Ultra-Short-Term Photovoltaic Power Prediction Based on Predictable Component Reconstruction and Spatiotemporal Heterogeneous Graph Neural Networks

Ultra-short-term PV power prediction (USTPVPP) results provide a basis for the development of intra-day rolling power generation plans. However, due to the feature information and the unpredictability of meteorology, the current ultra-short-term PV power prediction accuracy improvement still faces t...

Full description

Saved in:
Bibliographic Details
Main Authors: Yingjie Liu, Mao Yang
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/15/4192
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Ultra-short-term PV power prediction (USTPVPP) results provide a basis for the development of intra-day rolling power generation plans. However, due to the feature information and the unpredictability of meteorology, the current ultra-short-term PV power prediction accuracy improvement still faces technical challenges. In this paper, we propose a combined prediction framework that takes into account the reconfiguration of the predictable components of PV stations and the spatiotemporal heterogeneous maps. A circuit singular spectral decomposition (CISSD) intrinsic predictable component extraction method is adopted to obtain specific frequency components in sensitive meteorological variables, a mechanism based on radiation characteristics and PV power trend predictable component extraction and reconstruction is proposed to enhance power predictability, and a spatiotemporal heterogeneous graph neural network (STHGNN) combined with a Non-stationary Transformer (Ns-Transformer) combination architecture to achieve joint prediction for different PV components. The proposed method is applied to a PV power plant in Gansu, China, and the results show that the prediction method based on the proposed combined spatio-temporal heterogeneous graph neural network model combined with the proposed predictable component extraction achieves an average reduction of 6.50% in the RMSE, an average reduction of 2.50% in the MAE, and an average improvement of 11.93% in the R<sup>2</sup> over the direct prediction method, respectively.
ISSN:1996-1073