A distributed computing model for telemetry data processing

Abstract

We present a new approach to distributing processed telemetry data among spacecraft flight controllers within the Control Centers at NASA's Johnson Space Center. This approach facilitates the development of application programs that integrate spacecraft-telemetered data and ground-based synthesized data, then distribute this information to flight controllers for analysis and decision-making. The new approach combines various distributed computing models into one hybrid distributed computing model. This model employs both client-server and peer-to-peer distributed computing models cooperating to provide users with information throughout a diverse operations environment. Specifically, it provides an attractive foundation upon which we are building critical real-time monitoring and control applications, while simultaneously lending itself to peripheral applications in playback operations, mission preparations, flight controller training, and program development and verification. We have realized the hybrid distributed computing model through an information sharing protocol. The motivations that inspired the creation of this protocol are described, along with a brief conceptual description of the distributed computing models it employs. The protocol design is described in more detail, discussing many of the program design considerations and techniques adopted. This model is especially suitable for supporting the implementation of distributed expert system applications.