Trust enforcement through self-adapting cloud workflow orchestration

Abstract

Providing runtime intelligence of a workflow in a highly dynamic cloud execution environment is a challenging task due the continuously changing cloud resources. Guaranteeing a certain level of workflow Quality of Service (QoS) during the execution will require continuous monitoring to detect any performance violation due to resource shortage or even cloud service interruption. Most of orchestration schemes are either configuration, or deployment dependent and they do not cope with dynamically changing environment resources. In this paper, we propose a workflow orchestration, monitoring, and adaptation model that relies on trust evaluation to detect QoS performance degradation and perform an automatic reconfiguration to guarantee QoS of the workflow. The monitoring and adaptation schemes are able to detect and repair different types of real time errors and trigger different adaptation actions including workflow reconfiguration, migration, and resource scaling. We formalize the cloud resource orchestration using state machine that efficiently captures different dynamic properties of the cloud execution environment. In addition, we use validation model checker to validate our model in terms of reachability, liveness, and safety properties. Extensive experimentation is performed using a health monitoring workflow we have developed to handle dataset from Intelligent Monitoring in Intensive Care III (MIMICIII) and deployed over Docker swarm cluster. A set of scenarios were carefully chosen to evaluate workflow monitoring and the different adaptation schemes we have implemented. The results prove that our automated workflow orchestration model is self-adapting, self-configuring, react efficiently to changes and adapt accordingly while supporting high level of Workflow QoS.