The integration of wind energy systems into the electric grid has become inevitable despite the many problems associated with this integration. Most of these problems are due to variations in wind speed. The problems are for example oscillations in the power generated, which implies the lack of guarantee of obtaining the maximum energy and the ripple in the electromechanical torque of the generator. This work aims at mitigating these problems for wind energy conversion system-driven doubly-fed induction generator (DFIG), which is the dominant generator used in wind energy applications. This mitigation is performed through direct reactive and active powers control of the DFIG using an artificial neural network. A DSP (Digital Signal Processor - dSPACE DS1104) was used to experimentally test the proposed strategy. The dynamic performances of the controlled generator are analyzed by using the designed intelligent strategy in the case of variable wind speeds and upon sudden change of the active power demand. Based on the obtained experimental results, it can be said that the designed intelligent strategy is more effective and robust than the classical techniques such as direct power control (DPC) and vector control in terms of reducing current harmonics, and torque fluctuations, and enhancing dynamic response.

Since modern power systems are susceptible to undesirable frequency oscillations caused by uncertainties in renewable energy sources (RESs) and loads, load frequency control (LFC) has a crucial role to get these systems’ frequency stability back. However, existing LFC techniques may not be sufficient to confront the key challenge arising from the low-inertia issue, which is due to the integration of high-penetration RESs. Therefore, to address this issue, this study proposes an optimized intelligent fractional-order integral (iFOI) controller for the LFC of a two-area interconnected modern power system with the implementation of virtual inertia control (VIC). Here, the proposed iFOI controller is optimally designed using an efficient metaheuristic optimization technique, called the gray wolf optimization (GWO) algorithm, which provides minimum values for system frequency deviations and tie-line power deviation. Moreover, the effectiveness of the proposed optimal iFOI controller is confirmed by contrasting its performance with other control techniques utilized in the literature, such as the integral controller and FOI controller, which are also designed in this study, under load/RES fluctuations. Compared to these control techniques from the literature for several scenarios, the simulation results produced by the MATLAB software have demonstrated the efficacy and resilience of the proposed optimal iFOI controller based on the GWO. Additionally, the effectiveness of the proposed controller design in regulating the frequency of interconnected modern power systems with the application of VIC is confirmed.

The world is shifting towards renewable energy sources due to the harmful effects of fossils fuel-based power generation in the form of global warming and climate change. When it comes to renewable energy sources, solar-based power generation remains on top of the list as a clean and carbon cutting alternative to the fossil fuels. Naturally, the sites chosen for installing solar parks to generate electricity are the ones that get maximum solar radiance throughout the year. Consequently, such sites offer challenges for the solar panels such as increased temperature, humidity and high dust levels that negatively affect their power generation capability. In this work, we are more concerned with the detection of dust from the images of the solar panels so that the cleaning process can be done in time to avoid power loses due to dust accumulation on the surface of solar panels. To this end, we utilize state-of-art deep learning-based image classification models and evaluate them on a publicly available dataset to identify the one that gives maximum classification accuracy for dusty solar panel detection. We utilize pre-trained models of 20 deep learning models to encode the images that are then used to train and validate four variants of a support vector machine. Among the 20 models, we get the maximum classification of 86.79% when the images are encoded with the pre-trained model of DenseNet169 and then use these encodings with a linear SVM for image classification.

Recently, hybrid wind/PV microgrids have gained great attention all over the world. It has the merits of being environmentally friendly, reliable, sustainable, and efficient compared to its counterparts. Though there has been great development in this issue, the control and energy management of these systems still face challenges. The source of those challenges is the intermittent nature of both wind and PV energy. On the other hand, a new intelligent control technique called Brain Emotional Learning-Based Intelligent Controller (BELBIC) has garnered more interest. This paper proposes the control and energy management of hybrid wind/PV microgrids using a BELBIC controller. To design the system, simple power and energy analyses were proposed. The proposed microgrid was modeled and simulated using MATLAB. The responses of the energy system were tested under two different types of disturbances, namely step and ramp disturbances. These disturbances are applied to the wind speed, the irradiation level of the PV, and the load power. The results indicate that the AC load voltage and frequency are steady with negligible transients against the previous disturbance. In addition, the performance is better than that of the classical PI controller. Also, energy management acts perfectly to compensate for the intermittence and disturbances of the wind and PV energies. On the other hand, the system robustness against model parameters uncertainties in the microgrid parameters are studied.

This paper proposes an end-to-end ( $E2E$ ) learning-based control policy to directly control a transformerless grid-tied three-level neutral-point-clamped ( 3L-NPC ) inverter powered by a photovoltaic ( PV ) array. This $E2E$ control policy is represented by an artificial neural network ( ANN ) and a time-delay neural network ( TDNN ), namely, ANN - and TDNN -based control policies, to properly estimate the optimal switching vector of the 3L-NPC . With such learning-based control policy, there exists no need for deriving or understanding deeply the complex mathematical model of the 3L-NPC , as the dynamics of both the system and the control scheme, as well as the cost function to be minimized, are learned via an end-to-end learning fashion that maps directly from the raw observations to the optimal switching states. This definitely eliminates the major barriers of the model-based control strategies (i.e., model predictive control ( MPC )) such as (i) the need for an accurate system model, and (ii) the exponential increase in computational complexity. In order to train the two control policies, the conventional MPC is employed, as an expert, for acquiring a set of training data (i.e., input-output pairs) and, thereafter, for assessing our proposed control schemes. The proposed E2E control strategies are validated using MATLAB/Simulink software, where the impact of having different input features and training data are studied. With the proposed control policies, especially the TDNN -based control policy that has only one time-delay window, a high-quality sinusoidal grid current is achieved with low total harmonic distortion ( THD ), resulting in enhancing the power quality of the utility grid. In addition, the leakage current is minimized compared to the conventional MPC by more than 25%. However, the same dynamic behavior is almost obtained during the irradiation changes compared to the MPC strategy. Moreover, the experimental verification of the proposed E2E control strategy is implemented on the basis of the Hardware-in-the-Loop (HIL) simulator using the C2000TM-microcontroller-LaunchPadXL TMS320F28379D kit, demonstrating the applicability and good performance of our proposed control strategy under realistic conditions.

Wind Turbine Generator (WTG) has become one of the most popular renewable-based power generation that is broadly connected to electricity grids worldwide. Till the year 2019, the total WTGs installed worldwide reached about 650.8GW. The WTG is interfaced to the electricity grid through power electronic converters with a proper control algorithm to facilitate a smooth power delivery as well as maintaining the system voltage and frequency stability during wind intermittency. However, power grids are usually subjected to load expansion which affects the stiffness of the grid and hence its stability. A weak electricity grid exhibits voltage instability that may affect the performance of WTGs and in some cases may lead to serious damages to the wind turbines and the entire system. In this paper, superconducting magnetic energy storage (SMES) technology based on fuzzy logic controller is implemented to effectively resolve this issue and improve the overall performance of WTGs. Hysteresis current and fuzzy logic-based control system is proposed to control the energy exchange between the SMES coil and the investigated system. Results show the effectiveness of the SMES to improve the overall system performance and along with the fault ride-through capability of the doubly-fed induction generator (DFIG).