This work introduces a new network simulation environment, developed by the research group, called the Georgia Tech Network Simulator (GTNetS), designed specifically to allow much larger-scale simulations than can easily be created by existing network simulation tools.
Abstract:
We introduce a new network simulation environment, developed by our research group, called the Georgia Tech Network Simulator (GTNetS). Our simulator is designed specifically to allow much larger-scale simulations than can easily be created by existing network simulation tools. The design of the simulator very closely matches the design of real network protocol stacks and hardware. Thus, anyone with a good understanding of networking in general can easily understand how the simulations are constructed. Further, our simulator is implemented completely in object-oriented C++, which leads to easy extension by users to experiment with new or modified behavior of existing simulation models. Our tool is designed from the beginning with scalability in mind, including the support for distributed simulations on a network of workstations as part of the basic design.We give an overview of the features of GTNetS, and present some preliminary scalability results we have obtained by running GTNetS on a computing cluster at the Pittsburgh Supercomputer Center.
TL;DR: The intent for this dataset is to assist various researchers in acquiring datasets of this kind for testing, evaluation, and comparison purposes, through sharing the generated datasets and profiles.
TL;DR: The SimGrid framework is described, a simulation-based framework for evaluating cluster, grid and P2P algorithms and heuristics and greatly improves on previous versions thanks to a novel and validated modular simulation engine that achieves higher simulation speed without hindering simulation accuracy.
TL;DR: This paper presents a computationally efficient heuristic for computing a feasible schedule under the physical interference model and proves, under uniform random node distribution, an approximation factor for the length of this schedule relative to the shortest schedule possible with physical interference.
TL;DR: This paper presents a comprehensive study and comparisons of the various publicly available VANET simulation software and their components, and contrast their software characteristics, graphical user interface (GUI), popularity, ease of use, input requirements, output visualization capability, accuracy of simulation, etc.
TL;DR: In this article, the authors have organized an NSF-funded, four-year community infrastructure project to develop the next version of ns-2, which will also be oriented towards community development and open source software practices to encourage participation from broader research and educational community.
TL;DR: Red gateways are designed to accompany a transport-layer congestion control protocol such as TCP and have no bias against bursty traffic and avoids the global synchronization of many connections decreasing their window at the same time.
TL;DR: OMNeT++ is fully programmable and modular, and it was designed from the ground up to support modeling very large networks built from reusable model components.
TL;DR: This work considers the problem of efficiently generating graph models that accurately reflect the topological properties of real internetworks, and proposes efficient methods for generating topologies with particular properties, including a transit-stub model that correlates well with the internet structure.
TL;DR: In this paper, the authors propose a protocol that allows dynamic distribution of the information needed to build tables totranslate an address A in protocol P's address space into a 48.bit Ethernet address.
TL;DR: This work has developed an empirical model of network traffic produced by HTTP, based on packet traces of HTTP conversations, which can be used by simulations to mimic World Wide Web network applications.
The web server model allows the enforcement of a limit on the number of simultaneous connections processed, which provides a basis for simulated denial of service style attacks.
Q2. What is the common approach to routing in a network simulator?
A common approach to routing in a network simulator is to use global topology knowledge to calculate a priori the best path from any node to all other nodes.
Q3. How does the protocol layer communicate with the layer below it?
Each protocol layer communicates with the layer below it by invoking a DataRequest method, specifying the packet (and current state of the PDU stack), and any protocol specific information required by the next lower layer.
Q4. How many simulation processes did the authors assign to each PSC system?
The authors assigned four simulation processes on each PSC system (one per CPU), and varied the number of systems from 1 to 32, giving a total number of simulation processes varying from 4 to 128.
Q5. What is the default value for a ns2 simulator?
For nearly every simulation object (links, queues, protocols, etc.), a default value is provided that allows for creation of this object without specifying details.
Q6. What are the different types of random number generators?
Simulation models for a number of different random number generators are provided, including exponential, pareto, normal, uniform, empirical, and constant.
Q7. What is the common reason for the large number of simulation events?
When running large–scale simulations, the total number of simulation events processed can be excessively large, potentially trillions or more.
Q8. What is the protocol graph used in GTNetS?
GTNetS includes simulation models of a number of popular protocols at the application layer, transport layer, network layer, and link layer, as discussed below.
Q9. What is the importance of the Gnutella model for distributed simulations?
This is especially important for distributed simulations, since the client and server may be on different processes, and will have no direct way of communicating that a new server endpoint is needed.
Q10. What is the difference between the sockets and the application layer?
The major difference between their implementation and the sockets API is the use of upcalls for received data, rather than the more familiar blocking read calls from the socket library.