Computationally-Efficient Decomposition Heuristic for the Static Traffic Assignment Problem

TL;DR

This paper introduces a decomposition heuristic for large-scale traffic assignment problems that significantly reduces computation time by partitioning networks and refining solutions iteratively, improving efficiency in megaregional planning.

Contribution

A novel decomposition heuristic with a three-stage algorithm and network transformation for efficient large-scale traffic assignment problem solving.

Findings

Achieves 15.1-67.8% computational savings.

Reduces initial relative gap to 0.02.

Enhances standard TAP algorithms with 10-35% savings when warmstarted.

Abstract

Applications such as megaregional planning require efficient methods for solving traffic assignment problems (TAPs) on large-scale networks. We propose a decomposition heuristic that generates approximate TAP solutions by partitioning the complete network into subnetworks which are solved in parallel and use an iterative-refinement algorithm for improving the network partitions. A novel network transformation and three-stage algorithm are also proposed to solve a constrained shortest path problem as a subproblem of the heuristic. Experiments on various networks show that the heuristic can generate 15.1-67.8% computational savings in finding solutions with initial relative gap of 0.02. The performance benefits of the proposed heuristic when warmstarting standard TAP algorithms are demonstrated with an average computational savings of 10-35% over a TAP solver without warmstarting.