Entropy-Regulated Job-Shop Scheduling: A Bottom–Up Artificial Bee Colony Algorithm for Semiconductor Manufacturing

Abstract

This paper addresses the Job-Shop Scheduling Problem in dynamic semiconductor manufacturing environments by proposing a decentralized, bottom-up Artificial Bee Colony (ABC) scheduling algorithm. Machines and lots are modeled as autonomous agents whose local interactions give rise to system-level scheduling behavior. Alongside classical scheduling objectives, the proposed approach focuses on regulating production dynamics by maintaining sufficient diversity in machine queues, formalized through entropy-based measures. Bottlenecks are treated not only as a consequence of static capacity constraints relative to work in progress, but also as emergent effects of short-term demand concentration, where multiple lots converge toward the same resources within limited time horizons. To manage these effects, a fitness formulation is introduced that promotes balanced queue states through local decision-making. Scheduling foresight is incorporated via a Look-Ahead Window, while uncertainty in distant future routing is accounted for using a decay factor, jointly enabling adaptive prioritization under bounded computational effort. Simulation-based evaluation across fabrication scenarios of increasing scale shows that the method achieves modest improvements in Flow Factor and Tardiness, while inducing an expected trade-off in Makespan under higher load conditions. More importantly, analysis of queue-level dynamics reveals more regular behavior in the evaluated scenarios, with reduced fluctuations in queue lengths, batch waiting, and minimum queue entropy over time. These results indicate that the proposed ABC-based approach can improve observed predictability at the queue level, offering a complementary perspective to performance-driven scheduling in highly dynamic environments.