TY - JOUR
T1 - Enabling network calculus-based simulation for TCP congestion control
AU - Kim, Hwangnam
AU - Hou, Jennifer C.
N1 - Funding Information:
Jennifer C. Hou passed away on December 2, 2007 in Houston, Texas at the age of 43. She received her BSE degree in Electrical Engineering from National Taiwan University, Taiwan, ROC in 1987, MSE degrees in Electrical Engineering and Computer Science (EECS) and in Industrial and Operations Engineering (I&OE) from the University of Michigan, Ann Arbor, Michigan in 1989 and in 1991, and Ph.D. degree in EECS also from the University of Michigan, Ann Arbor, Michigan in 1993. She was an assistant professor in Electrical and Computer Engineering at the University of Wisconsin, Madison, Wisconsin from 1993 to 1996, and an assistant/associate professor in Electrical Engineering at Ohio State University, Columbus, Ohio from 1996 to 2001. She joined the University of Illinois Computer Science faculty in 2001. She was a principal researcher in networked systems and served as the director of the Illinois Network Design and Experimentation (INDEX) research group. Her research interests in networked systems ranged from issues of Quality of Service in wireless networks to enabling software infrastructure for assisted living. She pursued topics in both the theoretical protocol design and deployment aspects of wireless sensor networks. She was elected as an Institute of Electrical and Electronics Engineers (IEEE) Fellow and an Association for Computing Machinery (ACM) Distinguished Scientist in 2007. She was a recipient of an ACM Recognition of Service Award in 2004 and 2007, a Cisco University Research Award from Cisco Inc., 2002, a Lumley Research Award from Ohio State University in 2001, a NSF CAREER award from the Network and Communications Research Infrastructure, National Science Foundation in 1996–2000, and a Women in Science Initiative Award from The University of Wisconsin-Madison in 1993–1995.
Funding Information:
This work was supported in part by the Korea Science and Engineering Foundation (KOSEF) grant funded by the Korea government (MOST) (No. R01-2007-000-20958-0), and in part by the I.T R&D program of MKE/IITA [2008-F-015-01, Research on Ubiquitous Mobility Management Methods for Higher Service Availability].
PY - 2009/1/16
Y1 - 2009/1/16
N2 - In this paper, we propose to speed up the simulation performance for TCP-operated networks by incorporating network calculus-based models in a simulation framework. In the simulation framework, we describes the operational properties of TCP congestion control, additive increase and multiplicative decrease (AIMD) and slow start, together with the queue discipline in the domain of network calculus. In order to determine network calculus models for TCP congestion, we first devise a simple TCP throughput model which approximately determines the range of per-flow throughput that one TCP can attain in a given interval, given the number of packet losses in the interval. We then exploit the TCP model to define a collection of network calculus theorems that regulate TCP flows in the range between the upper- and lower-limits on the TCP per-flow throughput in the corresponding interval. Finally, we incorporate the derived rules (theorems) into ns-2 to obtain a network calculus-based (NC-based) simulation, and carry out both the NC-based and the packet-level simulation to evaluate the performance gain and accuracy of the NC-based simulation, where the former is represented in perspective of the execution time (wall time) incurred in conducting the simulations and the later is evaluated in terms of the difference between results obtained in both the packet-level and NC-based simulation. The simulation results indicate that an order of magnitude or more (maximally 30 times) improvement in the execution time is achieved and the performance improvement becomes more salient as the network size increases in perspective of network-link capacities and the number of flows. The discrepancy observed between the NC-based simulation and the packet-level simulation, on the other hand, is minimally 1-2% and maximally 8-12% in a wide spectrum of network topologies and traffic loads. Additionally the results also indicate that the NC-based simulation outperforms a fluid-model-based simulation realized with the use of the time-stepped hybrid simulation technique, and that the performance improvement of the NC-based simulation is still held in IEEE 802.11-based wireless networks and also immune to the type of the simulation platform consisting of ns-2, operating system, and hardware specification.
AB - In this paper, we propose to speed up the simulation performance for TCP-operated networks by incorporating network calculus-based models in a simulation framework. In the simulation framework, we describes the operational properties of TCP congestion control, additive increase and multiplicative decrease (AIMD) and slow start, together with the queue discipline in the domain of network calculus. In order to determine network calculus models for TCP congestion, we first devise a simple TCP throughput model which approximately determines the range of per-flow throughput that one TCP can attain in a given interval, given the number of packet losses in the interval. We then exploit the TCP model to define a collection of network calculus theorems that regulate TCP flows in the range between the upper- and lower-limits on the TCP per-flow throughput in the corresponding interval. Finally, we incorporate the derived rules (theorems) into ns-2 to obtain a network calculus-based (NC-based) simulation, and carry out both the NC-based and the packet-level simulation to evaluate the performance gain and accuracy of the NC-based simulation, where the former is represented in perspective of the execution time (wall time) incurred in conducting the simulations and the later is evaluated in terms of the difference between results obtained in both the packet-level and NC-based simulation. The simulation results indicate that an order of magnitude or more (maximally 30 times) improvement in the execution time is achieved and the performance improvement becomes more salient as the network size increases in perspective of network-link capacities and the number of flows. The discrepancy observed between the NC-based simulation and the packet-level simulation, on the other hand, is minimally 1-2% and maximally 8-12% in a wide spectrum of network topologies and traffic loads. Additionally the results also indicate that the NC-based simulation outperforms a fluid-model-based simulation realized with the use of the time-stepped hybrid simulation technique, and that the performance improvement of the NC-based simulation is still held in IEEE 802.11-based wireless networks and also immune to the type of the simulation platform consisting of ns-2, operating system, and hardware specification.
KW - Network calculus
KW - Performance modeling and simulation
UR - http://www.scopus.com/inward/record.url?scp=56449097880&partnerID=8YFLogxK
U2 - 10.1016/j.comnet.2008.07.015
DO - 10.1016/j.comnet.2008.07.015
M3 - Article
AN - SCOPUS:56449097880
SN - 1389-1286
VL - 53
SP - 1
EP - 24
JO - Computer Networks
JF - Computer Networks
IS - 1
ER -