Data-driven control systems based on Deep Reinforcement Learning (DRL) agents are emerging as a promising alternative to traditional control approaches in power converter applications because of the enhanced robustness under uncertainties, external disturbances, and system nonlinearities. However, the hyperparameters of required neural networks– such as the number of layers, neurons, and activation functions– are still selected through empirical tuning, resulting in suboptimal performance and limited generalization. This work presents a data-driven control system for current tracking problem in three-phase voltage source inverter (VSI) using a simple perceptron as actor policy within a Reinforcement Learning framework. The control policy is trained using Soft Actor Critic (SAC) algorithm in order to generate continuous duty cycle using a simple state vector. Two neural network (NN) architectures are evaluated: a simple perceptron, and a simple perceptron with extended state inputs, including real-time current measurements. In addition, the performance of the data-driven control system is analyzed in terms of root mean square error (RMSE) and total harmonic distortion (THD). Results disclose that a simple perceptron is enough to control the VSI for the specific current tracking problem. Under this configuration, the proposed controller achieves a maximum RMSE of 1.20 A and a THD of 6.28% at a 5 kHz sampling frequency. The results validate the applicability of compact, data-driven control architectures for power electronic converters, offering a balance between computational efficiency and control performance.

In photovoltaic (PV) systems, the adoption of the single-stage microinverters present an attractive proposition. Unlike their two-stage counterparts, which consist of separate dc-dc and dc-ac conversion stages, single-stage microinverters simplify the conversion process by integrating both functions into a single unit. This combination offers advantages in terms of size, efficiency and overall system performance. In this context, the boost inverter with bypass mode connection emerges as an attractive alternative; however control challenges arise, particularly in the non-linearities inherent in these systems. The linearization process of the converter for conventional control strategies becomes complicated, promoting the exploration of alternative control approaches. This paper proposes a predictive control scheme for a Bypass Boost Inverter (BBI), addressing the aforementioned challenges. The control strategy employs a cascaded design, where the inner loop uses Finite Control Set-Model Predictive Control (FCS-MPC) to regulate inductor currents, indirectly controlling the output current for grid connection. The proposed control scheme is validated through simulations in PLECs software, demonstrating its performance in managing a PV panel. The results show good tracking of inductor current references and compliance with the standards for grid connection.

This paper presents a simulation of a Maximum Power Point Tracking method applied to a point absorber Wave Energy Converter using a linear generator with three independent coils. Each of the three coils of the linear generator is individually connected to a submodule of the DC Modular Multilevel Converter. These submodules feature two stages with a capacitor DC-link between them. The first stage measures the current and voltage from each submodule. It applies the proposed MPPT method to calculate the reference current, which is then controlled with a PI controller to maximize the energy harvested. The second stage measures the output current and the voltage of each capacitor, applying a cascade control involving two loops. An outer loop controls the capacitor voltage using a reference current, while an inner loop employs a PI controller to regulate the output current. This MMC-DC topology is implemented in a simulation to maximize energy transfer.

Power quality of electric networks with high penetration of photovoltaic systems has been analyzed in different publications. It has been noted that inverters may increase their harmonic emissions when connected to weak networks, this harmonics may affect other equipments connected to the network and decreasing their performance. This document shows the effects of connecting multiple photovoltaic generators in a network through simulations using MATLAB-Simulink SimPowerSystems.