Ecosystem-oriented distributed evolutionary computing

Abstract

Abstract-We create a novel optimisation technique inspired by natural ecosystems, where the optimisation works at two levels: a first optimisation, migration of genes which are distributed in a peer-to-peer network, operating continuously in time; this process feeds a second optimisation based on evolutionary computing that operates locally on single peers and is aimed at finding solutions to satisfy locally relevant constraints. We consider from the domain of computer science distributed evolutionary computing, with the relevant theory from the domain of theoretical biology, including the fields of evolutionary and ecological theory, the topological structure of ecosystems, and evolutionary processes within distributed environments. We then define ecosystemoriented distributed evolutionary computing, imbibed with the properties of self-organisation, scalability and sustainability from natural ecosystems, including a novel form of distributed evolutionary computing. Finally, we conclude with a discussion of the apparent compromises resulting from the hybrid model created, such as the network topology.

Bridging Ecology and Cloud: Transposing Ecological Perspective to Enable Better Cloud Autoscaling

“…Briscoe and Wilde [2] intend to apply ecological thinking to create scalable and selforganizing approaches for distributed evolutionary computing. The aim is to maintain a stable evolution of the processes in distributed environment, i.e., what processes should run independently or incorrporately.…”

“…There have been some successful attempts in applying ecological principles, theories and models to address issues in computer science. Examples can be found in the area of software engineering [15], collaborative adaptive systems [1] [14], distributed computing [2] and grid computing [9]. However, there have been very limited efforts on adopting ecological view for cloud autoscaling.…”

The Computing of Digital Ecosystems

“…These agents then feed a second optimisation level based on an evolutionary algorithm that operates locally on single habitats (peers), aiming to find solutions that satisfy locally relevant constraints. The local search is sped up through this twofold process, providing better local optima as the distributed optimisation provides prior sampling of the search space by making use of computations already performed in other peers with similar constraints (Briscoe, Chli, & Vidal, 2006). So, the Digital Ecosystem supports the automatic combining of numerous agents (which represent services), by their interaction in evolving populations to meet user requests for applications, in a scalable architecture of distributed interconnected habitats.…”