<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>This study deals with the performance of PV2-state model in intra-hour forecasting of photovoltaic (PV) power. The PV2-state model links an empirical model for estimating the PV power delivered by a PV system under clear-sky with a model for forecasting the relative position of the Sun and clouds. Sunshine number (SSN), a binary quantifier showing if the Sun shines or not, is used as a measure for the Sun position with respect to clouds. A physics-based approach to intra-hour forecasting, processing cloud field information from an all-sky imager, is applied to predict SSN. The quality of SSN prediction conditions the overall quality of PV2-state forecasts. The PV2-state performance was evaluated against a challenging database (high variability in the state-of-the-sky, thin cloud cover, broken cloud field, isolated passing clouds) comprising radiometric data and sky-images collected on the Solar Platform of the West University of Timisoara, Romania. The investigation was performed from two perspectives: general model accuracy and, as a novelty, identification of characteristic elements in the state-of-the-sky which fault the SSN prediction. The outcome of such analysis represents the basis of further research aiming to increase the performance in PV power forecasting.</p>
</abstract>

This study deals with the performance of PV2-state model in intra-hour forecasting of photovoltaic (PV) power. The PV2-state model links an empirical model for estimating the PV power delivered by a PV system under clear-sky with a model for forecasting the relative position of the Sun and clouds. Sunshine number (SSN), a binary quantifier showing if the Sun shines or not, is used as a measure for the Sun position with respect to clouds. A physics-based approach to intra-hour forecasting, processing cloud field information from an all-sky imager, is applied to predict SSN. The quality of SSN prediction conditions the overall quality of PV2-state forecasts. The PV2-state performance was evaluated against a challenging database (high variability in the state-of-the-sky, thin cloud cover, broken cloud field, isolated passing clouds) comprising radiometric data and sky-images collected on the Solar Platform of the West University of Timisoara, Romania. The investigation was performed from two perspectives: general model accuracy and, as a novelty, identification of characteristic elements in the state-of-the-sky which fault the SSN prediction. The outcome of such analysis represents the basis of further research aiming to increase the performance in PV power forecasting.

Short-Term PV Power Forecasting Based on Sky Imagery. A Case Study at the West University of Timisoara

Annals of West University of Timisoara - Physics

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

This study deals with the performance of PV2-state model in intra-hour forecasting of photovoltaic (PV) power. The PV2-state model links an empirical model for...

Short-Term PV Power Forecasting Based on Sky Imagery. A Case Study at the West University of Timisoara

Online veröffentlicht: 28. Nov. 2022

Seitenbereich: 148 - 157

Eingereicht: 09. Okt. 2022

Akzeptiert: 11. Nov. 2022

DOI: https://doi.org/10.2478/awutp-2022-0010

Schlüsselwörter
PV power forecasting, all-sky imager, sunshine number, cloud motion

© 2022 Robert Blaga et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Short-Term PV Power Forecasting Based on Sky Imagery. A Case Study at the West University of Timisoara

Online veröffentlicht: 28. Nov. 2022

Seitenbereich: 148 - 157

Eingereicht: 09. Okt. 2022

Akzeptiert: 11. Nov. 2022

DOI: https://doi.org/10.2478/awutp-2022-0010

SchlüsselwörterPV power forecasting, all-sky imager, sunshine number, cloud motion

© 2022 Robert Blaga et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Schlüsselwörter
PV power forecasting, all-sky imager, sunshine number, cloud motion