Iterative beam search algorithms for the permutation flowshop

TL;DR

This paper introduces an iterative beam search algorithm for permutation flowshop scheduling that combines branch-and-bound inspired strategies with LR heuristic guidance, achieving competitive results and new best solutions on key benchmarks.

Contribution

It presents a novel iterative beam search method that does not rely on NEH-based branching or iterative-greedy strategies, improving solution quality for flowshop scheduling.

Findings

Achieved many new-best-so-far solutions on VFR and Taillard benchmarks.

Obtained competitive results in makespan and flowtime minimization.

Source code is publicly available for reproducibility.

Abstract

We study an iterative beam search algorithm for the permutation flowshop (makespan and flowtime minimization). This algorithm combines branching strategies inspired by recent branch-and-bounds and a guidance strategy inspired by the LR heuristic. It obtains competitive results, reports many new-best-so-far solutions on the VFR benchmark (makespan minimization) and the Taillard benchmark (flowtime minimization) without using any NEH-based branching or iterative-greedy strategy. The source code is available at: https://gitlab.com/librallu/cats-pfsp.