Ensemble solar forecasting using data-driven models with probabilistic post-processing through GAMLSS

Yagli, Gokhan Mert; Yang, Di; Srinivasan, Dipti

doi:10.1016/j.solener.2020.07.040

Cited by 25 publications

(9 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These forecasts are then considered as quantiles. The corresponding distribution F(y) can be mathematically modeled as follows [2]:…”

Section: Examples Of Non-parametric Probabilistic Forecasting Modelsmentioning

confidence: 99%

“…Thus, the information gap produces possibilities, and this range of possibilities increases as the information gap grows. In this way, decision makers may decide to base their decisions upon the best-informed available model and disregard the uncertainties, which results in insufficient decision-making [2]. To resolve this issue, probabilistic forecasting is suggested.…”

Section: Introduction 1motivation and Contributionmentioning

confidence: 99%

See 1 more Smart Citation

Applications of Probabilistic Forecasting in Smart Grids: A Review

Khajeh

Laaksonen

2022

Applied Sciences

View full text Add to dashboard Cite

This paper reviews the recent studies and works dealing with probabilistic forecasting models and their applications in smart grids. According to these studies, this paper tries to introduce a roadmap towards decision-making under uncertainty in a smart grid environment. In this way, it firstly discusses the common methods employed to predict the distribution of variables. Then, it reviews how the recent literature used these forecasting methods and for which uncertain parameters they wanted to obtain distributions. Unlike the existing reviews, this paper assesses several uncertain parameters for which probabilistic forecasting models have been developed. In the next stage, this paper provides an overview related to scenario generation of uncertain parameters using their distributions and how these scenarios are adopted for optimal decision-making. In this regard, this paper discusses three types of optimization problems aiming to capture uncertainties and reviews the related papers. Finally, we propose some future applications of probabilistic forecasting based on the flexibility challenges of power systems in the near future.

show abstract

“…These forecasts are then considered as quantiles. The corresponding distribution F(y) can be mathematically modeled as follows [2]:…”

Section: Examples Of Non-parametric Probabilistic Forecasting Modelsmentioning

confidence: 99%

Section: Introduction 1motivation and Contributionmentioning

confidence: 99%

Applications of Probabilistic Forecasting in Smart Grids: A Review

Khajeh

Laaksonen

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…For considerations in the context of solar irradiance forecasting, see e.g. Yang (2020d), Yagli et al (2020), and La Salle et al (2020). In those previous works, forecast distributions are truncated at zero, i.e., probability mass belonging to negative values before truncation is re-assigned to positive values by restricting the support to the positive half-axis and multiplying the PDF with a constant factor.…”

Section: Choice Of Forecast Distributionmentioning

confidence: 99%

“…La Salle et al (2020) propose an EMOS model for global horizontal irradiance where truncated normal and generalized extreme value distributions are used as forecast distributions, and compare to quantile regression and analog ensemble methods. Yagli et al (2020) compare several parametric and nonparametric postprocessing methods for hourly clear-sky index forecasting, including EMOS models based on Gaussian, truncated logistic and skewed Student's t distributions as well as quantile regression based on random forests, and generalized additive models for location, scale and shape. In closely related work, Yang (2020c) proposes the use of EMOS models for probabilistic site adaptation of gridded solar irradiance products, and Yang (2020d) compares building models for irradiance and for the clearsky index and investigates the choice of parametric distributions.…”

Section: Introductionmentioning

confidence: 99%

Post-processing numerical weather prediction ensembles for probabilistic solar irradiance forecasting

Lerch¹,

Schulz²,

Ayari³

et al. 2021

Preprint

View full text Add to dashboard Cite

<p>In order to enable the transition towards renewable energy sources, probabilistic energy forecasting is of critical importance for incorporating volatile power sources such as solar energy into the electrical grid. Solar energy forecasting methods often aim to provide probabilistic predictions of solar irradiance. In particular, many hybrid approaches combine physical information from numerical weather prediction models with statistical methods. Even though the physical models can provide useful information at intra-day and day-ahead forecast horizons, ensemble weather forecasts from multiple model runs are often not calibrated and show systematic biases. We propose a post-processing model for ensemble weather predictions of solar irradiance at temporal resolutions between 30 minutes and 6 hours. The proposed models provide probabilistic forecasts in the form of a censored logistic probability distribution for lead times up to 5 days and are evaluated in two case studies covering distinct physical models, geographical regions, temporal resolutions, and types of solar irradiance. We find that post-processing consistently and significantly improves the forecast performance of the ensemble predictions for lead times up to at least 48 hours and is well able to correct the systematic lack of calibration.</p>

show abstract

“…This is perhaps the most comprehensive of the present methods. Ensemble forecasting of clear sky index followed by post processing of the raw forecasts was used in [8]. Reforecasting using ANN methods is utilised in [9] to improve the skill of three methods, physical based on cloud movement, ARMA and k nearest neighbour approaches.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Forecasting of Wind and Solar Farm Output

Boland

Farah

2021

Energies

View full text Add to dashboard Cite

Accurately forecasting the output of grid connected wind and solar systems is critical to increasing the overall penetration of renewables on the electrical network. This includes not only forecasting the expected level, but also putting error bounds on the forecast. The National Electricity Market (NEM) in Australia operates on a five minute basis. We used statistical forecasting tools to generate forecasts with prediction intervals, trialing them on one wind and one solar farm. In classical time series forecasting, construction of prediction intervals is rudimentary if the error variance is constant—Termed homoscedastic. However, if the variance changes—Either conditionally as with wind farms, or systematically because of diurnal effects as with solar farms—The task is much more complicated. The tools were trained on segments of historical data and then tested on data not used in the training. Results from the testing set showed good performance using metrics, including Coverage and Interval Score. The methods used can be adapted to various time scales for short term forecasting.

show abstract

Ensemble solar forecasting using data-driven models with probabilistic post-processing through GAMLSS

Cited by 25 publications

References 49 publications

Applications of Probabilistic Forecasting in Smart Grids: A Review

Applications of Probabilistic Forecasting in Smart Grids: A Review

Post-processing numerical weather prediction ensembles for probabilistic solar irradiance forecasting

Probabilistic Forecasting of Wind and Solar Farm Output

Contact Info

Product

Resources

About