Integration renewable energy sources into current power generation systems necessitates accurate forecasting to optimize and preserve supply–demand restrictions in the electrical grids. Due to the highly random nature of environmental conditions, accurate prediction of PV power has limitations, particularly on long and short periods. Thus, this research provides a new hybrid model for forecasting short PV power based on the fusing of multi-frequency information of different decomposition techniques that will allow a forecaster to provide reliable forecasts. We evaluate and provide insights into the performance of five multi-scale decomposition algorithms combined with a deep convolution neural network (CNN). Additionally, we compare the suggested combination approach's performance to that of existing forecast models. An exhaustive assessment is carried out using three grid-connected PV power plants in Algeria with a total installed capacity of 73.1 MW. The developed fusing strategy displayed an outstanding forecasting performance. The comparative analysis of the proposed combination method with the stand-alone forecast model and other hybridization techniques proves its superiority in terms of forecasting precision, with an RMSE varying in the range of [0.454–1.54] for the three studied PV stations.

This paper proposes an innovative approach to improve the performance of grid-connected photovoltaic (PV) systems operating in environments with variable atmospheric conditions. The dynamic nature of atmospheric parameters poses challenges for traditional control methods, leading to reduced PV system efficiency and reliability. To address this issue, we introduce a novel integration of fuzzy logic and sliding mode control methodologies. Fuzzy logic enables the PV system to effectively handle imprecise and uncertain atmospheric data, allowing for decision-making based on qualitative inputs and expert knowledge. Sliding mode control, known for its robustness against disturbances and uncertainties, ensures stability and responsiveness under varying atmospheric conditions. Through the integration of these methodologies, our proposed approach offers a comprehensive solution to the complexities posed by real-world atmospheric dynamics. We anticipate applications in grid-connected PV systems across various geographical locations and climates. By harnessing the synergistic benefits of fuzzy logic and sliding mode control, this approach promises to significantly enhance the performance and reliability of grid-connected PV systems in the presence of variable atmospheric conditions. On the grid side, both PSO (Particle Swarm Optimization) and GA (Genetic Algorithm) algorithms were employed to tune the current controller of the PI (Proportional-Integral) current controller (inverter control). Simulation results, conducted using MATLAB Simulink, demonstrate the effectiveness of the proposed hybrid MPPT technique in optimizing the performance of the PV system. The technique exhibits superior tracking efficiency, achieving a convergence time of 0.06 s and an efficiency of 99.86%, and less oscillation than the classical methods. The comparison with other MPPT techniques highlights the advantages of the proposed approach, including higher tracking efficiency and faster response times. The simulation outcomes are analyzed and demonstrate the effectiveness of the proposed control strategies on both sides (the PV array and the grid side). Both PSO and GA offer effective methods for tuning the parameters of a PI current controller. According to considered IEEE standards for low-voltage networks, the total current harmonic distortion values (THD) obtained are considerably high (8.33% and 10.63%, using the PSO and GA algorithms, respectively). Comparative analyses with traditional MPPT methods demonstrate the superior performance of the hybrid approach in terms of tracking efficiency, stability, and rapid response to dynamic changes.

This study presents the Enhanced Cheetah Optimizer Algorithm (ECOA) designed to tackle the intricate real-world challenges of dynamic economic dispatch (DED). These complexities encompass demand-side management (DSM), integration of non-conventional energy sources, and the utilization of pumped-storage hydroelectric units. Acknowledging the variability of solar and wind energy sources and the existence of a pumped-storage hydroelectric system, this study integrates a solar-wind-thermal energy system. The DSM program not only enhances power grid security but also lowers operational costs. The research addresses the DED problem with and without DSM implementation to analyze its impact. Demonstrating effectiveness on two test systems, the suggested method's efficacy is showcased. The recommended method's simulation results have been compared to those obtained using Cheetah Optimizer Algorithm (COA) and Grey Wolf Optimizer. The optimization results indicate that, for both the 10-unit and 20-unit systems, the proposed ECOA algorithm achieves savings of 0.24% and 0.43%, respectively, in operation costs when Dynamic Economic Dispatch is conducted with Demand-Side Management (DSM). This underscores the advantageous capability of DSM in minimizing costs and enhancing the economic efficiency of the power systems. Our ECOA has greater adaptability and reliability, making it a promising solution for addressing multi-objective energy management difficulties within microgrids, particularly when demand response mechanisms are incorporated. Furthermore, the suggested ECOA has the ability to elucidate the multi-objective dynamic optimal power flow problem in IEEE standard test systems, particularly when electric vehicles and renewable energy sources are integrated.

The lifetime of power transformers is closely related to the insulating oil performance. This latter can degrade according to overheating, electric arcs, low or high energy discharges, etc. Such degradation can lead to transformer failures or breakdowns. Early detection of these problems is one of the most important steps to avoid such failures. More efficient diagnostic systems, such as artificial intelligence techniques, are recommended to overcome the limitations of the classical methods. This work deals with diagnosing the power transformer insulating oil by analysis of dissolved gases using new techniques. For this, we have proposed intelligent techniques based on Multilayer artificial neural networks (ANN). Thus, a multi-layer ANN-based model for fault detection is presented. To improve its classification rate, this one was optimized by a meta-heuristic technique as the particle swarm optimization (PSO) technique. Optimized ANNs have never been used in transformer insulating oil diagnostics so far. The robustness and effectiveness of the proposed model is demonstrated, and high accuracy is obtained.

This research discusses the solar and wind sourcesintegration in aremote location using hybrid power optimization approaches and a multi energy storage system with batteries and supercapacitors. The controllers in PV and wind turbine systems are used to efficiently operate maximum power point tracking (MPPT) algorithms, optimizing the overall system performance while minimizing stress on energy storage components. More specifically, on PV generator, the provided method integrating the Perturb & Observe (P&O) and Fuzzy Logic Control (FLC) methods. Meanwhile, for the wind turbine, the proposed approach combines the P&O and FLC methods. These hybrid MPPT strategies for photovoltaic (PV) and wind turbine aim to optimize its operation, taking advantage of the complementary features of the two methods. While the primary aim of these hybrid MPPT strategies is to optimize both PV and wind turbine, therefore minimizing stress on the storage system, they also aim to efficiently supply electricity to the load. For storage, in this isolated renewable energy system, batteries play a crucial role due to several specific benefits and reasons. Unfortunately, their energy density is still relatively lower compared to some other forms of energy storage. Moreover, they have a limited number of charge–discharge cycles before their capacity degrades significantly. Supercapacitors (SCs) provide significant advantages in certain applications, particularly those that need significant power density, quick charging and discharging, and long cycle life. However, their limitations, such as lower energy density and specific voltage requirements, make them most effective when combined with other storage technologies, as batteries. Furthermore, their advantages are enhanced, result a more dependable and cost-effective hybrid energy storage system (HESS). The paper introduces a novel algorithm for power management designed for an efficient control. Moreover, it focuses on managing storage systems to keep their state of charge (SOC) within defined range. The algorithm is simple and effective. Furthermore, it ensures the longevity of batteries and SCs while maximizing their performance. The results reveal that the suggested method successfully keeps the limits batteries and SCs state of charge (SOC). To show the significance of system design choices and the impact on the battery’s SOC, which is crucial for the longevity and overall performance of the energy storage components, a comparison in of two systems have been made. A classical system with one storage (PV/wind turbine/batteries) and the proposed system with HESS (PV/wind turbine system with batteries). The results show that the suggested scenario investigated with both wind and solar resources appears to be the optimum solution for areas where the two resources are both significant and complementary. The balance between the two resources seems to contribute to less stress on storage components, potentially leading to a longer lifespan. An economical study has been made, using the Homer Pro software, to show the feasibility of the proposed system in the studied area.

This paper introduces an innovative, adaptive Fractional Open-Circuit Voltage (FOCV) algorithm combined with a robust Improved Model Reference Adaptive Controller (IMRAC) for Maximum Power Point Tracking (MPPT) in standalone photovoltaic (PV) systems. The proposed two-stage control strategy enhances energy efficiency, simplifies system operation, and addresses limitations in conventional MPPT methods, such as slow convergence, high oscillations, and susceptibility to environmental fluctuations. The first stage dynamically estimates the Maximum Power Point (MPP) voltage using a novel adaptive FOCV method, which eliminates the need for irradiance sensors or physical disconnection of PV modules. This stage incorporates a real-time adjustment of the kv factor based on variations in PV power, ensuring precise voltage estimation. In the second stage, the IMRAC controller ensures accurate tracking of the MPP by adapting swiftly to changes in irradiance and temperature, while minimizing ripple and power loss. Validation of the proposed system was carried out using Processor-in-the-Loop (PIL) testing on an Arduino Due microcontroller, showcasing real-world applicability. Comparative analysis with state-of-the-art MPPT controllers, including P&O-PI, InC-SMC, FLC, and VS P&O Backstepping, demonstrates superior tracking efficiency exceeding 99.49% under EN 50,530 standard test conditions. The system also maintains exceptional performance with minimal efficiency loss across a wide range of temperature and irradiance variations. By combining simplicity, robustness, and sustainability, this work establishes a cutting-edge solution for standalone PV systems, paving the way for more efficient and reliable renewable energy applications.