Towards a Case-based Reasoning Approach for Cloud Provisioning

Resource provisioning is an important issue of cloud computing. Most of the recent cloud solutions implement a simple way with static thresholds to provide resources. Some more sophisticated approaches consider the cloud provisioning problem a multi-dimensional optimization approach. However, the calculation effort for solving optimization problems is significant. An intelligent resource provisioning with a reduced calculation effort requires smart cloud management methods. In this position paper, we propose a case-based reasoning approach for cloud management. A case records a problem situation in cloud management and its solution. We introduce a case model and a retrieval method for previously solved problem cases with the aim to reuse their re-configuration actions for a recent problem situation. The case model uses the container notion correlated with QoS problems. We present a novel, composite similarity function that allows to compare a recent problem situation with the cases from the past. During retrieval, the similarity function creates a ranking of the cases according to their relevance to the current problem situation. Further, we describe the prototypical implementation of the core elements of our case based-reasoning concept. The plausiblility of the retrieval approach has been tested by means of sample cases with simulated data.