Auto-Tuned Model Predictive Control-Based Neural Network Controller for Modular Multilevel Converters
Bibliographic record
Abstract
This paper investigates the control of the Modular Multilevel Converter (MMC), a versatile converter topology. The MMC offers advantages such as modularity, scalability, and fault- tolerance capabilities. To address the challenges of controlling the MMC, various methods including Model Predictive Control (MPC) have been proposed. This paper focuses on online weighting factor selection for MPC in Direct MPC and Indirect MPC and emulating these control techniques with neural network controllers. Dynamic equations of the MMC considering a novel method for including the discrete-time common model voltage are derived, and direct MPC (DMPC) and indirect MPC (IMPC) with online weighting factor selection are implemented. Auto-tuned DMPC and IMPC are used to extract data for training neural networks, which emulate the auto-tuned MPC controllers.The optimal neural network structure is selected and trained. Comparisons of steady-state and transient performance among auto-tuned DMPC, IMPC, and neural network-based controllers reveal that neural network-based controllers perform similarly to conventional auto-tuned MPC controllers, but with reduced computational burden. These controllers exhibit improved robustness to parameter mismatches and unpredictable converter performance, indicating their potential as viable replacements for conventional auto-tuned MPC controllers in MMC control, offering enhanced efficiency and reduced calculation burden.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".