A new evolutionary forest model via incremental tree selection for short-term global solar irradiance forecasting under six various climatic zones

Abstract

The increasing integration of solar sources into the energy mix presents significant challenges, particularly in short-term energy management. Accurate solar irradiance forecasts can greatly assist solar power plant operators and energy network managers in making informed decisions about energy production and consumption. This paper aims to develop a new accurate forecasting model for short-term global solar irradiance based on an innovative evolutionary forest approach. Our model, baptized EFITS, performs incremental tree selection through appropriate evolutionary operators maintaining a good tradeoff between accuracy and diversity, generating progressively near-optimal decision trees to construct the final evolutionary forest forecaster. This new evolution process also automatically selects near-optimal input parameters, enhancing the overall model accuracy and generalization ability. Six climatically diverse locations in Morocco and three types of inputs (endogenous, exogenous, and hybrid) are used to assess the performance of the proposed. The results demonstrate that our proposed model exhibits excellent performance across all studied sites and horizons. Among all input types, hybrid inputs delivered the best forecasting accuracy across all studied sites and horizons. Notably, the continental climate site (Bni Mellal) achieved the highest accuracy, with nRMSE ranging from 4.94% to 7.54% and nMBE from 0.71% to −0.46% for 1 to 6 h forecasts. Conversely, Ifrane city, characterized by a humid temperate climate, showed the lowest accuracy, with nRMSE ranging from 10.34% to 18.94% and nMBE from 1.21% to −1.54%. Finally, a detailed comparison with benchmarking models (random forest, bagging, gradient boosting, single decision tree, bidirectional long short-term memory network, and scaled persistence models), revealed that our model consistently outperforms them across all tested scenarios, locations, and forecasting horizons.