What the study found
The study found that an online genetic programming framework can learn scheduling strategies directly in the operating environment and perform well on dynamic flexible job shop scheduling problems, which involve flexible job shops where jobs can be assigned to different machines and routing can change.
Why the authors say this matters
The authors say this matters because the approach does not rely on prior knowledge or an explicit simulation model, and they describe it as a robust and generalisable optimisation framework for dynamic decision-making in changing environments.
What the researchers tested
The researchers developed an Online Genetic Programming (OGP) framework with an adaptive fitness function that combines real-time performance feedback with predictive evaluation from a phenotypic archive, plus a pre-selection strategy and a soft restart mechanism. They tested it on dynamic flexible job shop scheduling (DFJSP) problems as representative environments.
What worked and what didn't
In the experiments, OGP outperformed existing scheduling algorithms when scheduling and routing decisions were considered together. As an automated heuristic design method, it also generated competitive rules compared with state-of-the-art genetic programming methods in test performance and the size of evolved rules.
What to keep in mind
The abstract does not describe detailed limitations, specific datasets, or failure cases. The findings are presented for DFJSP test environments, so the scope described in the abstract is limited to that setting.
Key points
- The study reports an online genetic programming framework that learns scheduling strategies in the operating environment.
- The method was tested on dynamic flexible job shop scheduling problems.
- OGP outperformed existing scheduling algorithms when scheduling and routing decisions were considered together.
- The authors say the approach does not rely on prior knowledge or an explicit simulation model.
- The abstract says the paper does not describe detailed limitations or failure cases.
Disclosure
- Research title:
- Online genetic programming improved scheduling in dynamic job shops
- Authors:
- Su Nguyen, Binh Tran, Xuan Nam Ngo, Duy Thinh Tran
- Institutions:
- RMIT University, La Trobe University, The University of Melbourne
- Publication date:
- 2026-02-23
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with peer-reviewed research without reading academic papers — one filtered digest, every Friday.