Renewable energy short-term prediction method based on data mining and variational mode decomposition

Abstract

The invention discloses a renewable energy short-term prediction method based on data mining and variational mode decomposition. The renewable energy short-term prediction method comprises the following steps: 1), dividing a clustering process into data clusters: dividing the data clusters into some different groups in a given data set through a clustering algorithm, and extracting historical power generation data similar to environmental features into the same class; 2) processing historical data by variational modal decomposition: determining the bandwidth and the center frequency of each modal component by continuously iterating and searching the optimal solution of a variational model, and performing adaptive subdivision on the signal in a frequency domain; and 3) utilizing an extremelearning machine to predict future data. The technical scheme of the embodiment of the invention is combined with the K-means clustering technology, utilizes the variational mode decomposition and theextreme learning machine to predict the power generation amount of renewable energy, and has better accuracy compared with a traditional prediction method.

Description

technical field [0001] The invention relates to a short-term prediction method for renewable energy based on data mining and variational mode decomposition, belonging to the technical field of new energy power generation. Background technique [0002] With the depletion of traditional fossil fuels, renewable energy sources (RES) such as wind energy and solar energy are increasingly used in power systems. Microgrid (MG) can integrate various renewable energy sources into the power grid, usually composed of distributed energy sources, controllable loads, energy storage devices and other components, and has developed rapidly in recent years. However, due to the highly variable and intermittent nature of renewable energy, the reliability and stability of microgrids are difficult to guarantee. Accurate renewable energy forecasting is of great significance for improving the power quality of microgrids and strengthening the energy management of microgrids, and it can also effectiv...

AI Technical Summary

Problems solved by technology

But EMD has the disadvantage of frequent modal aliasing

[0005] To sum up, the current renewable energy forecasting usually has a single forecasting method, and there are the following challenges: 1) Insufficient extraction of relevant features on the forecast day

2) Insufficient signal analysis and processing of renewable energy

3) Renewable energy forecasting methods represented by traditional neural networks generally have problems such as long training time and overfitting

Images