A Bayesian Optimization-based Evolutionary Algorithm for Flexible Job Shop Scheduling

Abstract

Flexible Job-shop Scheduling Problem (fJSP) is a typical and important scheduling problem in Flexible Manufacturing System (FMS). The fJSP is an extended version of Job-shop Scheduling (JSP) that is NP hard problem. Due to it according with the real production system, we adopt a hybrid evolutionary computation algorithm to solve the fJSP problems. Among them, the Bayesian Optimization Algorithm (BOA) is introduced to the characteristics of scheduling and uncertainty characteristics of the time in the fJSP. On this basis, we propose a distributed evolutionary algorithm and parameter adaptive mechanism. Finally, through experiments, we conclude that the proposed hybrid evolutionary algorithm based on BOA with grouping mechanism get better solution than original algorithm and improve robustness of algorithm. Meanwhile, the paper also have objective perspective, that is we can group the data different from each other, make the whole population into sub-populations, and then make the experiment separately on different and parallel machines in distributed environment, so that not only optimizes the best solution, but also enhance the efficiency and shortened the time.