This article proposes a machine learning (ML)-based emulation of model predictive control (MPC) for modular multilevel converters (MMCs). In particular, the artificial neural network model, trained offline by the data collected from the traditional fast MPC method, is used to control the MMCs with high accuracy. With this offline training, the majority of computational burden is transferred from online to offline. Therefore, the proposed ML MPC can replace the role of the traditional MPC. The experimental results show that the proposed ML-based MPC has the same performance as the conventional MPC but a significantly computationally efficient structure. The finding from the letter provides ground for many other applications for ML-based emulation of complex controllers in power electronic systems.

This article presents the modeling and experimental validation of a recently presented DFIG wind power system driven by a two-level three-phase converter in which the grid-side converter is connected in series with the grid. The series-grid-side converter is able to compensate for stator-voltage sags, unbalance and harmonic distortion resulting in a high-power-quality system with considerable low-voltage-ride-through capability. The proposed control technique makes it feasible to obtain such high-power-quality system using a conventional two-level three-phase converter composed of 12 IGBTs, with no need of extra switches, while maintaining the usual high efficiency and low cost inherent to the DFIG configuration. Moreover, using the proposed linear model, one can design the dc-link-voltage controller's parameters according to the desired dynamic behavior. Experimental results are presented using a 15 kW test bench, which validate the proposed control technique.

The DFIG has been widely used in the wind power industry due to its technical advantages. However, current researches are being developed aiming at overcoming some of its drawbacks concerning reliability, efficiency and power quality. Since the wind farms are usually located at remote places, connected to weak grids, high reliability is required and some power quality issues deserve attention. This paper proposes a low-complexity, robust control of a DFIG driven by a direct matrix converter based on a model predictive rotor current control. The matrix converter is interesting due to the absence of the bulky and sensitive dc-link capacitors, leading to higher reliability. The predictive control is used to perform speed regulation. Moreover, this combination of converter and straightforward control is proven to be a robust technique that naturally compensates for stator current issues, which arises due to a low-power-quality grid voltage. Besides, a linear model of the proposed system is presented in order to be possible to use the linear-control-theory tools to execute the system control design. A processor-in-the-loop simulation is employed to validate the proposed control.

Large offshore wind power plants (OWPPs) installed far from the coastline are emerging to benefit from the strong and steady wind resources available at these locations. The high-voltage direct-current (HVDC) transmission system based on the modular multilevel converter (MMC) is the most appropriate solution to transmit the produced energy to the onshore grid, in a way that a complex power-electronic-based electrical system is formed at the OWPP. Undesired interactions can occur between the MMC-based HVDC station, the several wind-turbine (WT) converters, and the passive elements of the offshore grid. To guarantee a safe and reliable operation of the OWPP, a small-signal analysis must be performed in advance to predict possible unstable situations and their root causes, in a way as to take corrective measures to avoid them. In this paper, a state space model of an OWPP is developed in which a recently proposed model in multiple dq frames is adopted for the MMC. With the developed model, an eigenvalue-based stability assessment is carried out, where participation factors are calculated to identify the main contributors to the unstable modes that appear as a consequence of undesired low-frequency interactions at the offshore grid. As far as the authors know, an eigenvalue-based stability assessment of an OWPP with an MMC-HVDC connection is a topic rarely or never explored in the literature before and, thus, this is the main contribution of this paper. An adaptation to the MMC state space model is proposed so that the converter’s dynamics in grid-forming mode can be represented, and this is another contribution of this paper. Finally, various studies are presented to prove that the adopted approximated MMC model is accurate enough for small-signal stability analyses.

A modular multilevel converter’s (MMC’s) submodule (SM)-capacitor voltage will increase under unbalanced grid conditions. Depending on the imbalance level, the voltage ripple can be considerably high, and it can exceed the pre-defined safe limits. If this occurs, the converter will trip, which can lead to serious stability problems for the grid. This paper first proposes an analytical solution for deriving the three-phase imbalanced SM ripple of an MMC under an unbalanced grid. With this analytical tool, the imbalance mechanism of the SM voltage ripple can be easily understood. What is more, the symmetrical component method is first applied to analyze the three-phase SM capacitor ripple, and the positive-/negative-/zero-sequence components of the three-phase SM voltage ripple are easily identified by the proposed analytical method. Then, based on this powerful analytical tool, the proper circulating-current profile to be injected can be obtained, allowing for the right compensation of the voltage ripple. Based on this approach, two new voltage ripple compensation methods are proposed in this paper. Simulations were carried out to validate the analytical description of the submodule-capacitor voltage ripple proposed in this paper. Moreover, simulation and experimental results are provided to validate the new compensation techniques introduced in this paper.

This paper presents an analysis of a new application of different direct matrix converter topologies used as power interfaces in AC, DC, and hybrid microgrids, with model predictive current control. Such a combination of a converter and control strategy leads to a high power quality microgrid voltage, even with a low power quality main grid voltage and even during the connection and disconnection of a variety of loads and generation sources to the microgrids. These robust systems are suitable for applications in which sensitive loads are to be supplied and these loads are connected close to distributed-generation sources with inherent intermittent behavior. The authors also propose the use of new direct matrix converter configurations with a reduced number of switches in order to achieve reduced cost, reduced failure rate, and higher reliability, which are very desirable in microgrids. Finally, the authors also introduce new hybrid direct matrix converter topologies that provide interesting options for the islanded operation of the microgrids with the use of a battery system. In other words, the proposed hybrid direct matrix converters result in flexible hybrid microgrid configurations integrating DC and AC devices with high power quality and high power supply reliability.