Comparison of intraday probabilistic forecasting of solar irradiance using only endogenous data

David, Mathieu; Aguiar, L. Mazorra; Lauret, Philippe

doi:10.1016/j.ijforecast.2018.02.003

Cited by 46 publications

(26 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding intraday quantile forecasts, the quality of four state-of-the-art probabilistic models will be appraised. In this paper, we will not give the details of the implementation of these models as they have already been described in previous works (David et al, 2018;Pedro et al, 2018). In addition, we recall that the goal here is to illustrate the application of the proposed evaluation framework and not to have a detailed evaluation of these models.…”

Section: Intraday Quantile Forecastsmentioning

confidence: 99%

“…Although solar probabilistic forecasting is not as mature as wind probabilistic forecasting (Hong et al, 2016), some recent works (Alessandrini et al, 2015;Sperati et al, 2016;Zamo et al, 2014;Grantham et al, 2016;David et al, 2016David et al, , 2018Chu and Coimbra, 2017;Golestaneh et al, 2016b;Verbois et al, 2018) proposed to assess the quality of the models with some classical diagnostic tools originated from the weather verification community like rank histogram and reliability diagram. This literature review also revealed that the CRPS is a commonly used scoring rule.…”

Section: Introductionmentioning

confidence: 99%

“…However, in our opinion, most of these works did not conduct a detailed analysis of how to use and interpret the verification tools. For instance, the CRPS formula proposed by (Hersbach, 2000) is restricted to ensemble forecasts but David et al (2018) and Lauret et al (2017) used it to compute the CRPS of discrete quantile forecasts. Moreover, most of the previous works that evaluated the overall skill of competing methods through the use of the CRPS did not attempt to have a detailed performance of the methods which is possible from the decomposition of the CRPS into reliability, resolution and uncertainty.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Verification of solar irradiance probabilistic forecasts

Lauret¹,

David²,

Pinson

2019

Solar Energy

Self Cite

View full text Add to dashboard Cite

We propose a framework for evaluating the quality of solar irradiance probabilistic forecasts. The verification framework is based on visual diagnostic tools and a set of scoring rules mostly originating from the weather forecast verification community. Two types of probabilistic forecasts are used as a basis to illustrate the application of these verification approaches. The first one consists in ensemble forecasts commonly provided by national or international meteorological centres. The second one originates from statistical methods and produces a set of discrete quantile forecasts, the nominal proportions of which span the unit interval. These probabilistic forecasts are evaluated for two selected sites that experience very different climatic conditions. The first site is located in the continental US while the second one is situated on La Réunion Island. Although visual diagnostic tools can help identify deficiencies in generated forecasts, it is recommended that a set of numerical scores be used to assess the quality of probabilistic forecasts. In particular, the Continuous Ranked Probability Score (CRPS) seems to have all the features needed to evaluate a probabilistic forecasting system and, as such, may become a standard for verifying solar irradiance probabilistic forecasts and by extension probabilistic forecasts of solar power generation.

show abstract

Section: Intraday Quantile Forecastsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Verification of solar irradiance probabilistic forecasts

Lauret¹,

David²,

Pinson

2019

Solar Energy

Self Cite

View full text Add to dashboard Cite

show abstract

“…A number of algorithms have been used to forecast the GHI over this timescale. For example, David et al (2018) compared the intra-day forecasting of deterministic GHI by three models: coupled autoregressive and dynamical system (CARDS); sequential neural network (NN); and more traditional recursive autoregressive and moving average (ARMA) model. Their results showed that the performance of the ARMA model is comparable to that of NN, but both of them outperform the CARDS.…”

Section: Introductionmentioning

confidence: 99%

Intra-day Forecast of Ground Horizontal Irradiance Using Long Short-term Memory Network (LSTM)

Chen

Huang

Cai

et al. 2020

Journal of the Meteorological Society of Japan

View full text Add to dashboard Cite

Accurate forecast of global horizontal irradiance (GHI) is one of the key issues for power grid managements with large penetration of solar energy. A challenge for solar forecasting is to forecast the solar irradiance with a lead time of 1-8 hours, here termed as intra-day forecast. This study investigated an algorithm using a long short-term memory (LSTM) model to predict the GHI in 1-8 hours. The LSTM model has been applied before for inter-day (> 24 hours) solar forecast but never for the intra-day forecast. Four years (2010-2013) of observations by the National Renewable Energy Laboratory (NREL) at Golden, Colorado were used to train the model. Observations in 2014 at the same site were used to test the model performance. According to the results, for a 1-4 hour lead time, the LSTM-based model can make predictions of GHIs with root-mean-square-errors (RMSE) ranging from 77 to 143 W m −2 , and normalized RMSEs around 18.4-33.0 %. With five-minute inputs, the forecast skill of LSTM with respect to smart persistence model is 0.34-0.42, better than random forest forecast (0.27) and the numerical weather forecast (−0.40) made by the Weather Research and Forecasting (WRF) model. The performance levels off beyond 4-hour lead time. The model performs better in fall and winter than in spring and summer, and better under clear-sky conditions than under cloudy conditions. Using adjacent information from the reanalysis as extra inputs can further improve the forecast performance.

show abstract

“…There are relatively few papers in which a comparison among multiple regression methods on the same data set for solar radiation or solar power forecasting is a primary goal. David et al (2018) made a comparison between probabilistic forecasts using random forests, neural networks, (weighted) quantile regression, gradient boosting decision trees, recursive GARCH and the sieve bootstrap.…”

Section: Introductionmentioning

confidence: 99%

Comparison of statistical post-processing methods for probabilistic NWP forecasts of solar radiation

et al. 2019

View full text Add to dashboard Cite

The increased usage of solar energy places additional importance on forecasts of solar radiation. Solar panel power production is primarily driven by the amount of solar radiation and it is therefore important to have accurate forecasts of solar radiation. Accurate forecasts that also give information on the * Corresponding author ranked probability skill score, the Brier skill score and reliability diagrams. We find that quantile regression and generalized random forests generally perform best. In (near) clear sky conditions the non-parametric methods have more skill than the parametric ones.

show abstract

Comparison of intraday probabilistic forecasting of solar irradiance using only endogenous data

Cited by 46 publications

References 44 publications

Verification of solar irradiance probabilistic forecasts

Verification of solar irradiance probabilistic forecasts

Intra-day Forecast of Ground Horizontal Irradiance Using Long Short-term Memory Network (LSTM)

Comparison of statistical post-processing methods for probabilistic NWP forecasts of solar radiation

Contact Info

Product

Resources

About