Investigation of the Generalisation Ability of Genetic Programming-evolved Scheduling Rules in Dynamic Flexible Job Shop Scheduling

2026-01-22

AI Summary

This study addresses the lack of systematic investigation into the cross-instance generalization capability of genetic programming (GP) for dynamic flexible job shop scheduling. Through multidimensional experiments, it systematically evaluates the generalization performance of GP-evolved dispatching rules across instances varying in scale, utilization, and data distribution. The work reveals, for the first time, that the number and distribution of decision points are critical factors influencing generalization, and demonstrates that structural similarity—particularly in terms of job count and machine configuration—between training and test instances plays a decisive role. Experimental results show that generalization performance improves significantly when training instances contain more jobs while keeping the number of machines fixed, and that greater similarity in decision point distributions leads to stronger cross-instance generalization.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Evolutionary Learning

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Dynamic Flexible Job Shop Scheduling (DFJSS) is a complex combinatorial optimisation problem that requires simultaneous machine assignment and operation sequencing decisions in dynamic production environments. Genetic Programming (GP) has been widely applied to automatically evolve scheduling rules for DFJSS. However, existing studies typically train and test GP-evolved rules on DFJSS instances of the same type, which differ only by random seeds rather than by structural characteristics, leaving their cross-type generalisation ability largely unexplored. To address this gap, this paper systematically investigates the generalisation ability of GP-evolved scheduling rules under diverse DFJSS conditions. A series of experiments are conducted across multiple dimensions, including problem scale (i.e., the number of machines and jobs), key job shop parameters (e.g., utilisation level), and data distributions, to analyse how these factors influence GP performance on unseen instance types. The results show that good generalisation occurs when the training instances contain more jobs than the test instances while keeping the number of machines fixed, and when both training and test instances have similar scales or job shop parameters. Further analysis reveals that the number and distribution of decision points in DFJSS instances play a crucial role in explaining these performance differences. Similar decision point distributions lead to better generalisation, whereas significant discrepancies result in a marked degradation of performance. Overall, this study provides new insights into the generalisation ability of GP in DFJSS and highlights the necessity of evolving more generalisable GP rules capable of handling heterogeneous DFJSS instances effectively.

Problem

• Dynamic Flexible Job Shop Scheduling
• Genetic Programming
• Generalisation Ability
• Scheduling Rules
• Combinatorial Optimisation

Innovation

• Generalisation
• Genetic Programming
• Dynamic Flexible Job Shop Scheduling
• Decision Point Distribution
• Cross-type Transfer