Distributed and Decentralized Control in Fully Distributed Processing Systems.
Abstract
Parallel processing has been a popular approach to improving system performance through several generations of computer systems design. Although it is not usually characterized as a 'parallel' processing system, a distributed processing system has the inherent capability for highly parallel operation. In order to capitalize on the potential performance improvements achievable by a distributed system, major parallel control problems must be solved. Central to the issue of parallel control is the design and implementation of distributed and decentralized control. The study of distributed and decentralized control was initiated with a survey of applicable control models. The results of this survey are presented along with an extensive discussion of the control problems applicable to distributed systems -- specifically 'fully' distributed systems. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 1981
- Accession Number
- ADA104379
Entities
People
- Philip H. Enslow Jr.
- Timothy G. Saponas
Organizations
- Georgia Tech