Neural Combinatorial Optimization for Stochastic Flexible Job Shop Scheduling Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Smit, Igor G., Wu, Yaoxin, Troubil, Pavel, Zhang, Yingqian, Nuijten, Wim P. M.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916531037798400
author Smit, Igor G.
Wu, Yaoxin
Troubil, Pavel
Zhang, Yingqian
Nuijten, Wim P. M.
author_facet Smit, Igor G.
Wu, Yaoxin
Troubil, Pavel
Zhang, Yingqian
Nuijten, Wim P. M.
contents Neural combinatorial optimization (NCO) has gained significant attention due to the potential of deep learning to efficiently solve combinatorial optimization problems. NCO has been widely applied to job shop scheduling problems (JSPs) with the current focus predominantly on deterministic problems. In this paper, we propose a novel attention-based scenario processing module (SPM) to extend NCO methods for solving stochastic JSPs. Our approach explicitly incorporates stochastic information by an attention mechanism that captures the embedding of sampled scenarios (i.e., an approximation of stochasticity). Fed with the embedding, the base neural network is intervened by the attended scenarios, which accordingly learns an effective policy under stochasticity. We also propose a training paradigm that works harmoniously with either the expected makespan or Value-at-Risk objective. Results demonstrate that our approach outperforms existing learning and non-learning methods for the flexible JSP problem with stochastic processing times on a variety of instances. In addition, our approach holds significant generalizability to varied numbers of scenarios and disparate distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14052
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Neural Combinatorial Optimization for Stochastic Flexible Job Shop Scheduling Problems
Smit, Igor G.
Wu, Yaoxin
Troubil, Pavel
Zhang, Yingqian
Nuijten, Wim P. M.
Artificial Intelligence
Machine Learning
Optimization and Control
Neural combinatorial optimization (NCO) has gained significant attention due to the potential of deep learning to efficiently solve combinatorial optimization problems. NCO has been widely applied to job shop scheduling problems (JSPs) with the current focus predominantly on deterministic problems. In this paper, we propose a novel attention-based scenario processing module (SPM) to extend NCO methods for solving stochastic JSPs. Our approach explicitly incorporates stochastic information by an attention mechanism that captures the embedding of sampled scenarios (i.e., an approximation of stochasticity). Fed with the embedding, the base neural network is intervened by the attended scenarios, which accordingly learns an effective policy under stochasticity. We also propose a training paradigm that works harmoniously with either the expected makespan or Value-at-Risk objective. Results demonstrate that our approach outperforms existing learning and non-learning methods for the flexible JSP problem with stochastic processing times on a variety of instances. In addition, our approach holds significant generalizability to varied numbers of scenarios and disparate distributions.
title Neural Combinatorial Optimization for Stochastic Flexible Job Shop Scheduling Problems
topic Artificial Intelligence
Machine Learning
Optimization and Control
url https://arxiv.org/abs/2412.14052