The integration of photovoltaic (PV) power generation systems has significantly increased the complexity of voltage distribution in power grids, making it challenging for conventional Load Ratio Control Transformers (LRTs) to manage voltage fluctuations caused by weather-dependent PV output variations. Power Conditioning Systems (PCSs) interconnected with PV installations are increasingly considered for voltage control to address these challenges. This study proposes a Machine Learning (ML)-based control method for sub-transmission grids, integrating long-term LRT tap-changing with short-term reactive power control of PCSs. The approach estimates the voltage at each grid node using a Deep Neural Network (DNN) that processes measurable substation data. Based on these estimated voltages, the method determines optimal LRT tap positions and PCS reactive power outputs using Deep Reinforcement Learning (DRL). This enables real-time voltage monitoring and control using only substation measurements, even in grids without extensive sensor installations, ensuring all node voltages remain within specified limits. To improve the model’s transparency, Shapley Additive Explanation (SHAP), an Explainable AI (XAI) technique, is applied to the DRL model. SHAP enhances interpretability and confirms the effectiveness of the proposed method. Numerical simulations further validate its performance, demonstrating its potential for effective voltage management in modern power grids.

In pursuit of enhancing the performance of power converters, high-frequency power devices have become indispensable due to their superior switching capabilities, reduced conduction loss, and enhanced thermal performance. However, optimizing their efficiency requires a profound comprehension of the interplay between various parameters (the current, voltage, and gate resistance) on switching dynamics and power losses. This study presents a comprehensive framework of loss characterization with multi-parametric variations. The influence of drain-source current $\left(I_{ds}\right)$, DC voltage $\left(V_{dc}\right)$, and gate resistor $\left(R_g\right)$ on switching and conduction losses are explicitly quantified. A significant contribution of this study lies in the comprehensive analytical and empirical characterization of the turn-on and turn-off power dissipation dynamics in SiC MOSFETs, emphasizing the intricate interplay between parameters and efficiency. Conventional studies primarily focus on empirical loss characterization, yet this work advances the field by introducing a predictive loss model that systematically correlates $R_g$, $I_{ds}$, and $V_{dc}$ variations with induced switching dynamics, and EMI mitigation strategies. Increasing $R_g$ effectively suppresses voltage overshoots and mitigates ringing effects, concurrently prolonging switching events, thereby broadening the power dissipation profile and influencing system-level performance. Furthermore, this study rigorously evaluates the commutation behavior of the SiC MOSFET/SBD pair, providing an in-depth examination of its dynamic loss characterization under varying conditions. This novel insight establishes a crucial framework for efficiency drive optimization.

The rapid integration of renewable energy sources, such as photovoltaic power systems, has reduced the necessary for synchronous generators, which traditionally contributed to grid stability during disturbances. This shift has led to a decrease in reactive power reserves (RPRs), raising concerns about voltage stability. Real-time monitoring of voltage stability is crucial for transmission system operators to implement timely corrective actions. However, conventional methods, such as continuation power flow calculations, are computationally intensive and unsuitable for large-scale power systems. Machine learning techniques using data from phasor measurement units have been proposed to estimate voltage stability. However, these methods do not consider changes in generator operating conditions and fluctuating RPRs. As renewable energy generation increases, the operating conditions of generators vary, which leads to significant changes in system RPRs and voltage stability. In this paper, a voltage stability margin is proposed using regression trees with RPRs varying based on generator operation conditions. Simulations based on the IEEE 9-bus system demonstrate that the proposed approach provides an accurate and efficient voltage stability estimation.

Power semiconductor devices are fundamental components in modern electronic power conversion. In applications demanding high power density and efficiency, the choice between silicon (Si) IGBTs and Silicon Carbide (SiC) MOSFETs is critical. SiC MOSFETs, owing to their high critical electric field, superior thermal conductivity, wide band gap, and low power loss, realize significant performance improvements and compact design. This work presents a comprehensive, simulation-driven comparative investigation under identical setups, evaluating both technologies across various parameters. The effects of temperature variations on gate-source threshold voltage drift, current slew rate, device stress, and energy dissipation during switching transitions are evaluated. Furthermore, the characteristic switching behavior when the DC-bus voltage, gate resistance, and load current are varied is investigated. This study addresses a current scarcity of systematic investigation by presenting a comprehensive comparative evaluation of switching losses and efficiency across varied operating conditions, providing validated conclusions for the design of advanced WBG converters. The results demonstrate that SiC exhibits lower losses and faster switching speeds than Si IGBTs, with minimal temperature-dependent loss variations, unlike Si devices, whose losses rise significantly with temperature. Si shows distinct tail currents during turn-off, absent in SiC devices. A conclusive comparative evaluation of switching energy losses under varied operating conditions demonstrates that SiC devices can effectively retrofit Si counterparts for fast, low-loss, high-efficiency applications.