In this paper, solar irradiance short-term forecasts were performed considering time horizons ranging from 5 min to 30 min, under a 5 min timestep. Global Horizontal Irradiance (GHI) and Direct Normal Irradiance (DNI) were computed using Deep Neural Networks with One-Dimensional Convolution (CNN-1D), Long-Short Term Memory (LSTM) and CNN-LSTM layers on the benchmarking dataset FOLSOM, which is formed by predictors obtained by recursive functions on the clear sky index time series and statistical attributes extracted from images collected by a camera pointed to the zenith, characterizing endogenous and exogenous variables, respectively. To analyze the endogenous predictors influence on the accuracy of the networks, the performance was evaluated for the cases with and without them. This analysis is motivated, to our best knowledge, by the lack of works that cite the FOLSOM dataset using deep learning models, and it is necessary to verify the impact of the endogenous and exogenous predictors in the forecasts results for this specific approach. The accuracy of the networks was evaluated by the metrics Mean Absolute Error (MAE), Mean Bias Error (MBE), Root Mean Squared Error (RMSE), Relative root-mean-squared error (rRMSE), Determination Coefficient (R²) and Forecast Skill (s). The network architectures using isolated CNN-1D and LSTM layers generally performed better. The best accuracy was obtained by the CNN-1D network for a horizon of 10 min ahead reaching an RMSE of 36.24 W/m², improving 11.15% on this error metric compared to the persistence model.

Merging machine learning with the power of quantum computing holds great potential for data-driven decision making and the development of powerful models for complex datasets. This area offers the potential for improving the accuracy of the real-time prediction of renewable energy production, such as solar irradiance forecasting. However, the literature on this topic is sparse. Addressing this knowledge gap, this study aims to develop and evaluate a quantum neural network model for solar irradiance prediction up to 3 h in advance. The proposed model was compared with Support Vector Regression, Group Method of Data Handling, and Extreme Gradient Boost classical models. The proposed framework could provide competitive results compared to its competitors, considering forecasting intervals of 5 to 120 min ahead, where it was the fourth best-performing paradigm. For 3 h ahead predictions, the proposed model achieved the second-best results compared with the other approaches, reaching a root mean squared error of 77.55 W/m² and coefficient of determination of 80.92% for global horizontal irradiance forecasting. The results for longer forecasting horizons suggest that the quantum model may process spatiotemporal information from the input dataset in a manner not attainable by the current classical approaches, thus improving forecasting capacity in longer predictive windows.

This paper proposes to analyze the performance increase in the forecasting of solar irradiance and wind speed by implementing a dynamic ensemble architecture for intra-hour horizon ranging from 10 to 60 min for a 10 min time step data. Global horizontal irradiance (GHI) and wind speed were computed using four standalone forecasting models (random forest, k-nearest neighbors, support vector regression, and elastic net) to compare their performance against two dynamic ensemble methods, windowing and arbitrating. The standalone models and the dynamic ensemble methods were evaluated using the error metrics RMSE, MAE, R², and MAPE. This work’s findings showcased that the windowing dynamic ensemble method was the best-performing architecture when compared to the other evaluated models. For both cases of wind speed and solar irradiance forecasting, the ensemble windowing model reached the best error values in terms of RMSE for all the assessed forecasting horizons. Using this approach, the wind speed forecasting gain was 0.56% when compared with the second-best forecasting model, whereas the gain for GHI prediction was 1.96%, considering the RMSE metric. The development of an ensemble model able to provide accurate and precise estimations can be implemented in real-time forecasting applications, helping the evaluation of wind and solar farm operation.

Quantum machine learning applications have become viable with the recent advancements in quantum computing. Merging ML with the power of quantum computing holds great potential for data-driven decision-making, as well as the development of more powerful models capable of handling more complex datasets with faster processing time. This area offers potential for improving the accuracy of real-time forecasting renewable energy production. However, the literature on this topic is sparse. Addressing this knowledge gap, this study aims to design, implement, and evaluate the performance of a quantum neural network forecast model for solar irradiance up to 3-hours ahead. The proposed model was compared with Support Vector Regression, Group Method of Data Handling, and Extreme Gradient Boost classical models. Using the best quantum neural network configuration found, the proposed framework could provide competitive results when compared to its competitors, considering forecasting intervals of 5- to 120-minutes ahead, where it was the fourth best-performing paradigm. For 3-hours ahead predictions, the QNN was able to overcome its clas-sical counterparts, but the XGBoost. This fact can be an indication that the quantum model may identify and retrieve relevant spatiotemporal information from the input dataset in such a manner not attainable by the current classical approaches.

In this paper, solar irradiance and wind speed forecasts were performed considering time horizons ranging from 10 min to 60 min, under a 10 min time-step. Global horizontal irradiance (GHI) and wind speed were computed using four forecasting models (Random Forest, k-Nearest Neighbours, Support Vector Regression, and Elastic Net) to compare their performance against two alternative dynamic ensemble methods (windowing and arbitrating). Forecasting models and dynamic forecasting ensembles were implemented in Python for performance evaluation. The performance comparison between the prediction models and the dynamic ensemble methods was carried out by evaluating the RMSE, MAE, R² and MAPE, to evaluate whether the dynamic ensemble forecasting method obtained greater. According to the results obtained windowing dynamic ensemble method was the most efficient among the tested. For the wind speed data, by varying its parameter λ (from 1 to 100), a variable performance profile was obtained, where from λ =1 to λ = 74, windowing proved to be the most efficient, reaching maximum efficiency for λ = 19. Windowing was the best method for the GHI analysis, reaching its best performance for λ = 1. The efficiency gain using windowing was 0.56% when using the wind speed model and 1.96% for GHI.

Neste trabalho, previsões da média diária de irradiação solar global foram obtidas pela aplicação de algoritmos de aprendizagem de máquina em dois conjuntos de dados formados por variáveis exógenas (insolação, temperatura do ar, precipitação, etc), variáveis endógenas (série temporal da média diária de irradiação solar global) e variáveis temporais (ano, mês e dia da medição). A diferença entre os conjuntos de dados está relacionada ao fato de que em um se considera as intensidades dos fenômenos climáticos do El Niño e da La Niña como preditores para os modelos de aprendizagem utilizados, enquanto no outro não se considera. Desta forma, foi possível avaliar se a adição do preditor relacionado ao El Niño/La Niña contribui para uma melhor acurácia de previsão por parte dos modelos aplicados: Máquina de Aprendizagem Mínima, Regressão por Vetor Suporte, Florestas Aleatórias, K-Vizinhos mais Próximos e uma árvore de regressão com o uso de Bootstrap. As métricas de erro Erro Médio Absoluto, Erro de Viés Médio, Raiz do Erro Quadrático Médio, Raiz do Erro Quadrático Médio Relativo e Habilidade de Previsão foram utilizadas para a análise do desempenho dos algoritmos. A média aritmética da Raiz do Erro Quadrático Médio e da Habilidade de Previsão para o caso em que se considerou o El Niño/La Niña como atibutos foram de 40.78 W/m² e 7,87% , respectivamente. Já para o caso em que não se considera tais preditores os valores obtidos foram de 40.86 W/m² e 7.69%. Indicando que o uso destes preditores aumenta a acurácia de previsão dos algoritmos em questão.