Please use this identifier to cite or link to this item: https://doi.org/10.1006/jpdc.2001.1778
Title: Efficient scheduling strategies for processing multiple divisible loads on bus networks
Authors: Veeravalli, B. 
Barlas, G.
Keywords: Bus networks
Communication delays
Computation delays
Divisible loads
Optimal processing time
Issue Date: 2002
Citation: Veeravalli, B., Barlas, G. (2002). Efficient scheduling strategies for processing multiple divisible loads on bus networks. Journal of Parallel and Distributed Computing 62 (1) : 132-151. ScholarBank@NUS Repository. https://doi.org/10.1006/jpdc.2001.1778
Abstract: The problem of scheduling multiple divisible loads on bus networks is addressed in this paper. The objective is to minimize the total processing time of all the divisible loads submitted to the system for processing. A heterogeneous system of processors in the network is considered, and strategies that minimize the total processing time of multiple divisible loads are designed. These strategies are shown to provide a complete flexibility in tuning the number of installments that can be used per load during the distribution process so as to meet the objective. Rigorous analysis for the proposed strategies is presented, and certain important conditions under which the utilization of the processors is a maximum are derived. When these conditions are violated, a set of alternate heuristic strategies are proposed, and a rigorous simulation study on these heuristic strategies is conducted. A detailed discussion on the time performance of these strategies and the results obtained are presented. Performance comparison of the proposed strategies with a strategy available in the literature so far is carried out. Some plausible extensions of this research are also presented. © 2001 Elsevier Science.
Source Title: Journal of Parallel and Distributed Computing
URI: http://scholarbank.nus.edu.sg/handle/10635/55805
ISSN: 07437315
DOI: 10.1006/jpdc.2001.1778
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.