arXiv subjects

John Lygeros

Publications and source records attributed to John Lygeros.

At least 145 records · Page 8Linked to original sources

arXiv2022

Controller-Aware Dynamic Network Management for Industry 4.0

In this paper, we consider a cyber-physical manufacturing system (CPMS) scenario containing physical components (robots, sensors, and actuators), operating in a digitally connected, constrained environment to perform industrial tasks. The CPMS has a centralized control plane with digital twins (DTs) of the physical resources, computational resources, and a network manager that allocates network resources. Existing approaches for allocation of network resources are typically fixed with respect to controller-dependent run-time specifications, which may impact the performance of physical processes. We propose a dynamic network management framework, where the network resource allocation schemes are controller-aware. The information about the controllers of the physical resources is implemented at the DT level, and metrics, such as regret bounds, take the process performance measures into account. The proposed network management schemes optimize physical system performance by balancing the shared resources between the physical assets on the plant floor, and by considering their control requirements, providing a new perspective for dynamic resource allocation. A simulation study is provided to illustrate the performance of the proposed network management approaches and compare their efficiencies.

eess.SY↗

arXiv2022

On Robustness in Optimization-Based Constrained Iterative Learning Control

Iterative learning control (ILC) is a control strategy for repetitive tasks wherein information from previous runs is leveraged to improve future performance. Optimization-based ILC (OB-ILC) is a powerful design framework for constrained ILC where measurements from the process are integrated into an optimization algorithm to provide robustness against noise and modelling error. This paper proposes a robust ILC controller for constrained linear processes based on the forward-backward splitting algorithm. It demonstrates how structured uncertainty information can be leveraged to ensure constraint satisfaction and provides a rigorous stability analysis in the iteration domain by combining concepts from monotone operator theory and robust control. Numerical simulations of a precision motion stage support the theoretical results.

eess.SY↗

arXiv2022

Plasma Spray Process Parameters Configuration using Sample-efficient Batch Bayesian Optimization

Recent work has shown constrained Bayesian optimization to be a powerful technique for the optimization of industrial processes. In complex manufacturing processes, the possibility to run extensive sequences of experiments with the goal of finding good process parameters is severely limited by the time required for quality evaluation of the produced parts. To accelerate the process parameter optimization, we introduce a parallel acquisition procedure tailored on the process characteristics. We further propose an algorithm that adapts to equipment status to improve run-to-run reproducibility. We validate our optimization method numerically and experimentally, and demonstrate that it can efficiently find input parameters that produce the desired outcome and minimize the process cost.

eess.SY↗

arXiv2022

Regret Analysis of Online Gradient Descent-based Iterative Learning Control with Model Mismatch

In Iterative Learning Control (ILC), a sequence of feedforward control actions is generated at each iteration on the basis of partial model knowledge and past measurements with the goal of steering the system toward a desired reference trajectory. This is framed here as an online learning task, where the decision-maker takes sequential decisions by solving a sequence of optimization problems having only partial knowledge of the cost functions. Having established this connection, the performance of an online gradient-descent based scheme using inexact gradient information is analyzed in the setting of dynamic and static regret, standard measures in online learning. Fundamental limitations of the scheme and its integration with adaptation mechanisms are further investigated, followed by numerical simulations on a benchmark ILC problem.

eess.SY↗

arXiv2022

Batch Model Predictive Control for Selective Laser Melting

Selective laser melting is a promising additive manufacturing technology enabling the fabrication of highly customizable products. A major challenge in selective laser melting is ensuring the quality of produced parts, which is influenced greatly by the thermal history of printed layers. We propose a Batch-Model Predictive Control technique based on the combination of model predictive control and iterative learning control. This approach succeeds in rejecting both repetitive and non-repetitive disturbances and thus achieves improved tracking performance and process quality. In a simulation study, the selective laser melting dynamics is approximated with a reduced-order control-oriented linear model to ensure reasonable computational complexity. The proposed approach provides convergence to the desired temperature field profile despite model uncertainty and disturbances.

eess.SY↗

arXiv2022

Behavioral uncertainty quantification for data-driven control

This paper explores the problem of uncertainty quantification in the behavioral setting for data-driven control. Building on classical ideas from robust control, the problem is regarded as that of selecting a metric which is best suited to a data-based description of uncertainties. Leveraging on Willems' fundamental lemma, restricted behaviors are viewed as subspaces of fixed dimension, which may be represented by data matrices. Consequently, metrics between restricted behaviors are defined as distances between points on the Grassmannian, i.e., the set of all subspaces of equal dimension in a given vector space. A new metric is defined on the set of restricted behaviors as a direct finite-time counterpart of the classical gap metric. The metric is shown to capture parametric uncertainty for the class of autoregressive (AR) models. Numerical simulations illustrate the value of the new metric with a data-driven mode recognition and control case study.

math.OC↗

arXiv2022

In-layer Thermal Control of a Multi-layer Selective Laser Melting Process

Selective Laser Melting (SLM) is an additive manufacturing technology that builds three dimensional parts by melting layers of metal powder together with a laser that traces out a desired geometry. SLM is popular in industry, however the inherent melting and re-solidification of the metal during the process can, if left uncontrolled, cause excessive residual stress, porosity, and other defects in the final printed parts. This paper presents a control-oriented thermal model of a multi-layer SLM process and proposes a structured model reduction methodology with an associated reduced order model based in-layer controller to track temperature references. Simulation studies demonstrate that the controller is able to prevent layer-to-layer heat buildup and that good closed-loop performance is possible using relatively low-order models.

eess.SY↗

arXiv2022

Policy Iteration for Multiplicative Noise Output Feedback Control

We propose a policy iteration algorithm for solving the multiplicative noise linear quadratic output feedback design problem. The algorithm solves a set of coupled Riccati equations for estimation and control arising from a partially observable Markov decision process (POMDP) under a class of linear dynamic control policies. We show in numerical experiments far faster convergence than a value iteration algorithm, formerly the only known algorithm for solving this class of problem. The results suggest promising future research directions for policy optimization algorithms in more general POMDPs, including the potential to develop novel approximate data-driven approaches when model parameters are not available.

eess.SY↗

arXiv2022

Robust MPC with data-driven demand forecasting for frequency regulation with heat pumps

With the increased amount of volatile renewable energy sources connected to the electricity grid, and the phase-out of fossil fuel based power plants, there is an increased need for frequency regulation. On the demand side, frequency regulation services can be offered by buildings or districts that are equipped with electric heating or cooling systems, by exploiting their thermal inertia. Existing approaches for tapping into this potential typically rely on dynamic building models, which in practice can be challenging to obtain and maintain. As a result, practical implementations of such systems are scarce. Moreover, actively controlling buildings requires extensive control infrastructure and may cause privacy concerns in district energy systems. Motivated by this, we exploit the thermal inertia of buffer storage for reserves, reducing the building models to demand forecasts here. By combining a control scheme based on Robust Model Predictive Control, with affine policies, and heating demand forecasting based on Artificial Neural Networks with online correction methods, we offer frequency regulation reserves and maintain user comfort with a system comprising a heat pump and buffer storage. While the robust approach ensures occupant comfort, the use of affine policies reduces the effect of disturbance uncertainty on the system state. In a first-of-its-kind experiment with a real district-like building energy system, we demonstrate that the scheme is able to offer reserves in a variety of conditions and track a regulation signal while meeting the heating demand of the connected buildings. 13.4% of the consumed electricity is flexible. In additional numerical studies, we demonstrate that using affine policies significantly decreases the cost function and increases the amount of offered reserves and we investigate the suboptimality in comparison to an omniscient control system.

eess.SY↗

arXiv2022

PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation

Despite their success, policy gradient methods suffer from high variance of the gradient estimate, which can result in unsatisfactory sample complexity. Recently, numerous variance-reduced extensions of policy gradient methods with provably better sample complexity and competitive numerical performance have been proposed. After a compact survey on some of the main variance-reduced REINFORCE-type methods, we propose ProbAbilistic Gradient Estimation for Policy Gradient (PAGE-PG), a novel loopless variance-reduced policy gradient method based on a probabilistic switch between two types of updates. Our method is inspired by the PAGE estimator for supervised learning and leverages importance sampling to obtain an unbiased gradient estimator. We show that PAGE-PG enjoys a $\mathcal{O}\left( ε^{-3} \right)$ average sample complexity to reach an $ε$-stationary solution, which matches the sample complexity of its most competitive counterparts under the same setting. A numerical evaluation confirms the competitive performance of our method on classical control tasks.

cs.LG↗

arXiv2022

Physics-informed linear regression is competitive with two Machine Learning methods in residential building MPC

Because physics-based building models are difficult to obtain as each building is individual, there is an increasing interest in generating models suitable for building MPC directly from measurement data. Machine learning methods have been widely applied to this problem and validated mostly in simulation; there are, however, few studies on a direct comparison of different models or validation in real buildings to be found in the literature. Methods that are indeed validated in application often lead to computationally complex non-convex optimization problems. Here we compare physics-informed Autoregressive-Moving-Average with Exogenous Inputs (ARMAX) models to Machine Learning models based on Random Forests and Input Convex Neural Networks and the resulting convex MPC schemes in experiments on a practical building application with the goal of minimizing energy consumption while maintaining occupant comfort, and in a numerical case study. We demonstrate that Predictive Control in general leads to savings between 26% and 49% of heating and cooling energy, compared to the building's baseline hysteresis controller. Moreover, we show that all model types lead to satisfactory control performance in terms of constraint satisfaction and energy reduction. However, we also see that the physics-informed ARMAX models have a lower computational burden, and a superior sample efficiency compared to the Machine Learning based models. Moreover, even if abundant training data is available, the ARMAX models have a significantly lower prediction error than the Machine Learning models, which indicates that the encoded physics-based prior of the former cannot independently be found by the latter.

cs.LG↗

arXiv2021

Stochastic convex optimization for provably efficient apprenticeship learning

We consider large-scale Markov decision processes (MDPs) with an unknown cost function and employ stochastic convex optimization tools to address the problem of imitation learning, which consists of learning a policy from a finite set of expert demonstrations. We adopt the apprenticeship learning formalism, which carries the assumption that the true cost function can be represented as a linear combination of some known features. Existing inverse reinforcement learning algorithms come with strong theoretical guarantees, but are computationally expensive because they use reinforcement learning or planning algorithms as a subroutine. On the other hand, state-of-the-art policy gradient based algorithms (like IM-REINFORCE, IM-TRPO, and GAIL), achieve significant empirical success in challenging benchmark tasks, but are not well understood in terms of theory. With an emphasis on non-asymptotic guarantees of performance, we propose a method that directly learns a policy from expert demonstrations, bypassing the intermediate step of learning the cost function, by formulating the problem as a single convex optimization problem over occupancy measures. We develop a computationally efficient algorithm and derive high confidence regret bounds on the quality of the extracted policy, utilizing results from stochastic convex optimization and recent works in approximate linear programming for solving forward MDPs.

cs.LG↗

arXiv2021

Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations

We consider large-scale Markov decision processes with an unknown cost function and address the problem of learning a policy from a finite set of expert demonstrations. We assume that the learner is not allowed to interact with the expert and has no access to reinforcement signal of any kind. Existing inverse reinforcement learning methods come with strong theoretical guarantees, but are computationally expensive, while state-of-the-art policy optimization algorithms achieve significant empirical success, but are hampered by limited theoretical understanding. To bridge the gap between theory and practice, we introduce a novel bilinear saddle-point framework using Lagrangian duality. The proposed primal-dual viewpoint allows us to develop a model-free provably efficient algorithm through the lens of stochastic convex optimization. The method enjoys the advantages of simplicity of implementation, low memory requirements, and computational and sample complexities independent of the number of states. We further present an equivalent no-regret online-learning interpretation.

cs.LG↗

arXiv2021

Learning-Based Repetitive Precision Motion Control with Mismatch Compensation

Learning-based control methods utilize run-time data from the underlying process to improve the controller performance under model mismatch and unmodeled disturbances. This is beneficial for optimizing industrial processes, where the dynamics are difficult to model, and the repetitive nature of the process can be exploited. In this work, we develop an iterative approach for repetitive precision motion control problems where the objective is to follow a reference geometry with minimal tracking error. Our method utilizes a nominal model of the process and learns the mismatch using Gaussian Process Regression (GPR). The control input and the GPR data are updated after each iteration to improve the performance in a run-to-run fashion. We provide a preliminary convergence analysis, implementation details of the proposed controller for minimizing different error types, and a case study where we demonstrate improved tracking performance with simulation and experimental results.

eess.SY↗

arXiv2021

Incentive-Based Electric Vehicle Charging for Managing Bottleneck Congestion

We propose an incentive-based traffic demand management policy to alleviate traffic congestion on a road stretch that creates a bottleneck for the commuters. The incentive targets electric vehicles owners by proposing a discount on the energy price they use to charge their vehicles if they are flexible in their departure time. We show that, with a sufficient monetary budget, it is possible to completely eliminate the traffic congestion and we compute the optimal discount. We analyse also the case of limited budget, when the congestion cannot be completely eliminated. We compute analytically the policy minimising the congestion and estimate the level of inefficiency for different budgets. We corroborate our theoretical findings with numerical simulations that allow us to highlight the power of the proposed method in providing practical advice for the design of policies.

math.OC↗

arXiv2021

Distributed Model Predictive Control with Reconfigurable Terminal Ingredients for Reference Tracking

Various efforts have been devoted to developing stabilizing distributed Model Predictive Control (MPC) schemes for tracking piecewise constant references. In these schemes, terminal sets are usually computed offline and used in the MPC online phase to guarantee recursive feasibility and asymptotic stability. Maximal invariant terminal sets do not necessarily respect the distributed structure of the network, hindering the distributed implementation of the controller. On the other hand, ellipsoidal terminal sets respect the distributed structure, but may lead to conservative schemes. In this paper, a novel distributed MPC scheme is proposed for reference tracking of networked dynamical systems where the terminal ingredients are reconfigured online depending on the closed-loop states to alleviate the aforementioned issues. The resulting non-convex infinite-dimensional problem is approximated using a quadratic program. The proposed scheme is tested in simulation where the proposed MPC problem is solved using distributed optimization.

eess.SY↗

arXiv2021

Parallel and Flexible Dynamic Programming via the Randomized Mini-Batch Operator

The Bellman operator constitutes the foundation of dynamic programming (DP). An alternative is presented by the Gauss-Seidel operator, whose evaluation, differently from that of the Bellman operator where the states are all processed at once, updates one state at a time, while incorporating into the computation the interim results. The provably better convergence rate of DP methods based on the Gauss-Seidel operator comes at the price of an inherent sequentiality, which prevents the exploitation of modern multi-core systems. In this work we propose a new operator for dynamic programming, namely, the randomized mini-batch operator, which aims at realizing the trade-off between the better convergence rate of the methods based on the Gauss-Seidel operator and the parallelization capability offered by the Bellman operator. After the introduction of the new operator, a theoretical analysis for validating its fundamental properties is conducted. Such properties allow one to successfully deploy the new operator in the main dynamic programming schemes, such as value iteration and modified policy iteration. We compare the convergence of the DP algorithm based on the new operator with its earlier counterparts, shedding light on the algorithmic advantages of the new formulation and the impact of the batch-size parameter on the convergence. Finally, an extensive numerical evaluation of the newly introduced operator is conducted. In accordance with the theoretical derivations, the numerical results show the competitive performance of the proposed operator and its superior flexibility, which allows one to adapt the efficiency of its iterations to different structures of MDPs and hardware setups.

math.OC↗

arXiv2021

Distributed Model Predictive Control of Buildings and Energy Hubs

Model predictive control (MPC) strategies can be applied to the coordination of energy hubs to reduce their energy consumption. Despite the effectiveness of these techniques, their potential for energy savings are potentially underutilized due to the fact that energy demands are often assumed to be fixed quantities rather than controlled dynamic variables. The joint optimization of energy hubs and buildings' energy management systems can result in higher energy savings. This paper investigates how different MPC strategies perform on energy management systems in buildings and energy hubs. We first discuss two MPC approaches; centralized and decentralized. While the centralized control strategy offers optimal performance, its implementation is computationally prohibitive and raises privacy concerns. On the other hand, the decentralized control approach, which offers ease of implementation, displays significantly lower performance. We propose a third strategy, distributed control based on dual decomposition, which has the advantages of both approaches. Numerical case studies and comparisons demonstrate that the performance of distributed control is close to the performance of the centralized case, while maintaining a significantly lower computational burden, especially in large-scale scenarios with many agents. Finally, we validate and verify the reliability of the proposed method through an experiment on a full-scale energy hub system in the NEST demonstrator in Dübendorf, Switzerland.

math.OC↗