensive attention of relevant researchers, and wind power forecasting is a solution to this problem Therefore, wind power forecasting has become one of the main research topics at home and abroad in recent years. [0003] At present, the power prediction methods of wind power clusters includ...

AI Technical Summary

Problems solved by technology

However, the accumulation method and the statistical upscaling method have obvious disadvantages. The accumulation method has high requirements for the completeness of historical data related to wind power prediction and numerical weather prediction data. There are many resources; the selection of the number of reference wind farms and the selection of reference wind farms in the statistical upscaling method have a great impact on the overall power prediction accuracy of the cluster, and it includes two prediction stages at the same time, and the calculation is more complicated

Images