Wind power cluster power prediction method based on spatio-temporal correlation

Abstract

The invention discloses a wind power cluster power prediction method based on spatio-temporal correlation, which analyzes spatio-temporal correlation among wind power plants in a wind power cluster, calculates by applying a plurality of types of correlation calculation methods, and weights by introducing a Shapley value method, so that correlation evaluation is more comprehensive, and the correlation in the wind power cluster is calculated more accurately. According to the prediction method, multiple factors influencing the power generation power are considered and fused together, so that the overall spatial-temporal correlation characteristics of the wind power cluster are extracted, the effect of directly predicting the power of the wind power cluster is achieved, the defect that errors caused by superposition prediction in an existing method are superposed is overcome, and the prediction precision is improved. Besides, key spatio-temporal correlation characteristics of the wind power cluster are extracted by applying the convolutional neural network, the purpose of reducing dimensionality is achieved, the space-time correlation characteristics of the wind power cluster can be directly input into the neural network and correspond to the power of the wind power cluster, the power generation power of the wind power cluster can be predicted more conveniently, and the prediction precision is higher.

Description

Technical field [0001] The present invention belongs to the field of wind power, and specifically, the power prediction method based on time and space-dependent wind power cluster is related to the wind power cluster power generation power, and accurately predicts the wind power cluster. Background technique [0002] In recent years, wind power has been flourishing in the world. The large-scale wind turbines are distributed in various regions. With the popularity of low wind winders, large-scale wind turbines can be installed in areas where low wind speed is small. With the construction of the large-scale wind farm, the wind power cluster also formed this, and a regional wind power set includes a plurality of wind farms, while a large-scale wind farm is grid, and has a strong impact on the security and scheduling of grid. [0003] For large-scale wind farms grunge, wind power cluster power prediction is an effective method for improving power system security and economy. At prese...

AI Technical Summary

Problems solved by technology

However, this method only considers the influence of wind speed on power and does not consider other factors, so the prediction accuracy is not very high

Images