Ultra-short-term Photovoltaic Power Prediction Based on Improved PatchTST Considering Data Drift

Authors

• Huawei Mei, Department of Computer, North China Electric Power University, Baoding 071003, China; Engineering Research Center of Intelligent Computing for Complex Energy Systems, Ministry of Education, Baoding 071003, China
• Penghui Yang, Department of Computer, North China Electric Power University, Baoding 071003, China
• Yang Yu, State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, Baoding 071003, China; Key Laboratory of Distributed Energy Storage and Microgrid of Hebei Province, Baoding 071003, China

Abstract

Existing PV power prediction methods often suffer from limited accuracy and robustness due to three key shortcomings: relying on single-point mapping that cannot fully extract local temporal patterns; inadequate exploration of the global temporal dependencies in PV output, and failure to account for prevalent data drift phenomena. To overcome these limitations,an improved patch time series transformer (PatchTST) based approach is proposed for ultra-short-term PV power prediction. The methodology applies rough set theory for feature dimensionality reduction, effectively preserving critical decision information by analyzing both feature-label relationships and inter-feature correlations. An enhanced PatchTST model with a modified channel-independent mechanism extracts local temporal patterns and captures complex mapping relationships between meteorological variables and PV output. The global-local attention fusion framework (GLAFF) module is incorporated to identify global temporal guidance patterns. An adaptive weighting mechanism dynamically optimizes the integration of local and global features to counteract data drift effects. Experimental validation using real-world datasets from a PV power plant in Inner Mongolia, China, and the Desert Knowledge Australia Solar Centre demonstrates that the proposed model achieves superior performance in both prediction accuracy and robustness.

Recommended Citation

Mei, Huawei; Yang, Penghui; and Yu, Yang (2026) "Ultra-short-term Photovoltaic Power Prediction Based on Improved PatchTST Considering Data Drift," Journal of System Simulation: Vol. 38: Iss. 5, Article 8.
DOI: 10.16182/j.issn1004731x.joss.25-0396
Available at: https://dc-china-simulation.researchcommons.org/journal/vol38/iss5/8

First Page

1239

Last Page

1254

CLC

TP391.9

Recommended Citation

Mei Huawei, Yang Penghui, Yu Yang. Ultra-short-term Photovoltaic Power Prediction Based on Improved PatchTST Considering Data Drift[J]. Journal of System Simulation, 2026, 38(5): 1239-1254.

Corresponding Author

Yu Yang

DOI

10.16182/j.issn1004731x.joss.25-0396