Load Balance Strategies for DEVS Approximated Parallel and Distributed Discrete-Event Simulations

Inostrosa-Psijas, Alonso; Gil-Costa, Verónica; Solar, Roberto

doi:10.1109/pdp.2015.13

Cited by 6 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A DEVS model of a WSE has been previously developed and evaluated with CD++. 7 This model was modified to be efficiently simulated in parallel by using PCD++ 8 and different load balance algorithms were evaluated in Inostrosa-Psijas et al 9 In this article, we show that efficient parallel simulations of DEVS models can be attained using an approximate and semi-asynchronous approach. In particular, besides the Spectral Clustering 10 load balance algorithm presented and evaluated in Inostrosa-Psijas et al, 9 we introduce a strategy for modeling and simulating WSE based on (1) an approximate approach to reduce the running time and memory consumption of parallel simulations.…”

Section: Event System Specification (Pdevs) Models Discrete-event Symentioning

confidence: 92%

“…A DEVS model of a WSE has been previously developed and evaluated with CD++ . This model was modified to be efficiently simulated in parallel by using PCD++ and different load balance algorithms were evaluated in Inostrosa‐Psijas et al…”

Section: Introductionmentioning

confidence: 99%

“…In this article, we show that efficient parallel simulations of DEVS models can be attained using an approximate and semi‐asynchronous approach. In particular, besides the Spectral Clustering load balance algorithm presented and evaluated in Inostrosa‐Psijas et al, we introduce a strategy for modeling and simulating WSE based on (1) an approximate approach to reduce the running time and memory consumption of parallel simulations. No rollback mechanisms are used to correct time causality errors .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Semi‐asynchronous approximate parallel DEVS simulation of web search engines

Inostrosa-Psijas

Gil-Costa

Wainer

2017

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary Discrete Event System Specification (DEVS) is a formalism for the modeling and analysis of discrete event systems. Parallel DEVS (PDEVS) is an extension of DEVS for supporting Parallel and Discrete Event Simulation, which is a powerful tool for evaluating the performance of large scale systems. In this work, we propose an optimistic approximate and semi‐asynchronous parallel strategy. The level of optimism is efficiently managed throughout the simulation execution, and it is automatically adjusted based on the simulation evolution. Load balance and model partitioning is automatically made by means of an algorithm that takes advantage of the communication pattern of the simulated model. Our proposal is designed for Web search engines, which are complex and highly optimized systems devised to operate on large clusters of processors and dealing with dynamic and unpredictable user query bursts. The results show that our proposal is able to reduce both execution times and memory usage of standard optimistic simulations of Web search engine models, at the expense of small errors.

show abstract

Section: Event System Specification (Pdevs) Models Discrete-event Symentioning

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semi‐asynchronous approximate parallel DEVS simulation of web search engines

Inostrosa-Psijas

Gil-Costa

Wainer

2017

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…We also collected data about the computation and communication costs of a computing platform using self-developed application-specific benchmark programs which use as input the synthetic trace of requests. To this end, we instrumented the codes of the social applications to measure the time required to process data in the CPU, to access secondary memory (disk) and to send messages through the network (for more details on benchmarks programs see [2,7]). We executed those benchmarks on a set of multi-core computers as described in Section 4.…”

Section: Data and Tracesmentioning

confidence: 99%

Experimental Framework to Simulate Rescue Operations after a Natural Disaster

Veas-Castillo

Ovando-Leon

Astudillo

et al. 2020

JC&ST

Self Cite

View full text Add to dashboard Cite

Computational simulation is a powerful tool for performance evaluation of computational systems. It is useful to make capacity planning of data center clusters, to obtain profiling reports of software applications and to detect bottlenecks. It has been used in different research areas like large scale Web search engines, natural disaster evacuations, computational biology, human behavior and tendency, among many others. However, properly tuning the parameters of the simulators, defining the scenarios to be simulated and collecting the data traces is not an easy task. It is an incremental process which requires constantly comparing the estimated metrics and the flow of simulated actions against real data. In this work, we present an experimental framework designed for the development of large scale simulations of two applications used upon the occurrence of a natural disaster strikes. The first one is a social application aimed to register volunteers and manage emergency campaigns and tasks. The second one is a benchmark application a data repository named MongoDB. The applications are deployed in a distributed platform which combines different technologies like a Proxy, a Containers Orchestrator, Containers and a NoSQL Database. We simulate both applications and the architecture platform. We validate our simulators using real traces collected during simulacrums of emergency situations.

show abstract

“…Some recent related efforts are described in [26][27][28] . Additionally, the concept of deriving executable DEVS code, using model-driven techniques and tools, has been intensively addressed, as described in a relevant survey [29] .…”

Section: Related Workmentioning

confidence: 99%