Wind power prediction method based on AFSA-GNN

Abstract

The embodiment of the invention provides a wind power prediction method based on AFSA-GNN, and the method comprises the steps: carrying out the cleaning of obtained wind power data, and carrying out the normalization processing; building an RNN model, and determining the number of hidden layer nodes of the RNN model; performing regression operation based on the obtained RNN model to obtain predicted power, and constructing an objective function by combining the minimum root-mean-square error of the predicted power and the actually measured power; initializing various parameters of an AFSA algorithm, and optimizing the weight of the RNN model by using the steps of the AFSA algorithm; and inputting the processed wind power data into the optimized RNN model for wind power prediction to obtain a wind power output power prediction value. The optimization of the connection weight of the ridgelet neural network is quickly realized by using the excellent optimization ability of the artificial fish swarm algorithm and taking the minimum RMSE as a target function, and the wind power output power prediction model is established by using the quick approximation ability of the ridgelet neural network to high-dimensional data, so that the prediction precision can be effectively improved.

Description

technical field [0001] This application relates to the field of wind power, and in particular to an AFSA-GNN-based wind power prediction method. Background technique [0002] There is a broad consensus on the development and utilization of renewable energy and the promotion of low-carbon green transformation of the economy. As a clean renewable energy, wind energy has been more and more widely used. However, due to the intermittence, volatility and randomness of wind energy itself, the output power of wind power fluctuates greatly and changes quickly. After wind power is connected to the grid, it will bring great challenges to the stable operation of the power system. Therefore, accurate prediction of wind power output can effectively improve the impact on the power system, and provide a basis for power dispatching departments to rationally arrange conventional energy generation and wind power generation, and to adjust power generation plans in a timely manner. [0003] At ...

AI Technical Summary

Problems solved by technology

The processing and operation of multi-dimensional functions will greatly reduce the speed and accuracy of the model, and the artificial neural network prediction model generally has problems such as the network itself is easy to fall into local extremum and slow convergence speed. At the same time, how to determine the number of nodes in the hidden layer of the neural network , the selection of weights all have an impact on the results of wind power forecasting

Images