arXiv subjects

Anirudh Subramanyam

Publications and source records attributed to Anirudh Subramanyam.

24 records · Page 2Linked to original sources

arXiv2022

Joint Routing of Conventional and Range-Extended Electric Vehicles in a Large Metropolitan Network

Range-extended electric vehicles combine the higher efficiency and environmental benefits of battery-powered electric motors with the longer mileage and autonomy of conventional internal combustion engines. This combination is particularly advantageous for time-constrained delivery routing in dense urban areas, where battery recharging along routes can be too time-consuming to economically justify the use of all-electric vehicles. However, switching from electric to conventional fossil fuel modes also results in higher costs and emissions and lower efficiency. This paper analyzes this heterogeneous vehicle routing problem and describes two solution methods: an exact branch-price-and-cut algorithm and an iterated tabu search metaheuristic. From a methodological perspective, we find that the exact algorithm consistently obtains tight lower bounds that also serve to certify the metaheuristic solutions as near-optimal. From a policy standpoint, we examine a large-scale real-world case study concerning parcel deliveries in the Chicago metropolitan area and quantify various operational metrics including energy costs and vehicle miles traveled. We find that by deploying roughly 20% of range-extended vehicles with a modest all-electric range of 33 miles, parcel distributors can save energy costs by up to 17% while incurring less than 0.5% increase in vehicle miles traveled. Increasing the range to 60 miles further reduces costs by only 4%, which can alternatively be achieved by decreasing the average service time by 1 minute or increasing driver working time by 1 hour. Our study reveals several key areas of improvement on which vehicle manufacturers, distributors, and policy makers can focus their attention.

math.OC↗

arXiv2021

A Globally Convergent Distributed Jacobi Scheme for Block-Structured Nonconvex Constrained Optimization Problems

Motivated by the increasing availability of high-performance parallel computing, we design a distributed parallel algorithm for linearly-coupled block-structured nonconvex constrained optimization problems. Our algorithm performs Jacobi-type proximal updates of the augmented Lagrangian function, requiring only local solutions of separable block nonlinear programming (NLP) problems. We provide a cheap and explicitly computable Lyapunov function that allows us to establish global and local sublinear convergence of our algorithm, its iteration complexity, as well as simple, practical and theoretically convergent rules for automatically tuning its parameters. This in contrast to existing algorithms for nonconvex constrained optimization based on the alternating direction method of multipliers that rely on at least one of the following: Gauss-Seidel or sequential updates, global solutions of NLP problems, non-computable Lyapunov functions, and hand-tuning of parameters. Numerical experiments showcase its advantages for large-scale problems, including the multi-period optimization of a 9000-bus AC optimal power flow test case over 168 time periods, solved on the Summit supercomputer using an open-source Julia code.

math.OC↗

arXiv2021

Data-driven two-stage conic optimization with zero-one uncertainties

We address high-dimensional zero-one random parameters in two-stage convex conic optimization problems. Such parameters typically represent failures of network elements and constitute rare, high-impact random events in several applications. Given a sparse training dataset of the parameters, we motivate and study a distributionally robust formulation of the problem using a Wasserstein ambiguity set centered at the empirical distribution. We present a simple, tractable, and conservative approximation of this problem that can be efficiently computed and iteratively improved. Our method relies on a reformulation that optimizes over the convex hull of a mixed-integer conic programming representable set, followed by an approximation of this convex hull using lift-and-project techniques. We illustrate the practical viability and strong out-of-sample performance of our method on nonlinear optimal power flow and multi-commodity network design problems that are affected by random contingencies, and we report improvements of up to 20\% over existing sample average approximation and two-stage robust optimization methods.

math.OC↗

arXiv2018

Robust optimization of a broad class of heterogeneous vehicle routing problems under demand uncertainty

This paper studies robust variants of an extended model of the classical Heterogeneous Vehicle Routing Problem (HVRP), where a mixed fleet of vehicles with different capacities, availabilities, fixed costs and routing costs is used to serve customers with uncertain demand. This model includes, as special cases, all variants of the HVRP studied in the literature with fixed and unlimited fleet sizes, accessibility restrictions at customer locations, as well as multiple depots. Contrary to its deterministic counterpart, the goal of the robust HVRP is to determine a minimum-cost set of routes and fleet composition that remains feasible for all demand realizations from a pre-specified uncertainty set. To solve this problem, we develop robust versions of classical node- and edge-exchange neighborhoods that are commonly used in local search and establish that efficient evaluation of the local moves can be achieved for five popular classes of uncertainty sets. The proposed local search is then incorporated in a modular fashion within two metaheuristic algorithms to determine robust HVRP solutions. The quality of the metaheuristic solutions is quantified using an integer programming model that provides lower bounds on the optimal solution. An extensive computational study on literature benchmarks shows that the proposed methods allow us to obtain high quality robust solutions for different uncertainty sets and with minor additional effort compared to deterministic solutions.

math.OC↗

arXiv2018

A Scenario Decomposition Algorithm for Strategic Time Window Assignment Vehicle Routing Problems

We study the strategic decision-making problem of assigning time windows to customers in the context of vehicle routing applications that are affected by operational uncertainty. This problem, known as the Time Window Assignment Vehicle Routing Problem, can be viewed as a two-stage stochastic optimization problem, where time window assignments constitute first-stage decisions, vehicle routes adhering to the assigned time windows constitute second-stage decisions, and the objective is to minimize the expected routing costs. We prove that a sampled deterministic equivalent of this stochastic model can be reduced to a variant of the Consistent Vehicle Routing Problem, and we leverage this result to develop a new scenario decomposition algorithm to solve it. From a modeling viewpoint, our approach can accommodate both continuous and discrete sets of feasible time window assignments as well as general scenario-based models of uncertainty for several routing-specific parameters, including customer demands and travel times, among others. From an algorithmic viewpoint, our approach can be easily parallelized, can utilize any available vehicle routing solver as a black box, and can be readily modified as a heuristic for large-scale instances. We perform a comprehensive computational study to demonstrate that our algorithm strongly outperforms all existing solution methods, as well as to quantify the trade-off between computational tractability and expected cost savings when considering a larger number of future scenarios during strategic time window assignment.

math.OC↗

arXiv2018

K-Adaptability in Two-Stage Mixed-Integer Robust Optimization

We study two-stage robust optimization problems with mixed discrete-continuous decisions in both stages. Despite their broad range of applications, these problems pose two fundamental challenges: (i) they constitute infinite-dimensional problems that require a finite-dimensional approximation, and (ii) the presence of discrete recourse decisions typically prohibits duality-based solution schemes. We address the first challenge by studying a $K$-adaptability formulation that selects $K$ candidate recourse policies before observing the realization of the uncertain parameters and that implements the best of these policies after the realization is known. We address the second challenge through a branch-and-bound scheme that enjoys asymptotic convergence in general and finite convergence under specific conditions. We illustrate the performance of our algorithm in numerical experiments involving benchmark data from several application domains.

math.OC↗