Optimization of Decision Making in CBR Based Self-Healing Systems

Abstract

Autonomic systems are the software systems capable to manage themselves. These systems undergo a learning process to achieve this capability. Case-based reasoning (CBR) is one of the promising learning paradigms for autonomic managers. Autonomic managers monitor the pulse of the monitored system on periodic basis and analyze the captured state of the system. In case of a problematic state, autonomic managers use their CBR based decision support system to rectify the problem. One of the critical problems in such systems is recovery from failures. The problem of identifying the factors affecting the performance of CBR system is a key element to build successful and accurate decision support systems. For this purpose, a hybrid CBR based self-healing system supported by attribute selection methods has been proposed. An empirical investigation has been conducted in this paper using different similarity measures, solution adaptation methods and attribute selection techniques. To address the performance problem of CBR in self-healing systems, we have conducted experiments on an emulator of self-healing systems called RUIBiS using different machine learning techniques to determine the significance of weights for these similarity distances.