b c

Dr. b c


Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 March 2019 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
JWJoseph Warrington
Joseph Warrington
PBPaul Nathaniel Beuchat
Paul Nathaniel Beuchat
JLJohn Lygeros
John Lygeros
We describe a nonlinear generalization of dual dynamic programming theory and its application to value function estimation for deterministic control problems over continuous state and action spaces, in a discrete-time infinite horizon setting. We prove, using a Benders-type argument leveraging the monotonicity of the Bellman operator, that the result of a one-stage policy evaluation can be used to produce nonlinear lower bounds on the optimal value function that are valid over the entire state space. These bounds contain terms reflecting the functional form of the system's costs, dynamics, and constraints. We provide an iterative algorithm that produces successively better approximations of the optimal value function, and prove under certain assumptions that it achieves an arbitrarily low desired Bellman optimality tolerance at pre-selected points in the state space, in a finite number of iterations. We also describe means of certifying the quality of the value function generated. We demonstrate the efficacy of the approach on systems whose dimensions are too large for conventional dynamic programming approaches to be practical.

25 October 2018 in IEEE Transactions on Power Systems
Verified
Journal Article
Closed access
MHMarc Hohmann
Marc Hohmann
JWJoseph Warrington
Joseph Warrington
JLJohn Lygeros
John Lygeros
Linearized models of power systems are often desirable to formulate tractable control and optimization problems that still reflect real-world physics adequately under various operating conditions. In this paper, we propose an approach that can make use of known data concerning the distribution of demand, and/or intermittent supply, to minimize expected model inconsistency with respect to the original non-linear model. The optimal linearization is obtained by approximating a generalized moment problem with a hierarchy of sparse semi-definite relaxations. The output is a linearization point that minimizes the expected absolute constraint violation with respect to the uncertain supply and demand. Numerical results for different power systems networks demonstrate the accuracy and scalability of our linearization method.

27 June 2017 in IEEE Control Systems Letters
Verified
Journal Article
Closed access
JWJoseph Warrington
Joseph Warrington
DDDaniel Drew
Daniel Drew
JLJohn Lygeros
John Lygeros
Many predictive control problems can be solved at lower cost if the practitioner is able to make use of a high-dimensional forecast of exogenous uncertain quantities. For example, power system operators must accommodate significant short-term uncertainty in renewable energy infeeds. These are predicted using sophisticated numerical weather models, which produce an ensemble of scenarios for the evolution of atmospheric conditions. We describe a means of incorporating such forecasts into a multistage optimization framework able to make use of spatial and temporal correlation information. We derive an optimal procedure for reducing the size of the look-ahead problem by generating a low-dimensional representation of the uncertainty, while still retaining as much information as possible from the raw forecast data. We then demonstrate application of this technique to a model of the Great Britain grid in 2030, driven by the raw output of a real-world highdimensional weather forecast from the U.K. Met Office. We also discuss applications of the approach beyond power systems.

11 January 2021 in IEEE Transactions on Automatic Control
Verified
Journal Article
Open access
PBPaul Nathaniel Beuchat
Paul Nathaniel Beuchat
JWJoseph Warrington
Joseph Warrington
JLJohn Lygeros
John Lygeros
In this article, we describe an approximate dynamic programming (ADP) approach to compute lower bounds on the optimal value function for a discrete time, continuous space, and infinite horizon setting. The approach iteratively constructs a family of lower bounding approximate value functions by using the so-called Bellman inequality. The novelty of our approach is that, at each iteration, we aim to compute an approximate value function that maximizes the point-wise maximum taken with the family of approximate value functions computed thus far. This leads to a nonconvex objective, and we propose a gradient ascent algorithm to find stationary points by solving a sequence of convex optimization problems. We provide convergence guarantees for our algorithm and an interpretation for how the gradient computation relates to the state-relevance weighting parameter appearing in related ADP approaches. We demonstrate through numerical examples that, when compared to the existing approaches, the algorithm we propose computes tighter suboptimality bounds with comparable computation time.

23 January 2020 in IEEE Transactions on Control Systems Technology
Verified
Journal Article
Closed access
BFBenjamin Flamm
Benjamin Flamm
AEAnnika Eichler
Annika Eichler
JWJoseph Warrington
Joseph Warrington
JLJohn Lygeros
John Lygeros
We present an approximate method for solving nonlinear control problems over long time horizons, in which the full nonlinear model is preserved over an initial part of the horizon, while the remainder of the horizon is modeled using a linear relaxation. As this approximate problem may still be too large to solve directly, we present a Benders decomposition-based solution algorithm that iterates between solving the nonlinear and linear parts of the horizon. This extends the dual dynamic programming approach commonly employed for optimization of linearized hydro power systems. We prove that the proposed algorithm converges after a finite number of iterations, even when the nonlinear initial stage problems are solved inexactly. We also bound the suboptimality of the split-horizon method with respect to the original nonlinear problem, in terms of the properties of a map between the linear and nonlinear state-input trajectories. We then apply this method to a case study concerning a multiple reservoir hydro system, approximating the nonlinear head effects in the second stage using McCormick envelopes. We demonstrate that near-optimal solutions can be obtained in a shrinking horizon setting when the full nonlinear model is used for only a short initial section of the horizon. For this example, the approach is shown to be more practical than both conventional dynamic programming and a multi-cell McCormick envelope approximation from the literature.

1 June 2014
Verified
Conference Paper
Closed access
JWJoseph Warrington
Joseph Warrington
CHChristian Hohl
Christian Hohl
PGPaul J. Goulart
Paul J. Goulart
MMManfred Morari
Manfred Morari
We describe a new approach to robust unit commitment for an electricity network, which couples the switching decisions to a set of time-coupled redispatch rules in order to minimize the expected cost of operation over a planning horizon. We assume bounded uncertainties arising from imperfect predictions of loads and intermittent renewable infeeds. We refer to the time-coupled redispatch rules as affine reserve policies, and they apply not only to generators but to other continuously-controllable devices such as energy storage units or demand response installations, which are modelled as generic mixed logical-dynamical systems. We use a lumped-parameter example to demonstrate that unit commitment decisions coupled with affine reserve policies can reduce the number of time periods in which expensive peaking plants need to be employed, and that the effect is present for a wide range of parameter values. An important benefit is that the approach allows the uncertainty of future energy storage levels to be managed more tightly than existing formulations would allow.