An artificial immune ecosystem model for hybrid cloud supervision

In this paper, we propose an Artificial Immune Ecosystem (AIE) model derived from the concepts of AIS and adapted to the supervision of performance rather than security of complex and heterogeneous infrastructures found in hybrid cloud networks. We explicit the architectural properties of such a framework, which exploits distributed analysis and reaction ability and enforces efficient sensing process through targeted probes. In particular, we use the low variability of the measured data to derive statistical approaches to outlier detection, instead of a stochastic antibody generation and selection algorithm. By reducing the number of signatures to be matched, we reduce the overall computations required to operate the system, therefore allowing its deployment on low-end monitoring servers or virtual machines.