Evaluating Supervised Machine Learning for Adapting Enterprise DRE Systems

Abstract

Several adaptation approaches, such as policy-based and reinforcement learning, have been devised to ensure end-to-end quality-of-service (QoS) for enterprise distributed systems in dynamic operating environments. Not all approaches are applicable for distributed real-time and embedded (DRE) systems, however, which have stringent accuracy, timeliness, and development complexity requirements. Supervised machine learning techniques, such as artificial neural networks (ANNs), are a promising approach to address time complexity concerns of adaptive enterprise DRE systems. Likewise, ANNs address the development complexity of adaptive DRE systems by ensuring that adaptations are appropriate for the operating environment. This paper empirically evaluates the accuracy and timeliness of the ANN machine learning technique for environments on which it has been trained. Our results show ANNs are highly accurate in determining correct adaptations and provide predictable time complexity, e.g., with response times less than 6 μseconds.