SIMUTools 2008 Technical Program
Please consider also visiting the program pages of our associated events:
SimulationWorks, SIMUTools' Industry track
QoSim, the 1st International Workshop on the Evaluation of Quality of Service through Simulation in the Future Internet
PNPTAP, the International Workshop on Petri Nets Tools and APplications
OMNET++, the 1st International Workshop on OMNeT++
NCM&S 2008, the Workshop on Net-Centric Modeling & Simulation
Round Table: Future Trends & Challenges in Distributed Simulation
Richard M. Fujimoto (Georgia Tech),
David R.C. Hill (ISIMA, France),
Bernard P. Zeigler (U. Arizona & ACIMS)
Chair: Luiz Felipe Perrone, Bucknell University
|Paper 7312 (Full Paper)||Modelling Personnel within a Defence Logistics Maintenance Process
|Author(s)||Guy Edward Gallasch
a military deployment, the operational availability of deployed
equipment will be affected by many factors including the equipment
usage rates, sparing policy, and importantly the composition,
disposition and distribution of maintenance personnel. In this paper,
we present a Coloured Petri Net model that captures the potentially
complex defence logistics maintenance process that links these factors
together. We then identify some simulation performance concerns with
the way in which personnel have been incorporated into the model, and
evaluate a number of alternative models of personnel in an attempt to
attain an acceptable level of simulation performance for use in rapid
calculations for business reviews and headquarter operations planning.
Finally, we present some directions for future investigation to improve
simulation performance further.
|Paper 7398 (Full Paper)||Simulating Process Chain Models with OMNeT++
paper presents an approach to simulate complex hierarchical process
chains resulting from large logistics networks in OMNeT++, a discrete
event simulation environment designed for communication networks. For
this purpose OMNeT++ has been integrated as a new simulation engine
into the ProC/B toolset which is designed for the analysis
and optimization of large logistics networks. The paper highlights the
main steps of the automatic transformation of a hierarchical process
chain model into a hierarchical model in OMNeT++. Furthermore it shows
how the transformation has been validated and how detailed performance
figures can be evaluated with OMNeT++.
back to top...
|Paper 7588 (Full Paper)||TOPSU-RDM A Simulation Platform for Railway Delay Management
in a railway network is a common problem that railway companies face in
their daily operations. When a train gets delayed, it may either be
beneficial to let a connecting train wait so that passengers in the
delayed train do not miss their connection, or it may be beneficial to
connecting train depart on time to avoid further delays. These
decisions naturally depend on the global structure of the network and
on the schedule.
The railway delay management (RDM) problem (in a broad sense) is to
decide which trains have to wait for connecting trains and which trains
have to depart on time.
The offline version (i.e. when all delays are known in advance) is
already NP-hard for very special networks. In this paper we show that
the online railway delay management~(ORDM) problem is PSPACE-hard and
present TOPSU-RDM, a simulation platform for evaluating and comparing
different heuristics for the ORDM problem
with stochastic delays. Our novel approach is to separate the actual
simulation and the program that implements the decision making policy,
thus enabling implementations of different heuristics to ``compete'' on
the same instances and delay distributions. For RDM and other logistic
planning processes, it is our goal to bridge the gap between
theoretical models, which are accessible to theoretical analysis, but
often too far away from practice, and the
methods which are used in practice today, whose performance is almost
impossible to measure.
Chair: Sandor Molnar, Budapest Univ. of Technology and Economics, Hungary.
|Paper 7203 (Full Paper)||A Framework for End-to-end Simulation of High-performance Computing Systems
present an end-to-end simulation framework that is capable of
simulating High-Performance Computing (HPC) systems with hundreds of
thousands of interconnected processors. The tool applies discrete event
simulation and is driven by real-world application traces. We refer to
it as MARS (MPI Application Replay network Simulator). It maintains
reasonable simulation details of both the processors in general and
specifically the interconnection network. Among other things, it
features several network topologies, flexible routing schemes,
arbitrary application task placement, point-to-point statistics
collection, and data visualization. With a few case studies, we
demonstrate the usefulness of this tool for assisting high-level system
design as well as for performance projection and application tuning of
future HPC systems.
|Paper 7547 (Full Paper)||P2PAM: a Framework for Peer-to-Peer Architectural Modeling based on PeerSim
peer-to-peer architectural model defines an overlay network topology
and a routing strategy. If these aspects are tied together by a
deterministic logical model, we say that the architecture is
structured. Otherwise, we say it is unstructured. Based on these
assumptions, in recent years many complex P2P architectural models have
been defined, their performance evaluation being carried out mainly by
means of simulative tools. However, there is an emerging need for a
general-purpose tool, enabling large-scale overlay network simulations,
yet also providing ready-to-use complex building blocks. The widely
known PeerSim simulator addresses the first issue quite effectively,
although it appears quite limited with respect to several important
aspects, i.e. churn modeling. In this paper we propose P2PAM as a
PeerSim enhancement providing a rather complete framework for
peer-to-peer architectural modeling. P2PAM effectiveness is
demonstrated by showing how it has been used to rapidly develop
simulations of two interesting systems, namely JXTA and HALO.
back to top...
|Paper 7563 (Full Paper)||Simulating SMEPP Middleware
,Jose Angel Dianes
Peer-to-Peer Systems (EP2P) represent a new challenge in the
development of software for distributed systems. The main objective of
the SMEPP (Secure Middleware for Embedded Peer-to-Peer Systems) project
is to develop a new middleware, based on a new network centric abstract
model, specially designed for the above described systems, and trying
to overcome the main problems of the currently existing domain specific
middleware proposals. This paper presents a SMEPP Middleware
component-based simulation tool. The main objective of develop this
simulator is to provide a tool to enable the testing of the service
model proposed for the middleware and to provide a framework to test
different middleware design choices. Simulations help us to make future
decisions. Simulate SMEPP applications, that is, applications running
on the SMEPP middleware and based on the API that it offers, help us to
make decisions about the most requirement-satisfactory way of
constructing the middleware. The simulated middleware API component
represents a first approach to middleware design, and introduces some
of the architectural issues that must to be solved in the next future.
Chair: Giovanni Stea, University of Pisa, Italy.
|Paper 7123 (Full Paper)||Importance Sampling in Rate-Sharing Networks
consider a network supporting elastic traffic, where
the service capacity is shared among the various classes according
to an alpha-fair sharing policy. Assuming Poisson arrivals and
exponentially distributed service requirements for each class,
the dynamics of the user population may be described by a Markov
process. We focus on the probability that, given that the network is in
some state $n_0$ at time $0$, the network is in some set of states $A$
at time $T$. In particular, we assume that the
underlying event is rare, i.e., the probability of interest is small.
As in general no explicit expressions are known for
this probability, an attractive approach may be to resort to
Monte-Carlo (MC) simulation.
However, due to the rarity of the event under consideration, MC
simulation is infeasible. A natural approach
to speed up the simulation is to use Importance Sampling (IS). We
present an IS algorithm to accelerate the simulation
that is based on large deviations results. With extensive simulation
experiments we assess the performance of the
algorithm; under rather general conditions a considerable speed-up is
|Paper 7250 (Full Paper)||Integration of Streaming and Elastic Traffic: A Fixed Point Approach
present a fixed point approach to evaluate the quality of service of
streaming traffic multiplexed with elastic traffic in multi-service
network. First, we handle elastic traffic66 and streaming traffic
separately, and then we derive a general fixed point formulation
integrating both types of traffic in best effort networks. Then, we
extend the application of this formulation to multi-service networks
where priorities and bandwidth sharing schemes can be applied to
different flows. Our approach is mainly oriented towards very large
scale networks where traditional simulation techniques are not
scalable, and where a large number of flows have to be evaluated in
reasonable time. We assess the accuracy of our approach by means of
|Paper 7498 (Full Paper)||Using LiTGen, a realistic IP traffic model, to evaluate the impact of burstiness on performance
practical reasons, network simulators have to be designed on traffic
models as realistic as possible. This paper presents the evaluation of
LiTGen, a realistic IP traffic
model, for the generation of IP traffic with accurate time scale
and performance. We confront LiTGen against real data traces using two
methods of evaluation. These methods respectively allow to observe the
causes and consequences of the traffic burstiness. Using a wavelet
spectrum analysis, we first highlight the intrinsic characteristics of
traffic and show LiTGen's ability to reproduce accurately the captured
traffic correlation structures over a wide range of timescales. Then, a
performance analysis based on simulations quantifies the impact of
these characteristics on a
simple queuing system, and demonstrates LiTGen's ability to generate
leading to realistic performance. Finally, we conduct an
investigation for a possible model reduction using memoryless
back to top...
|Paper 7555 (Full Paper)||A method for validating the aggregated signaling traffic model using simulations in ns-2 platform
|Author(s)||Jordi Mongay Batalla
the architectures of the networks, which offer Quality of Service
(QoS), the setup procedure is the exchange of signaling messages to
complete the codec agreement and the resource reservation. This
exchange of packets between two or more signaling entities causes that
this traffic strongly depends on the network scenario and network
conditions. Therefore, it is very difficult to find general signaling
traffic models, which are valid for any scenario. In this paper we
propose a method for validating the aggregated signaling traffic model.
This validation is performed using our own developed module of the ns-2
simulator, which simulates the signaling message exchange during the
connection setup in an IP based network with QoS guaranties. For this
new simulation tool, we provide technical description and discuss some
implementation issues under ns-2 platform. The final results of the
validation process show under what traffic conditions the versatile
Poisson model is valid. The drawn conclusions provide some guidelines
for the usage of analytical models in the network provisioning process
concerned with signaling traffic.
Chair: Thomas R. Henderson, Boeing & Univ. Washington
|Paper 7556 (Full Paper)||Design and Implementation of a QoS-included WiMAX Module for NS-2 Simulator
is a very promising technology. The main promises are the high
throughput and the large coverage. As for all new technologies,
performance studies are required. The network simulation is considered
as a solution to test the performance of technologies and especially
the wireless networks. In this paper, we propose a new WiMAX module for
NS-2 simulator. This module is based on the NIST implementation of
WiMAX . Our contributions consists of the addition of the QoS
classes as well as the management of the QoS requirements, unicast and
contention request opportunities mechanisms, and scheduling algorithms
for the UGS, rtPS and BE QoS classes. Simulations results provide
interesting observations about the throughput and mean sojourn time
values. Simulation results show that our UGS, rtPS, and BE schedulers
are in accordance with the specification of the QoS classes defined in
the IEEE 802.16 standard.
back to top...
|Paper 7650 (Full Paper)||An 802.16 Model for NS2 Simulator with an Integrated QoS Architecture
|Author(s)||Ikbal Chammakhi Msadaa
to its ability to support multimedia services and to operate in
multiple physical environments, the IEEE 802.16 technology emerges as a
promising solution for BWA. Also, with data rates in excess of 120
Mbps, it provides a cost-effective alternative to wireline broadband
access systems. Unfortunately no open-source simulation environment
supporting this technology has been proposed so far. Therefore this
work is meant to be a contribution to build an 802.16 simulation model
for NS2, the most popular network simulator. In this paper, we present
the details of design and implementation of the proposed simulation
model. Our model includes a novel QoS architecture, and addresses
802.16 fixed BWA systems that use Orthogonal Frequency Division
Multiplexing (OFDM) modulation and operate in TDD mode. The QoS
architecture we propose consists in a call admission control (CAC)
policy and a hierarchical scheduling algorithm that flexibly adjusts
uplink and downlink bandwidth to serve unbalanced traffic. Both
scheduling and CAC algorithms are based on an adaptive modulation and
coding (AMC) scheme.
Chair: Gabriel Wainer, Carleton University, Canada.
|Paper 7164 (Full Paper)||TopGen - Internet Router-Level Topology Generation Based on Technology Constraints
order to realistically simulate algorithms and evaluate overlay
topologies for the Internet, a detailed model of the underlying router
topology is required. Since actively measuring this topology is
extremely laborious and furthermore a waste of network resources,
traditionally topology generators are used in order to create synthetic
router-level graphs. For this, usually graph models are selected that
are known to generate graphs which are similar to the actual Internet
in respect to a certain metric like e.g. vertex degree distribution.
These models are often superseded or adjusted as soon as new metrics
are being introduced which better differentiate between graphs.
Furthermore it has been shown, that graphs that are similar in respect
to e.g. vertex degree distribution can be very different from a
structural point of view. In this paper TopGen, a generic, extensible
and easy-to-use topology generation platform is presented. It contains
a topology generation module which bases the generation of router-level
graphs on the Internet's underlying principles and the technological
constraints of routers rather than trying to effectuate similarity in
respect to a certain metric. Apart from describing TopGen's general
topology generation approach, graphs created with its Internet topology
module are evaluated and found to be encouragingly similar to
real-world datasets in various respects.
|Paper 7201 (Full Paper)||Extending the Functionality of RTP/RTCP Implementation in Network Simulator (NS-2) to support TCP friendly congestion control
this paper, we present a modification of the ns2 code for the RTP/RTCP
protocols. The legacy RTP/RTCP code in ns2 has not yet validated but it
provides a framework of the protocol’s specification for experimental
use. We have modified the code by adding most of the RTP/RTCP
protocol’s attributes that are defined in RFC 3550. We also implemented
additional algorithms and functions in order to enhance our modified
code with TCP friendly bandwidth share behavior. Our protocol, named
RTPUP (“UP” stands for the University of Patras), is offered as a
package and is fully documented so that it can be used for simulations
and research within the ns2 simulation environment.
back to top...
|Paper 7549 (Full Paper)||Implementing MAC Protocols for Cooperative Relaying: A Compiler-Assisted Approach
the performance of a cooperative relaying protocol requires an
implementation for simulators and/or software-defined radios (SDRs)
with an appropriate model for error detection, combining, and Medium
Access Control (MAC) automaton. Such implementations are essential for
meaningful evaluation of practical systems since any protocol
introduces overhead that constrains the theoretical performance in
non-obvious ways. Unfortunately, protocols for cooperative relaying
often yield complex implementations which are tedious to implement and
debug. Therefore, we identify basic operations that are inherent to all
cooperative relaying protocols, and we propose a new specification
language for their specification. Then, we show how to construct a
compiler for the proposed language that generates most of the required
implementation (model and MAC automaton) automatically. This approach
prevents subtle mistakes during implementation of the protocol, and can
significantly increase development time. In addition, this paper
discusses code generation exemplarily for OMNeT++/Mobility Framework,
but the approach is not restricted to a specific simulator or SDR.
Chair: Luiz Felipe Perrone, Bucknell University
|Paper 7302 (Full Paper)||Application-level simulation for network security
introduce and describe a novel network simulation tool called NeSSi
(Network Security Simulator). NeSSi incorporates a variety of features
relevant to network security distinguishing it from general-purpose
network simulators. Its capabilities such as profile-based automated
attack generation, and traffic analysis allow it to be used for
security research and evaluation purposes. NeSSi has been utilized for
testing intrusion detection algorithms, conducting network security
analysis, and developing distributed security frameworks at the
application level. NeSSi is built upon the agent componentware
framework JIAC, resulting in a flexible, distributed, and
easy-to-extend architecture. In this paper, we provide an overview of
the NeSSi architecture and briefly demonstrate its usage in two example
security research projects.
|Paper 7304 (Full Paper)||An Investigation of Credit-based Flow Control mechanisms
flow control mechanisms, such as those used in the Transmission Control
Protocol, allow flow control and error control procedures of data
transfer protocols to operate independently. We create a Coloured Petri
Net model of a class of data transfer protocols, which uses
retransmissions and acknowledgements for error control and ``credits''
for flow control. This model is characterized by 3 parameters: the
maximum sequence number, the maximum number of retransmissions and the
maximum receiver buffer size. From the analysis results, we derive
expressions in these parameters for the channel bounds and the number
of terminal states. These expressions are verified for a range of
values of the parameters.
back to top...
|Paper 7583 (Full Paper)||MAlSim - Mobile Agent Malware Simulator
,Igor Nai Fovino
of the problems related to the simulation of attacks against critical
infrastructures is the lack of adequate tools for the simulation of
malicious software (malware). Malware attacks are the most frequent in
the Internet and they pose a serious threat against critical networked
infrastructures. To address this issue we developed Mobile Agent
Malware Simulator (MAlSim). The framework uses the technology of mobile
agents and it aims at simulation of various types of malicious software
(viruses, worms, malicious mobile code). Moreover it can be flexibly
deployed over computer network of an arbitrary information system.
Chair: Jonathan Billington, University of South Australia
|Paper 7184 (Full Paper)||Vehicular Mobility Modelling: A Potential-Flow Approach
,Sean Mc Grath
studies have shown mobility characteristics of vehicles are determined
by physical environments and time which until now have not been
incorporated into synthetic mobility models. Empirical data from
Departments of Transport provide these characteristics and the
integration of these data sets with potential flow theory give the
proposed model realism and flexibility. The model is used to create a
highway lane where travelling cars communicate using wireless
technology. Various routing protocols are evaluated for anti-collision
|Paper 7332 (Full Paper)||Simulation of Ad Hoc Networks: ns-2 compared to JiST/SWANS
the evaluation of ad hoc network protocols, researchers traditionally
use simulations because they easily allow for a large number of nodes
and reproducible environment conditions. But still, simulations are
costly in terms of required processing time and memory. New approaches
like the Java-based simulator JiST/SWANS promise to provide significant
performance advantages compared to existing, well-known network
simulators like ns-2. Though its creators have done comparison studies
regarding processing time and memory requirements of JiST/SWANS, they
did not test the validity of the results produced by the SWANS stack as
well as its performance in detail. In this work, we focus on the
comparability of the implemented protocols and models in SWANS. Using
the corresponding counterparts both in SWANS and ns-2, with
an identical set of parameters, we are able to produce results and
compare them afterward. In addition, we also provide a performance
analysis using these simulations. By showing that JiST/SWANS produces
equivalent simulation results as ns-2 in less time and with less
memory, we support JiST/SWANS as a potential alternative.
|Paper 7579 (Full Paper)||ns-2 vs. OPNET: a comparative study of the IEEE 802.11e technology on MANET environments
|Author(s)||P. Pablo Garrido
,Manuel P. Malumbres
,Carlos T. Calafate
this work we present the results of a comparative study
between two well-known network simulators: ns-2 and OPNET Modeler. In
particular, we focus on a performance evaluation of the IEEE 802.11e
technology on Mobile Ad-hoc Networks (MANETs) in both stationary and
mobile scenarios. The paper describes the tested scenarios in detail,
and discusses simulation results obtained with OPNET Modeler, comparing
them with those obtained with ns-2. The performance of IEEE 802.11e in
the presence of legacy IEEE 802.11 stations is also analyzed. Due to
the significant differences between both simulators, we enumerate those
changes required so as to make results obtained via both simulators
comparable. The results that have been reached support the conclusion
that the behavior of both simulators is quite similar in general. We
believe that such finding validates simulation results obtained with
either of them.
back to top...
|Paper 7593 (Full Paper)||MOMOSE: A Mobility Model Simulation Environment for Mobile Wireless Ad-hoc Networks
,Miriam Di Ianni
paper describes MOMOSE, a highly flexible and easily extensible
environment for the simulation of mobility models. MOMOSE not only
allows a programmer to easily integrate a new mobility model into the
set of models already included in its distribution, but it also allows
the user to let the nodes of the MANET move in different ways by
associating any mobility model to any subset of the nodes themselves.
Moreover, MOMOSE can be easily adapted in order to record, during the
simulation time, all the data necessary for the evaluation of the
performance of any communication protocol or of any MANET-based
Session 8 (Short Papers)
Chair: Tania Jimenes, University of Avignon
|Paper 7219 (Short Paper)||PDST: A Peer Database Simulation Tool for Data Sharing Systems
|Author(s)||Md Mehedi Masud
present there are many simulation tools developed in order to simulate
P2P systems. All the simulators are dedicated to peer-to-peer (P2P)
content distribution, network simulation for measuring efficiency of
the network, and file sharing systems. In the last few years, steady
progress has been made in research on peer database systems. However,
there is no simulator that helps the research community of the peer
database systems to experiment their work in a large P2P environment.
In this paper, we present a simulation tool that can simulate a real
P2P database system. Using the simulator, a user can create peers,
databases with synthetic data, acquaintances, mappings between peers,
and perform different operations (e.g. queries and updates). The
simulator provides a GUI to set different parameters for experimenting
a peer database system.
|Paper 7266 (Short Paper)||Interface connecting the INET simulation framework with the real world
,Erwin P. Rathgeb
|Abstract||The INET framework for the widely used OMNeT++ simulation environment supports
discrete event simulation for IP-based networks. During the development of a
simulation model for the new IETF transport protocol SCTP within this framework,
INET was extended to also support external interfaces.
These interfaces allow to set up hybrid scenarios where simulated nodes
communicate with real external IP-based nodes.
This paper will first give a short introduction on OMNeT++ and the
INET framework. Then the requirements for the external interfaces will be discussed
and some implementation aspects will be described. Hybrid scenarios offer a whole
range of potential applications which will also be presented briefly.
The performance of this technique is crucial for its applicability.
Therefore, several test setups are evaluated to verify the feasibility of
|Paper 7318 (Short Paper)||A post-processed 3D visualization tool for forest fire simulations
,David RC Hill
collaboration between simulationists and scientists working on fire
spread and ecology led to the design of a 3D visualization tool. This
tool is a post-processor which can be linked to existing discrete event
fire spread models. An object-oriented analysis and design has been
retained to produce flexible open source software. The tool developed
can produce realistic 3D landscape rendering of fire spread on regular
PC. This software is now used in Corsica to help in prospective studies
around the region of Montegrosso.
back to top...
|Paper 7582 (Short Paper)||A Windows Based Web Cache Simulator Tool
this paper, we describe a Windows based Web cache simulator tool. This
tool is able to process the IRCache based traces files and reproduce
the behavior of a Web Proxy Cache. It can be configured to simulate
fifteen replacement policies and two admission control policies. The
cache size, the percentage of warm-up and the cost function of some
replacement policies can also be configured. The simulations can be
performed in a batch process and the results are stored in text format
files that can be automatically analyzed using other tools like Matlab
to obtain performance graphs.
Session 9: Invited Session & Round table
Chair: Olivier Dalle, Université de Nice Sophia Antipolis, CNRS & INRIA, France.
|Paper I001 (Invited Paper)||MARTE: A Profile for RT/E Systems Modeling, Analysis -and Simulation?
,Robert de Simone
|Abstract||As its name promises, the Unified Modeling Language (UML) provides a collection of diagrammatic modeling styles. To the early class/objects and use-case diagrams were almost immediately added state-, activity-, collaboration-, and component diagrams. All these modeling views, required for structural and behavioral representations of systems, were then progressed to further detailed expressivity. Provision for domain-specific specializations was made under the form of (augmented) profiles.
Somehow this goal of being rather universal and extendible discarded the possibility of UML to adopt too strict and precise a semantics; as users were generally to define and refine it in their stereotyped profiles anyway. As a result, even the little execution semantics there is in the standard is often not considered in such specializations.
We tackled the general issue of defining a broadly expressive Time Model as a sub-profile of the upcoming OMG Profile for Modeling and Analysis of Real-Time Embedded systems (MARTE), currently undergoing finalization at OMG. The goal is to provide a generic timed interpretation, on which timed models of computation and timed simulation semantics could be built inside the UML definition scope, instead of as part of the many external proprietary profiles. The MARTE time library can be used as the basis for the definition of a UML real-time simulator.
back to top...
|Paper I002 (Invited Presentation)||Virtualization and distributed computing for stochastic simulation
|Author(s)||David R.C. Hill
|Abstract||Among the new computer science buzzwords we are now (re)discovering virtualization. Since the sixties IBM was providing virtual machines abstracting computer hardware and resources. We will present the current status of virtualization taxonomy and we will give a larger focus to the virtualization of resources that we observe in distributed computing. Grid computing will also be discussed (as a virtualization of resources) and the case of successful large scale simulations on the EGEE Grid will be presented. The presentation will also deal with the distribution of stochastic simulations and of simulation experiments (whether stochastic or not). The different techniques in use to distribute pseudo-random numbers will be presented as well as possible research directions.
Session 10 (Posters)
|Paper 7220 (Poster)||Design of a Web-based Visual Simulator and its Evaluation based on some cases of Real Computer Education
|Abstract||A visual computer simulator has been designed and developed
to help learners to understand computer architecture and organization efficiently.
It is used in a real education, such as classroom lecture of computer architecture
and exercise of assembly programming.
Our simulator is written in a pure Java language and works not only as an applet
but also as a stand-alone application.
Its graphical user interface (GUI) provides visual simulating function
in the register-transfer level and assists beginners of computer science
to comprehend how a computer works.
The simulator also equips built-in e-mail handlers to facilitate communicating function
and supports asynchronous information sharing between learners and instructors.
We have applied our simulator into a real education and evaluated its simulating and
This paper reports statistic evaluation of visualization and communication by means of
chi-square-test and t-test, respectively.
It is confirmed that capabilities of visualization and communication of our visual
simulator are statistically significant.
|Paper 7223 (Poster)||PlanetSim: An extensible framework for overlay network and services simulations
|Author(s)||Jordi Pujol Ahullo
,Pedro Garcia Lopez
,Marc Sanchez Artigas
,Marcel Arrufat Arias
,Gerard Paris Aixala
community on distributed systems, and in particular
on peer-to-peer systems, needs tools for evaluating their own protocols
and services, as well as against other protocols with the same
precondictions. Since a (TCP/IP) experimental evaluation is not always
feasible, simulation tools appeared.
In this paper we introduce PlanetSim, a discrete event-based
simulation framework for overlay networks and services, as
well as extensions from third parties that prove its true extensibility
and adaptability to the reserarchers' needs. In addition, we introduce
within PlanetSim a novel way of implementing peer-to-peer overlay
protocols based on behaviors.
|Paper P001 (Poster)||An open and free Scilab/Scicos toolbox for the modelling
and simulation of communication systems
|Abstract||ßModnumŕ is an open source and free Scilab/Scicos
toolbox for the modelling and simulation of communication
systems. It is downloadable since March 2006 and have been
primary designed for the research and development of new
secured systems based on chaos. Today the toolbox gives
many Scilab functions and Scicos blocks that mainly focus
on spread-spectrum systems for both Direct-Sequence(DS)
systems and Frequency Hopping(FH) systems.
|Paper P002 (Poster)||Performance Study by Simulations of Intersection Location Service
Compared to Two Location Service Algorithms for Vehicular Ad Hoc
Networks in Metropolitan Environments
|Abstract||Numerous works have been found on location
service algorithms for random waypoint VANETs but
very few in metropolitan environments. In this paper,
we have studied the performance of Intersection
Location Service (ILS), a novel location service
algorithm that is designed to work in the city
environments with streets and intersections. A faultrecovery
mechanism based on the Chord algorithm is
used to retrieve location information of vehicles when
the corresponding location services go out of service.
The simulation analysis compares the performance of
the proposed scheme with other two location based
algorithms (GLS, HLS). The simulation results confirm
the effectiveness of the ILS scheme in terms of
increased success ratios under different network
topologies. We also found the ILS algorithm not only
remains robust at high car speeds but also demonstrates
higher scalability than the other two with respect to
|Paper P003 (Poster)||WCET Determination Tool for Embedded Systems Software
,Michael Werner, Rudolf Fuchsen
|Abstract||Embedded systems are special-purpose computer systems
within environments such as automotive, avionic, telecom-
munication, etc. As these systems often perform time-critical
control tasks, it is necessary to precisely predict their be-
haviour. Software-based solutions on the one hand provide
high flexibility. On the other hand, especially when multi-
ple software processes are to be executed concurrently on
the same hardware, the software approach makes prediction
more difficult. Predictions essentially rely on the knowledge
of when a software process terminates. For a reasonable
system architecture it has to be known at an early stage of
design time to scale the system well. Dynamic factors such
as cache usage, amount of data, and availability of shared
resources have great impact on the result. Thus, tools are
necessary to determine execution time as accurate as pos-
sible. The execution time is commonly approximated by
determining the interval of best and worst case execution
time (BCET & WCET). While the BCET can be roughly
estimated by evaluating the shortest path the achievement
of good approximations for the WCET is heavy. Consid-
ering all possible execution paths of the analysed program
as well as the effects of the underlying architecture on the
timing properties affected by pipelining and caches create
a hard issue to solve. Nevertheless these figures are impor-
tant in certification processes in the application fields given
above as well as performance prediction and solving design
issues. Another motivation is the lack of tools targeted to
an intermediate level of abstraction. In general tools are
retargetable frameworks analysing high-level code with so-
phisticated algorithms or similar algorithms are applied to
low-level code that lacks context and type information.
|Paper P004 (Poster)||How to implement a layer 2 bridge in ns-3
|Abstract||The main objective of this poster is to show the key points
of the ns-3 software architecture in order to modify its internal
functionality (e.g. creation of new module). It is intended
for those researchers that want to use ns-3 for their
simulations and need more than a simple user level platform.
The work presented in here is the first part of a larger
project which objective is to build a layer-2 simulation platform
(concretely IEEE 802.1). The first step is to implement
a separate node that contains the basic functionalities
of a layer-2 interconnection element (bridge). The main features
this platform requires are (a) extensibility to improve
the simulator with added functionalities; (b) scalability to
simulate large network topologies; and (c) user interface to
execute massive simulation runs in order to deal with a complete
ns-3 has been elected as the base of the simulation. It is a
discrete-event simulator based on a modular object-oriented
architecture with very intuituve classes for networking researchers
(e.g. a node works with the usual OSI layers).
Moreover, ns-3 will probably become the most used simulator
within the research community in the next few years.
|Paper Q001 (Poster)||Performance Study of the Mobile IPv6 Protocol and its Variations
|Abstract||In this paper, we use the OMNET++ simulator in order to evaluate the performance of the basic Mobile IPv6 protocol and some of its proposed variations. The most important metric we are interested in is the handover latency, which we measure for various combinations of the proposed Mobile IPv6 variations and then use this metric, combined with factors such as the complexity of the implementation, in order to evaluate and identify the best possible configuration for the operation of the protocol
|Paper Q002 (Poster)||Comparison of Steady-State Methods Computing Markov Modulated Fluid Models
|Abstract||The Markov-modulated fluid models are mathematical tools widely used in telecommunication networks modeling. These models assimilate the discrete entities of the network traffic into a continuous fluid whose rates depend on a background Markov process.The study of the fluid models shows that they are governed by a linear differential system. Many techniques are used to solve these equations such as spectral analysis, Laplace transforms, orthogonal polynomials and recurrence relations. The purpose of this work is to study mathematically the resolution techniques and to compare their computational complexity accuracy and stability.
|Paper Q003 (Poster)||Impact of traffic models on access management for heterogeneous mobile networks
|Author(s)||Juan Antonio Guerrero Ibańez
|Abstract||Traffic characterization for the dimensioning of cellular networks has traditionally relied on Poisson models, with the underlying assumption that such networks would primarily carry voice traffic. However, future mobile networks increasingly carry a mix of voice, data and multimedia traffic. In particular, the advent of fourth generation (4G) systems brings about the need to consider the impact of different services, and the terminal mobility in designing, dimensioning and optimizing the network. It is well accepted that Poisson arrival assumptions do not accurately model service traffic, which often exhibits self-similar characteristics. In this paper we analyze the impact of traffic models on the performance of heterogeneous mobile communication systems. We perform a study about user mobility behavior into an urban zone; we generate a traffic model based in the results of the study. We analyze the impact of the different traffic models on performance of access management in heterogeneous mobile systems. Moreover, results from the application of the analyzed models in a simulation network are also contained.
back to top...
|Paper Q005 (Poster)||Upstream Traffic Management in EPONs : A Simulation Based Analysis
|Author(s)||NGO Minh Thanh
|Abstract||To meet the explosive increase in network traffic that has occurred due to the rapid growth of the Internet, the Passive Optical Network (PON) with Dynamic Bandwidth Allocation (DBA) is considered to be one of the most cost-effective solutions. This new technology is intended to provide a simple, scalable solution which is capable of delivering multiservice access to end-customers. The
standards have been approved, but bandwidth distribution between users and QoS provisioning has been left to the implementer.
In particular, there have been many proposals of dynamic bandwidth allocation (DBA) mechanisms to be implemented in the upstream channel. An ideal DBA should support both Committed Bandwidth (CB) and Best Effort services, with a good control of the usual QoS characteristics (delay, jitter, loss) while utilizing the available bandwidth with a good efficiency. There is currently no generally recommended DBA and therefore, there is a need to develop methodologies to evaluate and to compare existing proposals. This paper first presents the characteristics of a generic simulation platform that is currently developed in our team to evaluate the performance characteristics of PONs DBAs and to assess the efficiency of their QoS support. It also demonstrates how a simple priority based traffic management
can efficiently support both QoS sensitive SLAs and Best-Effort transport.
Chair: Andrea d'Ambrogio, University Roma "Tor Vergata"
|Paper 7139 (Full Paper)||Bridging UMTS and Multicast Routing in ns-2
this paper, we present the design and the implementation of a novel
scheme for the multicast transmission of data over Universal Mobile
Telecommunications System (UMTS) networks. The proposed scheme is
implemented as an ns-2 network simulator module which can be employed
to investigate various aspects of UMTS multicast. Apart from the normal
multicast transmission over UMTS, we consider the handling of
exceptional cases induced by user mobility scenarios. The proposed
scheme is in accordance with the current specifications of the
Multimedia Multicast/Broadcast Service (MBMS) defined by the 3rd
Generation Partnership Project (3GPP) and introduces minor
modifications in the UMTS architecture and the mobility management
mechanisms. The performance of the proposed scheme is validated and
analyzed through simulation experiments. Finally, the simulation
results are presented along with their analysis.
|Paper 7195 (Full Paper)||Path Computation Algorithms in NS2
designed to improve the efficiency of packets forwarding, MPLS provides
support for Traffic Engineering and network resilience.
Constrained-based path computation is a key building block for Traffic
Engineering in MPLS networks, since it allows to set-up LSPs along
paths that satisfy QoS constraints.
This paper deals with three distinct categories of path computation
algorithms: on-line path computation algorithms, online multi path
algorithms, and novel off-line path computation algorithms. All these
algorithms have been implemented in NS2 as an extension of OSPF-TE\ns
and integrated with RSVP-TE\ns.
back to top...
|Paper 7494 (Full Paper)||Software Development for Automated Network Design Supporting Unicast and Multicast Traffics in Next Generation Network
this paper, a summary has been presented on our experiences in
developing a software tool for IP/MPLS NGN traffic engineering
computations. The developed NGN software consists of three main
modules. Firstly, the NGN design module can be used to help network
engineers find the minimum link capacity needed for NGN unicast (e.g.
VoIP service) and multicast service (e.g. VDO conference) provision
while maintaining the resultant QoS at a specified target level.
Secondly, the NGN performance analysis module is based on a
discrete-event simulation of sequential routing and trunk reservation
CAC. This module can be used to help network engineers analyse the
performance of NGN. It can also be used to predict the effect of link
failure, traffic surge and new routing plan implementation. Finally,
both the NGN design and performance analysis modules can be executed
via the developed NGN GUI module. With GUI, network engineers can
visualise the status of network components. Further, GUI permits both
entering and editing all relevant network parameters efficiently. It is
therefore very convenient for our developed NGN software to be utilised
in practice and should be an indispensable traffic engineering tool for
improving the NGN planning and operational tasks.
Chair: Adelinde Uhrmacher, University of Rostock, Germany.
|Paper 7175 (Full Paper)||Real-time emulation of networked robot systems
this paper we present a methodology for the evaluation of networked
systems communicating using WLAN technology. We show a case study of
goal-oriented cooperating robots, for which our approach is
particularly useful. Developing robots is expensive; hence emulation
can be employed in the first part of the development cycle to study
robot software implementations in realistic conditions at a reduced
cost. Our methodology is based on the emulation of both the robots and
the WLAN communication technology. The robots we consider cooperate in
order to reach a destination while avoiding collisions. The WLAN
communication emulation engine QOMET is deployed in the emulated robots
to allow recreating network conditions similar to those occurring in a
real WLAN environment. The experiments are run on a large-scale network
experiment environment, StarBED, using the support software Rune.
Currently, over one hundred emulated robots can be run simultaneously
during an experiment on our testbed.
|Paper 7587 (Full Paper)||PRT Simulation in an Immersive Virtual World
|Author(s)||Cristina V. Lopes
virtual world environments, such as Second Life (SL), have the
potential to dramatically improve the process of analyzing usability
within technically correct system simulations, long before the system
is built. We report our findings with the SL simulation of a Personal
Rapid Transit (PRT) system. The SL model and simulation were done
according to the original technical specifications. In interacting with
this simulation, the system designers were able to identify several
usability issues that would have gone unnoticed in a non-immersive
simulation environment. Namely: (1) a problem with the design of the
offramp to the station; (2) further requirements for the design of the
top of the vehicles, so that the suspended track is out of direct sight
of the people inside; (3) further safety requirements for dealing with
unexpected obstacles along the path.
While all of these issues would have been identified upon
deployment of the physical prototype, the contribution of our work is
to show how usability issues like these can now be identified much
earlier, using simulations in a virtual world.
back to top...
|Paper 7600 (Full Paper)||A Grid-Enabled Toolkit for In Silico Oncology Simulations
Silico Oncology is a multi disciplinary field that has as a subject the
examination and modeling of the mechanisms that constitute the
phenomenon of cancer. The simulation model may be used for evaluating
and comparing different therapeutic schemes and thus providing some
indication about the optimal treatment of a specific patient. Because
of the exponential increase in requirements for computational resources
as the precision of simulation increases, and also due to the large
number of potentially involved patients, a grid environment is
considered as an opportunity to execute these simulations and make the
In Silico Oncology available to the biomedical and research community.
In this paper, we describe a toolkit that enables the execution of In
Silico Oncology simulations on grid infrastructures. This toolkit is
designed and developed as a web portal with advanced features that
facilitates the execution of In Silico Oncology simulations in grid
environments. Several scenarios of radiotherapy simulations have been
performed on the EGEE grid and indicative simulation results, as well
as execution times are presented.
Chair: Pierluigi Crescenzi, University of Florence
|Paper 7149 (Full Paper)||Embedded System Protocol Design Flow based on SDL: From Specification to Hardware/Software Implementation
(Specification and Description Language) is popular for
communication protocol design. SDL tools allow simulating and verifying
SDL models. In this paper, we show how SDL models can be transformed
into hardware/software implementations for embedded systems. Our design
flow contains a lightweight operating system integration layer and a
cosimulation framework that supports hardware/software partitioning.
The design methodology has been applied to an implementation of the
IEEE 802.15.3 MAC protocol. We present results from a prototypical
system including a protocol accelerator.
|Paper 7544 (Full Paper)||An Overview of the OMNeT++ Simulation Environment
OMNeT++ discrete event simulation environment has been
publicly available since 1997. It has been created with the
simulation of communication networks, multiprocessors and other
distributed systems in mind as application area, but instead of
building a specialized simulator, OMNeT++ was designed to be as general
as possible. Since then, the idea has proven to work, and OMNeT++ has
been used in numerous domains from queuing network simulations to
wireless and ad-hoc network simulations, from business process
simulation to peer-to-peer network, optical switch and storage area
network simulations. This paper presents an overview of the OMNeT++
framework, recent challenges brought about by the growing amount and
complexity of third party simulation models, and the solutions we
introduce in the next major revision of the simulation framework.
back to top...
|Paper 7580 (Full Paper)||A Layered Architecture for the Model-driven Development of Distributed Simulators
development of a distributed simulator requires knowledge and skills
that might not be available or suitable in particular situations.
Bringing model-driven approaches to the development of distributed
simulators contributes to reduce both the need for specific skills and
the development effort. To support this innovative development
methodology, we introduce a layered simulation architecture named
SimArch that allows to define simulation models that can be
transparently transformed into a simulation programs ready to be
executed in a distributed (as well as local) fashion.
SimArch defines layers of services at increasing levels of abstraction
on the top of the distributed environment, thus allowing developers to
build distributed simulators without explicit knowledge about the
execution environment (local/distributed) and the specific distributed
simulation infrastructure (e.g., HLA). In order to show the
effectiveness of the proposed approach, SimArch has been provided with
an Extended Queueing Network (EQN) simulation modeling language, which
has been applied to the development of an example distributed simulator
in the computer network domain.
Session 14 (Work In Progress)
Chair: Gabriel Wainer, University of Carleton, Canada.
|Paper 7334 (WIP)||A State Class Approach to Time Petri Nets with Weak Semantics
time semantics are usually adopted for time Petri nets (TPNs) in
different application context: a strong semantics and a weak one. State
class approaches are a fundamental and most widely applied technique
for time analysis in TPNs. But the existing state class methods focus
on the strong semantics. In this paper, we define the formal semantics
of TPN with weak semantics in terms of Labeled Transition System and
then propose a state class method for this model. We further prove the
correctness of this method in computing the relative firing domain.
Finally, an application of this method to a typical manufacturing
system is illustrated.
|Paper 7594 (WIP)||Realistic Simulation of Vehicular Communication and Vehicle-2-X Applications
future intelligent transport systems, wireless vehicular communication
will provide the basis for new applications to enhance safety, traffic
efficiency, and provide infotainment services. In the near future,
field tests are to be carried out to verify the improvements that could
be achieved by these new Vehicle-2-X applications. However, the
realisation of such field tests is very complex and expensive.
Therefore, detailed simulations are necessary to prepare the tests in
the real world and reduce their costs. Current simulation tools do not
support all aspects necessary for Vehicle-2-X applications. In this
paper, we present an integrated software simulation environment that
fulfils the special requirements of Vehicle-2-X applications.
Furthermore, we introduce our testbed architecture that allows
simulating vehicular communication under real physical conditions.
back to top...
|Paper 7609 (WIP)||Between Small Complex and Large Simplistic Network Simulators
discrete-even network simulation market is split among a number of
popular simulators, such as NS-x, OMNET++, Opnet, and maybe a few
others. These tools are very common in research that targets small to
medium size networks. Whenever one needs to simulate a large network of
many tens of thousands nodes, the ability to use traditional network
simulators is questionable. Since performance, and specifically,
execution speed, is the number priority in traditional network
simulation, simulation runs are normally implemented as solid
executables running in a memory space, to which there is a physical
limit. The other extreme is topology generators such as BRITE, using
which one is able to create large topologies but is limited in
inserting intelligence in individual nodes. This paper proposes a
different paradigm of simulation that specifically aims at the ability
to simulate large networks while supporting models in nodes with any
level of complexity. The paper contains details of design,
implementation, and trial results of the proposed network simulation
Session 15 (Work In Progress)
Chair: John Heath, University of So Maine, USA.
|Paper 7540 (WIP)||Evaluation of Home Based Junior Doctor Medical Simulator
This paper presents initial research on a home based junior doctor
medical simulator (JDoc) to improve the efficiency of junior doctor
training within the restrictions imposed by the European Working Time
Directive (EWTD). Our goal is to make complex theoretical medical
knowledge more accessible. We developed a high fidelity test framework
JDoc. Our objective is to understand the potential for medical
simulation in junior doctor training. The paper outlines the design
process and the construction of the simulator as well as a small scale
post-test usability study amongst junior doctors from which we can
assess the benefits of JDoc.
|Paper 7558 (WIP)||Multi-Agent Geosimulation In Support To “What if” Courses Of Action Analysis
this paper we propose an approach to support “what-if” analysis in the
context of COA evaluation. Our approach consists in using multiagent
geosimulation to simulate the execution of COAs in a Virtual Geographic
Environment (VGE) which can change during the simulation, and then
allowing the user to explore various assumptions and to analyse their
outcomes. We identify the requirements to support this approach and we
present how we implement them in the MAGS-COA software. We also
illustrate our approach on a case study and we present future works.
|Paper 7561 (WIP)||Simulation of Agilla Middleware on TOSSIM
this study, we performed a simulation of mobile agents running on
Agilla middleware using TOSSIM. We simulated different agents
corresponding to various functions and measured the time they take to
execute on the simulator. We also compared the results of migration
delay and reliability in the simulation of different agents with those
of the real life experiments. The results presented in the study show
that simulations produce results comparable to real life experiments.
back to top...
|Paper 7581 (WIP)||SimStudio: a Next Generation Modeling and Simulation Framework
|Author(s)||Mamadou K. Traoré
is an operational framework that must serve to capitalize theoretical
advances in Modeling and Simulation (M&S) as well as to gather
M&S tools and make them accessible through a web browser. From a
software perspective, SimStudio is a middleware for the federation of
simulators and the collaborative building of simulations. From a
hardware perspective, SimStudio is a mean to aggregate intensive
computing resources through the http protocol.
Session 16 (Work In Progress)
Chair: Olivier Dalle, Université de Nice Sophia Antipolis, CNRS & INRIA, France.
|Paper 7478 (WIP)||SimCon - A Simulation and Visualization Environment for Overlay Networks and Large-Scale Applications
substantial number of massive large-scale applications require scalable
underlying network topologies. Nowadays structured Peer-to-Peer overlay
networks meet these requirements very well. But there is still a need
to decide which of these overlay networks is most suitable for
providing the best possible performance for a certain application. This
paper describes SimCon - a simulation environment for overlay networks
and large-scale applications. SimCon allows the comparison of different
overlay networks with respect to predefined metrics derived from
requirements of the considered application. This approach allows to
determine which overlay network suits the needs of a given application
best, which in turn is a great support for developers of large-scale
|Paper 7573 (WIP)||An Autonomic ENUM Implementation in Network Simulator-2
paper presents the implementation of an autonomic ENUM simulation model
which is validated with real measurements. It explains the approach
used to build the model and integrate with NS-2. The main objective for
this work is to use this simulation model to use different
configurations or algorithms in ENUM system and come up with a
promising solution to reduce the global response time for an ENUM
query. For ENUM to be used for VoIP solutions, their response time
should be as compared to the real time telecommunication systems;
otherwise it is not going to be successful. We are convinced that this
model could also be used to study different implementation models for a
particular ENUM scenario and identify an optimized implementation.
back to top...
|Paper 7578 (WIP)||INES: Network Simulations on Virtual Environments
paper discuses the goals, design ideas, models and implementation state
of a new discrete-event simulator of computer networks. The Integrated
Network-Environment Simulator (INES) aims at creating a suitable
simulation tool for the evaluation of network algorithms and protocols
within virtual environments, making it particularly useful for testing
mobile networks, situated communications and other technologies that
make use of environmental information, such as wireless sensor
networks. The simulator uses mesh geometries to describe objects of the
virtual environment that have an effect on nodes and their
communications. Parallel to the development of INES is the
implementation of the Packet Animator, which has an OpenGL-based
animation engine to visualize INES traces. Finally, the paper discusses
examples that make use of the mobility and communication models
currently available in the simulator.