Intelligent architecture for automatic resource allocation in computer clusters

Abstract

As the need for more reporting and assessment of information increase exponentially, computer-based applications consume resources at an alarmingly rapid rate. Therefore, traditional techniques for managing resource allocation, topology and systems need urgent revision. In this paper, we present an intelligent architecture that introduces a new strategy for managing resource discovery, allocation and dynamic reconfiguration at run-time. Our building methodology involves the employment of new types of clustered systems based on large application groupings, each having a master cluster controller. Each controlling engine consists of self-healing intelligent entities that can compensate for a variety of software or hardware problems. We also present evaluation results of extensive experiments in a production environment, which demonstrate the advantages of our approach.