Wind turbine active power prediction and error correction method based on neural network

Abstract

The invention discloses a wind turbine active power prediction and error correction method based on neural network. The method includes the following steps: firstly using a wavelet spectrum analyzing method to extract a significant period sequence hidden in an active power time sequence of a wind turbine and perform separation to obtain a residual sequence, then separately predicting the prominent period sequence and the residual sequence by using a neural network model, wherein the prominent period sequence uses a BP neural network which is optimized based on particle swarm optimization and laminated with error correction to perform prediction, the residual sequence uses a RBF neural network which is optimized based on particle swarm optimization and laminated with error correction to perform prediction, and acquiring a final result of wind turbine active power prediction based on the prediction results of the significant period sequence and the residual sequence. According to the invention, the method can predict the active power of each wind turbine in a wind power plant in a precise manner so as to effectively increase short-term output prediction level of the entire wind power plant.

Description

technical field [0001] The invention belongs to the field of wind energy forecasting, and in particular relates to a neural network-based active power forecasting and error correction method of a wind generator. Background technique [0002] In order to effectively integrate wind energy into the grid, it is extremely necessary and critical to accurately forecast the output of wind farms. Among them, the short-term forecast of 0 to 6 hours is necessary for real-time scheduling of the grid, ensuring grid frequency, power and voltage balance, etc. The technical parameters of grid security are of great significance. [0003] As a renewable clean energy, wind energy has the advantages of flexible installed capacity, high reliability of wind power generating units, low cost, and simple operation and maintenance. According to the "2014 Wind Power Industry Monitoring Situation" published by the National Energy Administration in February 2015, by the end of 2014, the cumulative inst...

AI Technical Summary

Problems solved by technology

The physical method does not require a large amount of measurement data, but requires an accurate mathematical description of the physical characteristics of the atmosphere and the characteristics of the wind turbines in the wind farm. These equations are difficult to solve, the required data are massive, the calculation is large, and the calculation time is long. It is difficult and expensive for departments to obtain data, so statistical methods are still commonly used in short-term active power forecasting of wind farms

At present, most of the statistical methods are based on the historical data of wind farm wind towers, using continuous method, random time series method, Kalman filter method, neural network method, support vector machine and other methods to predict the wind farm as a whole. The biggest disadvantage is that wind farms are affected by terrain, turbulent flow, and wind turbine operating conditions, which will inevitably lead to large forecast errors, which has nothing to do with the specific forecast method

Images