Very short-term solar irradiance forecasting based on open-source low-cost sky imager and hybrid deep-learning techniques

Publication Type

Journal Article

Name of Author

• Martin Ansong, Institute of Microstructure Technology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany
• Gan Huang, Institute of Microstructure Technology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany
• Thomas N. Nyang’onda, Department of Physics, University of Nairobi, Kenya
• Robinson Juma Musembi, University of Nairobi, Kenya
• Bryce S. Richards, Karlsruher Institut für Technologie, Campus Nord, Eggenstein-Leopoldshafen, Germany

Publication Date (Issue Year)

2025

Journal Name

Solar Energy

Abstract

Solar irradiance (SI) forecasting is vital for reliable photovoltaic (PV) operation. This is especially true for regions like Africa where many SI forecasting approaches rely on scarce historical data and the inherent instabilities of electric grids are further compounded by SI variability. Accurate solar forecasting is essential for improving grid management, enabling operators to balance supply and demand and enhance stability. Ground-based sky imaging is a promising technique for SI forecasting that do not require extensive historical data. However, commercial sky imagers are expensive and offer limited flexibility. This paper introduces the Karlsruhe low-cost all-sky imager (KALiSI), made from off-the-shelf components that captures high-resolution images and can be assembled for less than €600. The KALiSI was installed in Karlsruhe, Germany, to collect images to train a convolution neural network-long short-term memory (CNN-LSTM) model for 15 min-ahead forecasting of global horizontal irradiance (GHI). The root mean squared (RMS) error of the model ranges from 19–206 W/m2, compared to 33–257 W/m2 for persistence, while mean absolute (MA) errors range from 15–144 W/m2 for CNN-LSTM and 30–159 W/m2 for persistence. The model’s performance using KALiSI’s images was compared with a commercial sky imager at the same location across various forecast horizons. The KALiSI showed normalised RMS error and MA error values of 6 % and 7 % higher, respectively, with some discrepancies noted on clear days. These results show the KALiSI’s suitability for very short-term forecasting and its open-source design offers a low-cost solution for developing countries.

Keywords

Low-cost sky imager, Solar irradiance, Short-term forecasting, Deep learning, CNN-LSTM, Cloud fraction

Grantee Name(s)

Robinson Juma Musembi

Project Title

Self-cleaning solar module for enhanced electrical output

Type of Grant

Research Award

Thematic Area

Energy including Renewables

Funding Statement

The authors acknowledge the Ph.D. scholarships for MA from the German Academic Exchange Services (DAAD) and the PASET Regional Scholarships and Innovation Fund (RSIF); the financial support provided by the Helmholtz Association via (i) the Recruitment Initiative Funding to BSR and (ii) the Research Field Energy Program-Materials and Technologies for the Energy Transition-Topic 1 Photovoltaics (38.01.05).

Recommended Citation

Ansong, M., Huang, G., Nyang’onda, T. N., Musembi, R. J., & Richards, B. S. (2025). Very short-term solar irradiance forecasting based on open-source low-cost sky imager and hybrid deep-learning techniques. Solar Energy https://doi.org/10.1016/j.solener.2025.113516