An Integrated Planning and Adaptive Resource Management Architecture for Distributed Real-Time Embedded Systems

Abstract

Distributed real-time embedded (DRE) systems often operate in open environments where operating conditions, input workload, and resource availability cannot be accurately characterized a priori. Some DRE systems, such as NASA's Magnetospheric Multi-Scale (MMS) mission, perform sequences of heterogeneous data collection, manipulation, and coordination tasks to meet specified objectives/goals. These systems are also required to operate with a high degree of local autonomy and adaptivity as new data is acquired and analyzed, and as environmental conditions change. Key challenges in managing open DRE systems include effective planning and online management of system resources to accommodate for changing mission goals, environmental conditions, resource needs, and resource availability. This paper explores the benefits of an integrated planning and adaptive resource management architecture that combines decision-theoretic planning with adaptive resource management to control and ensure efficient functioning of open DRE systems.

A simulation as a service cloud middleware

“…In prior work [26,37], we have designed and deployed multi-layered resource management algorithms integrated with higher-level task (re-)planning mechanisms to provide performance assurances to distributed real-time and embedded applications. These algorithms were integrated within middleware solutions that were deployed on a distributed cluster of machines, which can be viewed as small-scale data centers.…”

Functional, physical, and organizational architectures of a fractionated space infrastructure for long-term earth observation missions

“…Due to this reason, fractionated spacecraft is a distributed real-time and embedded (DRE) system. In such systems autonomous operations are preferred to make the system adapt to changing mission goals and environmental conditions [20]. However, autonomous operations of each module are insufficient for fractionated spacecraft; cooperation among modules is also required, as mentioned before not only to make each module become shared resource in the cluster, but also to perform unique operations related to fractionated spacecraft.…”

Self-Stabilization in Energy-Constraint Wireless Ad Hoc Networks

“…It is worthy of note that, in regard to graph Laplacians, there exists a great discrepancy between wireless ad hoc networks and other large, artificial or natural, networks (such as power network and geneprotein interaction network). 3 See Fig. 4 for (exemplificative) illustration.…”

“…Nonetheless, the unique nature of these networks poses various technological challenges to system design and application development. ENS are prone to transient timing problems, such as missed deadlines, message skipping, and buffer overflows [1]- [3]. They habitually operate in an open, distributed, and mission-critical environment where many run-time conditions cannot be accurately characterized a priori [3].…”

“…ENS are prone to transient timing problems, such as missed deadlines, message skipping, and buffer overflows [1]- [3]. They habitually operate in an open, distributed, and mission-critical environment where many run-time conditions cannot be accurately characterized a priori [3]. It is worthy of note that for wireless ad hoc networks, the inherent scarce resources (esp.…”