Abstract
The wide-scale adoption of modern smart phones and other multi-radio mobile devices, has begun to provide pragmatic deployment environments for non-cellular mobile ad hoc network (MANET) services (i.e., for disaster recovery scenarios, peered mobile games, social networking applications, etc.). User perceptions of the quality of such MANET services will be driven, in part, by standard network-level quality of service (QoS) metrics such as delay, jitter, throughput, etc. Much of the existing MANET literature has explored these issues, as well as MANET routing protocol design, through single computer Monte Carlo simulations (e.g., via ns-2, ns-3, OMNeT++, or OpNet). Results are then reported as the averages of these Monte Carlo runs. As is well known from probability and statistics, such averaging is only meaningful when applied across statistically ergodic data (i.e., data drawn from the same underlying distribution). But, assessing the validity of this underlying ergodic assumption requires transitioning to more rigorous cluster-based MANET simulation frameworks. This work highlights the theoretical rationale for such ergodicity testing, the developments of a cluster-based framework, the STARs framework, to support such testing, and the results and insights obtained by using this framework to evaluate the popular DYMO and OLSR MANET routing protocols. This work also discusses why the insights ergodic testing provides are of interest to potential real-world MANET deployments.
Similar content being viewed by others
Notes
It is also possible that subsets of k are ergodic with respect to each other but not across the whole set K of Monte Carlo runs (i.e., ergodic modes of behavior may arise implying a degree of sensitivity exists with respect to the initial conditions).
This formalization of Birkhoff’s Ergodic Theorem is taken from [22].
It should be noted that if P t,k (x)=P k (x) then all statistics that can be calculated on P t,k (x) will also be time independent.
Assessing the true uncertainty in \(\hat {P}_{q,k}(x)\) requires that P t,k (x) be known, which is not. Hence, pragmatically the W k are set such that each W q,k for q>1 has at least 150 observed data samples.
Other stricter distribution free goodness-of-fit tests, such as the Anderson-Darling test, could be used, but goodness-of-fits test such as Pearson’s χ 2-test, requiring analytical knowledge of the P t,k (x) cannot be used.
The exact form of the CDFs is, of course, innately tied to the exact configuration scenario simulated in the Monte Carlo runs whereas the variations between the CDFs arise due to sensitivities to the initial conditions (i.e., each runs initial random seeds).
The sheer number of configuration parameters precludes directly including these details within this work.
References
Rahman, M., Al Muktadir, A.: The impact of data send rate, node velocity and transmission range on QoS parameters of OLSR and DYMO MANET routing protocols. In: 10th International Conference on Computer and Information Technology (ICCIT 2007), pp. 1–6 (2007)
Krasnovsky, M., Wieser, V.: A performance of wireless ad-hoc network routing protocol. In: 17th International Conference Radioelektronika 2007, pp. 1–3 (2007)
Benkovic, J., Kotuliak, I., Truchly, P.: Comparison of DSR and DYMO routing protocols in building environments. In: International Symposium ELMAR ’09, pp. 109–112 (2009)
Koltsidas, G., Karapantazis, S., Theodoridis, G., Pavlidou, F.: A detailed study of dynamic MANET on-demand multipath routing for mobile ad hoc networks. In: International Conference on Wireless and Optical Communications Networks (IFIP 2007), pp. 1–5 (2007)
Kum, D.W., Park, J.S., Cho, Y.Z., Cheon, B.Y.: Performance evaluation of AODV and DYMO routing protocols in MANET. In: 7th IEEE Consumer Communications and Networking Conference (CCNC), pp. 1–2 (2010)
Koltsidas, G., Pavlidou, F.N., Kuladinithi, K., Timm-Giel, A., Gorg, C.: Investigating the performance of a multipath DYMO protocol for ad-hoc networks. In: IEEE 18th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC 2007), pp. 1–5 (2007)
Malany, A., Chandrasekaran, R.: Mobility impact, timing analysis and repeatability issues of DYMO protocol in a precise mobile ad hoc network. Int. J. Comput. Sci. Netw. Secur. 9(6), 107–112 (2005)
OPNET. http://www.opnet.com/
OMNeT++. http://www.omnetpp.org/
The network simulator—ns2. http://www.isi.edu/nsnam/ns/
The network simulator—ns3. http://www.isi.edu/nsnam/ns/
Yoon, J., Liu, M., Noble, B.: Random waypoint considered harmful. In: Twenty-Second Annual Joint Conference of the IEEE Computer and Communications (INFOCOM 2003), vol. 2, pp. 1312–1321 (2003)
McGuire, M.: Stationary distributions of random walk mobility models for wireless ad hoc networks. In: Proceedings of the 6th ACM International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc ’05), pp. 90–98 (2005)
Millman, E., Arora, D., Neville, S.: STARS: A framework for statistically rigorous simulation-based network research. In: IEEE Workshops of International Conference on Advanced Information Networking and Applications (WAINA 2011), pp. 733–739 (2011)
Varga, A., Sekercioglu, A.: The OMNeT++ discrete event simulation system. In: Proceedings of the European Simulation Multiconference (2001)
Dreibholz, T.: In: SimProcTC: a powerful tool-chain for setup, distributed processing and analysis of OMNeT++ simulations (2009). http://www.iem.uni-due.de/~dreibh/omnetpp/
Sroka, S., Karl, H.: Using Akaroa2 with OMNeT++. In: Proceedings of the Second International OMNeT++ Workshop, pp. 43–50 (2002)
Seggelmann, R., Rungeler, I., Tuxen, M., Rathgeb, E.P.: Parallelizing OMNeT++ simulations using Xgrid. In: Proceedings of the 2nd International Conference on Simulation Tools and Techniques, pp. 1–8 (2009)
Dreibholz, T.: Applicability of reliable server pooling for real-time distributed computing. Internet-draft (2008)
Knop, R.: GNU-R. http://sonic.net/~rknop/php/Unux/R-.php
Papoulis, A., Pillai, S.: Probability, Random Variables and Stochastic Processes. McGraw Hill, New York (2002)
Barnes, J., Koss, L.: The ergodic theory carnival. Math. Mag. 83(3), 180–190 (2010)
Millman, E., Neville, S.: STARS: a framework for statistically rigorous simulation-based network research (2011). https://github.com/emillman/STARS
Bendat, J.S., Piersol, A.G.: Random Data: Analysis and Measurement Procedures, 3rd edn. Wiley-Interscience, New York (2000)
Lemeshko, B., Lemeshko, S., Postovalov, S.: Comparative analysis of the power of goodness-of-fit tests for near competing hypotheses. 1. The verification of simple hypotheses. J. Appl. Ind. Math. 3(4), 462–475 (2009)
Bendat, J.S., Piersol, A.G.: Random Data: Analysis and Measurement Procedures, 3rd edn. Wiley-Interscience, New York (2000)
Paxson, V.: Fast approximation of self-similar network traffic. Lawrence Berkeley Laboratory (1995). http://books.google.co.in/books?id=7C1JHAAACAAJ
Ikeda, M., DeMarco, G., Yang, T., Barolli, L.: Performance analysis of an adhoc network for emergency and collaborative environments. Telecommun. Syst. 38, 133–146 (2008)
Al-Maashri, A., Ould-Khaoua, M.: Performance analysis of MANET routing protocols in the presence of self-similar traffic. In: IEEE 31st Conference on Local Computer Networks Proceedings, pp. 801–807 (2006)
AhleHagh, H., Michalson, W., Finkel, D.: Statistical characteristics of wireless network traffic and its impact on ad hoc network performance. In: Applied Telecommunication Symposium Proceedings (2003)
Chakeres, I.D., Perkins, C.E.: Dynamic MANET on-demand routing protocol. ETF internet draft. draft-ietf-manet-dymo-12.txt (2008)
Millman, E.: Analyzing MANET jamming strategies (2011). http://dspace.library.uvic.ca:8080/handle/1828/3745
Koltsidas, G., Karapantazis, S., Theodoridis, G., Pavlidou, F.: A detailed study of dynamic manet on-demand multipath routing for mobile ad hoc networks. In: International Conference on Wireless and Optical Communications Networks (IFIP 2007), pp. 1–5 (2007)
Koltsidas, G., Pavlidou, F.N., Kuladinithi, K., Tinini-Giel, A., Gorg, C.: Investigating the performance of a multipath DYMO protocol for ad-hoc networks. In: Proceedings of IEEE 18th International Symposium on Personal, Indoor and Mobile Radio Communications, pp. 1–5 (2007)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Arora, D., Millman, E. & Neville, S.W. Enabling richer statistical MANET simulations through cluster computing. Cluster Comput 16, 989–1003 (2013). https://doi.org/10.1007/s10586-013-0247-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10586-013-0247-x