Please use this identifier to cite or link to this item:
Title: A Workflow Architecture for Cloud-Based Distributed Simulation
Authors: Chaudhry, NR
Anagnostou, A
Taylor, SJE
Keywords: modeling and simulation;distributed simulation;HLA;cloud computing;scientific workflows;science gateway
Issue Date: 4-Mar-2022
Publisher: Association for Computing Machinery (ACM)
Citation: Chaudhry, N.R., Anagnostou, A. and Taylor, S.J.E. (2021) 'A Workflow Architecture for Cloud-Based Distributed Simulation', ACM Transactions on Modeling and Computer Simulation, 32 (2), 15, pp. 1-26. doi: 10.1145/3503510.
Abstract: Copyright © 2021 The Author(s). Distributed Simulation has still to be adopted significantly by the wider simulation community. Reasons for this might be that distributed simulation applications are difficult to develop and access to multiple computing resources are required. Cloud computing offers low-cost on-demand computing resources. Developing applications that can use cloud computing can be also complex, particularly those that can run on different clouds. Cloud-based Distributed Simulation (CBDS) is potentially attractive, as it may solve the computing resources issue as well as other cloud benefits, such as convenient network access. However, as possibly shown by the lack of sustainable approaches in the literature, the combination of cloud and distributed simulation may be far too complex to develop a general approach. E-Infrastructures have emerged as large-scale distributed systems that support high-performance computing in various scientific fields. Workflow Management Systems (WMS) have been created to simplify the use of these e-Infrastructures. There are many examples of where both technologies have been extended to use cloud computing. This article therefore presents our investigation into the potential of using these technologies for CBDS in the above context and the WORkflow architecture for cLoud-based Distributed Simulation (WORLDS), our contribution to CBDS. We present an implementation of WORLDS using the CloudSME Simulation Platform that combines the WS-PGRADE/gUSE WMS with the CloudBroker Platform as a Service. The approach is demonstrated with a case study using an agent-based distributed simulation of an Emergency Medical Service in REPAST and the Portico HLA RTI on the Amazon EC2 cloud.
ISSN: 1049-3301
Other Identifiers: 15
Appears in Collections:Dept of Computer Science Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdf© ACM, 2022. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM Transactions on Modeling and Computer Simulation, 32, 2, April 2022, Article No.: 15, pp 1–26. MBAdobe PDFView/Open

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