Model-Free Neural Network-Based Predictive Control for Robust Operation of Power Converters
An accurate definition of a system model significantly affects the performance of model-based control strategies, for example, model predictive control (MPC). In this paper, a model-free predictive control strategy is presented to mitigate all ramifications of the model’s uncertainties and parameter...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/14/8/2325 |
_version_ | 1797537075866632192 |
---|---|
author | Sanaz Sabzevari Rasool Heydari Maryam Mohiti Mehdi Savaghebi Jose Rodriguez |
author_facet | Sanaz Sabzevari Rasool Heydari Maryam Mohiti Mehdi Savaghebi Jose Rodriguez |
author_sort | Sanaz Sabzevari |
collection | DOAJ |
description | An accurate definition of a system model significantly affects the performance of model-based control strategies, for example, model predictive control (MPC). In this paper, a model-free predictive control strategy is presented to mitigate all ramifications of the model’s uncertainties and parameter mismatch between the plant and controller for the control of power electronic converters in applications such as microgrids. A specific recurrent neural network structure called state-space neural network (ssNN) is proposed as a model-free current predictive control for a three-phase power converter. In this approach, NN weights are updated through particle swarm optimization (PSO) for faster convergence. After the training process, the proposed ssNN-PSO combined with the predictive controller using a performance criterion overcomes parameter variations in the physical system. A comparison has been carried out between the conventional MPC and the proposed model-free predictive control in different scenarios. The simulation results of the proposed control scheme exhibit more robustness compared to the conventional finite-control-set MPC. |
first_indexed | 2024-03-10T12:09:57Z |
format | Article |
id | doaj.art-c7249e179eeb40b2a658a30e3ef2976d |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-10T12:09:57Z |
publishDate | 2021-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-c7249e179eeb40b2a658a30e3ef2976d2023-11-21T16:20:05ZengMDPI AGEnergies1996-10732021-04-01148232510.3390/en14082325Model-Free Neural Network-Based Predictive Control for Robust Operation of Power ConvertersSanaz Sabzevari0Rasool Heydari1Maryam Mohiti2Mehdi Savaghebi3Jose Rodriguez4Department of Electrical and Computer Engineering, Semnan University, Semnan 35131-19111, IranEnergy Technology Department, Aalborg University of Denmark, 9220 Aalborg, DenmarkDepartment of Electrical Engineering, University of Yazd, Yazd 89158-18411, IranDepartment of Mechanical and Electrical Engineering, University of Southern Denmark, 5230 Odense, DenmarkDepartment of Engineering Science, Universidad Andres Bello, 7500971 Santiago, ChileAn accurate definition of a system model significantly affects the performance of model-based control strategies, for example, model predictive control (MPC). In this paper, a model-free predictive control strategy is presented to mitigate all ramifications of the model’s uncertainties and parameter mismatch between the plant and controller for the control of power electronic converters in applications such as microgrids. A specific recurrent neural network structure called state-space neural network (ssNN) is proposed as a model-free current predictive control for a three-phase power converter. In this approach, NN weights are updated through particle swarm optimization (PSO) for faster convergence. After the training process, the proposed ssNN-PSO combined with the predictive controller using a performance criterion overcomes parameter variations in the physical system. A comparison has been carried out between the conventional MPC and the proposed model-free predictive control in different scenarios. The simulation results of the proposed control scheme exhibit more robustness compared to the conventional finite-control-set MPC.https://www.mdpi.com/1996-1073/14/8/2325model-free predictive controlmodel predictive control (MPC)power converterstate-space neural network with particle swarm optimization (ssNN-PSO)identificationrobust performance |
spellingShingle | Sanaz Sabzevari Rasool Heydari Maryam Mohiti Mehdi Savaghebi Jose Rodriguez Model-Free Neural Network-Based Predictive Control for Robust Operation of Power Converters Energies model-free predictive control model predictive control (MPC) power converter state-space neural network with particle swarm optimization (ssNN-PSO) identification robust performance |
title | Model-Free Neural Network-Based Predictive Control for Robust Operation of Power Converters |
title_full | Model-Free Neural Network-Based Predictive Control for Robust Operation of Power Converters |
title_fullStr | Model-Free Neural Network-Based Predictive Control for Robust Operation of Power Converters |
title_full_unstemmed | Model-Free Neural Network-Based Predictive Control for Robust Operation of Power Converters |
title_short | Model-Free Neural Network-Based Predictive Control for Robust Operation of Power Converters |
title_sort | model free neural network based predictive control for robust operation of power converters |
topic | model-free predictive control model predictive control (MPC) power converter state-space neural network with particle swarm optimization (ssNN-PSO) identification robust performance |
url | https://www.mdpi.com/1996-1073/14/8/2325 |
work_keys_str_mv | AT sanazsabzevari modelfreeneuralnetworkbasedpredictivecontrolforrobustoperationofpowerconverters AT rasoolheydari modelfreeneuralnetworkbasedpredictivecontrolforrobustoperationofpowerconverters AT maryammohiti modelfreeneuralnetworkbasedpredictivecontrolforrobustoperationofpowerconverters AT mehdisavaghebi modelfreeneuralnetworkbasedpredictivecontrolforrobustoperationofpowerconverters AT joserodriguez modelfreeneuralnetworkbasedpredictivecontrolforrobustoperationofpowerconverters |