Multistep direct model predictive control for power electronics — Part 2: Analysis

The performance of direct model predictive control (MPC) with reference tracking and long prediction horizons is evaluated, using the current control problem of a variable speed drive system with a voltage source inverter as an illustrative example. A modified sphere decoding algorithm allows one to efficiently solve the optimization problem underlying MPC also for long horizons. For a horizon of five and a three-level inverter, for example, the computational burden is reduced by four orders of magnitude, compared to the standard exhaustive search approach. This work illustrates the performance gains that are achievable by using prediction horizons larger than one. Specifically, for long prediction horizons and a low switching frequency, the total harmonic distortion of the current is significantly lower than for space vector modulation, making direct MPC with long horizons an attractive and computationally viable control scheme.