Wind power short-term power prediction method and device and readable storage medium

Abstract

The invention provides a wind power short-term power prediction method, which comprises the following steps of: acquiring operation data of a wind power plant, and dividing the operation data into four groups according to seasons; cleaning the operation data; variational mode decomposition is carried out on the cleaned data; carrying out normalization processing on the decomposed data, and constructing training data and verification data; selecting features most relevant to the daily power of the wind power plant; establishing an ELM (Extreme Learning Model) of the power of the wind power plant in different seasons, and selecting an improved bat algorithm to optimize an initial weight and a threshold value in the ELM; the ELM model is trained; and predicting the wind power short-term power based on the ELM model. The improved bat algorithm is used to optimize the weight and bias of the ELM, and compared with a traditional wind power prediction method using the ELM, the accuracy of wind power short-term power prediction can be effectively improved.

Description

technical field [0001] The present invention relates to wind power short-term power forecasting, more specifically a wind power short-term power forecasting method based on the combination of VMD and ELM. Background technique [0002] Due to the high pollution levels of thermal power plants and their negative impact on the environment, renewable energy sources such as wind, solar, and wave energy are now seriously considered as viable alternatives to electrical energy. Among the resources mentioned above, wind power generation has the highest growth rate in the power system. The power generation of wind farms affects the planning, scheduling and scheduling of power systems. However, due to the characteristics of large randomness, strong fluctuation and intermittency of wind speed, it is easy to have a huge impact on the safety and stable operation of the power grid. Excessive wind speed directly affects the wind power ride-through power, which will seriously affect the saf...

AI Technical Summary

Problems solved by technology

However, due to the characteristics of large randomness, strong fluctuation and intermittent wind speed, it is easy to have a huge impact on the safety and stable operation of the power grid.

Excessive wind speed will directly affect the wind power ride-through power. When the power is large, it will seriously affect the safety of the power system.

Images