Evolutionary and embryogenic approaches to autonomic systems
Proceedings of the 3rd International Conference on Performance Evaluation Methodologies and Tools
In this paper we present a review of state-of-the-art techniques for automated creation and evolution of software. The focus is on bio-inspired bottom-up approaches, in which complexity is grown from interactions among simpler units. First, we review Evolutionary Computation (EC) techniques, highlighting their potential application to the automated optimization of computer programs in an online, dynamic environment. Then, we survey approaches inspired by embryology, in which artificial entities
... artificial entities undergo a developmental process. We introduce the concept of EmbryoWare to refer to software that can be modified via an embryogenic process. We refer to Evolutionary Developmental Computation as the combined evo-devo approach in software, and describe its constituent elements. The paper concludes with a short discussion and outlook for applications of the aforementioned techniques to autonomic computing and communication systems. * This work has been partially funded by the European Commission within the framework of the BIONETS project EU-IST-FET-SAC-FP6-027748, www.bionets.eu.