Machine Learning Based Adaptive Prediction Horizon in Finite Control Set Model Predictive Control

In this paper, an adaptive prediction horizon approach based on machine learning is presented for the finite control set model predictive control (FCS-MPC) of power converters. Usually, in FCS-MPC, the prediction horizon is kept constant. A large prediction horizon improves performance, however, it significantly increases the computational cost. The prediction horizon is typically chosen to be just large enough to give the required performance. We present a novel technique, where the prediction horizon adapts to the states of the converter. We define a cyber-physical objective function that penalizes both the error in converter performance and computational complexity. We perform several offline simulations to find the optimal prediction horizon based on the instantaneous state of the converter, based on a cyber-physical objective function. An artificial neural network is trained to calculate the optimal prediction horizon in run time. The proposed scheme allows a varying prediction horizon that reduces the overall computational complexity, while guaranteeing the required physical performance. The simulations and experimental results of the proposed technique justify the usefulness of our approach.

[1]  Paolo Tenti,et al.  General-purpose fuzzy controller for DC-DC converters , 1997 .

[2]  Andreas Kugi,et al.  Nonlinear H∞ controller design for a DC-to-DC power converter , 1999, IEEE Trans. Control. Syst. Technol..

[3]  Manfred Morari,et al.  Hybrid Model Predictive Control of the Step-Down DC–DC Converter , 2008, IEEE Transactions on Control Systems Technology.

[4]  A. Massarini,et al.  Feedforward control of DC-DC PWM boost converter , 1997 .

[5]  U. Ammann,et al.  Model Predictive Control—A Simple and Powerful Method to Control Power Converters , 2009, IEEE Transactions on Industrial Electronics.

[6]  Justin M. Bradley,et al.  Toward Continuous State–Space Regulation of Coupled Cyber–Physical Systems , 2012, Proceedings of the IEEE.

[7]  Paolo Mattavelli,et al.  Small-signal analysis of DC-DC converters with sliding mode control , 1995, Proceedings of 1995 IEEE Applied Power Electronics Conference and Exposition - APEC'95.

[8]  Tobias Geyer,et al.  Direct Model Predictive Control: A Review of Strategies That Achieve Long Prediction Intervals for Power Electronics , 2014, IEEE Industrial Electronics Magazine.

[9]  Tobias Geyer,et al.  Direct Voltage Control of DC–DC Boost Converters Using Enumeration-Based Model Predictive Control , 2014, IEEE Transactions on Power Electronics.

[10]  John Y. Hung,et al.  Implementation of a fuzzy controller for DC-DC converters using an inexpensive 8-b microcontroller , 1997, IEEE Trans. Ind. Electron..

[11]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[12]  Marian K. Kazimierczuk,et al.  Dynamic performance of PWM DC-DC boost converter with input voltage feedforward control , 1999 .

[13]  James B. Rawlings,et al.  Postface to “ Model Predictive Control : Theory and Design ” , 2012 .

[14]  Gabor Karsai,et al.  Toward a Science of Cyber–Physical System Integration , 2012, Proceedings of the IEEE.

[15]  S. Hiti,et al.  Robust nonlinear control for boost converter , 1993 .

[16]  Tobias Geyer,et al.  On the benefit of long-horizon direct model predictive control for drives with LC filters , 2014, 2014 IEEE Energy Conversion Congress and Exposition (ECCE).

[17]  C. K. Michael Tse,et al.  General Design Issues of Sliding-Mode Controllers in DC–DC Converters , 2008, IEEE Transactions on Industrial Electronics.

[18]  Justin M. Bradley,et al.  Coupled Cyber–Physical System Modeling and Coregulation of a CubeSat , 2015, IEEE Transactions on Robotics.

[19]  M. Morari,et al.  Move blocking strategies in receding horizon control , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[20]  Gabriele Pannocchia,et al.  Disturbance models for offset‐free model‐predictive control , 2003 .

[21]  J. Álvarez-Ramírez,et al.  A stable design of PI control for DC-DC converters with an RHS zero , 2001 .