Scheduling Jobs with Estimation Errors for Multi-Server Systems
R. Mailach, and D. Down. 29th International Teletraffic Congress (ITC 29), Genoa, Italy, (2017)
Abstract
When scheduling single server systems, Shortest Remaining Processing Time (SRPT) minimizes the number of jobs in the system at every point in time. However, a major
limitation of SRPT is that it requires job processing times a priori. In practice, it is likely that only estimates of job processing times are available. This paper proposes a policy that schedules jobs with estimated job processing times. The proposed Modified Comparison Splitting Scheduling (MCSS) policy is compared to SRPT when scheduling both single and multi-server systems. In the single server system we observe from simulations that the proposed scheduling policy provides robustness that is crucial for achieving good performance. In contrast, in a multi-server system we observe that robustness to estimation errors is not dependent on the scheduling policy. However, as the number of servers grows, SRPT becomes preferable.
%0 Conference Paper
%1 Mailach.2017
%A Mailach, Rachel
%A Down, Douglas
%B 29th International Teletraffic Congress (ITC 29)
%C Genoa, Italy
%D 2017
%K itc itc29
%T Scheduling Jobs with Estimation Errors for Multi-Server Systems
%U https://gitlab2.informatik.uni-wuerzburg.de/itc-conference/itc-conference-public/-/raw/master/itc29/Mailach.2017.pdf?inline=true
%X When scheduling single server systems, Shortest Remaining Processing Time (SRPT) minimizes the number of jobs in the system at every point in time. However, a major
limitation of SRPT is that it requires job processing times a priori. In practice, it is likely that only estimates of job processing times are available. This paper proposes a policy that schedules jobs with estimated job processing times. The proposed Modified Comparison Splitting Scheduling (MCSS) policy is compared to SRPT when scheduling both single and multi-server systems. In the single server system we observe from simulations that the proposed scheduling policy provides robustness that is crucial for achieving good performance. In contrast, in a multi-server system we observe that robustness to estimation errors is not dependent on the scheduling policy. However, as the number of servers grows, SRPT becomes preferable.
@inproceedings{Mailach.2017,
abstract = {When scheduling single server systems, Shortest Remaining Processing Time (SRPT) minimizes the number of jobs in the system at every point in time. However, a major
limitation of SRPT is that it requires job processing times a priori. In practice, it is likely that only estimates of job processing times are available. This paper proposes a policy that schedules jobs with estimated job processing times. The proposed Modified Comparison Splitting Scheduling (MCSS) policy is compared to SRPT when scheduling both single and multi-server systems. In the single server system we observe from simulations that the proposed scheduling policy provides robustness that is crucial for achieving good performance. In contrast, in a multi-server system we observe that robustness to estimation errors is not dependent on the scheduling policy. However, as the number of servers grows, SRPT becomes preferable.},
added-at = {2017-10-05T16:41:49.000+0200},
address = {Genoa, Italy},
author = {Mailach, Rachel and Down, Douglas},
biburl = {https://www.bibsonomy.org/bibtex/23abe64190ccd8af080c9d10c920fec91/itc},
booktitle = {29th International Teletraffic Congress (ITC 29)},
interhash = {20035285f3b8023ff93ec05dbaa8c9e4},
intrahash = {3abe64190ccd8af080c9d10c920fec91},
keywords = {itc itc29},
timestamp = {2020-04-30T18:18:14.000+0200},
title = {Scheduling Jobs with Estimation Errors for Multi-Server Systems},
url = {https://gitlab2.informatik.uni-wuerzburg.de/itc-conference/itc-conference-public/-/raw/master/itc29/Mailach.2017.pdf?inline=true},
year = 2017
}