Renewable energy (RE) sources, such as wind, geothermal, bioenergy, and solar, have gained interest in developed regions. The rapid expansion of the economies in the Middle East requires massive increases in electricity production capacity, and currently fossil fuel reserves meet most of the power station demand. There is a considerable measure of unpredictability surrounding the locations of the concerned regions where RE can be used to generate electricity. This makes forecasting difficult for the investor to estimate future electricity production that could be generated in each area over the course of a specific period. Energy production forecasting with complex time-series data is a challenge. However, artificial neural networks (ANNs) are well suited for handling nonlinearity effectively. This research aims to investigate the various ANN models capable of providing reliable predictions for sustainable sources of power such as wind and solar. In addition to the ANN models, a state-of-the-art ensemble learning approach is used to improve the accuracy of predictions further. The proposed strategies can forecast RE generation accurately over short and long time frames, relying on historical data for precise predictions. This work proposes a new hybrid ensemble framework that strategically combines multiple complementary machine learning (ML) models to improve RE forecasting accuracy. The ensemble learning (EL) methodology outperforms long short-term memory (LSTM), light gradient boosting machine (LightGBM), and sequenced-GRU in predicting wind power (MAE: 0.782, MAPE: 0.702, RMSE: 0.833) and solar power (MAE: 1.082, MAPE: 0.921, RMSE: 1.055). It achieved an impressive R² value of 0.9821, indicating its superior accuracy.

The stability performance of smart grid power systems is critical and requires special attention. Additionally, the combination of Battery Energy Storage (BES) systems, Solar Photovoltaic (SPV), and wind systems in the intelligent grid model provides utilities with excellent efficiency and dependability. However, a coordination grid with PV and other resources frequently results in severe issues, such as outages or power disruptions. A power outage in the grid might result in a power loss in the delivery system. As a result, the distributed grid model’s dependable performance is intended for integrated wind energy, SPV arrays, and BE systems. This paper proposes a renewable intelligent grid model to sustain solar power generation. The model incorporates a boost converter to optimize the performance of solar panels by converting the DC power generated by the panels into AC power for use in the grid. The boost converter is optimized using a novel Horse Herd Optimization Algorithm (HOA) method. In this case, the HOA method is used to optimize the control parameters of the boost converter, such as the duty cycle and the inductor and capacitor values. According to the final results, the proposed method has reduced the Total Harmonic Deformation (THD) and power loss. Additionally, the proposed method outperformed existing strategies related to the Expected Energy Not Supplied (EENS), Loss of Load Probability (LOLP), and Loss of Load Expected (LOLE), indicating the sustainability of power generation.