Learning to Solve Resource-Constrained Project Scheduling Problems with Duration Uncertainty using Graph Neural Networks
Preprint
Abstract
The Resource-Constrained Project Scheduling Problem (RCPSP) is a classical scheduling problem that has received significant attention due to of its numerous applications in industry. However, in practice, task durations are subject to uncertainty that must be considered in order to propose resilient scheduling. In this paper, we address the RCPSP variant with uncertain tasks duration (modeled using known probabilities) and aim to minimize the overall expected project duration. Our objective is to produce a baseline schedule that can be reused multiple times in an industrial setting regardless of the actual duration scenario. We leverage Graph Neural Networks in conjunction with Deep Reinforcement Learning (DRL) to develop an effective policy for task scheduling. This policy operates similarly to a priority dispatch rule and is paired with a Serial Schedule Generation Scheme to produce a schedule. Our empirical evaluation on standard benchmarks demonstrates the approach's superiority in terms of performance and its ability to generalize. The developed framework, Wheatley, is made publicly available online to facilitate further research and reproducibility.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Fifty years of research on resource-constrained project scheduling explored from different perspectivesEuropean Journal of Operational Research, 2025
- Efficient optimization of robust project scheduling for industry 4.0: A hybrid approach based on machine learning and meta-heuristic algorithmsInternational Journal of Production Economics, 2024
- Surrogate-assisted cooperative learning genetic programming for the resource-constrained project scheduling problem with stochastic activity durations and transfer timesComputers & Operations Research, 2024
- An efficient genetic programming approach to design priority rules for resource-constrained project scheduling problemExpert Systems with Applications, 2022
- An updated survey of variants and extensions of the resource-constrained project scheduling problemEuropean Journal of Operational Research, 2022
- A multilayer feed-forward neural network (MLFNN) for the resource-constrained project scheduling problem (RCPSP)Decision Science Letters, 2022
- Ensembles of priority rules for resource constrained project scheduling problemApplied Soft Computing, 2021
- Automatic detection of the best performing priority rule for the resource-constrained project scheduling problemExpert Systems with Applications, 2021
- Insertion techniques for static and dynamic resource-constrained project schedulingEuropean Journal of Operational Research, 2003
- Serial and parallel resource-constrained project scheduling methods revisited: Theory and computationEuropean Journal of Operational Research, 1996