You are here

UCF Digital Collections ยป ETD Collection

ROLLBACK-ABLE RANDOM NUMBER GENERATORS FOR THE SYNCHRONOUS PARALLEL ENVIRONMENT FOR EMULATION AND DISCRETE-EVENT SIMULATION (SPEEDES)

Download pdf | Full Screen View

Date Issued:
2005
Abstract/Description:
Random Numbers form the heart and soul of a discrete-event simulation system. There are few situations where the actions of the entities in the process being simulated can be completely predicted in advance. The real world processes are more probabilistic than deterministic. Hence, such chances are represented in the system by using various statistical models, like random number generators. These random number generators can be used to represent a various number of factors, such as length of the queue. However, simulations have grown in size and are sometimes required to run on multiple machines, which share the various methods or events in the simulation among themselves. These Machines can be distributed across a LAN or even the internet. In such cases, to keep the validity of the simulation model, we need rollback-able random number generators. This thesis is an effort to develop such rollback able random number generators for the Synchronous Parallel Environment for Emulation and Discrete-Event Simulation (SPEEDES) environment developed by NASA. These rollback-able random number generators will also add several statistical distribution models to the already rich SPEEDES library.
Title: ROLLBACK-ABLE RANDOM NUMBER GENERATORS FOR THE SYNCHRONOUS PARALLEL ENVIRONMENT FOR EMULATION AND DISCRETE-EVENT SIMULATION (SPEEDES).
31 views
13 downloads
Name(s): Narayanan, Ramaswamy Karthik, Author
Rabelo, Luis , Committee Chair
University of Central Florida, Degree Grantor
Type of Resource: text
Date Issued: 2005
Publisher: University of Central Florida
Language(s): English
Abstract/Description: Random Numbers form the heart and soul of a discrete-event simulation system. There are few situations where the actions of the entities in the process being simulated can be completely predicted in advance. The real world processes are more probabilistic than deterministic. Hence, such chances are represented in the system by using various statistical models, like random number generators. These random number generators can be used to represent a various number of factors, such as length of the queue. However, simulations have grown in size and are sometimes required to run on multiple machines, which share the various methods or events in the simulation among themselves. These Machines can be distributed across a LAN or even the internet. In such cases, to keep the validity of the simulation model, we need rollback-able random number generators. This thesis is an effort to develop such rollback able random number generators for the Synchronous Parallel Environment for Emulation and Discrete-Event Simulation (SPEEDES) environment developed by NASA. These rollback-able random number generators will also add several statistical distribution models to the already rich SPEEDES library.
Identifier: CFE0000328 (IID), ucf:46292 (fedora)
Note(s): 2005-05-01
M.S.
Engineering and Computer Science, Other
Masters
This record was generated from author submitted information.
Subject(s): SPEEDES
Random Numbers
Rollback-able
Rabelo
Sepulveda
Random number generators
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFE0000328
Restrictions on Access: public
Host Institution: UCF

In Collections