Surrogate-Assisted Evolutionary Multitask Genetic Programming for Dynamic Flexible Job Shop Scheduling

Dynamic flexible job shop scheduling (JSS) is an important combinatorial optimization problem with complex routing and sequencing decisions under dynamic environments. Genetic programming (GP), as a hyperheuristic approach, has been successfully applied to evolve heuristics for JSS. However, its training process time consuming, it faces the retraining once characteristics of scenarios vary. It known that multitask learning promising paradigm solving multiple tasks simultaneously by sharing knowledge among tasks. To improve efficiency effectiveness, this article proposes novel surrogate-assisted evolutionary algorithm via GP share useful between different Specifically, we employ phenotypic characterization measuring behaviors rules building surrogate each task accordingly. The built surrogates are used not only single but also transfer in large number individuals. results show proposed can significantly quality all scenarios. In addition, manages solve collaboratively terms evolved scenario.