|
Digital
Library of the European Council for Modelling and Simulation |
Title: |
Minimizing Mean Response
Time In Non-Observable Distributed Systems With Processor Sharing Nodes |
Authors: |
Mikhail
Konovalov, Rostislav Razumchik |
Published in: |
(2019). ECMS 2019
Proceedings Edited by: Mauro Iacono, Francesco Palmieri, Marco Gribaudo,
Massimo Ficco, European Council for Modeling and
Simulation. DOI: http://doi.org/10.7148/2019 ISSN:
2522-2422 (ONLINE) ISSN:
2522-2414 (PRINT) ISSN:
2522-2430 (CD-ROM) 33rd International ECMS Conference on Modelling and Simulation, Caserta, Italy, June 11th
– June 14th, 2019 |
Citation
format: |
Mikhail Konovalov, Rostislav Razumchik (2019). Minimizing Mean Response Time In Non-Observable Distributed Systems With Processor Sharing Nodes, ECMS 2019 Proceedings Edited by: Mauro Iacono, Francesco Palmieri, Marco Gribaudo, Massimo Ficco European Council for Modeling and Simulation. doi: 10.7148/2019-0456 |
DOI: |
https://doi.org/10.7148/2019-0456 |
Abstract: |
Consider a
non-observable distributed processing system with N ≥ 2 single server queues
operating in parallel, each under the processor sharing discipline. Jobs
arrive one by one to the dispatcher, which immediately routes it to one of
the queues. When making a routing decision the dispatcher does not have any
online information about the system (current queues’ sizes, size of the
arriving job etc.) The only information available to the dispatcher is: job
size distribution, job’s inter-arrival time distribution, server’s speeds,
time instants of previously arrived jobs and previous routing decisions.
Under these conditions, one is interested in the routing policies
which minimize the job’s long-run mean response time. Two new class of policies are being proposed, which, according to
the numerical experiments, may significantly outperform the optimal
probabilistic policy and the Round Robin policy. |
Full
text: |