This paper proposes a machine learning-based controller for the DC/AC inverter, integrating a linear quadratic regulator (LQR) with recurrent equilibrium networks (RENs). Traditional LQR controller suffers from model dependency and the difficulty in determining the cost function weight matrix. To address these issues, the proposed controller introduces an auxiliary control variable via feedback REN, ensuring superior transient and steady-state performance under varying operating conditions, including step changes in output current references, filter parameter uncertainties, and different load scenarios. The proposed approach is characterized by high computational efficiency during both training and implementation, with verified closed-loop system stability. The effectiveness of the proposed approach is validated through experimental comparisons with existing control methods.

Space-vector modulation (SVM) is widely used in multilevel inverters because of its ability to improve DC bus utilization, reduce harmonic distortion, and enhance operational flexibility. However, the increasing complexity of multilevel inverter topologies, such as neutral-point clamped, cascaded H-bridge, and modular multilevel converters, presents challenges in terms of computational efficiency, neutral-point voltage balancing, and common-mode voltage suppression. A detailed review of SVM techniques is provided, including traditional methods and advanced variants such as carrier-based SVM, selective harmonic elimination SVM, and virtual SVM. Additionally, recent hybrid approaches that combine multiple strategies to address specific performance requirements are discussed. The findings highlight advancements in improving the modulation performance, reducing switching losses, and achieving better harmonic attenuation. A discussion of the future challenges and opportunities for multilevel inverter modulation strategies is concluded.