Evaluation of an all sky imager based nowcasting system for distinct conditions and five sites

Nouri, Bijan; Wilbert, Stefan; Blum, Niklas; Kuhn, Pascal Moritz; Schmidt, Thomas; Yasser, Zeyad; Zarzalejo, Luis F.; Lopes, Francis M.; Silva, Hugo; Schroedter-Homscheidt, Marion; Kazantzidis, Andreas; Raeder, Christian; Blanc, Philippe; Pitz‐Paal, Robert

doi:10.1063/5.0028670

Cited by 10 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Being surrounded by multiple mountain ranges, very complex cloud conditions are often observed at PSA, making it a challenging site for irradiance nowcasts, as also previously analyzed in ref. [26]. In another study, [ 27 ] it was also shown that the distribution of clouds, with respect to cloud base height, is quite uniform at PSA, characterized by a slightly higher prevalence of low‐layer clouds overall.…”

Section: Datamentioning

confidence: 94%

Combining Deep Learning and Physical Models: A Benchmark Study on All‐Sky Imager‐Based Solar Nowcasting Systems

Fabel,

Nouri,

Wilbert

et al. 2024

Solar RRL

Self Cite

View full text Add to dashboard Cite

Intermittent solar irradiance due to passing clouds poses challenges for integrating solar energy into existing infrastructure. By making use of intra‐hour nowcasts (very short‐term forecasts), changing conditions of solar irradiance can be anticipated. All‐sky imagers, capturing sky conditions at high spatial and temporal resolution, can be the basis of such nowcasting systems. In this work, a deep learning (DL) model for solar irradiance nowcasts based on the transformer architecture is presented. The model is trained end‐to‐end using sequences of sky images and irradiance measurements as input to generate point‐forecasts up to 20 min ahead. Further, the effect of integrating this model into a hybrid system, consisting of a physics‐based model and smart persistence, is examined. A comparison between the DL and two hybrid models (with and without the DL model) is conducted on a benchmark dataset. Forecast accuracy for deterministic point‐forecasts is analyzed under different conditions using standard error metrics like root‐mean‐square error (RMSE) and forecast skill (FS). Furthermore, spatial and temporal aggregation effects are investigated. In addition, probabilistic nowcasts for each model are computed via a quantile approach. Overall, the DL model outperforms both hybrid models under the majority of conditions and aggregation effects.This article is protected by copyright. All rights reserved.

show abstract

Section: Datamentioning

confidence: 94%

Combining Deep Learning and Physical Models: A Benchmark Study on All‐Sky Imager‐Based Solar Nowcasting Systems

Fabel,

Nouri,

Wilbert

et al. 2024

Solar RRL

Self Cite

View full text Add to dashboard Cite

show abstract

“…This method is frequently used in the literature [3] to help to identify the state of the sky due to its simplicity. The daily clearness index or kt is defined as the ratio between the daily GHI and the daily extraterrestrial horizontal radiation: (1) where H d g0 is the daily horizontal global radiation and H d 0 is the daily horizontal extraterrestrial radiation.…”

Section: Input Data and Classification Methodsmentioning

confidence: 99%

“…The classification of days according to the solar radiation features is one of the tools frequently used for the solar resource assessment, modelling or forecasting [1]. Recent studies discuss the appropriate classification method or number of type of days [2], but these studies usually don't take into account, at least in an explicit way, the relation between the types of days and the yield of solar plants.…”

Section: Introductionmentioning

confidence: 99%

Comparison of the representativeness of solar radiation type of days from the viewpoint of the production of parabolic trough and central receiver plants

Moreno-Tejera¹,

Jiménez-Valero²,

Pérez-Aparicio³

et al. 2022

AIP Conference Proceedings

View full text Add to dashboard Cite

The classification of days according to the solar radiation features is one of the tools frequently used for the solar resource assessment, modelling or forecasting. Recent studies discuss the appropriate classification method or number of types of days, but these studies usually don't take into account, at least in an explicit way, the relation between the types of days and the yield of solar plants. In this work, we compare the representativeness of the types of days defined by two classification methods from the viewpoint of the production of a Central Receiver (CR) and a Parabolic Trough (PT) solar plant. The selected classification methods are based on the daily solar radiation features: energy, variability and temporal distribution. So, in a first step, the days of a period of 16 years of measurements recorded in Seville (Spain) are classified by these two methods. In a second step, the daily gross productions of both CSP plants are estimated using System Advisor Model program. Then, the representativeness of the types of days of each classification method is evaluated according to the production of the CR and the PT plant by means of a methodology based on the clear sky yield index or kp index. Finally, the ARE and the annual relative RMSE and the MAE for the plants and classification methods analyzed are compared. Then, we can conclude, that the representativeness of the types of days of a classification method has a certain dependence on the plant that depends on the classification method applied.

show abstract

“…The performance of this ASI nowcasting system has been evaluated in Germany (Oldenburg and Julich), Portugal (Evora), and Spain (La Africana and PSA) [25]. In the performance evaluation, the mean absolute deviation (MAD) and root mean square deviation (RMSD) were calculated for DNI, and in some locations also for GHI, but not for solar PV power output.…”

Section: Introduction Background and Motivationmentioning

confidence: 99%

Solar Irradiance Nowcasting System Trial and Evaluation for Islanded Microgrid Control Purposes

et al. 2022

Self Cite

View full text Add to dashboard Cite

The rapid increase in solar photovoltaic (PV) integration into electricity networks introduces technical challenges due to varying PV outputs. Rapid ramp events due to cloud movements are of particular concern for the operation of remote islanded microgrids (IMGs) with high solar PV penetration. PV systems and optionally controllable distributed energy resources (DERs) in IMGs can be operated in an optimised way based on nowcasting (forecasting up to 60 min ahead). This study aims to evaluate the performance under Perth, Western Australian conditions, of an all-sky imager (ASI)-based nowcasting system, installed at Murdoch University in Perth, Western Australia (WA). Nowcast direct normal irradiance (DNI) and global horizontal irradiance (GHI) are inputted into a 5 kWp solar PV system with a direct current (DC) power rating/alternating current (AC) power rating ratio of 1.0. A newly developed classification method provided a simplified irradiance variability classification. The obtained nowcasting system evaluation results show that the nowcasting system’s accuracy decreases with an increase in lead time (LT). Additionally, the nowcasting system’s accuracy is higher when the weather is either mostly clear (with a recorded LT15 mean absolute deviation (MAD) of 0.38 kW) or overcast (with a recorded LT15 MAD of 0.19 kW) than when the weather is intermittently cloudy with varying cloud conditions (with a recorded LT15 MAD of 0.44 kW). With lower errors observed in lower LTs, overall, it might be possible to integrate the nowcasting system into the design of IMG controllers. The overall performance of the nowcasting system at Murdoch University was as expected as it is comparable to the previous evaluations in five other different sites, namely, PSA, La Africana, Evora, Oldenburg, and Julich.

show abstract

Evaluation of an all sky imager based nowcasting system for distinct conditions and five sites

Cited by 10 publications

References 17 publications

Combining Deep Learning and Physical Models: A Benchmark Study on All‐Sky Imager‐Based Solar Nowcasting Systems

Combining Deep Learning and Physical Models: A Benchmark Study on All‐Sky Imager‐Based Solar Nowcasting Systems

Comparison of the representativeness of solar radiation type of days from the viewpoint of the production of parabolic trough and central receiver plants

Solar Irradiance Nowcasting System Trial and Evaluation for Islanded Microgrid Control Purposes

Contact Info

Product

Resources

About