Minimum-Energy Control for Stochastic Linear Systems: A Data-Driven Approach with Finite-Sample Guarantees
Abstract
The open-loop minimum-energy control (MEC) problem asks for control inputs that minimize the control energy while ensuring the terminal state reaches a desired value. In this paper, we study the open-loop MEC problem for stochastic linear time-invariant systems. We consider a variety of stochastic constraints that enforce the terminal error to be small, and show that Stochastic MEC (SMEC) problem can be formulated as a QCQP. We obtain the optimal solution for SMEC and show that it generalizes the well-known Deterministic MEC problem by introducing novel stochastic variants of controllability and Gramian matrices. When the system dynamics is unknown, we obtain a direct data-driven solution to the SMEC problem using maximum-likelihood estimation and conformal calibration approaches. Finally, we quantify the sub-optimality and constraint violation of our data-driven solutions via finite-sample high-probability upper bounds, and highlight their dependence on the number of experiments, system dimension, and noise-to-signal ratio. We present numerical simulations to validate the theoretical results.
Related
- Minimum-Energy Control for Stochastic Linear Systems
- Robust stochastic optimal control via variance penalization: application to energy management systems
- Improved Approximation Guarantees for Periodic-Review Stochastic Inventory Control
- Jordan-Block Degeneracy and Cubic-Order Bifurcating Periodic Orbits in Minimum-Energy Optimal Control of Hamiltonian Equilibria
- L1 Minimum Energy Estimation of Positive Systems
BibTeX
@misc{sharma2026minimumenergy,
title = {{Minimum-Energy Control for Stochastic Linear Systems: A Data-Driven Approach with Finite-Sample Guarantees}},
author = {Vaishnavi Sharma and Vaibhav Katewa},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.27599},
eprint = {2610.27599},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.27599},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Minimum-Energy Control for Stochastic Linear Systems: A Data-Driven Approach with Finite-Sample Guarantees
AU - Vaishnavi Sharma
AU - Vaibhav Katewa
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.27599
UR - https://arxiv.org/abs/2610.27599
AB - The open-loop minimum-energy control (MEC) problem asks for control inputs that minimize the control energy while ensuring the terminal state reaches a desired value. In this paper, we study the open-loop MEC problem for stochastic linear time-invariant systems. We consider a variety of stochastic constraints that enforce the terminal error to be small, and show that Stochastic MEC (SMEC) problem can be formulated as a QCQP. We obtain the optimal solution for SMEC and show that it generalizes the well-known Deterministic MEC problem by introducing novel stochastic variants of controllability and Gramian matrices. When the system dynamics is unknown, we obtain a direct data-driven solution to the SMEC problem using maximum-likelihood estimation and conformal calibration approaches. Finally, we quantify the sub-optimality and constraint violation of our data-driven solutions via finite-sample high-probability upper bounds, and highlight their dependence on the number of experiments, system dimension, and noise-to-signal ratio. We present numerical simulations to validate the theoretical results.
ER -