Energija, Vol. 73. No. 4., 2024.
Izvorni znanstveni članak
https://doi.org/10.37798/2024734707
Regional Solar Irradiance Forecasting Using Multi-Camera Sky Imagery and Machine Learning Models
Alen Jakoplić
; Tehnički fakultet Sveučilište u Rijeci, Rijeka, Hrvatska
*
Dubravko Franković
orcid.org/0000-0003-1734-4662
; Croatian Transmission System Operator
Tomislav Plavšić
orcid.org/0000-0002-6747-4329
; Hrvatski operator prijenosnog sustava
Branka Dobraš
; Croatian Transmission System Operator
* Dopisni autor.
Sažetak
With the increasing integration of photovoltaic (PV) systems into power grids, accurate short-term solar irradiance fore-casting is essential for efficient energy management. This paper presents a machine learning model developed using a synthetic dataset designed to analyze the potential of multicamera sky imaging for regional solar irradiance forecasting. The dataset, generated in a con-trolled simulation environment, captures cloud dynamics and solar irradiance at multiple locations within a region. The proposed model utilizes sky images from multiple virtual cameras strategically positioned to provide spatially distributed observations. By combining image-based features with historical irradiance measurements, the model shows improved forecasting accuracy compared to single-cam-era approaches. The results indicate that multi-camera systems better capture the spatial variability of cloud cover and allow the model to predict solar irradiance for locations without installed cameras. This research highlights the potential of multi-camera configurations for regional forecasting and provides valuable insights for grid operators and energy planners. The results support the adoption of distributed sky imaging networks as a practical approach to improve solar irradiance predictions and ultimately contribute to the stability and reliability of solar powered energy systems through improved forecast accuracy.
Ključne riječi
solar irradiance forecasting; photovoltaic systems; multi-camera sky imaging; renewable energy integration
Hrčak ID:
338951
URI
Datum izdavanja:
1.12.2024.
Posjeta: 246 *