Managing resource contention in embedded service-oriented systems with dynamic orchestration

As embedded systems become increasingly complex, not only are dependability and timeliness indicators of success, but also the ability to dynamically adapt to changes in the runtime environment. Typically, they operate in resource-constrained environments and often find application in isolated locations, making them expensive to manage with small resource changes in their operating environment having a significant impact on system quality. The service-oriented model of deployment offers a possible solution to these challenges; however, resource contention between services and resource saturation can result in significant Quality of Service (QoS) degradation. This emergent QoS is difficult to anticipate before deployment as changes in QoS are often dynamic. This paper presents EQoSystem, a runtime, resource-aware framework that combines monitoring with dynamic workflow orchestration to mediate resource contention within the orchestration environment. The results from a medium-sized case study demonstrate the efficacy of EQoSystem.