A Wind Power Prediction Method Based on Improved Satin Blue Bowerbird Algorithm to Optimize LSSVR

Abstract

The invention belongs to the technical field of wind power, and in particular relates to a wind power prediction method based on an improved satin blue bower bird algorithm to optimize LSSVR. The present invention proposes an ultra-short-term prediction method of LSSVR wind power based on secondary decomposition and ISBO optimization parameters, and considers the model training process and the complexity of prediction, and constructs a secondary decomposition based on secondary decomposition and t-mean test strategy, decompose, dynamically divide, and reconstruct the original wind power sequence; in order to improve the population diversity and algorithm convergence of the satin blue bower bird algorithm in the iterative process, the standard satin blue bower bird algorithm is improved and used The improved satin blue bower bird algorithm optimizes the two parameters of the least squares support vector regression model, and establishes a wind power LSSVR prediction model with excellent performance.

Description

technical field [0001] The invention belongs to the technical field of wind power, and in particular relates to a wind power prediction method based on an improved satin blue bower bird algorithm to optimize LSSVR. Background technique [0002] With the rapid development of the wind power market, the installed capacity of wind power and wind power generation continue to increase. Due to the random fluctuation of wind power, large-scale wind power grid integration has a serious impact on the safety, controllability and economy of the power system. By establishing a high-performance wind power forecasting system, accurate forecasting of wind power in the future can be achieved, which can effectively promote the stable connection of large-scale wind power to the power network. Considering that historical wind power data is a time series with fluctuation characteristics, combining signal decomposition technology with machine learning and applying it to wind power forecasting ca...

AI Technical Summary

Problems solved by technology

[0011] The purpose of the present invention is to propose a super-short-term prediction method of LSSVR wind power based on secondary decomposition and ISBO optimized parameters, which can effectively solve the problem that parameters are difficult to determine when using least square support vector regression to establish a wind power prediction model , and using the quadratic decomposition method to deeply mine the time series characteristics of wind power, the existing problems of model training and prediction complexity

Images