Designing complex, self-organising systems is challenging. It requires to design local, decentralised rules for the agents which result in a good global performance of the overall system. In this talk, we look at a self-organising semiconductor manufacturing system where local dispatching rules are used for decentralised scheduling. We show how Genetic Programming, combined with a simulation model to evaluate candidate solutions, can be used to automatically generate dispatching rules that outperform even the best dispatching rules from the literature.


Juergen Branke

Evolutionary computation methods e-session