Biblio

A distributed spacecraft is a cluster of independent satellite modules flying in formation that communicate via ad-hoc wireless networks. This system in space is a cloud platform that facilitates sharing sensors and other computing and communication resources across multiple applications, potentially developed and maintained by different organizations. Effectively, such architecture can realize the functions of monolithic satellites at a reduced cost and with improved adaptivity and robustness. Openness of these architectures pose special challenges because the distributed software platform has to support applications from different security domains and organizations, and where information flows have to be carefully managed and compartmentalized. If the platform is used as a robust shared resource its management, configuration, and resilience becomes a challenge in itself. We have designed and prototyped a distributed software platform for such architectures. The core element of the platform is a new operating system whose services were designed to restrict access to the network and the file system, and to enforce resource management constraints for all non-privileged processes Mixed-criticality applications operating at different security labels are deployed and controlled by a privileged management process that is also pre-configuring all information flows. This paper describes the design and objective of this layer.

Multi-module Cyber-Physical Systems (CPSs), such as satellite clusters, swarms of Unmanned Aerial Vehicles (UAV), and fleets of Unmanned Underwater Vehicles (UUV) are examples of managed distributed real-time systems where mission-critical applications, such as sensor fusion or coordinated flight control, are hosted. These systems are dynamic and reconfigurable, and provide a “CPS cluster-as-a-service” for mission-specific scientific applications that can benefit from the elasticity of the cluster membership and heterogeneity of the cluster members. Distributed and remote nature of these systems often necessitates the use of Deployment and Configuration (D&C) services to manage lifecycle of software applications. Fluctuating resources, volatile cluster membership and changing environmental conditions require resilience. However, due to the dynamic nature of the system, human intervention is often infeasible. This necessitates a self-adaptive D&C infrastructure that supports autonomous resilience. Such an infrastructure must have the ability to adapt existing applications on the fly in order to provide application resilience and must itself be able to adapt to account for changes in the system as well as tolerate failures.

This paper describes the design and architectural considerations to realize a self-adaptive, D&C infrastructure for CPSs. Previous efforts in this area have resulted in D&C infrastructures that support application adaptation via dynamic re-deployment and re-configuration mechanisms. Our work, presented in this paper, improves upon these past efforts by implementing a self- adaptive D&C infrastructure which itself is resilient. The paper concludes with experimental results that demonstrate the autonomous resilience capabilities of our new D&C infrastructure.

Cyber-physical systems increasingly rely on distributed computing platforms where sensing, computing, actuation, and communication resources are shared by a multitude of applications. Such `cyber-physical cloud computing platforms' present novel challenges because the system is built from mobile embedded devices, is inherently distributed, and typically suffers from highly fluctuating connectivity among the modules. Architecting software for these systems raises many challenges not present in traditional cloud computing. Effective management of constrained resources and application isolation without adversely affecting performance are necessary. Autonomous fault management and real-time performance requirements must be met in a verifiable manner. It is also both critical and challenging to support multiple end-users whose diverse software applications have changing demands for computational and communication resources, while operating on different levels and in separate domains of security.

The solution presented in this paper is based on a layered architecture consisting of a novel operating system, a middleware layer, and component-structured applications. The component model facilitates the construction of software applications from modular and reusable components that are deployed in the distributed system and interact only through well-defined mechanisms. The complexity of creating applications and performing system integration is mitigated through the use of a domain-specific model-driven development process that relies on a domain-specific modeling language and its accompanying graphical modeling tools, software generators for synthesizing infrastructure code, and the extensive use of model-based analysis for verification and validation.