Control Heuristics for Scheduling in a Parallel Blackboard System (1993)
Cached
Download Links
- [mas.cs.umass.edu]
- [ftp.cs.umass.edu]
- [ftp.cs.umass.edu]
- DBLP
Other Repositories/Bibliography
| Venue: | INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE |
| Citations: | 9 - 6 self |
BibTeX
@ARTICLE{Decker93controlheuristics,
author = {Keith Decker and Alan Garvey and Marty Humphrey and Victor Lesser},
title = {Control Heuristics for Scheduling in a Parallel Blackboard System},
journal = {INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE},
year = {1993},
volume = {7}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper investigates the effects of parallelism on blackboard system scheduling heuristics. A parallel blackboard system is described that allows multiple knowledge source instantiations (KSIs) to execute in parallel using a shared-memory blackboard approach. New classes of control knowledge are defined that order the agenda by using information about the relationships between the goals of the KSIs. This control knowledge is implemented and tested in the DVMT application on a Sequent multiprocessor using BB1-style control heuristics. The usefulness of the heuristics is examined by comparing the effectiveness of problem-solving with and without the heuristics (as a group and individually). Problem solving with the new control knowledge results in improved system performance.
Keyphrases
parallel blackboard system control heuristic control knowledge new class blackboard system shared-memory blackboard approach new control knowledge result dvmt application sequent multiprocessor bb1-style control heuristic improved system performance multiple knowledge source instantiation
