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

TL;DR

This paper presents PISSM, a lightweight physics-informed state space model that improves solar irradiance forecasting accuracy for off-grid systems while ensuring physical plausibility and computational efficiency.

Contribution

The paper introduces PISSM, combining a dynamic Hankel matrix, linear state space modeling, and a physics-informed gating mechanism to enhance forecasting accuracy and physical consistency.

Findings

PISSM outperforms existing models on multi-year datasets.

It achieves high accuracy with fewer than 40,000 parameters.

PISSM ensures physically plausible predictions, avoiding nocturnal errors.

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.