A dEVS Simulation Algorithm Based on Shared Memory for Enhancing Performance

Cárdenas, Román; Henares, Kevin; Arroba, Patricia; Wainer, Gabriel; Risco‐Martín, José L.

doi:10.1109/wsc48552.2020.9383948

Cited by 3 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…16 This alternative xDEVS simulation algorithm, called the chained simulator, aims to improve the performance of sequential and parallel simulations by using a function-oriented approach instead of message-passing. 18 This algorithm exploits shared memory patterns to avoid unnecessary message propagation. Appendix F provides an example implementation of the algorithm.…”

Section: Memory-shared Portsmentioning

confidence: 99%

“…The Python version of xDEVS implements a modification of the PDEVS abstract simulator algorithm originally proposed by Chow and Zeigler 16 . This alternative xDEVS simulation algorithm, called the chained simulator, aims to improve the performance of sequential and parallel simulations by using a function‐oriented approach instead of message‐passing 18 . This algorithm exploits shared memory patterns to avoid unnecessary message propagation.…”

Section: Xdevs Architecturementioning

confidence: 99%

“…Generally, models with a high number of couplings and models that generate more than one event per port simultaneously can benefit the most from this algorithm. The chained algorithm has been proven to reduce up to 40% of synchronization overhead 18 …”

Section: Xdevs Architecturementioning

confidence: 99%

See 2 more Smart Citations

xDEVS: A toolkit for interoperable modeling and simulation of formal discrete event systems

et al. 2022

Self Cite

View full text Add to dashboard Cite

Employing Modeling and Simulation (M&S) extensively to analyze and develop complex systems is the norm today. The use of robust M&S formalisms and rigorous methodologies is essential to deal with complexity. Among them, the Discrete Event System Specification (DEVS) provides a solid framework for modeling structural, behavior and information aspects of any complex system.This gives several advantages to analyze and design complex systems: completeness, verifiability, extensibility, and maintainability. DEVS formalism has been implemented in many programming languages and executable on multiple platforms. In this paper, we describe the features of an M&S framework called xDEVS that builds upon the prevalent DEVS Application Programming Interface (API) for both modeling and simulation layers, promoting interoperability between the existing platform-specific (C++, Java, Python) DEVS implementations. Additionally, the framework can simulate the same model using sequential, parallel, or distributed architectures. The M&S engine has been reinforced with several strategies to improve performance, as well as tools to perform model analysis and verification. Finally, xDEVS also facilitates systems engineers to apply the vision of model-based systems engineering (MBSE), model-driven engineering (MDE), and model-driven systems engineering (MDSE) paradigms.We highlight the features of the proposed xDEVS framework with multiple examples and case studies illustrating the rigor and diversity of application domains it can support.

show abstract

Section: Memory-shared Portsmentioning

confidence: 99%

Section: Xdevs Architecturementioning

confidence: 99%

See 1 more Smart Citation

xDEVS: A toolkit for interoperable modeling and simulation of formal discrete event systems

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Analyzing the publications that study the performance of DEVS simulation engines through DEVStone, we may find that the HO set offers a good balance between CPU and memory usage [29,33]. As a result, we use the HO set of DEVStone models to evaluate the performance of our DEVS parallel and distributed simulation engines.…”

Section: The Devstone Benchmarkmentioning

confidence: 99%

A unified cloud-enabled discrete event parallel and distributed simulation architecture

Risco‐Martín

Henares

Mittal

et al. 2022

Simulation Modelling Practice and Theory

Self Cite

View full text Add to dashboard Cite

“…Since the introduction of the original abstract DEVS simulator, 1 several variants have been proposed in the literature, including sequential simulation algorithms [2][3][4][5][6][7] as well as parallel and distributed versions. [8][9][10][11][12] Yet, the proper measure of the computational complexity of such approaches has not been systematically addressed. As systems become larger and more complex, the efficiency of the DEVS simulation algorithms becomes a major issue.…”

Section: Introductionmentioning

confidence: 99%

A theoretical approach to the computational complexity measure of abstract DEVS simulators

Diouf¹,

Maiga²,

Traoré³

2022

Int. J. Model. Simul. Sci. Comput.

View full text Add to dashboard Cite

DEVS is a sound Modeling and Simulation (M&S) framework that describes a model in a modular and hierarchical way. It comes along with an abstract simulation algorithm which defines its operational semantics. Many variants of such an algorithm have been proposed by DEVS researchers. Yet, the proper interpretation and analysis of the computational complexity of such approaches have not been systematically addressed and defined. As systems become larger and more complex, the efficiency of the DEVS simulation algorithms in terms of time complexity measure becomes a major issue. Therefore, it is necessary to devise a method for computing this complexity. This paper proposes a generic method to address such an issue, taking advantage of the recursion embedded in the triggered-by-message principle of the DEVS simulation protocol. The applicability of the method is shown through the complexity analysis of various DEVS simulation algorithms.

show abstract

A dEVS Simulation Algorithm Based on Shared Memory for Enhancing Performance

Cited by 3 publications

References 10 publications

xDEVS: A toolkit for interoperable modeling and simulation of formal discrete event systems

xDEVS: A toolkit for interoperable modeling and simulation of formal discrete event systems

A unified cloud-enabled discrete event parallel and distributed simulation architecture

A theoretical approach to the computational complexity measure of abstract DEVS simulators

Contact Info

Product

Resources

About