Physics-Informed State Space Models for Reliable Solar Irradiance Forecasting in Off-Grid Systems

Mohammed Ezzaldin Babiker Abdullah

cs.LGApr 13, 2026

Physics-Informed State Space Models for Reliable Solar Irradiance Forecasting in Off-Grid Systems

Authors: Mohammed Ezzaldin Babiker Abdullah

Organizations: Department of Electrical and Electronic Engineering, Faculty of Engineering Sciences, Omdurman Islamic University, Omdurman, Sudan

Abstract

The stable operation of off-grid photovoltaic systems requires accurate, computationally efficient solar forecasting. Contemporary deep learning models often suffer from massive computational overhead and physical blindness, generating impossible predictions. This paper introduces the Physics-Informed State Space Model (PISSM) to bridge the gap between efficiency and physical accuracy for edge-deployed microcontrollers. PISSM utilizes a dynamic Hankel matrix embedding to filter stochastic sensor noise by transforming raw meteorological sequences into a robust state space. A Linear State Space Model replaces heavy attention mechanisms, efficiently modeling temporal dependencies for parallel processing. Crucially, a novel Physics-Informed Gating mechanism leverages the Solar Zenith Angle and Clearness Index to structurally bound outputs, ensuring predictions strictly obey diurnal cycles and preventing nocturnal errors. Validated on a multi-year dataset for Omdurman, Sudan, PISSM achieves superior accuracy with fewer than 40,000 parameters, establishing an ultra-lightweight benchmark for real-time off-grid control.

Explore similar work

Thermodynamic Liquid Manifold Networks: Physics-Bounded Deep Learning for Solar Forecasting in Autonomous Off-Grid Microgrids
Apr 13, 2026Mohammed Ezzaldin Babiker AbdullahSolar Power Forecasting Physics-Informed ML
Department of Electrical and Electronic Engineering, Faculty of Engineering Sciences Omdurman Islamic University, Omdurman, Sudan
Outperforming Self-Attention Mechanisms in Solar Irradiance Forecasting via Physics-Guided Neural Networks
Apr 15, 2026Mohammed Ezzaldin Babiker Abdullah, Rufaidah Abdallah Ibrahim MohammedSolar Power Forecasting Time Series Forecasting
Omdurman Islamic University, Omdurman, Sudan.
FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting
Aug 6, 2026Yann Fabel, Bijan Nouri, Milon Miah +4Time Series Forecasting Solar Power Forecasting
1DLR, Institute of Solar Research · 2RWTH Aachen University · 3CIEMAT, Energy Department, Renewable Energy Division

Apr 13, 2026J/K move · Enter open · S save

Thermodynamic Liquid Manifold Networks: Physics-Bounded Deep Learning for Solar Forecasting in Autonomous Off-Grid Microgrids

Mohammed Ezzaldin Babiker Abdullah

Department of Electrical and Electronic Engineering, Faculty of Engineering Sciences Omdurman Islamic University, Omdurman, Sudan

Solar Power Forecasting Physics-Informed ML Power Systems

Open paper AskPDF arXiv

The stable operation of autonomous off-grid photovoltaic systems requires solar forecasting algorithms that respect atmospheric thermodynamics. Contemporary deep learning models consistently exhibit critical anomalies, primarily severe temporal phase lags during cloud transients and physically impossible nocturnal power generation. To resolve this divergence between data-driven modeling and deterministic celestial mechanics, this research introduces the Thermodynamic Liquid Manifold Network. The methodology projects 22 meteorological and geometric variables into a Koopman-linearized Riemannian manifold to systematically map complex climatic dynamics. The architecture integrates a Spectral Calibration unit and a multiplicative Thermodynamic Alpha-Gate. This system synthesizes real-time atmospheric opacity with theoretical clear-sky boundary models, structurally enforcing strict celestial geometry compliance. This completely neutralizes phantom nocturnal generation while maintaining zero-lag synchronization during rapid weather shifts. Validated against a rigorous five-year testing horizon in a severe semi-arid climate, the framework achieves an RMSE of 18.31 Wh/m2 and a Pearson correlation of 0.988. The model strictly maintains a zero-magnitude nocturnal error across all 1826 testing days and exhibits a sub-30-minute phase response during high-frequency optical transients. Comprising exactly 63,458 trainable parameters, this ultra-lightweight design establishes a robust, thermodynamically consistent standard for edge-deployable microgrid controllers.

Abstract

Explore similar work

Thermodynamic Liquid Manifold Networks: Physics-Bounded Deep Learning for Solar Forecasting in Autonomous Off-Grid Microgrids

Outperforming Self-Attention Mechanisms in Solar Irradiance Forecasting via Physics-Guided Neural Networks

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