The output voltage of a photovoltaic (PV) system relies on temperature and solar irradiance; therefore, the PV system and a load cannot be connected directly. To control the output voltage, a DC-DC boost converter is required. However, regulating this converter is a very complicated problem due to its non-linear time-variant and non-minimum phase circuit. Furthermore, the problem becomes more challenging due to uncertainty about the output voltage of the PV system and variation in the load, which is a non-linear disturbance. In this study, an observer-based backstepping sliding mode control (OBSMC) is proposed to regulate the output voltage of a DC-DC boost converter. The input voltage of the converter can be a DC energy source such as PV-based microgrid systems. An adaptive scheme and sliding mode controller constructed from a dynamic model of the converter is used to design an observer. This observer estimates unmeasured system states such as inductor current, capacitor voltage, uncertainty output voltages of the PV cell, and variation of loads such that the system does not need any sensors. In addition, the backstepping technique has been combined with the SMC to make the controller more stable and robust. In addition, the Lyapunov direct method is employed to ensure the stability of the proposed method. By employing the proposed configuration, the control performance was improved. To verify the effectiveness of the proposed controller, a numerical simulation was conducted. The simulation results show that the proposed method is always able to accurately follow the desired voltage with more robustness, fewer steady-state errors, smaller overshoot, faster recovery time, and faster transient response time. In addition, the proposed method consistently produces the least value of integral absolute error.

The uncertainty in wind speed and load demand fluctuations has made the deployment of renewable energy (RE) challenging. However, in islanded microgrids, the implementation of hybrid energy storage systems (HESS) can improve the reliability of power supply and enable further utilization of surplus energy. In this study, we configure an energy management system (EMS) for an optimally constructed system that includes wind turbines (WTs), an electric storage system (i.e., lithium-ion battery), a hydrogen storage system (i.e., PEM type), and diesel generator (DG), based on model predictive control (MPC), to meet specified technical and economic benchmarks for a standalone microgrid (SMG). MPC is intended to maintain the state of charge (SOC) and level of hydrogen (LOH) within their technical limits to prevent degradation and extend the lifetimes of HESS by minimizing the objective function. Additionally, disturbances due to wind power and load demand variations are captured to determine the optimal instantaneous powers of hydrogen and DG sources exposed to certain weighting factors within opted constraints. To perform the simulations, MPC toolbox in MATLAB Simulink environment is used. We consider four cases under various weather conditions to validate the robustness of MPC on the designed EMS for the SMG with shared system element powers for 24 hours using real data of wind velocity and load demand. From the simulation results, we observe minimum and maximum SOC of 20% and 88.52%, and LOH of 10% and 90.06% for the entire studied periods respectively. The results of the designed EMS show that MPC has ensured the HRES bounds to prevent degradation, overcome power interruptions due to weather intermittencies, and reduce grid-integration establishment charges. Moreover, the utilization of the entire renewable energy produced by wind turbines is achieved. Likewise, the load demand is met completely by using this technique and excellent performance of MPC under uncertainty is achieved.

The growing interest in solar energy stems from its potential to reduce greenhouse gas emissions. Global horizontal irradiance (GHI) is a crucial determinant of the productivity of solar photovoltaic (PV) systems. Consequently, accurate GHI forecasting is essential for efficient planning, integration, and optimization of solar PV energy systems. This study evaluates the performance of six machine learning (ML) regression models—artificial neural network (ANN), decision tree (DT), elastic net (EN), linear regression (LR), Random Forest (RF), and support vector regression (SVR)—in predicting GHI for a site in northern Saudi Arabia known for its high solar energy potential. Using historical data from the NASA POWER database, covering the period from 1984 to 2022, we employed advanced feature selection techniques to enhance the predictive models. The models were evaluated based on metrics such as R-squared (R²), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Error (MAE). The DT model demonstrated the highest performance, achieving an R² of 1.0, MSE of 0.0, RMSE of 0.0, MAPE of 0.0%, and MAE of 0.0. Conversely, the EN model showed the lowest performance with an R² of 0.8396, MSE of 0.4389, RMSE of 0.6549, MAPE of 9.66%, and MAE of 0.5534. While forward, backward, and exhaustive search feature selection methods generally yielded limited performance improvements for most models, the SVR model experienced significant enhancement. These findings offer valuable insights for selecting optimal forecasting strategies for solar energy projects, contributing to the advancement of renewable energy integration and supporting the global transition towards sustainable energy solutions.