NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Prediction-based dynamic load-sharing heuristicsThe authors present dynamic load-sharing heuristics that use predicted resource requirements of processes to manage workloads in a distributed system. A previously developed statistical pattern-recognition method is employed for resource prediction. While nonprediction-based heuristics depend on a rapidly changing system status, the new heuristics depend on slowly changing program resource usage patterns. Furthermore, prediction-based heuristics can be more effective since they use future requirements rather than just the current system state. Four prediction-based heuristics, two centralized and two distributed, are presented. Using trace driven simulations, they are compared against random scheduling and two effective nonprediction based heuristics. Results show that the prediction-based centralized heuristics achieve up to 30 percent better response times than the nonprediction centralized heuristic, and that the prediction-based distributed heuristics achieve up to 50 percent improvements relative to their nonprediction counterpart.
Document ID
19930071789
Document Type
Reprint (Version printed in journal)
External Source(s)
Authors
Goswami, Kumar K. (Illinois Univ. Urbana, United States)
Devarakonda, Murthy (IBM Thomas J. Watson Research Center Yorktown Heights, NY, United States)
Iyer, Ravishankar K. (Illinois Univ. Urbana, United States)
Date Acquired
August 16, 2013
Publication Date
June 1, 1993
Publication Information
Publication: IEEE Transactions on Parallel and Distributed Systems
Volume: 4
Issue: 6
ISSN: 1045-9219
Subject Category
COMPUTER SYSTEMS
Funding Number(s)
CONTRACT_GRANT: NAG1-613
Distribution Limits
Public
Copyright
Other