arXiv subjects

Colin N. Jones

Publications and source records attributed to Colin N. Jones.

At least 91 records · Page 5Linked to original sources

arXiv2021

Distributed Multi-Building Coordination for Demand Response

This paper presents a distributed optimization algorithm tailored for solving optimal control problems arising in multi-building coordination. The buildings coordinated by a grid operator, join a demand response program to balance the voltage surge by using an energy cost defined criterion. In order to model the hierarchical structure of the building network, we formulate a distributed convex optimization problem with separable objectives and coupled affine equality constraints. A variant of the Augmented Lagrangian based Alternating Direction Inexact Newton (ALADIN) method for solving the considered class of problems is then presented along with a convergence guarantee. To illustrate the effectiveness of the proposed method, we compare it to the Alternating Direction Method of Multipliers (ADMM) by running both an ALADIN and an ADMM based model predictive controller on a benchmark case study.

math.OC↗

arXiv2020

Reference tracking stochastic model predictive control over unreliable channels and bounded control actions

A stochastic model predictive control framework over unreliable Bernoulli communication channels, in the presence of unbounded process noise and under bounded control inputs, is presented for tracking a reference signal. The data losses in the control channel are compensated by a carefully designed transmission protocol, and that of the sensor channel by a dropout compensator. A class of saturated, disturbance feedback policies is proposed for control in the presence of noisy dropout compensation. A reference governor is employed to generate trackable reference trajectories and stability constraints are employed to ensure mean-square boundedness of the reference tracking error. The overall approach yields a computationally tractable quadratic program, which can be iteratively solved online.

math.OC↗

arXiv2020

KPC: Learning-Based Model Predictive Control with Deterministic Guarantees

We propose Kernel Predictive Control (KPC), a learning-based predictive control strategy that enjoys deterministic guarantees of safety. Noise-corrupted samples of the unknown system dynamics are used to learn several models through the formalism of non-parametric kernel regression. By treating each prediction step individually, we dispense with the need of propagating sets through highly non-linear maps, a procedure that often involves multiple conservative approximation steps. Finite-sample error bounds are then used to enforce state-feasibility by employing an efficient robust formulation. We then present a relaxation strategy that exploits on-line data to weaken the optimization problem constraints while preserving safety. Two numerical examples are provided to illustrate the applicability of the proposed control method.

eess.SY↗

arXiv2020

Convergence Certificate for Stochastic Derivative-Free Trust-Region Methods based on Gaussian Processes

In many machine learning applications, one wants to learn the unknown objective and constraint functions of an optimization problem from available data and then apply some technique to attain a local optimizer of the learned model. This work considers Gaussian processes as global surrogate models and utilizes them in conjunction with derivative-free trust-region methods. It is well known that derivative-free trust-region methods converge globally---provided the surrogate model is probabilistically fully linear. We prove that \glspl{gp} are indeed probabilistically fully linear, thus resulting in fast (compared to linear or quadratic local surrogate models) and global convergence. We draw upon the optimization of a chemical reactor to demonstrate the efficiency of \gls{gp}-based trust-region methods.

eess.SY↗

arXiv2020

Towards an Unified Structure for Reinforcement Learning: an Optimization Approach

Both the optimal value function and the optimal policy can be used to model an optimal controller based on the duality established by the Bellman equation. Even with this duality, no parametric model has been able to output both policy and value function with a common parameter set. In this paper, a unified structure is proposed with a parametric optimization problem. The policy and the value function modelled by this structure share all parameters, which enables seamless switching among reinforcement learning algorithms while continuing to learn. The Q-learning and policy gradient based on the proposed structure is detailed. An actor-critic algorithm based on this structure, whose actor and critic are both modelled by the same parameters, is validated by both linear and nonlinear control.

eess.SY↗

arXiv2020

A Resource-Aware Approach to Self-Triggered Model Predictive Control: Extended Version

In this paper, we consider a self-triggered formulation of model predictive control. In this variant, the controller decides at the current sampling instant itself when the next sample should be taken and the optimization problem be solved anew. We incorporate a pointwise-in-time resource constraint into the optimization problem, whose exact form can be chosen by the user. Thereby, the proposed scheme is made resource-aware with respect to a universal resource, which may pertain in practice for instance to communication, computation, energy or financial resources. We show that by virtue of the pointwise-in-time constraints, also a transient and an asymptotic average constraint on the resource usage are guaranteed. Furthermore, we derive conditions on the resource under which the proposed scheme achieves recursive feasibility and convergence. Finally, we demonstrate our theoretical results in a numerical example.

eess.SY↗

arXiv2020

NSM Converges to a k-NN Regressor Under Loose Lipschitz Estimates

Although it is known that having accurate Lipschitz estimates is essential for certain models to deliver good predictive performance, refining this constant in practice can be a difficult task especially when the input dimension is high. In this work, we shed light on the consequences of employing loose Lipschitz bounds in the Nonlinear Set Membership (NSM) framework, showing that the model converges to a nearest neighbor regressor (k-NN with k=1). This convergence process is moreover not uniform, and is monotonic in the univariate case. An intuitive geometrical interpretation of the result is then given and its practical implications are discussed.

eess.SY↗

arXiv2018

Communication reduction in distributed optimization via estimation of the proximal operator

We introduce a reduced-communication distributed optimization scheme based on estimating the solution to a proximal minimization problem. Our proposed setup involves a group of agents coordinated by a central entity, altogether operating in a collaborative framework. The agents solve proximal minimization problems that are hidden from the central coordinator. The scheme enables the coordinator to construct a convex set within which the agents' optimizers reside, and to iteratively refine the set every time that an agent is queried. We analyze the quality of the constructed sets by showing their connections to the ε-subdifferential of a convex function and characterize their size. We prove convergence results related to the solution of such distributed optimization problems and we devise a communication criterion that embeds the proposed scheme in the Alternating Direction Method of Multipliers (ADMM). The developed scheme demonstrates significant communication reduction when applied to a microgrid setting.

math.OC↗

arXiv2018

An Inertial Parallel and Asynchronous Fixed-Point Iteration for Convex Optimization

Two characteristics that make convex decomposition algorithms attractive are simplicity of operations and generation of parallelizable structures. In principle, these schemes require that all coordinates update at the same time, i.e., they are synchronous by construction. Introducing asynchronicity in the updates can resolve several issues that appear in the synchronous case, like load imbalances in the computations or failing communication links. However, and to the best of our knowledge, there are no instances of asynchronous versions of commonly-known algorithms combined with inertial acceleration techniques. In this work we propose an inertial asynchronous and parallel fixed-point iteration from which several new versions of existing convex optimization algorithms emanate. Departing from the norm that the frequency of the coordinates' updates should comply to some prior distribution, we propose a scheme where the only requirement is that the coordinates update within a bounded interval. We prove convergence of the sequence of iterates generated by the scheme at a linear rate. One instance of the proposed scheme is implemented to solve a distributed optimization load sharing problem in a smart grid setting and its superiority with respect to the non-accelerated version is illustrated.

math.OC↗

arXiv2017

On Turnpike and Dissipativity Properties of Continuous-Time Optimal Control Problems

This paper investigates the relations between three different properties, which are of importance in optimal control problems: dissipativity of the underlying dynamics with respect to a specific supply rate, optimal operation at steady state, and the turnpike property. We show in a continuous-time setting that if along optimal trajectories a strict dissipation inequality is satisfied, then this implies optimal operation at this steady state and the existence of a turnpike at the same steady state. Finally, we establish novel converse turnpike results, i.e., we show that the existence of a turnpike at a steady state implies optimal operation at this steady state and dissipativity with respect to this steady state. We draw upon a numerical example to illustrate our findings.

eess.SY↗

arXiv2016

Stability and Performance Verification of Optimization-based Controllers

This paper presents a method to verify closed-loop properties of optimization-based controllers for deterministic and stochastic constrained polynomial discrete-time dynamical systems. The closed-loop properties amenable to the proposed technique include global and local stability, performance with respect to a given cost function (both in a deterministic and stochastic setting) and the $\mathcal{L}_2$ gain. The method applies to a wide range of practical control problems: For instance, a dynamical controller (e.g., a PID) plus input saturation, model predictive control with state estimation, inexact model and soft constraints, or a general optimization-based controller where the underlying problem is solved with a fixed number of iterations of a first-order method are all amenable to the proposed approach. The approach is based on the observation that the control input generated by an optimization-based controller satisfies the associated Karush-Kuhn-Tucker (KKT) conditions which, provided all data is polynomial, are a system of polynomial equalities and inequalities. The closed-loop properties can then be analyzed using sum-of-squares (SOS) programming.

math.OC↗

arXiv2016

Asynchronous Splitting Design for Model Predictive Control

This paper focuses on the design of an asynchronous dual solver suitable for embedded model predictive control (MPC) applications. The proposed solver relies on a state-of-the-art variance reduction (VR) scheme, previously used in the context of stochastic proximal gradient methods, and on the alternating minimization algorithm (AMA). The resultant algorithm, a stochastic AMA with VR, shows geometric convergence (in the expectation) to a suboptimal solution of the MPC problem and, compared to other state-of-the-art dual asynchronous algorithms, allows to tune the probability of the asynchronous updates to improve the quality of the estimates. We apply the proposed algorithm to a specific class of splitting methods, i.e., the decomposition along the length of the prediction horizon, and provide preliminary numerical results on a practical application, the longitudinal control of an Airbus passenger aircraft.

math.OC↗

arXiv2016

Convergence rates of moment-sum-of-squares hierarchies for optimal control problems

We study the convergence rate of moment-sum-of-squares hierarchies of semidefinite programs for optimal control problems with polynomial data. It is known that these hierarchies generate polynomial under-approximations to the value function of the optimal control problem and that these under-approximations converge in the L1 norm to the value function as their degree d tends to infinity. We show that the rate of this convergence is O(1/ log log d). We treat in detail the continuous-time infinite-horizon discounted problem and describe in brief how the same rate can be obtained for the finite-horizon continuous-time problem and for the discrete-time counterparts of both problems.

math.OC↗

arXiv2016

Inexact Alternating Minimization Algorithm for Distributed Optimization with an Application to Distributed MPC

In this paper, we propose the inexact alternating minimization algorithm (inexact AMA), which allows inexact iterations in the algorithm, and its accelerated variant, called the inexact fast alternating minimization algorithm (inexact FAMA). We show that inexact AMA and inexact FAMA are equivalent to the inexact proximal-gradient method and its accelerated variant applied to the dual problem. Based on this equivalence, we derive complexity upper-bounds on the number of iterations for the inexact algorithms. We apply inexact AMA and inexact FAMA to distributed optimization problems, with an emphasis on distributed MPC applications, and show the convergence properties for this special case. By employing the complexity upper-bounds on the number of iterations, we provide sufficient conditions on the inexact iterations for the convergence of the algorithms. We further study the special case of quadratic local objectives in the distributed optimization problems, which is a standard form in distributed MPC. For this special case, we allow local computational errors at each iteration. By exploiting a warm-starting strategy and the sufficient conditions on the errors for convergence, we propose an approach to certify the number of iterations for solving local problems, which guarantees that the local computational errors satisfy the sufficient conditions and the inexact distributed optimization algorithm converges to the optimal solution.

math.OC↗

arXiv2015

An Alternating Trust Region Algorithm for Distributed Linearly Constrained Nonlinear Programs, Application to the AC Optimal Power Flow

A novel trust region method for solving linearly constrained nonlinear programs is presented. The proposed technique is amenable to a distributed implementation, as its salient ingredient is an alternating projected gradient sweep in place of the Cauchy point computation. It is proven that the algorithm yields a sequence that globally converges to a critical point. As a result of some changes to the standard trust region method, namely a proximal regularisation of the trust region subproblem, it is shown that the local convergence rate is linear with an arbitrarily small ratio. Thus, convergence is locally almost superlinear, under standard regularity assumptions. The proposed method is successfully applied to compute local solutions to alternating current optimal power flow problems in transmission and distribution networks. Moreover, the new mechanism for computing a Cauchy point compares favourably against the standard projected search as for its activity detection properties.

math.OC↗

arXiv2015

Guaranteeing Input Tracking For Constrained Systems: Theory and Application to Demand Response

A method for certifying exact input trackability for constrained discrete time linear systems is introduced in this paper. A signal is assumed to be drawn from a reference set and the system must track this signal with a linear combination of its inputs. Using methods inspired from robust model predictive control, the proposed approach certifies the ability of a system to track any reference drawn from a polytopic set on a finite time horizon by solving a linear program. Optimization over a parameterization of the set of reference signals is discussed, and particular instances of parameterization of this set that result in a convex program are identified, allowing one to find the largest set of trackable signals of some class. Infinite horizon feasibility of the methods proposed is obtained through use of invariant sets, and an implicit description of such an invariant set is proposed. These results are tailored for the application of power consumption tracking for loads, where the operator of the load needs to certify in advance his ability to fulfill some requirement set by the network operator. An example of a building heating system illustrates the results.

math.OC↗

arXiv2015

Quantization Design for Distributed Optimization

We consider the problem of solving a distributed optimization problem using a distributed computing platform, where the communication in the network is limited: each node can only communicate with its neighbours and the channel has a limited data-rate. A common technique to address the latter limitation is to apply quantization to the exchanged information. We propose two distributed optimization algorithms with an iteratively refining quantization design based on the inexact proximal gradient method and its accelerated variant. We show that if the parameters of the quantizers, i.e. the number of bits and the initial quantization intervals, satisfy certain conditions, then the quantization error is bounded by a linearly decreasing function and the convergence of the distributed algorithms is guaranteed. Furthermore, we prove that after imposing the quantization scheme, the distributed algorithms still exhibit a linear convergence rate, and show complexity upper-bounds on the number of iterations to achieve a given accuracy. Finally, we demonstrate the performance of the proposed algorithms and the theoretical findings for solving a distributed optimal control problem.

eess.SY↗

arXiv2015

Controller design and value function approximation for nonlinear dynamical systems

This work considers the infinite-time discounted optimal control problem for continuous time input-affine polynomial dynamical systems subject to polynomial state and box input constraints. We propose a sequence of sum-of-squares (SOS) approximations of this problem obtained by first lifting the original problem into the space of measures with continuous densities and then restricting these densities to polynomials. These approximations are tightenings, rather than relaxations, of the original problem and provide a sequence of rational controllers with value functions associated to these controllers converging (under some technical assumptions) to the value function of the original problem. In addition, we describe a method to obtain polynomial approximations from above and from below to the value function of the extracted rational controllers, and a method to obtain approximations from below to the optimal value function of the original problem, thereby obtaining a sequence of asymptotically optimal rational controllers with explicit estimates of suboptimality. Numerical examples demonstrate the approach.

math.OC↗