Title: Energy Efficient Data Driven Distributed Traffic Simulations

SaBra A. Neal

Ph.D. Candidate

School of Computational Science and Engineering 

College of Computing

Georgia Institute of Technology 

Date: Friday, March 30, 2018

Time: 10:30am - 12:30pm (EST)

Location: KACB 1212

Committee:
————————————

Dr. Richard Fujimoto (Advisor, School of Computational Science and Engineering, Georgia Institute of Technology)

Dr. Richard Vuduc (School of Computational Science and Engineering, Georgia Institute of Technology)

Dr. Margaret Loper (Georgia Tech Research Institute, Georgia Institute of Technology)

Dr. Michael Hunter (School of Civil and Environmental Engineering, Georgia Institute of Technology)

Dr. David Goldsman (School of Industrial & Systems Engineering, Georgia Institute of Technology)

Abstract:
————————————

With the growing capabilities of the Internet of Things and proliferation of mobile devices interest in the use of real-time data as a means for input to distributed online simulations has increased.  Online simulations allow users the ability to utilize real-time data to make adaptations to their simulation system to reflect the realistic components that are portrayed in the system under study.  One problem that arises with using these systems on mobile devices is that they are dependent upon the device’s stored energy.  It is vital to understand and know how all components of such a system use the stored energy in order to understand how to develop such systems for these constrained environments. 

This thesis investigates the energy consumed in running a distributed dynamic data driven application system for online traffic simulations in energy constrained environments. Such a system consists of embedded traffic simulations and requires a means of communication amongst the distributed simulations throughout the system under study in order to characterize the behavior of the entire system.  Data distribution management provides a means to manage communications in such a system. Understanding how the components of data distribution management systems consume energy is essential to understanding how to use such a system in energy constrained environments. This thesis also explores how data distribution management components affect energy consumption. 

This thesis explores an energy aware approach applicable for systems that are restricted to energy-constrained environments.  The approach offers mechanisms to implement energy aware distributed simulations and communication mechanisms. This thesis assesses the role that discrete event driven and cellular automata models have on energy consumption in embedded systems. Discrete event driven simulations are dependent on their future event list for execution, it is beneficial when running such simulations on embedded systems to discern the effect the data structure used for the future event list has on energy consumption.