arXiv subjects

Dinesh Krishnamoorthy

Publications and source records attributed to Dinesh Krishnamoorthy.

17 recordsLinked to original sources

arXiv2026

Learning myopic mixed-integer nonlinear model predictive control from expert demonstrations

Applying nonlinear model predictive control (NMPC) to systems with hybrid dynamics or discrete actions typically yields mixed-integer nonlinear programs (MINLPs), whose real-time solution remains a major challenge and limits the applicability of mixed-integer NMPC (MINMPC). This paper proposes a myopic MINMPC framework that incorporates value-function approximation to substantially reduce the online computational burden. Using Bellman's principle of optimality, we shorten the prediction horizon and append a value function learned offline from expert state-action demonstrations via inverse optimization with optimality residual minimization. A central feature is the dual treatment of discrete decisions, whereby integer constraints are relaxed during offline learning to enable KKT-residual-based value function synthesis, while the online controller enforces the true integer constraints to ensure feasibility. The learned value function induces a policy that is approximately policy-consistent with the expert demonstrations. The resulting controller achieves high closed-loop performance with a significantly shorter horizon, enabling real-time MINMPC. The effectiveness of the approach is demonstrated on the Lotka-Volterra fishing problem and a satellite attitude control system with discrete actuators.

eess.SY↗

arXiv2025

MPC strategies for density profile control with pellet fueling in nuclear fusion tokamaks under uncertainty

Control of the density profile based on pellet fueling for the ITER nuclear fusion tokamak involves a multi-rate nonlinear system with safety-critical constraints, input delays, and discrete actuators with parametric uncertainty. To address this challenging problem, we propose a multi-stage MPC (msMPC) approach to handle uncertainty in the presence of mixed-integer inputs. While the scenario tree of msMPC accounts for uncertainty, it also adds complexity to an already computationally intensive mixed-integer MPC (MI-MPC) problem. To achieve real-time density profile controller with discrete pellets and uncertainty handling, we systematically reduce the problem complexity by (1) reducing the identified prediction model size through dynamic mode decomposition with control, (2) applying principal component analysis to reduce the number of scenarios needed to capture the parametric uncertainty in msMPC, and (3) utilizing the penalty term homotopy for MPC (PTH-MPC) algorithm to reduce the computational burden caused by the presence of mixed-integer inputs. We compare the performance and safety of the msMPC strategy against a nominal MI-MPC in plant simulations, demonstrating the first predictive density control strategy with uncertainty handling, viable for real-time pellet fueling in ITER.

eess.SY↗

arXiv2025

A Scenario-based Model Predictive Control Scheme for Pandemic Response through Non-pharmaceutical Interventions

This paper presents a scenario-based model predictive control (MPC) scheme designed to control an evolving pandemic via non-pharmaceutical intervention (NPIs). The proposed approach combines predictions of possible pandemic evolution to decide on a level of severity of NPIs to be implemented over multiple weeks to maintain hospital pressure below a prescribed threshold, while minimizing their impact on society. Specifically, we first introduce a compartmental model which divides the population into Susceptible, Infected, Detected, Threatened, Healed, and Expired (SIDTHE) subpopulations and describe its positive invariant set. This model is expressive enough to explicitly capture the fraction of hospitalized individuals while preserving parameter identifiability w.r.t. publicly available datasets. Second, we devise a scenario-based MPC scheme with recourse actions that captures potential uncertainty of the model parameters. e.g., due to population behavior or seasonality. Our results show that the scenario-based nature of the proposed controller manages to adequately respond to all scenarios, keeping the hospital pressure at bay also in very challenging situations when conventional MPC methods fail.

eess.SY↗

arXiv2024

A Comparative Study of Distributed Feedback Optimizing Control Architectures

This paper considers the problem of steady-state real-time optimization (RTO) of interconnected systems with a common constraint that couples several units, for example, a shared resource. Such problems are often studied under the context of distributed optimization, where decisions are made locally in each subsystem, and are coordinated to optimize the overall performance. Here, we use distributed feedback-optimizing control framework, where the local systems and the coordinator problems are converted into feedback control problems. This is a powerful scheme that allows us to design feedback control loops, and estimate parameters locally, as well as provide local fast response, allowing different closed-loop time constants for each local subsystem. This paper provides a comparative study of different distributed feedback optimizing control architectures using two case studies. The first case study considers the problem of demand response in a residential energy hub powered by a common renewable energy source, and compares the different feedback optimizing control approaches using simulations. The second case study experimentally validates and compares the different approaches using a lab-scale experimental rig that emulates a subsea oil production network, where the common resource is the gas lift that must be optimally allocated among the wells. %The pros and cons of the different approaches are discussed.

math.OC↗

arXiv2024

ECCBO: An Inherently Safe Bayesian Optimization with Embedded Constraint Control for Real-Time Optimization

This paper introduces a model-free real-time optimization (RTO) framework based on unconstrained Bayesian optimization with embedded constraint control. The main contribution lies in demonstrating how this approach simplifies the black-box optimization problem while ensuring "always-feasible" setpoints, addressing a critical challenge in real-time optimization with unknown cost and constraints. Noting that controlling the constraint does not require detailed process models, the key idea of this paper is to control the constraints to "some" setpoint using simple feedback controllers. Bayesian optimization then computes the optimum setpoint for the constraint controllers. By searching over the setpoints for the constraint controllers, as opposed to searching directly over the RTO degrees of freedom, this paper achieves an inherently safe and practical model-free RTO scheme. In particular, this paper shows that the proposed approach can achieve zero cumulative constraint violation without relying on assumptions about the Gaussian process model used in Bayesian optimization. The effectiveness of the proposed approach is demonstrated on a benchmark Williams-Otto reactor example.

math.OC↗

arXiv2024

On Building Myopic MPC Policies using Supervised Learning

The application of supervised learning techniques in combination with model predictive control (MPC) has recently generated significant interest, particularly in the area of approximate explicit MPC, where function approximators like deep neural networks are used to learn the MPC policy via optimal state-action pairs generated offline. While the aim of approximate explicit MPC is to closely replicate the MPC policy, substituting online optimization with a trained neural network, the performance guarantees that come with solving the online optimization problem are typically lost. This paper considers an alternative strategy, where supervised learning is used to learn the optimal value function offline instead of learning the optimal policy. This can then be used as the cost-to-go function in a myopic MPC with a very short prediction horizon, such that the online computation burden reduces significantly without affecting the controller performance. This approach differs from existing work on value function approximations in the sense that it learns the cost-to-go function by using offline-collected state-value pairs, rather than closed-loop performance data. The cost of generating the state-value pairs used for training is addressed using a sensitivity-based data augmentation scheme.

cs.LG↗

arXiv2024

Learning the cost-to-go for mixed-integer nonlinear model predictive control

Application of nonlinear model predictive control (NMPC) to problems with hybrid dynamical systems, disjoint constraints, or discrete controls often results in mixed-integer formulations with both continuous and discrete decision variables. However, solving mixed-integer nonlinear programming problems (MINLP) in real-time is challenging, which can be a limiting factor in many applications. To address the computational complexity of solving mixed integer nonlinear model predictive control problem in real-time, this paper proposes an approximate mixed integer NMPC formulation based on value function approximation. Leveraging Bellman's principle of optimality, the key idea here is to divide the prediction horizon into two parts, where the optimal value function of the latter part of the prediction horizon is approximated offline using expert demonstrations. Doing so allows us to solve the MINMPC problem with a considerably shorter prediction horizon online, thereby reducing the online computation cost. The paper uses an inverted pendulum example with discrete controls to illustrate this approach.

eess.SY↗

arXiv2023

A Bayesian optimization framework for the automatic tuning of MPC-based shared controllers

This paper presents a Bayesian optimization framework for the automatic tuning of shared controllers which are defined as a Model Predictive Control (MPC) problem. The proposed framework includes the design of performance metrics as well as the representation of user inputs for simulation-based optimization. The framework is applied to the optimization of a shared controller for an Image Guided Therapy robot. VR-based user experiments confirm the increase in performance of the automatically tuned MPC shared controller with respect to a hand-tuned baseline version as well as its generalization ability.

cs.RO↗

arXiv2023

Mixed-Integer MPC Strategies for Fueling and Density Control in Fusion Tokamaks

Model predictive control (MPC) is promising for fueling and core density feedback control in nuclear fusion tokamaks, where the primary actuators, frozen hydrogen fuel pellets fired into the plasma, are discrete. Previous density feedback control approaches have only approximated pellet injection as a continuous input due to the complexity that it introduces. In this letter, we model plasma density and pellet injection as a hybrid system and propose two MPC strategies for density control: mixed-integer (MI) MPC using a conventional mixed-integer programming (MIP) solver and MPC utilizing our novel modification of the penalty term homotopy (PTH) algorithm. By relaxing the integer requirements, the PTH algorithm transforms the MIP problem into a series of continuous optimization problems, reducing computational complexity. Our novel modification to the PTH algorithm ensures that it can handle path constraints, making it viable for constrained hybrid MPC in general. Both strategies perform well with regards to reference tracking without violating path constraints and satisfy the computation time limit for real-time control of the pellet injection system. However, the computation time of the PTH-based MPC strategy consistently outpaces the conventional MI-MPC strategy.

eess.SY↗

arXiv2023

Stability Properties of the Adaptive Horizon Multi-Stage MPC

This paper presents an adaptive horizon multi-stage model-predictive control (MPC) algorithm. It establishes appropriate criteria for recursive feasibility and robust stability using the theory of input-to-state practical stability (ISpS). The proposed algorithm employs parametric nonlinear programming (NLP) sensitivity and terminal ingredients to determine the minimum stabilizing prediction horizon for all the scenarios considered in the subsequent iterations of the multi-stage MPC. This technique notably decreases the computational cost in nonlinear model-predictive control systems with uncertainty, as they involve solving large and complex optimization problems. The efficacy of the controller is illustrated using three numerical examples that illustrate a reduction in computational delay in multi-stage MPC.

math.OC↗

arXiv2023

An Improved Data Augmentation Scheme for Model Predictive Control Policy Approximation

This paper considers the problem of data generation for MPC policy approximation. Learning an approximate MPC policy from expert demonstrations requires a large data set consisting of optimal state-action pairs, sampled across the feasible state space. Yet, the key challenge of efficiently generating the training samples has not been studied widely. Recently, a sensitivity-based data augmentation framework for MPC policy approximation was proposed, where the parametric sensitivities are exploited to cheaply generate several additional samples from a single offline MPC computation. The error due to augmenting the training data set with inexact samples was shown to increase with the size of the neighborhood around each sample used for data augmentation. Building upon this work, this letter paper presents an improved data augmentation scheme based on predictor-corrector steps that enforces a user-defined level of accuracy, and shows that the error bound of the augmented samples are independent of the size of the neighborhood used for data augmentation.

eess.SY↗

arXiv2023

Multi-agent Black-box Optimization using a Bayesian Approach to Alternating Direction Method of Multipliers

Bayesian optimization (BO) is a powerful black-box optimization framework that looks to efficiently learn the global optimum of an unknown system by systematically trading-off between exploration and exploitation. However, the use of BO as a tool for coordinated decision-making in multi-agent systems with unknown structure has not been widely studied. This paper investigates a black-box optimization problem over a multi-agent network coupled via shared variables or constraints, where each subproblem is formulated as a BO that uses only its local data. The proposed multi-agent BO (MABO) framework adds a penalty term to traditional BO acquisition functions to account for coupling between the subsystems without data sharing. We derive a suitable form for this penalty term using alternating directions method of multipliers (ADMM), which enables the local decision-making problems to be solved in parallel (and potentially asynchronously). The effectiveness of the proposed MABO method is demonstrated on an intelligent transport system for fuel efficient vehicle platooning.

math.OC↗

arXiv2022

Personalized Dose Guidance using Safe Bayesian Optimization

This work considers the problem of personalized dose guidance using Bayesian optimization that learns the optimum drug dose tailored to each individual, thus improving therapeutic outcomes. Safe learning using interior point method ensures patient safety with high probability. This is demonstrated using the problem of learning the optimum bolus insulin dose in patients with type 1 diabetes to counteract the effect of meal consumption. Starting from no a priori information about the patients, our dose guidance algorithm is able to improve the therapeutic outcome (measured in terms of % time-in-range) without jeopardizing patient safety. Other potential healthcare applications are also discussed.

math.OC↗

arXiv2022

Safe Bayesian Optimization using Interior-Point Methods -- Applied to Personalized Insulin Dose Guidance

This paper considers the problem of Bayesian optimization for systems with safety-critical constraints, where both the objective function and the constraints are unknown, but can be observed by querying the system. In safety-critical applications, querying the system at an infeasible point can have catastrophic consequences. Such systems require a safe learning framework, such that the performance objective can be optimized while satisfying the safety-critical constraints with high probability. In this paper we propose a safe Bayesian optimization framework that ensures that the points queried are always in the interior of the partially revealed safe region, thereby guaranteeing constraint satisfaction with high probability. The proposed interior-point Bayesian optimization framework can be used with any acquisition function, making it broadly applicable. The performance of the proposed method is demonstrated using a personalized insulin dosing application for patients with type 1 diabetes.

math.OC↗

arXiv2022

A Sensitivity-based Data Augmentation Framework for Model Predictive Control Policy Approximation

Approximating model predictive control (MPC) policy using expert-based supervised learning techniques requires labeled training data sets sampled from the MPC policy. This is typically obtained by sampling the feasible state-space and evaluating the control law by solving the numerical optimization problem offline for each sample. Although the resulting approximate policy can be cheaply evaluated online, generating large training samples to learn the MPC policy can be time consuming and prohibitively expensive. This is one of the fundamental bottlenecks that limit the design and implementation of MPC policy approximation. This technical note aims to address this challenge, and proposes a novel sensitivity-based data augmentation scheme for direct policy approximation. The proposed approach is based on exploiting the parametric sensitivities to cheaply generate additional training samples in the neighborhood of the existing samples.

math.OC↗

arXiv2022

Sensitivity Assisted Alternating Directions Method of Multipliers for Distributed Optimization and Statistical Learning

This paper considers the problem of distributed model fitting using the alternating directions method of multipliers (ADMM). ADMM splits the learning problem into several smaller subproblems, usually by partitioning the data samples. The different subproblems can be solved in parallel by a set of worker computing nodes coordinated by a master node, and the subproblems are repeatedly solved until convergence. At each iteration, the worker nodes must solve a convex optimization problem whose difficulty increases with the size of the problem. In this paper, we propose a sensitivity-assisted ADMM algorithm that leverages the parametric sensitivities such that the subproblems solutions can be approximated using a tangential predictor, thus easing the computational burden to computing one linear solve. We study the convergence properties of the proposed sensitivity-assisted ADMM algorithm. The numerical performance of the algorithm is illustrated on a nonlinear parameter estimation problem, and a multilayer perceptron learning problem.

math.OC↗

arXiv2021

On the Design and Analysis of Multivariable Extremum Seeking Control using Fast Fourier Transform

This paper proposes a multivariable extremum seeking scheme using Fast Fourier Transform (FFT) for a network of subsystems working towards optimizing the sum of their local objectives, where the overall objective is the only available measurement. Here, the different inputs are perturbed with different dither frequencies, and the power spectrum of the overall output signal obtained using FFT is used to estimate the steady-state cost gradient w.r.t. each input. The inputs for the subsystems are then updated using integral control in order to drive the respective gradients to zero. This paper provides analytical rules for designing the FFT-based gradient estimation algorithm and analyzes the stability properties of the resulting extremum seeking scheme for the static map setting. The effectiveness of the proposed FFT-based multivariable extremum seeking scheme is demonstrated using two examples, namely, wind farm power optimization problem, and a heat exchanger network for industrial waste-to-heat recovery.

math.OC↗