Abstract
A commonly used technique for evaluating and comparing the performance of systems using 802.11 (WiFi) networks is to conduct experiments. This approach is appealing and important because it inherently captures critical properties of wireless signal transmission that are difficult to analytically model and simulate. Unfortunately, obtaining consistent and statistically meaningful empirical results using 802.11 networks, even in well-controlled environments, can be quite challenging and time consuming because channel conditions can vary over time.
In this paper, we use 2.4 and 5 GHz 802.11n MIMO networks to study different methodologies that could be used to evaluate and compare the performance of different alternatives used in 802.11 systems (e.g., different systems, configurations or algorithms). We first illustrate that some of the more commonly used methods in existing research are flawed and explain why. We then describe a methodology called multiple interleaved trials that, to our knowledge, has not been used for, or studied on, 802.11 networks. We evaluate this methodology and find that it can be used to repeat experiments and to compare the performance of different alternatives. Finally, we discuss other possible applications of this approach for comparative performance evaluations.
- S. Ganu, H. Kremo, R. Howard, and I. Seskar, "Addressing repeatability in wireless experiments using orbit testbed," in Tridentcom, 2005. Google ScholarDigital Library
- R. Burchfield, E. Nourbakhsh, J. Dix, K. Sahu, S. Venkatesan, and R. Prakash, "RF in the jungle: Effect of environment assumptions on wireless experiment repeatability," in ICC, 2009. Google ScholarDigital Library
- G. Judd and P. Steenkiste, "Using emulation to understand and improve wireless networks and applications," in NSDI, 2005. Google ScholarDigital Library
- D. Johnson and A. Lysko, "Comparison of MANET routing protocols using a scaled indoor wireless grid," Mobile Networks and Applications, 2008. Google ScholarDigital Library
- P. De, A. Raniwala, R. Krishnan, K. Tatavarthi, J. Modi, N. A. Syed, S. Sharma, and T. Chiueh, "Mint-m: An autonomous mobile wireless experimentation platform," in MobiSys, 2006.Google Scholar
- O. Rensfelt, F. Hermans, P. Gunningberg, and L.-A. Larzon, "Repeatable experiments with mobile nodes in a relocatable WSN testbed," in DCOSSW, 2010.Google Scholar
- B. Blywis, M. Günes, F. Juraschek, and J. H. Schiller, "Trends, advances, and challenges in testbed-based wireless mesh network research," Mobile Networks and Applications, 2010. Google ScholarDigital Library
- I. Pefkianakis, Y. Hu, S. H. Wong, H. Yang, and S. Lu, "MIMO rate adaptation in 802.11n wireless networks," in MobiCom, 2010. Google ScholarDigital Library
- L. Deek, E. Garcia-Villegas, E. Belding, S.-J. Lee, and K. Almeroth, "Joint rate and channel width adaptation for 802.11 MIMO wireless networks," in SECON, 2013.Google Scholar
- K. Nikitopoulos, J. Zhou, B. Congdon, and K. Jamieson, "Geosphere: Consistently turning MIMO capacity into throughput," in SIGCOMM, 2014. Google ScholarDigital Library
- S. H. Y. Wong, H. Yang, S. Lu, and V. Bharghavan, "Robust rate adaptation for 802.11 wireless networks," in MobiCom, 2006. Google ScholarDigital Library
- Aniket, N. Carlsson, C. Williamson, and M. Arlitt, "Ambient interference effects in WiFi networks," in NETWORKING, 2010. Google ScholarDigital Library
- S. Rayanchu, A. Patro, and S. Banerjee, "Airshark: detecting non-WiFi RF devices using commodity WiFi hardware," in IMC, 2011. Google ScholarDigital Library
- S. Lakshmanan, S. Sanadhya, and R. Sivakumar, "On link rate adaptation in 802.11n WLANs," in INFOCOM, 2011.Google Scholar
- C.-Y. Li, C. Peng, S. Lu, and X. Wang, "Energy-based rate adaptation for 802.11n," in Mobicom, 2012. Google ScholarDigital Library
- X. Tie, A. Seetharam, A. Venkataramani, D. Ganesan, and D. L. Goeckel, "Anticipatory wireless bitrate control for blocks," in CoNEXT, 2011. Google ScholarDigital Library
- H. Rahul, F. Edalat, D. Katabi, and C. G. Sodini, "Frequency-aware rate adaptation and mac protocols," in Mobicom, 2009. Google ScholarDigital Library
- D. Gupta, D. Wu, P. Mohapatra, and C.-N. Chuah, "Experimental comparison of bandwidth estimation tools for wireless mesh networks," in INFOCOM, 2009.Google Scholar
- A. Abedi and T. Brecht, "T-RATE: A framework for the trace-driven evaluation of 802.11 rate adaptation algorithms," in MASCOTS, 2014.Google Scholar
- L. Deek, E. Garcia-Villegas, E. Belding, S.-J. Lee, and K. Almeroth, "The impact of channel bonding on 802.11n network management," in CoNEXT, 2011. Google ScholarDigital Library
- AirMagnet, "Fluke networks." http://www.flukenetworks.com/enterprisenetwork/wireless-network/AirMedic.Google Scholar
- IPerf. http://sourceforge.net/projects/iperf/.Google Scholar
- W.-L. Shen, Y.-C. Tung, K.-C. Lee, K. C.-J. Lin, S. Gollakota, D. Katabi, and M.-S. Chen, "Rate adaptation for 802.11 multiuser MIMO networks," in Mobicom, 2012. Google ScholarDigital Library
- D. Montgomery, Design and Analysis of Experiments. Wiley, 2012.Google Scholar
- G. Judd, X. Wang, and P. Steenkiste, "Efficient channel-aware rate adaptation in dynamic environments," in MobiSys, 2008. Google ScholarDigital Library
- D. Halperin, W. Hu, A. Sheth, and D. Wetherall, "Predictable 802.11 packet delivery from wireless channel measurements," in SIGCOMM, 2010. Google ScholarDigital Library
- G. Judd and P. Steenkiste, "A simple mechanism for capturing and replaying wireless channels," in ACM SIGCOMM workshop on Experimental approaches to wireless network design and analysis, 2005. Google ScholarDigital Library
- E. Lillie, B. Patay, J. Diamant, B. Issell, E. Topol, and N. Schork, "The n-of-1 clinical trial: the ultimate strategy for individualizing medicine?," Personalized Medicine, vol. 8, no. 2, pp. 161--173, 2011.Google ScholarCross Ref
- J. Schad, J. Dittrich, and J.-A. Quiané-Ruiz, "Runtime measurements in the cloud: observing, analyzing, and reducing variance," Proceedings of the VLDB Endowment, vol. 3, no. 1-2, pp. 460--471, 2010. Google ScholarDigital Library
Recommendations
Conducting Repeatable Experiments in Highly Variable Cloud Computing Environments
ICPE '17: Proceedings of the 8th ACM/SPEC on International Conference on Performance EngineeringPrevious work has shown that benchmark and application performance in public cloud computing environments can be highly variable. Utilizing Amazon EC2 traces that include measurements affected by CPU, memory, disk, and network performance, we study ...
Conducting experiments with Experiment Manager
WSC '96: Proceedings of the 28th conference on Winter simulationThis tutorial demonstrates how to conduct experiments and perform analysis with Experiment Manager, CACI's tool for design and analysis of simulation experiments. Experiment Manager works in conjunction with SIMPROCESS and provides a quick and object ...
Experiences conducting experiments in industry: the ESEIL FiDiPro project
CESI '16: Proceedings of the 4th International Workshop on Conducting Empirical Studies in IndustryThe Experimental Software Engineering Industry Laboratory (ESEIL) project funded by the Finland Distinguished Professor Programme (FiDiPro) kicked off in January 2013. The aim of this research is to gain insight into whether experiments in the software ...
Comments