A new programming model for dependable adaptive real-time applications

The CORTEX project envisions a new class of applications comprising (possibly many) smart components, called sentient objects, that can sense their environment and interact with it and each other by accepting and producing events. These interactions might occur in ways that demand predictable and sometimes guaranteed quality of service (QoS). However, achieving predictability is difficult given the objects' changing environments dictated by unstable and mobile object populations, unpredictable network load, varying connectivity, and failed system components. We devised an innovative programming model that aims to reconcile uncertainty with an application's required predictability. The model is based on fulfilling two predicates - coverage stability and no-contamination - by programs or protocols subject to varying conditions of system timeliness.