Adapting to Run-Time Changes in Policies Driving Autonomic Management

Abstract

The use of policies within autonomic computing has received significant interest in the recent past. Policy-driven management offers significant benefit since it makes it more straight forward to define and modify systems behavior at run-time, through policy manipulation, rather than through re- engineering. In this paper, we present an adaptive policy-driven autonomic management system which makes use of reinforcement learning methodologies to determine how to best use a set of active policies to meet different performance objectives. The focus, in particular, is on strategies for adapting what has been learned for one set of policy actions to a ";similar"; set of policies when run-time policy modifications occur. We illustrate the impact of the adaptation strategies on the behavior of a multi-component Web server.