A runtime resource-aware architecture for service-oriented embedded systems

Abstract

Embedded systems typically operate in resource-constrained environments and often find themselves in difficult to access locations, making system maintenance expensive and the management of quality difficult to achieve. The service-oriented model of deployment offers a potential solution to these challenges as it allows for software systems to be dynamically composed and reconfigured using services discoverable at runtime. However, the resource contention between services on the orchestration platform can cause significant falls in Quality of Service (QoS). This emergent QoS is difficult to anticipate before deployment as changes in QoS are often dynamic and influenced by many factors. This paper presents EQoSystem, a resource-aware architecture combining resource monitoring with dynamic workflow management and service orchestration. We demonstrate the efficacy of EQoSystem using a medium-sized case study deployed on an embedded platform. The results show that continuous and effective resource management changes can be made to maintain resource consumption within preset thresholds. © 2012 IEEE.