Taming Service Uncertainty through Probabilistic Model Learning, Analysis and Synthesis

Abstract

Cloud computing owes much of its success to the ease and cost effectiveness with which new systems can be built using remote third-party services. However, the response time, reliability and other quality-of-service (QoS) properties of these services are often uncertain. As such, ensuring that service-based systems achieve their QoS requirements is very challenging. This talk will describe how recent advances in probabilistic model learning, analysis and synthesis can help address this challenge both during service-based system design and verification, and at runtime.