TY - JOUR
T1 - Machine Learning Emulation of Model Predictive Control for Modular Multilevel Converters
AU - Wang, Songda
AU - Dragicevic, Tomislav
AU - Gontijo, Gustavo Figueiredo
AU - Chaudhary, Sanjay K.
AU - Teodorescu, Remus
N1 - Publisher Copyright:
IEEE
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2021/11
Y1 - 2021/11
N2 - This paper 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 the 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 lower computational burden. This finding provides ground for many other applications for ML based emulation of complex controllers in power electronic systems.
AB - This paper 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 the 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 lower computational burden. This finding provides ground for many other applications for ML based emulation of complex controllers in power electronic systems.
KW - computational burden
KW - machine learning
KW - model predictive control
KW - Modular multilevel converter
UR - http://www.scopus.com/inward/record.url?scp=85096864797&partnerID=8YFLogxK
U2 - 10.1109/TIE.2020.3038064
DO - 10.1109/TIE.2020.3038064
M3 - Journal article
AN - SCOPUS:85096864797
SN - 0278-0046
VL - 68
SP - 11628
EP - 11634
JO - IEEE Transactions on Industrial Electronics
JF - IEEE Transactions on Industrial Electronics
IS - 11
ER -