In this article a finite control set model predictive control, is used to track a current reference in a power converter connected to an $RL$ load. An artificial intelligence approach is presented for real-time determination of the weighting factor that regulates the average switching frequency, independently of the operating point. The article focuses on the design, training, and digital implementation of an artificial neural network (ANN) that can be developed in a low-cost control platform. It is presented a sampling and offline ANN training procedure, together with a low-cost hardware implementation based on integer quantization of the ANN. The abovementioned approach provides a standalone application, serving as a framework for the development of ANN applications for power-converters. The main advantage of the presented approach is that the ANN inference is executed in real time. In this way, the weighting factor is automatically updated in real-time, allowing the system to quickly adapt to any reference step changes, and consequently provide the desired behavior. Executing the setup in laboratory prototype confirmed the theoretical analysis and successful tracking of the reference frequency.

A finite control set model predictive control (FCS-MPC) strategy consists of a prediction model, a cost function and an optimization algorithm. Consequently, the performance of the FCS-MPC depends on the proper design of these three elements. This article assesses the influence of the prediction model of an uninterruptible power supply (UPS). Since the load connected to the voltage source inverter (VSI) affects the dynamic of the system state variables, the load dynamic should be included in the system model. This makes the design of the prediction model a challenge because the load connected to the VSI is generally unknown. To deal with this uncertainty, this work proposes an augmented prediction model based on a state observer that includes as many harmonic components as necessary to accurately represent the output current. The performance of the FCS-MPC for a UPS is evaluated in a laboratory prototype using the proposed and the conventional prediction models. Experimental results show that the proposed solution provides a more accurate representation of the output current, improving the system performance.

Finite control set model predictive control (FCS-MPC) is a salient control method for power conversion systems that has recently enjoyed remarkable popularity. Several studies highlight the performance benefits that long prediction horizons achieve in terms of closed-loop stability, harmonic distortions, and switching losses. However, the practical implementation is not straightforward due to its inherently high computational burden. To overcome this obstacle, the control problem can be formulated as an integer least-squares optimization problem, which is equivalent to the closest point search or closest vector problem in lattices. Different techniques have been proposed in the literature to solve it, with the sphere decoding algorithm (SDA) standing out as the most popular choice to address the long prediction horizon FCS-MPC. However, the state-of-the-art in this field offers solutions beyond the conventional SDA that will be described in this article alongside future trends and challenges in the topic.

Successful application of finite control set model predictive control strategies with long prediction horizon depends on the careful design of the optimization algorithm. The conventional method involves transforming the problem to an equivalent box-constrained integer least-squares formulation that can be solved with branch-and-bound techniques, such as the sphere decoding algorithm (SDA). In this work, it is proposed to define an artificial neural network (ANN) to replace the SDA, avoiding its inherent computational variability. Similarly to practical applications of the SDA, the ANN finds an approximate solution of the underlying optimization problem. In contrast, the main benefit of the proposed approach is that it can be implemented in a low-cost microprocessing platform, greatly improving the performance in terms of resources in comparison with other advanced techniques proposed in the literature.

Finite control set model predictive control (FCS-MPC) strategies for power conversion devices benefit from extending the prediction horizon length. Solving this problem relies on the definition of the underlying integer least-squares problem. Sphere decoding algorithm (SDA) has been extensively used in previous works as an approach to solve this problem. In this article, a parallel and fully scalable K-best SDA hardware design is proposed as an alternative. The K-best SDA establishes a different breadth-first search strategy, which addresses some of the main drawbacks of the SDA. Through experimental tests based on an uninterruptible power supply, the K-best SDA performance for long prediction horizon FCS-MPC is assessed and verified. Results demonstrate key beneficial aspects through which the K-best SDA is capable of rendering an improved control performance when compared to the conventional SDA.

Long prediction horizon finite control set model predictive control (LPH-FCS-MPC) for power converters can be reformulated as a box-constrained integer-least squares (ILS) problem to find the optimal control action without requiring an exhaustive search. Instead, the solution can be found by means of a sphere decoding method that still presents several intricacies regarding its complexity and its variable computational cost. This article provides a study of the computational behavior of this approach. Special emphasis is placed on how the generator matrix is calculated, either as a lower or an upper triangular structure. This choice decides whether the switching sequences are explored forward- or backward-in-time during the optimization process. In this work, it is explained how this selection holds a great impact on the computational burden of the algorithm. Similarly, it is also analyzed how the tuning of the FCS-MPC and system parameters also drastically impacts the computational cost.