Neural Network Based Model Predictive Controllers for Modular Multilevel Converters

Wang, Songda; Dragicevic, Tomislav; Gao, Yuan; Teodorescu, Remus

Abstract

Modular multilevel converter (MMC) has attracted much attention for years due to its good performance in harmonics reduction and efficiency improvement. Model predictive control (MPC) based controllers are widely adopted for MMC because the control design is straightforward and different control objectives can be simply implemented in a cost function. However, the computational burden of MPC imposes limitations in the control implementation of MMC because of many possible switching states. To solve this, we design machine learning (ML) based controllers for MMC based on the data collection from the MPC algorithm. The ML models are trained to emulate the MPC controllers which can effectively reduce the computation burden of real-time control since the trained models are built with simple math functions that are not correlated with the complexity of the MPC algorithm. The ML method applied in this study is a neural network (NN) and there are two types of establishing ML controllers: NN regression and NN pattern recognition. Both are trained using the sampled data and tested in a real-time MMC system. A comparison of experimental results shows that NN regression has a much better control performance and lower computation burden than the NN pattern recognition.

Citation

Wang, S., Dragicevic, T., Gao, Y., & Teodorescu, R. (2021). Neural Network Based Model Predictive Controllers for Modular Multilevel Converters. IEEE Transactions on Energy Conversion, 36(2), 1562-1571. https://doi.org/10.1109/TEC.2020.3021022

• Journal Article Type: Article
• Acceptance Date: Aug 28, 2020
• Online Publication Date: Sep 1, 2020
• Publication Date: Jun 1, 2021
• Deposit Date: Sep 28, 2020
• Publicly Available Date: Sep 28, 2020
• Journal: IEEE Transactions on Energy Conversion
• Print ISSN: 0885-8969
• Electronic ISSN: 1558-0059
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 36
• Issue: 2
• Pages: 1562-1571
• DOI: https://doi.org/10.1109/TEC.2020.3021022
• Keywords: Electrical and Electronic Engineering; Energy Engineering and Power Technology
• Public URL: https://nottingham-repository.worktribe.com/output/4925038
• Publisher URL: https://ieeexplore.ieee.org/document/9183974
• Additional Information: “© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”; ; Wang, S., Dragicevic, T., Gao, Y., & Teodorescu, R. (2020). Neural Network based Model Predictive Controllers for Modular Multilevel Converters. IEEE Transactions on Energy Conversion, 1–1. https://doi.org/10.1109/tec.2020.3021022