Scholars' Mine Doctoral Dissertations Student Theses and Dissertations Fall 2007 Modeling network traffic on a global network-centric system with artificial neural networks Douglas K. Swift Follow this and additional works at: https://scholarsmine.mst.edu/doctoral_dissertations Part of the Systems Engineering Commons Department: Engineering Management and Systems Engineering Recommended Citation Swift, Douglas K., "Modeling network traffic on a global network-centric system with artificial neural networks" (2007). Doctoral Dissertations. 2006. https://scholarsmine.mst.edu/doctoral_dissertations/2006 This thesis is brought to you by Scholars' Mine, a service of the Missouri S&T Library and Learning Resources. This work is protected by U. S. Copyright Law. Unauthorized use including reproduction for redistribution requires the permission of the copyright holder. For more information, please contact [email protected]. MODELING NETWORK TRAFFIC ON A GLOBAL NETWORK-CENTRIC SYSTEM WITH ARTIFICIAL NEURAL NETWORKS by DOUGLAS KEITH SWIFT A DISSERTATION Presented to the Faculty of the Graduate School of the UNIVERSITY OF MISSOURI - ROLLA In Partial Fulfillment of the Requirements for the Degree DOCTOR OF PHILOSOPHY in SYSTEMS ENGINEERING 2007 _______________________________ _______________________________ Cihan H. Dagli, Advisor David L. Enke _______________________________ _______________________________ Scott E. Grasman Ann K. Miller _______________________________ _______________________________ Sreeram Ramakrishnan Paul J. Schachter © 2007 Douglas Keith Swift All Rights Reserved iii ABSTRACT This dissertation proposes a new methodology for modeling and predicting network traffic. It features an adaptive architecture based on artificial neural networks and is especially suited for large-scale, global, network-centric systems. Accurate characterization and prediction of network traffic is essential for network resource sizing and real-time network traffic management. As networks continue to increase in size and complexity, the task has become increasingly difficult and current methodology is not sufficiently adaptable or scaleable. Current methods model network traffic with express mathematical equations which are not easily maintained or adjusted. The accuracy of these models is based on detailed characterization of the traffic stream which is measured at points along the network where the data is often subject to constant variation and rapid evolution. The main contribution of this dissertation is development of a methodology that allows utilization of artificial neural networks with increased capability for adaptation and scalability. Application on an operating global, broadband network, the Connexion by Boeing® network, was evaluated to establish feasibility. A simulation model was constructed and testing was conducted with operational scenarios to demonstrate applicability on the case study network and to evaluate improvements in accuracy over existing methods. iv ACKNOWLEDGMENTS I would like to express appreciation and gratitude to my advisor, Dr. Cihan H. Dagli, for his invaluable guidance, council, instruction, and encouragement in support of this research and also for his patience and tireless effort in setting up a Ph.D. program in Systems Engineering under which this research could be conducted. I would also like to thank my committee members, Dr. David Enke, Dr. Scott Grasman, Dr. Ann Miller, Dr. Sreeram Ramakrishnan, and Dr. Paul Schachter for their time in reviewing this work and for their valuable suggestions. I would also like to thank my children – Tianna, Talitha, Joshua, Nathanael, Malachi, Doranda, Isaac, and Caleb. Finally, I would especially like to thank my wife Jacquelyn for her support and love. Without her encouragement nothing would be possible. v TABLE OF CONTENTS Page ABSTRACT.......................................................................................................................iii ACKNOWLEDGMENTS ................................................................................................. iv LIST OF ILLUSTRATIONS........................................................................................... xiv LIST OF TABLES.........................................................................................................xviii LIST OF ACRONYMS AND NOMENCLATURE........................................................ xix SECTION 1. INTRODUCTION...................................................................................................... 1 1.1. OVERVIEW ....................................................................................................... 1 1.2. PROBLEM DEFINITION.................................................................................. 2 1.2.1. Increasingly Complex Systems ................................................................ 2 1.2.2. Emergence of Network-Centric Systems ................................................. 4 1.2.3. Complex Network Traffic ........................................................................ 6 1.3. ADAPTIVE MODELING WITH COMPUTATIONAL INTELLIGENCE...... 9 1.4. RESEARCH OBJECTIVES ............................................................................. 10 1.5. CONNEXION BY BOEING CASE STUDY................................................... 10 1.6. METHODOLOGY ........................................................................................... 12 1.7. CONTRIBUTIONS TO LITERATURE .......................................................... 12 1.8. SECTION ORGANIZATION .......................................................................... 14 2. NETWORK-CENTRIC SYSTEMS LITERATURE REVIEW .............................. 15 2.1. RELEVANCE OF NCS TO THIS RESEARCH.............................................. 15 2.2. CHARACTERISTICS OF NETWORK-CENTRIC SYSTEMS...................... 16 2.2.1. System Concepts .................................................................................... 17 2.2.1.1 Systems .......................................................................................17 2.2.1.2 Complex systems ........................................................................18 2.2.1.3 System-of-Systems .....................................................................19 2.2.2. Importance of Networks......................................................................... 20 2.2.3. Flow of Information ............................................................................... 22 vi 2.2.3.1 Traditional flow of information ..................................................22 2.2.3.2 Network-centric flow of information..........................................23 2.2.3.3 Information superiority ...............................................................23 2.2.4. Domains of Operation ............................................................................ 25 2.2.5. Desired Characteristics........................................................................... 27 2.2.5.1 Shared awareness........................................................................27 2.2.5.2 Collaboration...............................................................................27 2.2.5.3 Synchronization ..........................................................................27 2.2.5.4 Self-synchronization ...................................................................28 2.2.5.5 Interoperability............................................................................28 2.2.6. Global Information Grid......................................................................... 29 2.2.7. Challenges and Issues............................................................................. 30 2.2.7.1 Complexity..................................................................................30 2.2.7.2 Trustworthiness...........................................................................30 2.2.7.3 Interoperability............................................................................30 2.2.7.4 Management................................................................................30 2.2.7.5 Information overload ..................................................................31 2.2.7.6 Evolutionary growth ...................................................................31 2.3. ARCHITECTURE FRAMEWORKS............................................................... 31 2.3.1. DoD Architecture Framework................................................................ 32 2.3.2. Other Architecture Frameworks............................................................. 33 2.3.2.1 Zachman Framework ..................................................................34 2.3.2.2 Federal Enterprise Architecture Framework...............................34 2.3.2.3 Treasury Enterprise Architecture Framework ............................34 2.4. EXAMPLE NCS’.............................................................................................. 34 2.4.1. Manufacturing ........................................................................................ 35 2.4.2. Retail ...................................................................................................... 35 2.4.3. Air Traffic Control ................................................................................. 35 2.4.4. Financial ................................................................................................. 36 2.4.5. Connexion by Boeing............................................................................
Details
-
File Typepdf
-
Upload Time-
-
Content LanguagesEnglish
-
Upload UserAnonymous/Not logged-in
-
File Pages308 Page
-
File Size-