Performance comparison of solar radiation forecasting between WRF and LSTM in Gifu, Japan

Araujo, Jose Manuel Soares de

doi:10.1088/2515-7620/ab7366

“…Several models of AI have been established. For instance, Fuzzy logic sets and systems using AI models, as well as neuro-fuzzy systems [28], neural networks [29], machine/deep learning [30] [31], and Long short-term memory (LSTM) [32] have all been employed in the estimation of Rs. In terms of ML, it has been used by many academics to predict Rs.…”

Section: Related Workmentioning

confidence: 99%

Accurate Solar Radiation Forecasting using an Effective Time Series with Feature Selection

Guezzaz

¹

,

Benkirane

²

,

Abderrahim

³

2023

Preprint

0

View full text Add to dashboard Cite

Solar rays on earth surface are essential for water resources, environmental and agricultural issues. They severely impact plant growth, global temperatures, mean sea levels, and climatic extremes. The most critical challenge in renewable energy applications is accurate solar radiation (Rs) forecasting. It has become increasingly important in directing solar energy conversion systems, selecting appropriate regions, and even making decision in future investment strategies. The most significant disadvantage of this energy is that it is nonlinear and works only when the load requires it. Since measurement tools are expensive, difficult to install, and not available in all regions of the world, as well as other concerns like equipment failure or water and dirt building up in the sensors, which might cause data to be missing or out of the expected range. Rs is seldom recorded at weather stations. As a result, several methodologies, including empirical, statistical, satellite, time series-based models, and others, have been employed to estimate it using other environmental parameters. Many approaches and preprocessing models based on machine learning (ML) are validated for Rs forecasting and complexity reduction to reduce these concerns. In this paper, we present a model that shows the impact of feature selection (FS) on time series for accurate Rs forecasting. The proposed model use recursive feature elimination (RFE) with random forest (RF), decision tree (DT), logistic regression (LR), classification and regression tree (CART), person (Pr) and gradient boosting models (GBM). The obtained results show that the models based on CART, LR, and GBM provide high accuracies of 0.894, 0.884, and 0.882, respectively. These three accurate methods have same standard deviation (std) of 0.033. In terms of the negative mean absolute error (nMAE) (std), the methods provide 0.892 (0.029), 0.885 (0.034), and 0.885 (0.035) respectively. Compared with other models, the RFE model provides significant impacts features and good performances.

show abstract

“…Ferrari et al [13] presented solar radiation prediction using the statistical approach and stated that ARIMA has minimum parameters compared to the AR and ARMA. de Araujo [14] investigated the WRF (Weather Research Forecasting) and LSTM performance to forecast solar radiation. A-Sbou and Alawasa [15] performed prediction of solar radiation in Mutah city with NARX (Nonlinear Autoregressive RNN with exogenous).…”

Section: Related Workmentioning

confidence: 99%

Combined Long Short-Term Memory Network-Based Short-Term Prediction of Solar Irradiance

Madhiarasan

¹

,

Louzazni

²

2022

International Journal of Photoenergy

View full text Add to dashboard Cite

Achieving the highly accurate and generic prediction of solar irradiance is arduous because solar irradiance possesses intermittent randomness and is influenced by meteorological parameters. Therefore, this paper endeavors a new combined long short-term memory network (CLSTMN) with various influence meteorological parameters as inputs. We investigated the proposed predictive model applicability for short-term solar irradiance prediction application and validated it in the real-time metrological dataset. The proposed prediction model is combined and accumulated by various inputs, incurring six individual long short-term memory models to improve solar irradiance prediction accuracy and generalization. Thus, the CLSTMN-based solar irradiance prediction can be generic and overcome the metrological parameters concerning variability. The experimental results ensure good prediction accuracy with minimal evaluation metrics of the proposed CLSTMN for solar irradiance prediction. The RMSE, MAPE, and MSE achieved based on the proposed CLSTMN one-hour-ahead prediction are 7.7729 × 10 − 04 , 8.2479 × 10 − 05 , and 6.0419 × 10 − 07 and for six-hour-ahead prediction are 0.0157, 0.0017, and 2.4627 × 10 − 04 for sunny days, and for cloudy days, the RMSE, MAPE, and MSE achieved based on the proposed CLSTMN one-hour-ahead prediction are 1.2969 × 10 − 04 , 1.6882 × 10 − 04 , and 1.6819 × 10 − 08 and for six-hour-ahead prediction are 0.0176, 0.0043, and 3.0863 × 10 − 04 , respectively. Finally, we investigate the CLSTMN performance effectiveness by comparative analysis with well-known baseline models. The investigative study shows the surpassing prediction performance of the proposed CLSTMN for short-term solar irradiance prediction.

show abstract

“…There is little time-series forecast analysis of the GEPU related to COVID-19. Therefore, it leads to our second contribution that RNN and LSTM networks are adopted to forecast the development of the GEPU index, which fills the gap in time series forecasting of the GEPU index (Araujo 2020). This study makes the third contribution that we investigate and predict uncertainty of the policy related to social and ecological environment changes in the post-COVID-19 era.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Post-COVID-19 economic and environmental policy and recovery based on recurrent neural network and long short-term memory network

Hu

¹

,

Xiong²,

Chen³

et al. 2022

Environ. Res. Commun.

View full text Add to dashboard Cite

COVID-19 has brought significant impacts on the global economy and environment. The Global Economic-and-environmental Policy Uncertainty (GEPU) index is a critical indicator to measure the uncertainty of global economic policies. Its prediction provides evidence for the good prospect of global economic and environmental policy and recovery. This is the first study using the monthly data of GEPU from January 1997 to January 2022 to predict the GEPU index after the COVID-19 pandemic. Both Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) models have been adopted to predict the GEPU. In general, the RNN outperforms the LSTM networks, and most results suggest that the GEPU index will remain stable or decline in the coming year. A few results point to the possibility of a short-term increase in GEPU, but still far from its two peaks during the first year of the COVID-19 pandemic. This forecast confirms that the impact of the epidemic on global economic and environmental policy will continue to wane. Lower economic and environmental policy uncertainty facilitates global economic and environmental recovery. Economic recovery brings more opportunities and a stable macroeconomic environment, which is a positive sign for both investors and businesses. Meanwhile, for the ecological environment, the declining GEPU index marks a gradual reduction in the direct impact of policy uncertainty on sustainable development, but the indirect environmental impact of uncertainty may remain in the long run. Our prediction also provides a reference for subsequent policy formulation and related research.

show abstract

Performance comparison of solar radiation forecasting between WRF and LSTM in Gifu, Japan

Cited by 19 publications

References 27 publications

Accurate Solar Radiation Forecasting using an Effective Time Series with Feature Selection

Accurate Solar Radiation Forecasting using an Effective Time Series with Feature Selection

Combined Long Short-Term Memory Network-Based Short-Term Prediction of Solar Irradiance

Prediction of Post-COVID-19 economic and environmental policy and recovery based on recurrent neural network and long short-term memory network

Contact Info

Product

Resources

About