Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop Scheduling

TL;DR

This paper introduces L-RHO, a learning-guided rolling horizon optimization framework that improves efficiency and solution quality for long-horizon flexible job-shop scheduling problems by intelligently fixing variables using neural networks.

Contribution

L-RHO is the first framework to integrate learning into RHO for COPs, reducing redundant computations and enhancing performance on FJSP.

Findings

L-RHO accelerates RHO by up to 54%.

L-RHO outperforms heuristic and learning baselines.

L-RHO demonstrates strong adaptability and generalization.

Abstract

Long-horizon combinatorial optimization problems (COPs), such as the Flexible Job-Shop Scheduling Problem (FJSP), often involve complex, interdependent decisions over extended time frames, posing significant challenges for existing solvers. While Rolling Horizon Optimization (RHO) addresses this by decomposing problems into overlapping shorter-horizon subproblems, such overlap often involves redundant computations. In this paper, we present L-RHO, the first learning-guided RHO framework for COPs. L-RHO employs a neural network to intelligently fix variables that in hindsight did not need to be re-optimized, resulting in smaller and thus easier-to-solve subproblems. For FJSP, this means identifying operations with unchanged machine assignments between consecutive subproblems. Applied to FJSP, L-RHO accelerates RHO by up to 54% while significantly improving solution quality, outperforming other heuristic and learning-based baselines. We also provide in-depth discussions and verify the desirable adaptability and generalization of L-RHO across numerous FJSP variates, distributions, online scenarios and benchmark instances. Moreover, we provide a theoretical analysis to elucidate the conditions under which learning is beneficial.