RVIP: bridging live networks and software virtual networks for large scale network simulation at real time

In this work we investigate real-virtual interface pair (RVIP), a new interface system proposed for hybrid network simulation. In the hybrid system, multiple live networks (LNs) and multiple software virtual networks (SVNs) are connected together via standard IP protocols in an arbitrary topology and at real time. RVIP seeks to implement a new Turing-indistinguishable mode so that an LN and its counterpart SVN are indistinguishable in regards to a third-party live node. To realize the new mode, three necessary conditions must be satisfied: (1) All needed changes incurred by introducing an SVN into a live network scenario are put on the simulation's side, RVIP requires that no change is made on any live node; (2) An SVN does not exchange simulation events with LNs, that is, only standard IP protocol interactions between SVN and LN are allowed. (3) Any LN can be dynamically plugged into the hybrid scenario at real time, just like being plugged into an equivalent purely live network. RVIP realizes the mapping between a live IP protocol stack and a virtual IP protocol stack (VIPS) by presenting a progressive series of connection patterns, namely mapping single virtual node to live node, combining LN with SVN and connecting multi-SVNs. Then we can construct more complex hybrid scenarios by combining these patterns. Compared to existing hybrid simulation efforts on NS-3, QualNet and OPNET, RVIP can support hybrid scenarios with multiple SVNs and multiple LNs connected by an arbitrary network topology. Our performance studies show that RVIP provides more efficient support in terms of common metrics such as larger throughput limit and smaller extra latency.

[1]  Dejan Kostic,et al.  Scalability and accuracy in a large-scale network emulator , 2002, CCRV.

[2]  Rajive L. Bagrodia,et al.  TWINE: A Hybrid Emulation Testbed for Wireless Networks and Applications , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[3]  Hao Wu,et al.  Large-scale network simulation: how big? how fast? , 2003, 11th IEEE/ACM International Symposium on Modeling, Analysis and Simulation of Computer Telecommunications Systems, 2003. MASCOTS 2003..

[4]  Xabiel G. Pañeda,et al.  Limitations of network emulation with single-machine and distributed ns-3 , 2010, SimuTools.

[5]  Daniel Mahrenholz,et al.  Real-Time Network Emulation with ns-2 , 2004, Eighth IEEE International Symposium on Distributed Simulation and Real-Time Applications.

[6]  Klaus Wehrle,et al.  Synchronized network emulation: matching prototypes with complex simulations , 2008, PERV.

[7]  Thomas Plagemann,et al.  Accuracy and scalability of ns-2’s distributed emulation extension , 2011, Simul..

[8]  Thomas Staub,et al.  VirtualMesh: an emulation framework for wireless mesh networks in OMNeT++ , 2009, SimuTools.

[9]  Joseph Ishac.  Traffic Generator , 2001 .

[10]  Lixia Zhang,et al.  Virtual Clock: A New Traffic Control Algorithm for Packet Switching Networks , 1990, SIGCOMM.

[11]  Jason Liu,et al.  Immersive real-time large-scale network simulation: A research summary , 2008, 2008 IEEE International Symposium on Parallel and Distributed Processing.

[12]  Yue Li,et al.  A large-scale real-time network simulation study using PRIME , 2009, Proceedings of the 2009 Winter Simulation Conference (WSC).

[13]  Kevin R. Fall,et al.  Network emulation in the VINT/NS simulator , 1999, Proceedings IEEE International Symposium on Computers and Communications (Cat. No.PR00250).

[14]  Klaus Wehrle,et al.  Device driver-enabled wireless network emulation , 2011, SimuTools.

[15]  Yi Yang,et al.  WHYNET: a hybrid testbed for large-scale, heterogeneous and adaptive wireless networks , 2006, WINTECH.

[16]  Yue Li,et al.  A real-time network simulation infrastructure based on OpenVPN , 2009, J. Syst. Softw..

[17]  Lixia Zhang.  VirtualClock: A New Traffic Control Algorithm for Packet-Switched Networks , 1991, ACM Trans. Comput. Syst..