Omnivision forecasting: Combining satellite and sky images for improved deterministic and probabilistic intra-hour solar energy predictions

Quentin, Paletta,; Arbod, Guillaume; Lasenby, Joan

doi:10.1016/j.apenergy.2023.120818

Cited by 26 publications

(15 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They can be combined to tackle the weaknesses of one method or to enhance each other to increase accuracy and strength [2]. One recent example is the work conducted by Paletta et al [33]. They combined All-Sky Imagery with satellite observations to investigate how these techniques can complement each other.…”

Section: Hybrid Approachesmentioning

confidence: 99%

“…The metrics mentioned before are well suited for determining average errors. However, they are not well suited for measuring the accuracy of predicting ramp events [7,9,33]. There is no strict definition of a ramp event, as it often depends on the end-use, whereby the events are critical [49].…”

Section: Assessment Of Ramp Events and Timing Errorsmentioning

confidence: 99%

Section: Data Resourcesmentioning

confidence: 99%

“…To gather the cloud cover information, sky conditions, and other meteorological parameters, Satellite Images from various satellites, including EUMETSAT's Meteosat, FengYun-4A, and MSG SEVIRI, are utilized [16,33,37]. NWPs from organizations such as ECMWF and NOAA play a significant role by providing data on atmospheric conditions, including cloud cover and temperature [33,37,44]. Ground-based measurements using pyranometers, pyrheliometers, and irradiance sensors directly measure the solar irradiance or power output, serving as crucial reference data for model validation and evaluation [44].…”

Section: Data Resourcesmentioning

confidence: 99%

“…Some studies validate and verify solar forecasting models by utilizing data from PV systems or solar power plants, which provide actual power generation values based on solar irradiance [16]. Additionally, sky cameras and ceilometers capture the localized cloud cover, cloud base height, and sky conditions, offering valuable supplementary data for solar forecasting models [33]. The relative frequency of the data sources that are used is summarized in Table 3.…”

Section: Data Resourcesmentioning

confidence: 99%

See 4 more Smart Citations

A Review of Solar Forecasting Techniques and the Role of Artificial Intelligence

Barhmi,

Heynen,

Golroodbari

et al. 2024

Solar

View full text Add to dashboard Cite

Solar energy forecasting is essential for the effective integration of solar power into electricity grids and the optimal management of renewable energy resources. Distinguishing itself from the existing literature, this review study provides a nuanced contribution by centering on advancements in forecasting techniques. While preceding reviews have examined factors such as meteorological input parameters, time horizons, the preprocessing methodology, optimization, and sample size, our study uniquely delves into a diverse spectrum of time horizons, spanning ultrashort intervals (1 min to 1 h) to more extended durations (up to 24 h). This temporal diversity equips decision makers in the renewable energy sector with tools for enhanced resource allocation and refined operational planning. Our investigation highlights the prominence of Artificial Intelligence (AI) techniques, specifically focusing on Neural Networks in solar energy forecasting, and we review supervised learning, regression, ensembles, and physics-based methods. This showcases a multifaceted approach to address the intricate challenges associated with solar energy predictions. The integration of Satellite Imagery, weather predictions, and historical data further augments precision in forecasting. In assessing forecasting models, our study describes various error metrics. While the existing literature discusses the importance of metrics, our emphasis lies on the significance of standardized datasets and benchmark methods to ensure accurate evaluations and facilitate meaningful comparisons with naive forecasts. This study stands as a significant advancement in the field, fostering the development of accurate models crucial for effective renewable energy planning and emphasizing the imperative for standardization, thus addressing key gaps in the existing research landscape.

show abstract

Section: Hybrid Approachesmentioning

confidence: 99%

Section: Assessment Of Ramp Events and Timing Errorsmentioning

confidence: 99%

Section: Data Resourcesmentioning

confidence: 99%

Section: Data Resourcesmentioning

confidence: 99%

Section: Data Resourcesmentioning

confidence: 99%

See 3 more Smart Citations

A Review of Solar Forecasting Techniques and the Role of Artificial Intelligence

Barhmi,

Heynen,

Golroodbari

et al. 2024

Solar

View full text Add to dashboard Cite

show abstract

Ramp Rate Metric Suitable for Solar Forecasting

Nouri,

Fabel,

Blum

et al. 2024

Solar RRL

View full text Add to dashboard Cite

Solar irradiance forecasting plays a crucial role in integrating large quantities of intermittent solar power. Forecasting systems are commonly evaluated using metrics like root‐mean‐ square error (RMSE) and skill scores. However, these metrics aggregated over larger data sets do not adequately assess the prediction of ramp events, which are critical for many applications. This article introduces a novel, simple, and adaptable ramp rate metric that analyzes ramp events between successive lead times within forecasts. A case study on ramp rate mitigation in PV systems benchmarks suitable ramp thresholds for various solar irradiance components. The capabilities and limitations of deterministic and probabilistic forecasts from two all‐sky imager‐based models are evaluated for ramp prediction. A state‐of‐the‐art data‐driven vision transformer End2End model excels in RMSE and skill scores but performs poorly in ramp prediction. Conversely, a novel generative forecasting model combined with a convolutional neural network‐based irradiance model shows superior ramp prediction, achieving an F1 score of ≥0.7 for critical ramp events. This study underscores the importance of suitable ramp rate metrics and highlights the potential of generative models for enhancing ramp forecasting.

show abstract

Solar energy generation and power prediction through computer vision and machine intelligence

Rout,

Shyamsukha,

Mittal

et al. 2025

Computer Vision and Machine Intelligence for Renewable Energy Systems

View full text Add to dashboard Cite

Omnivision forecasting: Combining satellite and sky images for improved deterministic and probabilistic intra-hour solar energy predictions

Cited by 26 publications

References 67 publications

A Review of Solar Forecasting Techniques and the Role of Artificial Intelligence

A Review of Solar Forecasting Techniques and the Role of Artificial Intelligence

Ramp Rate Metric Suitable for Solar Forecasting

Solar energy generation and power prediction through computer vision and machine intelligence

Contact Info

Product

Resources

About