Case-Based Reasoning for Autonomous Service Failure Diagnosis and Remediation in Software Systems

Self-healing, one of the four key properties characterizing Autonomic Systems, aims to enable large-scale software systems delivering complex services on a 24/7 basis to meet their goals without any human intervention. Achieving self-healing requires the elicitation and maintenance of domain knowledge in the form of 〈service failure diagnosis, remediation strategy〉 patterns, a task which can be overwhelming. CaseBased Reasoning (CBR) is a lazy learning paradigm that largely reduces this kind of knowledge acquisition bottleneck. Moreover, the application of CBR for failure diagnosis and remediation in software systems appears to be very suitable, as in this domain most errors are re-occurrences of known problems. In this paper, we describe a CBR approach for providing large-scale, distributed software systems with self-healing capabilities, and demonstrate the practical applicability of our methodology by means of some experimental results on a real world application.