PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 7, 2026Journal of Renewable and Sustainable Energy0 citations

Self-supervised pretraining for PV power forecasting: Toward enhanced interpretability

View Full Paper
HTHao TaXYXiuying YanKWKexin Wang

Key Points

  • This research aims to enhance accuracy and interpretability of photovoltaic power forecasting.
  • Developed a two-stage forecasting framework incorporating self-supervised TabNet pretraining and multilayer perceptron.
  • Utilized a masked self-supervised task for learning meteorological and temporal representations.
  • Employed a sparse attention mechanism for automatic feature selection.
  • Achieved a 42.7% reduction in root mean square error and 39.2% reduction in mean absolute error compared to LSTM.
  • Under adverse weather conditions, RMSE reductions between 20% and 30% were observed relative to conventional models.
  • Implemented multi-horizon forecasting showed slower error accumulation with improved accuracy.

Abstract

Accurate photovoltaic (PV) power forecasting is essential for stable and efficient grid operation. To address the challenges posed by coupled meteorological and temporal variability, this study proposes an interpretable two-stage forecasting framework integrating self-supervised TabNet pretraining with a multilayer perceptron (MLP) regressor. In the first stage, TabNet jointly learns meteorological and temporal representations through a masked self-supervised task, while its sparse attention mechanism enables automatic feature selection and quantitative attribution. In the second stage, the pretrained representations are transferred to an MLP for efficient regression forecasting. Experiments on a 50 MW grid-connected PV plant demonstrate significant performance improvements. On the annual dataset, the proposed model reduces the root mean square error (RMSE) and mean absolute error by 42.7% and 39.2%, respectively, compared with the long short-term memory model. Under cloudy and rainy/snowy conditions, the model achieves additional RMSE reductions of 20%–30% relative to conventional baselines. Multi-horizon forecasting further demonstrates slower error accumulation and consistently superior accuracy. Overall, the proposed TabNet-MLP framework provides an effective and interpretable solution for multi-timescale PV power forecasting.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Ta et al. (2026) studied this question.

synapsesocial.com/papers/69fbef68164b5133a91a357fhttps://doi.org/10.1063/5.0300730
Ask AI
Helpful
Bookmark
Share
View Full Paper