Photovoltaic power prediction method and device based on space-time cooperation, equipment and medium

Abstract

This invention provides a method, apparatus, device, and medium for photovoltaic power prediction based on spatiotemporal coordination, relating to the field of photovoltaic power prediction technology. The method includes: constructing a three-dimensional spatiotemporal input feature vector based on historical irradiance data, historical temperature data, and historical wind speed data of a target photovoltaic power station; inputting the three-dimensional spatiotemporal input feature vector into an improved graph attention network to obtain a spatial feature matrix of the target photovoltaic power station; inputting the three-dimensional spatiotemporal input feature vector into a bidirectional long short-term memory network to obtain a temporal feature matrix of the target photovoltaic power station; performing attention fusion on the spatial and temporal feature matrices to obtain a fused feature matrix of the target photovoltaic power station; and predicting the power generation of the target photovoltaic power station based on the fused feature matrix. This invention can significantly improve photovoltaic power generation, especially in terms of prediction accuracy and robustness under ultra-short to short-term timescales and different seasons and weather scenarios.

Images