We are upgrading the repository! A content freeze is in effect until December 6th, 2024 - no new submissions will be accepted; however, all content already published will remain publicly available. Please reach out to repository@u.library.arizona.edu with your questions, or if you are a UA affiliate who needs to make content available soon. Note that any new user accounts created after September 22, 2024 will need to be recreated by the user in November after our migration is completed.
Rights
Copyright © International Foundation for TelemeteringCollection Information
Proceedings from the International Telemetering Conference are made available by the International Foundation for Telemetering and the University of Arizona Libraries. Visit http://www.telemetry.org/index.php/contact-us if you have questions about items in this collection.Abstract
The expanding requirement in Modern Telemetry Systems for Real-Time Data Processing has necessitated the commutation of a vast majority of the data processing functions into Front End Processors. Even the fastest of Host Processors has proven incapable of keeping pace with high speed data rates (up to 4 Megawords). The commutation of processing power into the telemetry front end has elicited the employment of distributive processing techniques in order to attain the desired throughput. A distributive processing system architecture achieves high processing throughput by apportioning data analysis functions. By defining and programming unique processing nodes to selectively acquire, distribute, compress, and/or convert data, extensive simultaneous operations are executable. Hardware merged bus structures have lent themselves conveniently to this method of data distribution and control. Conversely, conventional software structures are unsuited to distributive processing architectures which must support a broad spectrum of modular configurations. Primarily, this is evidenced when the composite system software must be repetitively customized as additional processing power or new capabilities are incorporated. Composite software that delivers a high degree of system configuration adaptability is nominally large and complex, is limited in application, depletes system memory resources and complicates sustaining software maintenance. In addition, an undesirable human interface is normally unavoidable with composite software since it requires that the user learn the specific front end system’s terminology and individual components. Bus Structure Software consigns itself to effectively support distributive processing techniques providing for adaptive system configurations. This disquisition will address the concepts of bus structured software and its application to distributive processing. Furthermore, this paper will discuss the architectural capability to service a wide range of telemetry users without specialized system tailoring. A typical implementation of this convention, the Advanced Decommutation System (ADS) designed by LORAL DATA SYSTEMS, San Diego, California will also be presented.Sponsors
International Foundation for TelemeteringISSN
0884-51230074-9079