Multicore acceleration of Discrete Event System Specification systems

Fine-Grained Parallel and Distributed Spatial Stochastic Simulation of Biological Reactions

Complex models in science and engineering need better techniques to execute simulations efficiently. As we need high performance computers with many processors and memory to execute complex simulations faster, we face a problem with the consumption of energy. Therefore, we need new ways to define efficiency in simulations, measured not only in terms of computation time, but in terms of the amount of energy required to execute them. The Discrete-Event System Specification (DEVS) formalism, a well-known technique for modeling and simulation, includes simulation algorithms that allow running DEVS models in parallel computers. Nevertheless, no studies exist on the execution of DEVS simulations on parallel computers efficiently in terms of energy use. In this work, we show an energy efficiency evaluation of the execution of DEVS simulations on a shared-memory multicore architecture. The results presented show that executing in parallel can improve energy efficiency in these architectures.

System models are constructed to design, study, and understand complex systems. According to the systems modeling language (SysML) that is a standard for model-based system engineering, all engineering activities should be performed using a common model. To validate complex system models defined in SysML, simulation is usually employed. There are numerous efforts to simulate SysML models using different simulation methods and tools. However, the efficient support of automated generation of executable simulation code is still an issue tangled by the research community. This paper introduces DEVSys, an integrated framework for utilizing existing SysML models and automatically producing executable discrete event simulation code, according to model driven architecture (MDA) concepts. Although this approach is not simulation-specific, discrete event system specification (DEVS) was employed, due to the similarities between SysML and DEVS, mainly in system structure description, and the mature, yet ongoing research on expressing executable DEVS models in a simulator-neutral manner. DEVSys framework elements include (a) a SysML profile for DEVS, enabling integration of simulation capabilities into SysML models, (b) a meta-model for DEVS, allowing the utilization of MDA concepts and tools, (c) a transformation of SysML models to DEVS models, using a standard model transformation language as query/view/transform (QVT), and (d) the generation of DEVS executable code for a DEVS simulation environment with an extensible markup language (XML) interface. The definition and implementation of DEVSys elements, as well as the process for its application are demonstrated and discussed, with the aid of a simple working example.

Discrete event system specification (DEVS), a formalism for modeling and simulation, has been recently applied to the engineering of CPS, which also makes the necessity of model checking for DEVS arisen. Model-transformation-based approaches were first proposed; timed or linear hybrid automata are obtained from DEVS models, and then verified using model checkers. But, due to the different semantics in state transitions, the transformation often involves manual tasks, such as abstraction and approximation. To eliminate such manual tasks, we have proposed a DEVS subclass that is less expressive, but verifiable. For reachability analysis, its models can be interpreted as transition systems and region automata (RA). Although our DEVS subclass and RA have different semantics with respect to model execution, they are equivalent in terms of reachability analysis. Thus, the reachability could be analyzed based on model checking techniques of timed automata. In many DEVS-based environments, models should be developed by programming languages. To enables the modelers to specify CPS in a visual way, we have proposed a visual modeling language based on our subclass. In our language, the behavior and structure of CPS are graphically specified by basic model diagrams and coupled model diagrams, respectively. Based on our subclass and languages, we have implemented a proof-of-concept environment that supports visual modeling of CPS as well as simulation and reachability analysis of the models. To enable the consideration of the hybrid nature and heterogeneity in CPS, DEVS subclasses, languages, verification techniques and environments will be further investigated.

Discrete Event System Specification (DEVS) is a popular formalism for modeling complex dynamic systems using a discrete-event abstraction. At this abstraction level, a timed sequence of pertinent "events" input to a system (or internal timeouts) cause instantaneous changes to the state of the system. Main advantages of DEVS are its rigorous formal definition and its support for modular composition. This tutorial introduces the Classic DEVS formalism in a bottom-up fashion, using a simple traffic light example. The syntax and operational semantics of atomic (i.e., non-hierarchical) models are introduced first. Coupled (i.e., hierarchical) models are introduced to structure and couple Atomic models. We continue to actual applications of DEVS, for example in performance analysis of queueing systems. All examples are presented with the tool PythonPDEVS, though this introduction is equally applicable to other DEVS tools. We conclude with further reading on DEVS theory, DEVS variants, and DEVS tools.

Artificial neural networks (ANNs), a branch of artificial intelligence, has become a very interesting domain since the eighties when back-propagation (BP) learning algorithm for multilayer feed-forward architecture was introduced to solve nonlinear problems. It is used extensively to solve complex nonalgorithmic problems such as prediction, pattern recognition and clustering. However, in the context of a holistic study, there may be a need to integrate ANN with other models developed in various paradigms to solve a problem. In this paper, we suggest discrete event system specification (DEVS) be used as a model of computation (MoC) to make ANN models interoperable with other models (since all discrete event models can be expressed in DEVS, and continuous models can be approximated by DEVS). By combining ANN and DEVS, we can model the complex configuration of ANNs and express its internal workings. Therefore, we are extending the DEVS-based ANN proposed by Toma et al. [A new DEVS-based generic artficial neural network modeling approach, The 23rd European Modeling and Simulation Symp. (Simulation in Industry), Rome, Italy, 2011] for comparing multiple configuration parameters and learning algorithms and also to do prediction. The DEVS models are described using the high level language for system specification (HiLLS), [Maïga et al., A new approach to modeling dynamic structure systems, The 29th European Modeling and Simulation Symp. (Simulation in Industry), Leicester, United Kingdom, 2015] a graphical modeling language for clarity. The developed platform is a tool to transform ANN models into DEVS computational models, making them more reusable and more interoperable in the context of larger multi-perspective modeling and simulation (MAS).

DEVS는 이산 사건 시스템을 명세하는 집합론에 근거한 수학적인 틀이다. 이러한 DEVS를 통해 시스템을 시뮬레이션할 때는 명세된 DEVS로부터 구현된 모델과 시뮬레이션 엔진으로 이루어진 실행 환경이 필요하다. 시뮬레이션 엔진은 스케줄링 알고리즘을 통해 모델을 해석하고 실행하는데, 주로 DEVS의 계층적이고 모듈러한 특성을 따라 계층적인 스케줄링 방법을 사용한다. 그러나 이 방법은 계층적인 구조로 인해 시간 관리와 메시지 패싱에 있어서 오버헤드가 존재한다. 본 논문에서는 이러한 오버헤드를 해결하기 위해 이벤트 지향 시뮬레이션을 적용한다. 이벤트 지향의 시뮬레이션은 이벤트에 의해서 모델이 실행되며 이벤트 리스트에 의해 이벤트가 관리된다. 이벤트 리스트에 의해서 시간 관리가 되고 메시지 패싱이 이루어지기 때문에 계층적인 오버헤드를 줄이고 성능 향상을 이룰 수 있다. 본 논문은 이벤트 리스트를 이용한 실행 환경을 제안하고 이러한 실행 환경을 위한 모델 구현 방안에 대해 논하며, 각 실행 환경의 성능을 비교, 분석한다. DEVS(Discrete Event Systems Specification) is a set theoretic formalism developed for specifying discrete event system. For execution of DEVS, we need an execution environment, which consists of simulation engine and models interpreted by the simulation engine. Common existing environments use hierarchical scheduling algorithm for DEVS execution. This hierarchical scheduling is a proper algorithm for DEVS execution because of hierarchical and modular characteristics. But this algorithm has overheads owing to message passing and time management. To overcome these overheads, we apply event-oriented simulation to DEVS execution and we remove hierarchical overheads. In eventoriented simulation, the scheduling of model execution is performed by events and event list. We propose three event-oriented execution environments for DEVS and experiment about the performance of our proposed environments in comparison with the existing execution environment using the hierarchical scheduling. The experimental results show our environments works better than existing environment using the hierarchical scheduling.

Real-time systems modeling and verification is a complex task. In many cases, formal methods have been employed to deal with the complexity of these systems, but checking those models is usually unfeasible. Modeling and simulation methods introduce a means of validating these model’s specifications. In particular, Discrete Event System Specification (DEVS) models can be used for this purpose. Here, we introduce a new extension to the DEVS formalism, called the Rational Time-Advance DEVS (RTA-DEVS), which permits modeling the behavior of real-time systems that can be modeled by the classical DEVS; however, RTA-DEVS models can be formally checked with standard model-checking algorithms and tools. In order to do so, we introduce a procedure to create timed automata (TA) models that are behaviorally equivalent to the original RTA-DEVS models. This enables the use of the available TA tools and theories for formal model checking. Further, we introduce a methodology to transform classic DEVS models to RTA-DEVS models, thus enabling formal verification of classic DEVS with an acceptable accuracy.

Telemedicine remote consultation and diagnosis (RCD) software is a complex and distributed system. RCD allows physicians to collaborate on radiology or pathology cases from distributed geographic locations. It is very important to simplify design, construction, and maintenance of such a system. Currently, object-oriented design methodology is used to design and develop a software system in a modular fashion. Object-oriented software is made of various objects that work together. From the design of the software system, we get information about object methods and inheritance. We also get information about which objects are contained in a particular object and which objects are used by another object. One important element that the traditional object-oriented design misses is time. We propose the use of discrete event system specification (DEVS) in the design and analysis of a software system, such as RCD. With DEVS, coupling between objects can be specified explicitly and an object behavior can be shown in time. We introduce DEVS, show the time-line analysis of Remote Consultation and Diagnosis session playback using DEVS, and then describe its implementation.

Parallel discrete-event simulation (PDES) is an important tool in the codesign of extreme-scale systems because PDES provides a cost-effective way to evaluate designs of high-performance computing systems. Optimistic synchronization algorithms for PDES, such as Time Warp, allow events to be processed without global synchronization among the processing elements. A rollback mechanism is provided when events are processed out of timestamp order. Although optimistic synchronization protocols enable the scalability of large-scale PDES, the performance of the simulations must be tuned to reduce the number of rollbacks and provide an improved simulation runtime. To enable efficient large-scale optimistic simulations, one has to gain insight into the factors that affect the rollback behavior and simulation performance. We developed a tool for ROSS model developers that gives them detailed metrics on the performance of their large-scale optimistic simulations at varying levels of simulation granularity. Model developers can use this information for parameter tuning of optimistic simulations in order to achieve better runtime and fewer rollbacks. In this work, we instrument the ROSS optimistic PDES framework to gather detailed statistics about the simulation engine. We have also developed an interactive visualization interface that uses the data collected by the ROSS instrumentation to understand the underlying behavior of the simulation engine. The interface connects real time to virtual time in the simulation and provides the ability to view simulation data at different granularities. We demonstrate the usefulness of our framework by performing a visual analysis of the dragonfly network topology model provided by the CODES simulation framework built on top of ROSS. The instrumentation needs to minimize overhead in order to accurately collect data about the simulation performance. To ensure that the instrumentation does not introduce unnecessary overhead, we perform a scaling study that compares instrumented ROSS simulations with their noninstrumented counterparts in order to determine the amount of perturbation when running at different simulation scales.

We consider the ability of Discrete Event System Specification (DEVS) to provide the concepts and formalisms needed for modeling and simulation of emergent behavior. We show that DEVS provides systems components and coupling for models of systems of systems with emergent behavior. Further, DEVS coupling supports dynamic structure for adaptive and evolution, and the Experimental Frame supports Emergence Behavior Observation, and a recent extension, DEVS Markov models, supports prediction of emergence derived from such observation. Finally, we introduce a concept of interactive specification based on generators that has the potential to provide a system-theoretic characterization of emergence modeling using language concepts.

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.

In this chapter, we formalize the multi-perspective architecture framework using the system-theoretic paradigm provided by the discrete event system specification (DEVS) formalism. The developed integration approach that allows linking up the isolated perspectives has been formalized through a concept based upon DEVS formalism called parameterized DEVS, whereby concurrent simulation processes cause live update through output-to-parameter integration. This sets up the basis for development of DEVS-based holistic models for efficient management of healthcare systems. Results of real case-based simulations are presented to show how holistic models provide new insights not heretofore attainable with unit and facility specific models.

Complex models in science and engineering need better techniques to execute simulations efficiently. The Discrete-Event System Specification (DEVS) formalism, a well-known technique for modeling and simulation, has been enhanced by executing in parallel computers. Here, we present the design and implementation of a parallel version of the Cadmium DEVS simulator. We conducted empirical evaluation for executing the protocol in multithreading architectures and discuss performance by applying these techniques in real problems.

In this paper, we introduce a novel parallelization technique for Discrete Event System Specification (DEVS) simulation of continuous and hybrid systems. Here, like in most parallel discrete event simulation methodologies, the models are first split into several sub-models which are then concurrently simulated on different processors. In order to avoid the cost of the global synchronization of all processes, the simulation time of each sub-model is locally synchronized in a real-time fashion with a scaled version of physical time, which implicitly synchronizes all sub-models. The new methodology, coined Scaled Real-Time Synchronization (SRTS), does not ensure a perfect synchronization in its implementation. However, under certain conditions, the synchronization error introduced only provokes bounded numerical errors in the simulation results. SRTS uses the same physical time-scaling parameter throughout the entire simulation. We also developed an adaptive version of the methodology (Adaptive-SRTS) where this parameter automatically evolves during the simulation according to the workload. We implemented the SRTS and Adaptive-SRTS techniques in PowerDEVS, a DEVS simulation tool, under a real-time operating system called the Real-Time Application Interface. We tested their performance by simulating three large-scale models, obtaining in all cases a considerable speedup.