A short-term solar radiation forecasting system for the Iberian Peninsula. Part 1: Models description and performance assessment

Rodríguez-Benítez, Francisco J.; Arbizu‐Barrena, Clara; Huertas‐Tato, Javier; Aler-Mur, Ricardo; Galván-León, Inés; Pozo‐Vázquez, D.

doi:10.1016/j.solener.2019.11.028

Cited by 40 publications

(15 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, when comparison against a reference baseline method is required, there may not be an overall agreement on the details of the implementation of such method and there is still debate regarding this topic, to which works such as [22] attempt to set the details for a standardized method. Additionally, as solar power forecasting has transitioned from the naïve persistence (irradiance I remains constant through forecast window, Equation (2), [23][24][25]) towards the smart persistence as the reference method (clear sky index K t cs remains constant through forecast window, Equation (3), [25,26]), the readers must be aware of which reference was used, making analysis and result comparison more difficult.Î…”

Section: Current State Of the Art In Solar Power Forecasting Performance Assessmentmentioning

confidence: 99%

“…To reduce forecast uncertainty due to the clear sky model, especially in cases of marked changes in Linke turbidity during nonclear conditions (as demonstrated in [35]), K t will be used instead of K tcs . As stated in Section 1, persistence forecasting as consensus baseline method has transitioned from naïve persistence (i.e., irradiance remains constant, Equation ( 2)) [23][24][25] towards smart persistence (i.e., clear sky index remains constant, Equation ( 3)) [25,26]. However, the estimation of the clear sky irradiance is subject to astronomical uncertainties (solar geometry modeling, Earth-Sun distance modeling and solar constant estimation uncertainty), atmospheric properties uncertainty (such as aerosol optical depth and integrated water vapor column estimation, among others, with specific effects depending on the clear sky model being used) and the intrinsic clear sky modeling error (which is model dependent).…”

Section: Dn I = (Ghi − Dh I) Sin α (9)mentioning

confidence: 99%

See 1 more Smart Citation

Short-Term Deterministic Solar Irradiance Forecasting Considering a Heuristics-Based, Operational Approach

2021

View full text Add to dashboard Cite

Solar energy is an economic and clean power source subject to natural variability, while energy storage might attenuate it, ultimately, effective and operationally feasible forecasting techniques for energy management are needed for better grid integration. This work presents a novel deterministic forecast method considering: irradiance pattern classification, Markov chains, fuzzy logic and an operational approach. The method developed was applied in a rolling manner for six years to a target location with no prior data to assess performance and its changes as new local data becomes available. Clearness index, diffuse fraction and irradiance hourly forecasts are analyzed on a yearly basis but also for 20 day types, and compared against smart persistence. Results show the proposed method outperforms smart persistence by ~10% for clearness index and diffuse fraction on the base case, but there are significant differences across the 20 day types analyzed, reaching up to +60% for clear days. Forecast lead time has the greatest impact in forecasting performance, which is important for any practical implementation. Seasonality in data gaps or rejected data can have a definite effect in performance assessment. A novel, comprehensive and detailed analysis framework was shown to present a better assessment of forecasters’ performance.

show abstract

Section: Current State Of the Art In Solar Power Forecasting Performance Assessmentmentioning

confidence: 99%

Section: Dn I = (Ghi − Dh I) Sin α (9)mentioning

confidence: 99%

Short-Term Deterministic Solar Irradiance Forecasting Considering a Heuristics-Based, Operational Approach

2021

View full text Add to dashboard Cite

show abstract

“…In addition, we used the persistence reference model, which is also known as Naïve Predictor [25,26] and which is widely used for the benchmark tests [27][28][29], in order to compare with other models in this study. In this reference model, the forecasted value at time t + 1 is equal to the value at time t. In other words, the persistence reference model is only based on the linear correlation between the present and the future photovoltaic power values.…”

Section: Multilayer Perceptronmentioning

confidence: 99%

Daily Photovoltaic Power Prediction Enhanced by Hybrid GWO-MLP, ALO-MLP and WOA-MLP Models Using Meteorological Information

2020

View full text Add to dashboard Cite

Solar energy is a safe, clean, environmentally-friendly and renewable energy source without any carbon emissions to the atmosphere. Therefore, there are many studies in the field of solar energy in order to obtain the maximum solar radiation during the day time, to estimate the amount of solar energy to be produced, and to increase the efficiency of solar energy systems. In this study, it was aimed to predict the daily photovoltaic power production using air temperature, relative humidity, total horizontal solar radiation and diffuse horizontal solar radiation parameters as multi-tupled inputs. For this purpose, grey wolf, ant lion and whale optimization algorithms were integrated to the multilayer perceptron. In addition, the effects of sigmoid, sinus and hyperbolic tangent activation functions on the prediction performance were analyzed in detail. As a result of overall accuracy indictors achieved, the grey wolf optimization algorithm-based multilayer perceptron model was found to be more successful and competitive for the daily photovoltaic power prediction. Furthermore, many meaningful patterns were revealed about the constructed models, input tuples and activation functions.

show abstract

“…The adoption of AI (machine learning and deep learning) models for the prediction or estimation of solar radiation have proven in literature to have a wider application and higher accuracy in comparison to other models. These models can accurately moderate the long-term, medium-term, and short-term prediction of solar radiation 14 . Gurel et al 15 presented the assessment of time series (Holt-Winters), machine learning (feed-forward neural network), empirical models (3 Angstrom-type models), and response surface methodology (RSM) for global solar radiation.…”

Section: Introductionmentioning

confidence: 99%

Comprehensive assessment, review, and comparison of AI models for solar irradiance prediction based on different time/estimation intervals

Bamisile

Cai

Oluwasanmi

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Solar energy-based technologies have developed rapidly in recent years, however, the inability to appropriately estimate solar energy resources is still a major drawback for these technologies. In this study, eight different artificial intelligence (AI) models namely; convolutional neural network (CNN), artificial neural network (ANN), long short-term memory recurrent model (LSTM), eXtreme gradient boost algorithm (XG Boost), multiple linear regression (MLR), polynomial regression (PLR), decision tree regression (DTR), and random forest regression (RFR) are designed and compared for solar irradiance prediction. Additionally, two hybrid deep neural network models (ANN-CNN and CNN-LSTM-ANN) are developed in this study for the same task. This study is novel as each of the AI models developed was used to estimate solar irradiance considering different timesteps (hourly, every minute, and daily average). Also, different solar irradiance datasets (from six countries in Africa) measured with various instruments were used to train/test the AI models. With the aim to check if there is a universal AI model for solar irradiance estimation in developing countries, the results of this study show that various AI models are suitable for different solar irradiance estimation tasks. However, XG boost has a consistently high performance for all the case studies and is the best model for 10 of the 13 case studies considered in this paper. The result of this study also shows that the prediction of hourly solar irradiance is more accurate for the models when compared to daily average and minutes timestep. The specific performance of each model for all the case studies is explicated in the paper.

show abstract

A short-term solar radiation forecasting system for the Iberian Peninsula. Part 1: Models description and performance assessment

Cited by 40 publications

References 47 publications

Short-Term Deterministic Solar Irradiance Forecasting Considering a Heuristics-Based, Operational Approach

Short-Term Deterministic Solar Irradiance Forecasting Considering a Heuristics-Based, Operational Approach

Daily Photovoltaic Power Prediction Enhanced by Hybrid GWO-MLP, ALO-MLP and WOA-MLP Models Using Meteorological Information

Comprehensive assessment, review, and comparison of AI models for solar irradiance prediction based on different time/estimation intervals

Contact Info

Product

Resources

About