Ph.D. Thesis Proposal Announcement

Title: Ad Hoc Distributed Simulation: A Method for Embedded Online Simulations

Ya-Lin Huang
School of Computational Science and Engineering
Georgia Institute of Technology

Date: Thursday, June 28th, 2012
Time: 1 - 3pm
Location: Klaus 1315

Committee:

• Dr. Richard Fujimoto, School of Computational Science and Engineering (Advisor)
• Dr. Christos Alexopoulos, School of Industrial and Systems Engineering
• Dr. Michael Hunter, School of Civil and Environmental Engineering
• Dr. George Riley, School of Electrical and Computer Engineering
• Dr. Richard Vuduc, School of Computational Science and Engineering

Abstract:
The continual growth of computing power in small devices has motivated the development of novel approaches to optimizing operational systems efficiently and effectively. These optimization problems are often so complex that solving them analytically may be difficult, if not prohibited. One method for solving such problems is to use online simulation. However, challenges in using online simulation include the issues of responsiveness (e.g., because of communication delays), scalability, and failure resistance. To tackle these issues, this study proposes embedding online simulations into a network of sensors that monitors the system under investigation.

This thesis explores an approach termed "ad hoc distributed simulation," which is based on embedding online simulations into a sensor network and adding communication and synchronization among simulators to model operational systems. This approach offers several potential advantages over existing approaches: (1) it can provide rapid response to system dynamics as well as efficiency since data exchange is local to the sensor network, (2) it can achieve better scalability to incorporate more sensors, and (3) it can provide better robustness to failures because portions of the system are still under local control. This research addresses several statistical issues in this ad hoc approach: (1) rapid and effective estimation of the input processes at model boundaries, (2) estimation of system-wide performance measures from individual simulator outputs, and (3) correction mechanisms responding to unexpected events or inaccuracies within the model.

This thesis examines ad hoc distributed simulation analytically and experimentally, mainly focusing on the prediction accuracy of the performance of queueing networks. Firstly, the analytical part formalizes the ad hoc approach and evaluates its accuracy at modeling certain class of open queueing networks. Then, empirical studies evaluate a broader class of networks and present evidence to show that the ad hoc approach can provide predictions comparable to those of sequential simulations. Furthermore, a "buffered-area" mechanism is proposed to substantially reduce prediction bias with a moderate increase in execution time.