Overview

Solar power forecasting estimates future photovoltaic output or solar irradiance, helping grid operators and energy systems plan around weather-driven variability and fast ramps. Methods range from persistence and statistical or boosted-tree models to temporal neural networks, transformers, graph models, and physics-informed approaches; many combine power histories with numerical weather forecasts, satellite data, or sky images. Probabilistic methods, including quantile and conformal prediction, add calibrated uncertainty, while transfer learning and synthetic histories address sites with scarce data. A central challenge is generalizing across sites and weather regimes: average accuracy can hide failures during extremes, and results depend on forecast inputs, evaluation design, and the trade-off between accuracy, reliability, and computational cost.

Latest papers

CardsList

49 papers7 papers in the last four weeks, up 40% on the four weeks before. 0.1% of all new papers.

  1. Edge-Adaptive Hiera-Seg Model for Building-Integrated Photovoltaic Power Forecasting

    Nov 15, 2026Na YuSolar Power ForecastingEdge Inference

  2. Federated versus Centralized PV Capacity-Factor Forecasting: A Non-Inferiority Study Across Seven Stations in North Macedonia

    Nov 14, 2026Amar Kumar Mandal, Yuvraj Chaudhary, Dimitar Kitanovski +1Solar Power ForecastingFederated Learning

  3. IMPACT: Inverter-Informed Multimodal Learning for Photovoltaic Generation Forecasting

    Oct 29, 2026Anushka Katiyar, Cong Feng, Jing Wang +3Physics-Informed ForecastingSolar Power Forecasting

  4. The Utility of Physics-Informed Machine Learning in Solar Power Production Forecasting

    Oct 28, 2026Peter Pavlík, Franz M. Rohrhofer, Bernhard C. GeigerPhysics-Informed ForecastingSolar Power Forecasting

  5. Reducing Multi-Horizon Photovoltaic Forecast Error through Tree-Anchored Expert Combination

    Oct 22, 2026Sun Ze, Zhou Liguo, Xu Yuqing +3Solar Power ForecastingTime Series Forecasting

  6. Foundation-Style Pretraining for Scalable and Transferable Distributed PV Forecasting

    Oct 20, 2026Dayin Chen, Xiaodan Shi, Xin Xu +6Solar Power ForecastingTime-Series Foundation Models

  7. A Hybrid TFT-NBEATS Framework for Robust Multi-Horizon Photovoltaic Power Forecasting

    Oct 19, 2026Shafi Bin Sultan, Sabik Bin Sultan, Mohammad Tajrian Arafat Alvi +2Solar Power ForecastingTime Series Forecasting

  8. PING: physics informed graph neural network for advection-diffusion processes with applications to solar power forecasting

    Oct 13, 2026Jelena Simeunović, Baptiste Schubnel, Pierre-Jean Alet +2Physics-Informed GNNsPhysics-Informed Forecasting

  9. Nearest Neighbor Functional Curve Completion for Intraday Probabilistic Revisions of Renewable Generation Forecasts

    Oct 12, 2026Guillermo Terrén-Serrano, Michael LudkovskiProbabilistic Time Series ForecastingTime Series Forecasting

  10. Constructed regional photovoltaic generation fields improve ultra-short-term distributed solar forecasting

    Oct 12, 2026Dayin Chen, Xiaodan Shi, Xin Xu +5Solar Power ForecastingSpatiotemporal Forecasting

  11. Transfer Learning with Conformalized Quantile Regression for Solar PV Forecasting Under Load-Shedding-Driven Data Scarcity

    Sep 22, 2026Rakib Abdullah, K. M. Tahlil Mahfuz FarukSolar Power ForecastingTransfer Learning

  12. Ensemble Complexity in Photovoltaic Forecasting

    Sep 14, 2026Sun Ze, Zhou Liguo, Xu Yuqing +2Ensemble LearningSolar Power Forecasting

  13. Horizon-specific Expert Fusion for Photovoltaic Power Forecasting

    Sep 14, 2026Xu Yuqing, Zhou Liguo, Sun Ze +2Ensemble LearningSolar Power Forecasting

  14. Solar Intelligence

    Sep 12, 2026Jyotsna SinghSolar Power Forecasting

  15. Bidirectional Multimodal Fusion of Sky Images and Time-Series for Solar Forecasting with Large Language Models

    Sep 10, 2026Ken Chen, Maneesha Perera, Wei Wang +3Multivariate Time Series ForecastingMultimodal Large Language Models

  16. SolarBench: A global solar energy nowcasting benchmark

    Sep 5, 2026Yuhao Nie, Stephen Campbell, Quentin Paletta +18Solar Power ForecastingSolar Irradiance Forecasting

  17. FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting

    Aug 6, 2026Yann Fabel, Bijan Nouri, Milon Miah +4Solar Irradiance ForecastingTime Series Forecasting

  18. An AI-Based Decision-Support Pipeline for Day-Ahead Photovoltaic Forecasting

    Aug 3, 2026Fariba Dehghan, Sebastian Stein, Vahid Yazdanpanah +2Ensemble LearningTime Series Forecasting

  19. A Controlled Visual-Backbone Benchmark for Multimodal Short-Term Solar Irradiance Forecasting

    Jul 26, 2026Oshadha Samarakoon, Dushan Herath, Ishara Ranmandala +4Solar Irradiance ForecastingVision Transformer

  20. Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study

    Jul 15, 2026Daniel Grillmeyer, Marius Hadry, Michael Stenger +3Solar Power ForecastingFeature Selection

  21. Robustness of Deep Learning Models for PV Power Forecasting under NWP Forecast Errors: A Spatiotemporal and Physically Interpretable Analysis

    Jul 14, 2026Dandan Chen, Yan Zhao, Xuepeng ChenTime Series ForecastingSolar Power Forecasting

  22. Climate-Invariant Conformal Prediction Intervals for Multi-Horizon Solar and Wind Forecasting

    Jul 13, 2026Shreedhar Gangwar, Abhinav Bains, Banalaxmi BrahmaRegression Prediction IntervalsGroup-Conditional Conformal Prediction

  23. PARA-PV: Physics-Aware Retrieval-Augmented PV Prediction Based on Frozen Foundation Model and Distribution Shift Correction

    Jul 9, 2026Hang Fan, Weican Liu, Ying Lu +3Time Series ForecastingNon-Stationary Time Series Forecasting

  24. Time series Foundation Models based on Physics-Informed Synthetic Histories for Cold-Start Photovoltaic Forecasting

    Jun 5, 2026Lorenzo Longarini, Alessandro Rongoni, Simone Silenzi +2Zero-Shot Time Series ForecastingTime Series Forecasting

  25. Decision-focused learning for optimal PV-Battery scheduling

    May 27, 2026Joris Depoortere, Hussain Kazmi, Johan DriesenSequential Decision MakingTime Series Forecasting

  26. Inpainting-Style Conditional Diffusion for Multivariable Time Series Forecasting

    May 27, 2026Kourosh Kiani, S. M. MuyeenMultivariate Time Series ForecastingTime Series Forecasting