Leveraging Genetic Algorithm to Refine Genetic Programming-Evolved Dispatching Rules for Flexible Job Shop Scheduling

Created by W.Langdon from gp-bibliography.bib Revision:1.8592

@InProceedings{salama:2025:GECCOcomp,

• author = "Shady Salama and Mate Kovacs",
• title = "Leveraging Genetic Algorithm to Refine Genetic Programming-Evolved Dispatching Rules for Flexible Job Shop Scheduling",
• booktitle = "Proceedings of the 2025 Genetic and Evolutionary Computation Conference Companion",
• year = "2025",
• editor = "Dirk Thierens and Elizabeth Wanner",
• pages = "535--538",
• address = "Malaga, Spain",
• series = "GECCO '25 Companion",
• month = "14-18 " # jul,
• organisation = "SIGEVO",
• publisher = "Association for Computing Machinery",
• publisher_address = "New York, NY, USA",
• keywords = "genetic algorithms, genetic programming, flexible job shop scheduling problem, dispatching rules, hyper-heuristics: Poster",
• isbn13 = "979-8-4007-1464-1",
• URL = "https://doi.org/10.1145/3712255.3726592",
• DOI = "doi:10.1145/3712255.3726592",
• size = "4 pages",
• abstract = "The Flexible Job Shop Scheduling Problem (FJSSP) is a complex combinatorial optimization problem with applications in manufacturing and cloud computing. Designing effective dispatching rules manually is time-consuming and requires expertise. Genetic Programming (GP) can evolve rules automatically but lacks mechanisms to prioritize important features. This paper proposes GPGA, a hybrid approach combining GP with a Genetic Algorithm (GA) to optimize feature weights and enhance rule quality. Leaf nodes are augmented with weight parameters, which GA evolves to minimize a scheduling objective. Weight refinement is applied to high quality rules every ten GP generations. Experiments on ten benchmark instances show that GPGA significantly reduces total weighted tardiness, outperforms a gradient-based GP method (GPGD) in two cases, lowers computational time in five instances, matches GPGD in test-time efficiency, and converges faster in training. These results highlight the benefits of integrating GA into GP for automated scheduling.",
• notes = "GECCO-2025 GA A Recombination of the 34th International Conference on Genetic Algorithms (ICGA) and the 30th Annual Genetic Programming Conference (GP)",

}

Genetic Programming entries for Shady Salama Mate Kovacs

Citations