Adaptive virtual infrastructure planning over interconnected IT and optical network resources using evolutionary game theory

This paper focuses on integrated optical network and IT infrastructures in support of the Future Internet and its new emerging applications. In this context, the concept of virtualization of the physical infrastructure is proposed and the process of virtual infrastructure planning is discussed. A novel optimization scheme suitable to adaptively plan virtual infrastructures employing evolutionary game theory is presented and compared to conventional centralized approaches. Our evolutionary game theory modelling results clearly show, that given sufficient time to learn the status of the underlying physical topology the virtual infrastructures planned have similar performance to those generated through traditional global optimization approaches such as integer linear programming.