Efficient Network Reconfiguration by Randomized Switching

TL;DR

This paper introduces a randomized switching algorithm for efficiently approximating solutions to complex network reconfiguration problems, outperforming traditional solvers in speed and scalability.

Contribution

The paper presents a novel randomized switching method that efficiently approximates solutions to NP-hard network reconfiguration problems using self-concordant functions and conditional gradient methods.

Findings

Outperforms state-of-the-art MISOCP solver by orders of magnitude

Efficiently finds nearly-optimal network configurations

Applicable to large-scale infrastructure network problems

Abstract

We present an algorithm that efficiently computes nearly-optimal solutions to a class of combinatorial reconfiguration problems on weighted, undirected graphs. Inspired by societally relevant applications in networked infrastructure systems, these problems consist of simultaneously finding an unreweighted sparsified graph and nodal potentials that satisfy fixed demands, where the objective is to minimize some congestion criterion, e.g., a Laplacian quadratic form. These are mixed-integer nonlinear programming problems that are NP-hard in general. To circumvent these challenges, instead of solving for a single best configuration, the proposed randomized switching algorithm seeks to design a distribution of configurations that, when sampled, ensures that congestion concentrates around its optimum. We show that the proposed congestion metric is a generalized self-concordant function in the space of switching probabilities, which enables the use of efficient and simple conditional gradient methods. We implement our algorithm and show that it outperforms a state-of-the-art commercial mixed-integer second-order cone programming (MISOCP) solver by orders of magnitude over a large range of problem sizes.