Wind power range short-term prediction method based on variation mode decomposition and relevant vector machine

Abstract

The invention discloses a wind power range short-term prediction method based on variation mode decomposition and a relevant vector machine. The method comprises: variation mode decomposition is carried out on a wind power sequence to obtain a plurality of components having different center frequencies; all components are processed by using a relevant vector machine algorithm to establish range prediction models respectively; and prediction results of all components are superposed to obtain a general range prediction result under a certain confidence level. With the method, the prediction precision and range coverage rate of the model are improved; and the range width is narrowed obviously, so that the short-term prediction result of the wind power range is improved obviously.

Description

technical field [0001] The invention belongs to the technical field of new energy power generation and smart grid, and relates to a short-term wind power interval prediction method based on variational mode decomposition and correlation vector machine. Background technique [0002] In today's shortage of fossil energy and severe environmental problems, the development and utilization of clean and pollution-free renewable energy has become a consensus. Among them, wind power generation has received more and more attention and attention because of its cleanness, pollution-free, abundant reserves, and recyclable utilization. Due to the randomness and volatility of natural wind, when wind power is connected to the grid on a large scale, the supply-demand balance and safe and stable operation of the grid will have a huge impact when large power fluctuations occur in wind turbines. Therefore, accurate wind power forecasting is the prerequisite for rationally formulating power gen...

AI Technical Summary

Problems solved by technology

However, the ANN method can easily lead to insufficient learning or over-fitting problems during training; machine learning algorithms such as SVM can effectively avoid the risk of falling into a local minimum and can achieve more accurate predictions, but there are still the following deficiencies: ①The kernel function must satisfy Mercer conditions, fewer optional kernel functions; ②It can only achieve point prediction, but cannot describe the uncertain information of the data; ③There are many parameters, and the support vector increases linearly with the increase of training samples, and the calculation amount is large

At present, this method has been applied in the fields of load forecasting, fault classification, pattern recognition, etc., but there are few applications in wind power interval prediction.

Images