scholarly journals Parallel Network Simulation With OMNeT++

2009 ◽  
Author(s):  
András Varga ◽  
Ahmet Y. Şekercioğlu Şekercioğlu
Keyword(s):  
Communication Networks ◽  
Large Scale ◽  
Distributed Simulation ◽  
Discrete Event ◽  
Rare Event ◽  
Telecommunication Networks ◽  
Event Simulation ◽  
Parallel And Distributed Simulation ◽  
Simulation Protocol ◽  
Parallel Network

This paper reports a new parallel and distributed simulation architecture for OMNeT++, an open-source discrete event simulation environment. The primary application area of OMNeT++ is the simulation of communication networks. Support for a conservative PDES protocol (the Null Message Algorithm) and the relatively novel Ideal Simulation Protocol has been implemented.Placeholder modules, a novel way of distributing the model over several logical processes (LPs) is presented. The OMNeT++ PDES implementation has a modular and extensible architecture, allowing new synchronization protocols and new communication mechanisms to be added easily, which makes it an attractive platform for PDES research, too. We intend touse this framework to harness the computational capacity of highperformance cluster computersfor modeling very large scale telecommunication networks to investigate protocol performance and rare event failure scenarios.

scholarly journals An Efficient Statistical Synchronization Method For Parallel Simulation

2009 ◽  
Author(s):  
Gábor Lencse
Keyword(s):  
Communication Networks ◽  
Discrete Event Simulation ◽  
Discrete Event ◽  
Simulation Models ◽  
Parallel Simulation ◽  
Telecommunication Networks ◽  
Parallel Discrete Event Simulation ◽  
Event Simulation ◽  
Synchronization Method ◽  
Parallel Discrete Event

In this paper, we propose the improved Statistical Synchronization Method (SSM-T) for parallel discrete event simulation. Criteria are given for the time-driven approach (SSM-T). It is proven that the level of the output error can be guaranteed. SSM-T is implemented in the OMNeT++ discrete event simulation tool, which is a useful and widespread framework for creating various simulation  models to evaluate the performance of telecommunication networks. Case studies have been performed, which shows that SSM-T is a very efficient synchronization method for the parallel simulation of communication networks.

scholarly journals DVCompute Simulator for discrete event simulation

2021 ◽  
Vol 16 (93) ◽  
pp. 93-108
Author(s):  
David E. Sorokin ◽  
Keyword(s):  
Discrete Event Simulation ◽  
Large Scale ◽  
Distributed Simulation ◽  
Discrete Event ◽  
Simulation Models ◽  
General Purpose ◽  
Agent Based Modeling ◽  
Agent Based ◽  
Event Simulation ◽  
Programming Techniques

The author of this article represents his own work DVCompute Simulator, which is a collection of general-purpose programming libraries for discrete event simulation. The aim of the research was to create a set of simulators in the Rust language, efficient in terms of speed of execution, based on a unified approach and destined for different simulation modes. The simulators implement such modes as ordinary sequential simulation, nested simulation and distributed simulation. The article describes that nested simulation is related to Theory of Games, while distributed simulation can be used for running large-scale simulation models on supercomputers. It is shown how these different simulation modes can be implemented based on the single approach that combines many paradigms: the event-oriented paradigm, the process-oriented one, blocks similar to the GPSS language and even partially agent-based modeling. The author's approach is based on using the functional programming techniques, where the simulation model is defined as a composition of computations. The results of testing two modules are provided, where the modules support both the optimistic and conservative methods of distributed simulation.

scholarly journals A Parallel Event System for Large-Scale Cloud Simulations in DISSECT-CF

2021 ◽  
Author(s):  
Dilshad Hassan Sallo ◽  
Gabor Kecskemeti
Keyword(s):  
Time Management ◽  
Large Scale ◽  
Discrete Event ◽  
Parallel Execution ◽  
Management Scenarios ◽  
Performance Improvements ◽  
Event Simulation ◽  
Independent Events ◽  
Event System ◽  
Significant Performance

Discrete Event Simulation (DES) frameworks gained significant popularity to support and evaluate cloud computing environments. They support decision-making for complex scenarios, saving time and effort. The majority of these frameworks lack parallel execution. In spite being a sequential framework, DISSECT-CF introduced significant performance improvements when simulating Infrastructure as a Service (IaaS) clouds. Even with these improvements over the state of the art sequential simulators, there are several scenarios (e.g., large scale Internet of Things or serverless computing systems) which DISSECT-CF would not simulate in a timely fashion. To remedy such scenarios this paper introduces parallel execution to its most abstract subsystem: the event system. The new event subsystem detects when multiple events occur at a specific time instance of the simulation and decides to execute them either on a parallel or a sequential fashion. This decision is mainly based on the number of independent events and the expected workload of a particular event. In our evaluation, we focused exclusively on time management scenarios. While we did so, we ensured the behaviour of the events should be equivalent to realistic, larger-scale simulation scenarios. This allowed us to understand the effects of parallelism on the whole framework, while we also shown the gains of the new system compared to the old sequential one. With regards to scaling, we observed it to be proportional to the number of cores in the utilised SMP host.

scholarly journals Modeling Large-Scale Slim Fly Networks Using Parallel Discrete-Event Simulation

2018 ◽  
Vol 28 (4) ◽  
pp. 1-25 ◽  
Author(s):  
Noah Wolfe ◽  
Misbah Mubarak ◽  
Christopher D. Carothers ◽  
Robert B. Ross ◽  
Philip H. Carns
Keyword(s):  
Discrete Event Simulation ◽  
Large Scale ◽  
Discrete Event ◽  
Parallel Discrete Event Simulation ◽  
Event Simulation ◽  
Parallel Discrete Event

scholarly journals Speeding Up Decision Support

2010 ◽  
pp. 255-273
Author(s):  
Navonil Mustafee ◽  
Simon J.E. Taylor ◽  
Korina Katsaliaki ◽  
Sally Brailsford
Keyword(s):  
Decision Support ◽  
Distributed Simulation ◽  
Discrete Event ◽  
Event Simulation ◽  
Healthcare Needs ◽  
Simulation Based ◽  
Long Time ◽  
Speed Up ◽  
Complex Health Problems ◽  
The Uk

Discrete-Event Simulation (DES) is a decision support technique that allows stakeholders to conduct experiments with models that represent real-world systems of interest. Its use in healthcare is comparatively new. Healthcare needs have grown and healthcare organisations become larger, more complex and more costly. There has never been a greater need for carefully informed decisions and policy. DES is valuable as it can provide evidence of how to cope with these complex health problems. However, the size of a healthcare system can lead to large models that can take an extremely long time to simulate. In this chapter the authors investigate how a technique called distributed simulation allows us to use multiple computers to speed up this simulation. Based on a case study of the UK National Blood Service they demonstrate the effectiveness of this technique and argue that it is a vital technique in healthcare informatics with respect to supporting decision making in large healthcare systems.

A Node-Oriented Discrete Event Scheduling Algorithm Based on Finite Resource Model

2019 ◽  
Vol 31 (3) ◽  
pp. 67-82
Author(s):  
Yu Huang ◽  
Wanxing Sheng ◽  
Peipei Jin ◽  
Baicuan Nie ◽  
Meikang Qiu ◽  
...  
Keyword(s):  
Discrete Event Simulation ◽  
Packet Loss ◽  
Large Scale ◽  
Network Simulation ◽  
Scheduling Algorithm ◽  
Discrete Event ◽  
Event Simulation ◽  
Resource Limited ◽  
Event Scheduling ◽  
Low Performance

Discrete event simulation is the most important and essential part in network simulation. The node-oriented model of discrete event scheduling is a model that allocates computing resources as nodes and makes the discrete event simulation as a simulation task on nodes. In this article the reason of low performance in large-scale network simulation is analyzed, and an ideal node-oriented model of discrete event scheduling is presented and a resource-limited node-oriented model of discrete event scheduling by adding some restrictions on network resources is proposed. Then, the authors complete contrast experiments of the resource-limited node-oriented model of discrete event scheduling and NS2. Finally, packet loss in resource-limited node-oriented model of discrete event scheduling is examined. Also, NS2 is discussed in this article and the authors have proposed an improved method for the packet loss algorithm in a resource-limited node-oriented model of discrete event scheduling.

Sign in / Sign up

Export Citation Format

Share Document