Using a Machine Learning Algorithm to Control an Artificial Hormone System

The Artificial Hormone System (AHS) is a decentralized software which can be used to allocate tasks in a system of heterogeneous processing elements (PEs). Tasks are allocated according to their suitability for the heterogeneous PEs, the current PE load and task relationships. The AHS also provides properties like self-configuration, self-optimization and self-healing in the context of task allocation. In addition, it is able to guarantee real-time bounds for such self-X-properties. Our contribution in this paper is a machine learning approach for gradually learning the hormone values of different tasks. This is a major advance because expert knowledge is needed to configure the AHS up to now. We present an Observer-/Controller architecture monitoring and controlling the behaviour of the AHS. The user has to provide a simple set of initial rules and the Observer-/Controller is able to generate new rules if needed. The evaluation of our approach is very promising and we show and discuss our evaluation.