In this paper, a neural network predictive controller (NNPC) is proposed to control a buck converter. Conventional controllers such as proportional-integral (PI) or proportional-integral-derivative (PID) are designed based on the linearized small-signal model near the operating point. Therefore, the performance of the controller in the start-up, load change, or reference change is not optimal since the system model changes by changing the operating point. The neural network predictive controller optimally controls the buck converter by following the concept of the traditional model predictive controller. The advantage of the NNPC is that the neural network system identification decreases the inaccuracy of the system model with inaccurate parameters. A NNPC with a well-trained neural network can perform as an optimal controller for the buck converter. To compare the effectiveness of the traditional buck converter and the NNPC, the simulation results are provided.

Meeting Name

2020 IEEE Texas Power and Energy Conference, TPEC (2020: Feb. 6-7, College Station, TX)


Electrical and Computer Engineering

Research Center/Lab(s)

Center for Research in Energy and Environment (CREE)

Keywords and Phrases

DC-DC Converters; Buck; Model Predictive Controller; Neural Network Predictive Controller

International Standard Book Number (ISBN)


Document Type

Article - Conference proceedings

Document Version

Accepted Manuscript

File Type





© 2020 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

07 Feb 2020