Building Self-Configuring Data Centers with Cross Layer Coevolution

This paper describes a biologically-inspired architecture, called SymbioticSphere, which allows data centers to autonomously adapt to dynamic environmental changes. SymbioticSphere follows biological principles such as decentralization, evolution and symbiosis to design application services and middleware platforms in a data center. Each service and platform is designed as a biological entity, and implements biological behaviors such as energy exchange, migration, reproduction and death. Each service/platform also possesses behavior policies, as genes, each of which defines when to and how to invoke a particular behavior. This paper presents a set of behaviors for services and platforms, and describes how services and platforms act and interact with each other. Simulation results show that services and platforms autonomously adapt to dynamic network conditions (e.g., user location, network traffic and resource availability) by evolving their behavior policies across generations. Simulation results also show that services and platforms coevolve to improve their adaptability by adjusting their behavior policies cooperatively.