Real-time virtual circuits for plasma shape control via neural network emulators
Abstract
Reliable position and shape control in tokamak plasmas requires accurate real-time regulation of several strongly coupled shape parameters. The control vectors that disentangle these couplings, referred to as \textit{virtual circuits} (VCs), enable independent shape parameter control for a specific Grad--Shafranov (GS) equilibrium. Numerical calculation of VCs is not currently feasible in real time, therefore VCs are usually computed prior to each experiment, using a small number of reference GS equilibria sampled along the desired scenario trajectory, with each VC used to control the plasma within a preset time interval. While effective near the reference equilibrium, this approach can lead to degraded performance as the plasma departs from the reference equilibrium and/or from the desired trajectory, and it complicates the design of robust control strategies for rapidly evolving plasma configurations. In this paper, we construct neural-network-based emulators of plasma shape parameters from which VCs can be derived, to provide the MAST Upgrade (MAST-U) plasma control system with state-aware VCs in real-time. To do this, we develop an extensive library of over a million simulated GS equilibria, covering a substantial portion of the MAST-U operational space. These emulators provide differentiable functions whose gradients can be rapidly computed, enabling the derivation of accurate VCs for real-time shape control. We perform extensive verification of the emulated VCs by testing whether they disentangle the control problem. The neural-network-based approach delivers high accuracy and orthogonality across a diverse range of equilibria. This work establishes the physical validity of emulated VCs as a scalable and general alternative to schedules of precomputed VCs.
Related
- Real-time virtual circuits for plasma shape control via neural network emulators: experimental demonstration on MAST Upgrade
- Measure Now, Mitigate Later: Virtual Error Cancellation for Logical Quantum Circuits
- Virtual photon bremsstrahlung in a magnetized quark-gluon-plasma
- BAHAMAS: A Control Plane for Optimization and Execution of Variational Quantum Circuits
- Sampling isometric tensor network states with monitored quantum circuits
BibTeX
@misc{ross2026realtime,
title = {{Real-time virtual circuits for plasma shape control via neural network emulators}},
author = {Alasdair Ross and George K. Holt and Kamran Pentland and Adriano Agnello and Nicola C. Amorisco and Pedro Cavestany and Aran Garrod and Timothy Nunn and Charles Vincent and Graham McArdle},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2605.14939},
eprint = {2605.14939},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.14939},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Real-time virtual circuits for plasma shape control via neural network emulators
AU - Alasdair Ross
AU - George K. Holt
AU - Kamran Pentland
AU - Adriano Agnello
AU - Nicola C. Amorisco
AU - Pedro Cavestany
AU - Aran Garrod
AU - Timothy Nunn
AU - Charles Vincent
AU - Graham McArdle
PY - 2026
DA - 2026/11/02
PB - arXiv
DO - 10.48550/arxiv.2605.14939
UR - https://arxiv.org/abs/2605.14939
AB - Reliable position and shape control in tokamak plasmas requires accurate real-time regulation of several strongly coupled shape parameters. The control vectors that disentangle these couplings, referred to as \textit{virtual circuits} (VCs), enable independent shape parameter control for a specific Grad--Shafranov (GS) equilibrium. Numerical calculation of VCs is not currently feasible in real time, therefore VCs are usually computed prior to each experiment, using a small number of reference GS equilibria sampled along the desired scenario trajectory, with each VC used to control the plasma within a preset time interval. While effective near the reference equilibrium, this approach can lead to degraded performance as the plasma departs from the reference equilibrium and/or from the desired trajectory, and it complicates the design of robust control strategies for rapidly evolving plasma configurations. In this paper, we construct neural-network-based emulators of plasma shape parameters from which VCs can be derived, to provide the MAST Upgrade (MAST-U) plasma control system with state-aware VCs in real-time. To do this, we develop an extensive library of over a million simulated GS equilibria, covering a substantial portion of the MAST-U operational space. These emulators provide differentiable functions whose gradients can be rapidly computed, enabling the derivation of accurate VCs for real-time shape control. We perform extensive verification of the emulated VCs by testing whether they disentangle the control problem. The neural-network-based approach delivers high accuracy and orthogonality across a diverse range of equilibria. This work establishes the physical validity of emulated VCs as a scalable and general alternative to schedules of precomputed VCs.
ER -