Simulation-based optimization for groups of cluster tools in semiconductor manufacturing using simulated annealing

Authors:
Tobias Uhlig;Oliver Rose
Affiliations:
Dresden University of Technology, Dresden, Germany;Dresden University of Technology, Dresden, Germany
Venue:
Proceedings of the Winter Simulation Conference
Year:
2011

Citing 5
Cited 0

Using simulation and genetic algorithms to improve cluster tool performance

Proceedings of the 31st conference on Winter simulation: Simulation---a bridge to the future - Volume 1
Simulated Annealing: A Proof of Convergence

IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to Evolutionary Computing

Introduction to Evolutionary Computing
Predicting cluster tool behavior with slow down factors

Proceedings of the 39th conference on Winter simulation: 40 years! The best is yet to come
Automated generation of analytical process time models for cluster tools in semiconductor manufacturing

Proceedings of the Winter Simulation Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

Simulation-based optimization is an established approach to handle complex scheduling problems. The problem examined in this study is scheduling jobs for groups of cluster tools in semiconductor manufacturing including a combination of sequencing, partitioning, and grouping of jobs with additional constraints. We use a specialized fast simulator to evaluate the generated schedules which allows us to run a large number of optimization iterations. For optimization we propose a simulated annealing algorithm to generate the schedules. It is implemented as a special instance of our adaptable evolutionary algorithm framework. As a consequence it is easy to adapt and extend the algorithm. For example, we can make use of various already existing problem representations that are geared to excel at certain aspects of our problem. Furthermore, we are able to parallelize the algorithm by using a population of optimization runs.