ACM Transactions on Modeling and Computer Simulation (TOMACS) is the journal that offered me articles to read and study at the very beginning of my activity related to simulation methods, algorithms, and systems. It has been my reference for a long time, and I am extremely honored to write this editorial as the new Editor-in-Chief (EIC) of this journal. TOMACS is known to publish excellent research results in many areas, covering a very wide set of topics. It is an extremely interdisciplinary journal that allows theory and practice to meet. This achievement has been possible thanks to the hard work of many persons, including past editors and all the members of the editorial board. I am glad to take the opportunity to continue their work. Nowadays, it is common to use modeling methods and simulation systems to devise strategies, to make critical decisions, and to drive the evolution of processes that affect our lives. Hence, further increasing the visibility of TOMACS across research communities, as well as widening its scope and impact, is a core target I will pursue. I am sure all the members of the editorial board will sustain me and will take an active role in the organization of journal issues, which will include extended versions of articles that have been early scouted as top-quality ones in well-known conferences or other excellent venues. Furthermore, it is my objective to additionally strengthen the linkage between TOMACS and conferences that have traditionally, or more recently, offered the support for thematic (although not narrow) special issues. I will welcome high-quality surveys providing an assessment of the state of the art and pointing to challenging research directions. Thanks to the big effort by the previous EIC Adelinde Uhrmacher, TOMACS has started being involved in the important process of Reproducibility of Computational Results (RCR). This process further qualifies the research results published in the journal by guaranteeing a more direct and fruitful re-usability of results across researchers. I will sustain the involvement of TOMACS in RCR by encouraging authors of submitted articles to participate in this initiative. Rigorously managing the review process is an additional target I will pursue, with the objective of combining high quality of the reviews with speed in the evaluation of the submitted articles. Timeliness in the diffusion of relevant research results will be of crucial importance for the TOMACS community, as well as for all the communities that can take advantage of these results for stepping ahead in their research paths and achievements. In the end, we will all benefit from it. For sure, handling TOMACS as EIC will be a challenge, in which I will put as much passion as I can.
ACM Transactions on Modeling and Computer Simulation (TOMACS)是在我刚开始从事与仿真方法、算法和系统相关的活动时为我提供文章阅读和研究的期刊。这是我长期以来的参考文献，我非常荣幸能以本刊新任主编(EIC)的身份撰写这篇社论。TOMACS以在许多领域发表优秀的研究成果而闻名，涵盖了非常广泛的主题。这是一本跨学科的杂志，理论与实践相结合。这一成就得益于许多人的辛勤工作，包括过去的编辑和编委会的所有成员。我很高兴借此机会继续他们的工作。如今，通常使用建模方法和仿真系统来设计策略，做出关键决策，并推动影响我们生活的过程的演变。因此，进一步提高TOMACS在研究界的知名度，以及扩大其范围和影响，是我将追求的核心目标。我相信编委会的所有成员都将支持我，并将在组织期刊发行方面发挥积极作用，其中包括在知名会议或其他优秀场所早期被评为高质量文章的扩展版本。此外，我的目标是进一步加强TOMACS与传统上或最近为专题(虽然不是狭义的)特别问题提供支持的会议之间的联系。我将欢迎高质量的调查，提供对艺术现状的评估，并指出具有挑战性的研究方向。由于前EIC Adelinde uhracher的巨大努力，TOMACS已经开始参与计算结果再现性(RCR)的重要过程。这一过程通过保证研究人员之间更直接、更有效地重用结果，进一步提高了发表在期刊上的研究结果的质量。我将通过鼓励提交文章的作者参与这一倡议来维持TOMACS对RCR的参与。严格管理审稿过程是我将追求的另一个目标，其目标是将审稿的高质量与对提交文章的评估速度相结合。相关研究成果传播的及时性对于TOMACS社区以及所有可以利用这些结果在其研究路径和成果方面取得进展的社区至关重要。最终，我们都会从中受益。当然，作为EIC来管理TOMACS将是一个挑战，我将尽我所能地投入激情。
{"title":"Editorial from the New Editor-in-Chief","authors":"F. Quaglia","doi":"10.1145/3377148","DOIUrl":"https://doi.org/10.1145/3377148","url":null,"abstract":"ACM Transactions on Modeling and Computer Simulation (TOMACS) is the journal that offered me articles to read and study at the very beginning of my activity related to simulation methods, algorithms, and systems. It has been my reference for a long time, and I am extremely honored to write this editorial as the new Editor-in-Chief (EIC) of this journal. TOMACS is known to publish excellent research results in many areas, covering a very wide set of topics. It is an extremely interdisciplinary journal that allows theory and practice to meet. This achievement has been possible thanks to the hard work of many persons, including past editors and all the members of the editorial board. I am glad to take the opportunity to continue their work. Nowadays, it is common to use modeling methods and simulation systems to devise strategies, to make critical decisions, and to drive the evolution of processes that affect our lives. Hence, further increasing the visibility of TOMACS across research communities, as well as widening its scope and impact, is a core target I will pursue. I am sure all the members of the editorial board will sustain me and will take an active role in the organization of journal issues, which will include extended versions of articles that have been early scouted as top-quality ones in well-known conferences or other excellent venues. Furthermore, it is my objective to additionally strengthen the linkage between TOMACS and conferences that have traditionally, or more recently, offered the support for thematic (although not narrow) special issues. I will welcome high-quality surveys providing an assessment of the state of the art and pointing to challenging research directions. Thanks to the big effort by the previous EIC Adelinde Uhrmacher, TOMACS has started being involved in the important process of Reproducibility of Computational Results (RCR). This process further qualifies the research results published in the journal by guaranteeing a more direct and fruitful re-usability of results across researchers. I will sustain the involvement of TOMACS in RCR by encouraging authors of submitted articles to participate in this initiative. Rigorously managing the review process is an additional target I will pursue, with the objective of combining high quality of the reviews with speed in the evaluation of the submitted articles. Timeliness in the diffusion of relevant research results will be of crucial importance for the TOMACS community, as well as for all the communities that can take advantage of these results for stepping ahead in their research paths and achievements. In the end, we will all benefit from it. For sure, handling TOMACS as EIC will be a challenge, in which I will put as much passion as I can.","PeriodicalId":50943,"journal":{"name":"ACM Transactions on Modeling and Computer Simulation","volume":"30 1","pages":"1 - 1"},"PeriodicalIF":0.9,"publicationDate":"2020-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/3377148","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"64025954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-10DOI: 10.5772/INTECHOPEN.79410
G. Dieck-Assad, José Luis Vega-Fonseca, Isaías Hernández Ramírez, A. Favela-Contreras
This chapter describes a modeling methodology to provide the main characteristics of a simulation tool to analyze the steady state, transient operation, and control of steam generation processes, such as heat recovery steam generators (HRSG). The methodology includes a modular strategy that considers individual heat exchangers such as: economizers, evapo-rators, superheaters, drum tanks, and control systems. The modular strategy consists of the development of a numerical modeling tool that integrates sub-models based upon first principle equations of mass, energy, and momentum balance. The main heat transfer mech- anisms characterize the dynamics of steam generation systems during normal and abnor-mal operations, which include the response of key process variables such as vapor pressure, temperature, and mass flow rate. Other important variables are: gas temperature, fluid temperature, drum pressure, drum ’ s liquid level, and mass flow rate at each module. Those variables are usually analyzed with design predicted performance of real industrial equip- ment such as HRSG systems. Finally, two case studies of the application of the modeling strategy are provided to show the effectiveness and utility of the methodology.
{"title":"Modeling, Simulation, and Control of Steam Generation Processes","authors":"G. Dieck-Assad, José Luis Vega-Fonseca, Isaías Hernández Ramírez, A. Favela-Contreras","doi":"10.5772/INTECHOPEN.79410","DOIUrl":"https://doi.org/10.5772/INTECHOPEN.79410","url":null,"abstract":"This chapter describes a modeling methodology to provide the main characteristics of a simulation tool to analyze the steady state, transient operation, and control of steam generation processes, such as heat recovery steam generators (HRSG). The methodology includes a modular strategy that considers individual heat exchangers such as: economizers, evapo-rators, superheaters, drum tanks, and control systems. The modular strategy consists of the development of a numerical modeling tool that integrates sub-models based upon first principle equations of mass, energy, and momentum balance. The main heat transfer mech- anisms characterize the dynamics of steam generation systems during normal and abnor-mal operations, which include the response of key process variables such as vapor pressure, temperature, and mass flow rate. Other important variables are: gas temperature, fluid temperature, drum pressure, drum ’ s liquid level, and mass flow rate at each module. Those variables are usually analyzed with design predicted performance of real industrial equip- ment such as HRSG systems. Finally, two case studies of the application of the modeling strategy are provided to show the effectiveness and utility of the methodology.","PeriodicalId":50943,"journal":{"name":"ACM Transactions on Modeling and Computer Simulation","volume":"5 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2019-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87857142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-24DOI: 10.1007/978-1-4419-1153-7_200685
GörderBjürn, KolonkoMichael
{"title":"Ranking and Selection","authors":"GörderBjürn, KolonkoMichael","doi":"10.1007/978-1-4419-1153-7_200685","DOIUrl":"https://doi.org/10.1007/978-1-4419-1153-7_200685","url":null,"abstract":"","PeriodicalId":50943,"journal":{"name":"ACM Transactions on Modeling and Computer Simulation","volume":"1 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2019-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45981872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-05DOI: 10.5772/INTECHOPEN.80070
Şebnem Bora, Sevcan Emek
Agent-based modeling and simulation is a powerful technique in simulating and explor- ing phenomena that includes a large set of active components represented by agents. The agents are actors operating in a real system, influencing the simulated environment and influenced by the simulated environment. The agents are included in the simula tion model as model components performing actions autonomously and interacting with other agents and the simulated environment to represent behaviors in the real system. In this chapter, we describe how to develop an agent-based model and simulation for biological systems in Repast Simphony platform, which is a Java-based modeling system. Repast Simphony helps developers to create a scenario tree including displays of agents, grid and continuous space, data sets, data loaders, histogram, and time charts. At the end of this chapter, we present case studies developed by our research group with references to demonstrate local behavior of biological system.
{"title":"Agent-Based Modeling and Simulation of Biological Systems","authors":"Şebnem Bora, Sevcan Emek","doi":"10.5772/INTECHOPEN.80070","DOIUrl":"https://doi.org/10.5772/INTECHOPEN.80070","url":null,"abstract":"Agent-based modeling and simulation is a powerful technique in simulating and explor- ing phenomena that includes a large set of active components represented by agents. The agents are actors operating in a real system, influencing the simulated environment and influenced by the simulated environment. The agents are included in the simula tion model as model components performing actions autonomously and interacting with other agents and the simulated environment to represent behaviors in the real system. In this chapter, we describe how to develop an agent-based model and simulation for biological systems in Repast Simphony platform, which is a Java-based modeling system. Repast Simphony helps developers to create a scenario tree including displays of agents, grid and continuous space, data sets, data loaders, histogram, and time charts. At the end of this chapter, we present case studies developed by our research group with references to demonstrate local behavior of biological system.","PeriodicalId":50943,"journal":{"name":"ACM Transactions on Modeling and Computer Simulation","volume":"2013 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2018-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87732468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-05DOI: 10.5772/INTECHOPEN.79939
Ivana Cvetković, M. Stojicevic, B. Popkonstantinović
The escapement is a very important horological invention and it is commonly used in theory of clocks and chronometers. It transfers energy to the timekeeping element and allows the number of its oscillations to be counted. The chronometer detent escape- ment used in marine chronometers was modified and simplified by Thomas Earnshaw, English renowned watchmaker, in order to make it available to the public. This chapter deals with 3D modeling and assembling of all escapement parts in SolidWorks, as well as constructive geometry of mechanism and computer simulation. The whole process has been accomplished in program “SolidWorks 2016,” where all parts are assembled by using standard mates since this approach is suitable for motion and dynamical analysis. Generated simulation results are very close to the real ones, thereby using computation ally strong kinematic solvers.
{"title":"Modeling, Motion Study, and Computer Simulation of Thomas Earnshaw’s Chronometer Detent Escapement Mechanism","authors":"Ivana Cvetković, M. Stojicevic, B. Popkonstantinović","doi":"10.5772/INTECHOPEN.79939","DOIUrl":"https://doi.org/10.5772/INTECHOPEN.79939","url":null,"abstract":"The escapement is a very important horological invention and it is commonly used in theory of clocks and chronometers. It transfers energy to the timekeeping element and allows the number of its oscillations to be counted. The chronometer detent escape- ment used in marine chronometers was modified and simplified by Thomas Earnshaw, English renowned watchmaker, in order to make it available to the public. This chapter deals with 3D modeling and assembling of all escapement parts in SolidWorks, as well as constructive geometry of mechanism and computer simulation. The whole process has been accomplished in program “SolidWorks 2016,” where all parts are assembled by using standard mates since this approach is suitable for motion and dynamical analysis. Generated simulation results are very close to the real ones, thereby using computation ally strong kinematic solvers.","PeriodicalId":50943,"journal":{"name":"ACM Transactions on Modeling and Computer Simulation","volume":"20 1","pages":""},"PeriodicalIF":0.9,"publicationDate":"2018-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90049660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Anastasis Georgoulas, J. Hillston, Guido Sanguinetti
Formal languages like process algebras have been shown to be effective tools in modelling a wide range of dynamic systems, providing a high-level description that is readily transformed into an executable model. However, their application is sometimes hampered because the quantitative details of many real-world systems of interest are not fully known. In contrast, in machine learning, there has been work to develop probabilistic programming languages, which provide system descriptions that incorporate uncertainty and leverage advanced statistical techniques to infer unknown parameters from observed data. Unfortunately, current probabilistic programming languages are typically too low-level to be suitable for complex modelling. In this article, we present a Probabilistic Programming Process Algebra (ProPPA), the first instance of the probabilistic programming paradigm being applied to a high-level, formal language, and its supporting tool suite. We explain the semantics of the language in terms of a quantitative generalisation of Constraint Markov Chains and describe the implementation of the language, discussing in some detail the different inference algorithms available and their domain of applicability. We conclude by illustrating the use of the language on simple but non-trivial case studies: here, ProPPA is shown to combine the elegance and simplicity of high-level formal modelling languages with an effective way of incorporating data, making it a promising tool for modelling studies.
像过程代数这样的形式语言已经被证明是建模各种动态系统的有效工具，它提供了易于转换为可执行模型的高级描述。然而，它们的应用有时会受到阻碍，因为许多感兴趣的现实世界系统的定量细节并不完全清楚。相比之下，在机器学习领域，人们一直致力于开发概率编程语言，这些语言提供包含不确定性的系统描述，并利用先进的统计技术从观察到的数据中推断未知参数。不幸的是，当前的概率编程语言通常太低级，不适合复杂的建模。在本文中，我们介绍了概率编程过程代数(Probabilistic Programming Process Algebra, ProPPA)，这是应用于高级形式语言的概率编程范式的第一个实例，以及它的支持工具套件。我们根据约束马尔可夫链的定量概括来解释该语言的语义，并描述该语言的实现，详细讨论了可用的不同推理算法及其适用范围。最后，我们举例说明了该语言在简单但不平凡的案例研究中的使用:在这里，ProPPA显示了将高级正式建模语言的优雅和简单性与有效的合并数据的方法相结合，使其成为建模研究的有前途的工具。
{"title":"ProPPA: Probabilistic Programming for Stochastic Dynamical Systems","authors":"Anastasis Georgoulas, J. Hillston, Guido Sanguinetti","doi":"10.1145/3154392","DOIUrl":"https://doi.org/10.1145/3154392","url":null,"abstract":"Formal languages like process algebras have been shown to be effective tools in modelling a wide range of dynamic systems, providing a high-level description that is readily transformed into an executable model. However, their application is sometimes hampered because the quantitative details of many real-world systems of interest are not fully known. In contrast, in machine learning, there has been work to develop probabilistic programming languages, which provide system descriptions that incorporate uncertainty and leverage advanced statistical techniques to infer unknown parameters from observed data. Unfortunately, current probabilistic programming languages are typically too low-level to be suitable for complex modelling. \u0000 \u0000In this article, we present a Probabilistic Programming Process Algebra (ProPPA), the first instance of the probabilistic programming paradigm being applied to a high-level, formal language, and its supporting tool suite. We explain the semantics of the language in terms of a quantitative generalisation of Constraint Markov Chains and describe the implementation of the language, discussing in some detail the different inference algorithms available and their domain of applicability. We conclude by illustrating the use of the language on simple but non-trivial case studies: here, ProPPA is shown to combine the elegance and simplicity of high-level formal modelling languages with an effective way of incorporating data, making it a promising tool for modelling studies.","PeriodicalId":50943,"journal":{"name":"ACM Transactions on Modeling and Computer Simulation","volume":"181 1","pages":"3:1-3:23"},"PeriodicalIF":0.9,"publicationDate":"2018-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80268728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Emergence becomes a distinguishing system feature as system complexity grows with the number of components, interactions, and connectivities. Examples of emergent behaviors include the flocking of birds, traffic jams, and hubs in social networks, among others. Despite significant research interest in recent years, there is a lack of formal methods to understand, identify, and predict emergent behavior in multiagent systems. Existing approaches either require detailed prior knowledge about emergent behavior or are computationally infeasible. This article introduces a grammar-based approach to formalize and identify the existence and extent of emergence without the need for prior knowledge of emergent properties. Our approach is based on weak (basic) emergence that is both generated and autonomous from the underlying agents. We employ formal grammars to capture agent interactions in the forms of words written on a common tape. Our formalism captures agents of diverse types and open systems. We propose an automated approach for the identification of emergent behavior and show its benefits through theoretical and experimental analysis. We also propose a significant reduction of state-space explosion through the use of our proposed degree of interaction metrics. Our experiments using the boids model show the feasibility of our approach but also highlight future avenues of improvement.
{"title":"Formalization of Weak Emergence in Multiagent Systems","authors":"Claudia Szabo, Y. M. Teo","doi":"10.1145/2815502","DOIUrl":"https://doi.org/10.1145/2815502","url":null,"abstract":"Emergence becomes a distinguishing system feature as system complexity grows with the number of components, interactions, and connectivities. Examples of emergent behaviors include the flocking of birds, traffic jams, and hubs in social networks, among others. Despite significant research interest in recent years, there is a lack of formal methods to understand, identify, and predict emergent behavior in multiagent systems. Existing approaches either require detailed prior knowledge about emergent behavior or are computationally infeasible. This article introduces a grammar-based approach to formalize and identify the existence and extent of emergence without the need for prior knowledge of emergent properties. Our approach is based on weak (basic) emergence that is both generated and autonomous from the underlying agents. We employ formal grammars to capture agent interactions in the forms of words written on a common tape. Our formalism captures agents of diverse types and open systems. We propose an automated approach for the identification of emergent behavior and show its benefits through theoretical and experimental analysis. We also propose a significant reduction of state-space explosion through the use of our proposed degree of interaction metrics. Our experiments using the boids model show the feasibility of our approach but also highlight future avenues of improvement.","PeriodicalId":50943,"journal":{"name":"ACM Transactions on Modeling and Computer Simulation","volume":"6 1","pages":"6:1-6:25"},"PeriodicalIF":0.9,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75271138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cloud and Virtual Machine (VM) technologies present new challenges with respect to performance and monetary cost in executing parallel discrete event simulation (PDES) applications. Due to the introduction of overall cost as a metric, the traditional use of the highest-end computing configuration is no longer the most obvious choice. Moreover, the unique runtime dynamics and configuration choices of Cloud and VM platforms introduce new design considerations and runtime characteristics specific to PDES over Cloud/VMs. Here, an empirical study is presented to help understand the dynamics, trends, and trade-offs in executing PDES on Cloud/VM platforms. Performance and cost measures obtained from multiple PDES applications executed on the Amazon EC2 Cloud and on a high-end VM host machine reveal new, counterintuitive VM--PDES dynamics and guidelines. One of the critical aspects uncovered is the fundamental mismatch in hypervisor scheduler policies designed for general Cloud workloads versus the virtual time ordering needed for PDES workloads. This insight is supported by experimental data revealing the gross deterioration in PDES performance traceable to VM scheduling policy. To overcome this fundamental problem, the design and implementation of a new deadlock-free scheduler algorithm are presented, optimized specifically for PDES applications on VMs. The scalability of our scheduler has been tested in up to 128 VMs multiplexed on 32 cores, showing significant improvement in the runtime relative to the default Cloud/VM scheduler. The observations, algorithmic design, and results are timely for emerging Cloud/VM-based installations, highlighting the need for PDES-specific support in high-performance discrete event simulations on Cloud/VM platforms.
{"title":"Efficient Parallel Discrete Event Simulation on Cloud/Virtual Machine Platforms","authors":"Srikanth B. Yoginath, K. Perumalla","doi":"10.1145/2746232","DOIUrl":"https://doi.org/10.1145/2746232","url":null,"abstract":"Cloud and Virtual Machine (VM) technologies present new challenges with respect to performance and monetary cost in executing parallel discrete event simulation (PDES) applications. Due to the introduction of overall cost as a metric, the traditional use of the highest-end computing configuration is no longer the most obvious choice. Moreover, the unique runtime dynamics and configuration choices of Cloud and VM platforms introduce new design considerations and runtime characteristics specific to PDES over Cloud/VMs. Here, an empirical study is presented to help understand the dynamics, trends, and trade-offs in executing PDES on Cloud/VM platforms. Performance and cost measures obtained from multiple PDES applications executed on the Amazon EC2 Cloud and on a high-end VM host machine reveal new, counterintuitive VM--PDES dynamics and guidelines. One of the critical aspects uncovered is the fundamental mismatch in hypervisor scheduler policies designed for general Cloud workloads versus the virtual time ordering needed for PDES workloads. This insight is supported by experimental data revealing the gross deterioration in PDES performance traceable to VM scheduling policy. To overcome this fundamental problem, the design and implementation of a new deadlock-free scheduler algorithm are presented, optimized specifically for PDES applications on VMs. The scalability of our scheduler has been tested in up to 128 VMs multiplexed on 32 cores, showing significant improvement in the runtime relative to the default Cloud/VM scheduler. The observations, algorithmic design, and results are timely for emerging Cloud/VM-based installations, highlighting the need for PDES-specific support in high-performance discrete event simulations on Cloud/VM platforms.","PeriodicalId":50943,"journal":{"name":"ACM Transactions on Modeling and Computer Simulation","volume":"51 1","pages":"5:1-5:26"},"PeriodicalIF":0.9,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77441973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Modeling and simulation has witnessed a surge of advanced methods and tools to improve the tasks of the simulation users, ranging from advanced methodologies, software development methods, middleware, visualization tools, analytics, Cloud computing, standards, and others. Within this context, the new ACM SIGSIM Conference on Principles of Advanced Discrete Simulation (SIGSIM-PADS) has allowed sharing and discussing new methods, tools and applications in this field. The new SIGSIM-PADS conference was rebuilt upon 26 years of history and the reputation for high-quality papers of the traditional PADS Workshop (Workshop on Principles of Advanced and Distributed Simulation). The objective of this new conference is now the intersection of computer science and modeling and simulation. The inaugural conference attracted 75 full paper submissions from 27 countries around the world. From the 29 papers accepted, the top 10 were invited to submit extended versions. There was also a call for papers for articles related to this field of research. The numerous articles (some of which were new, and others were extended versions of the original SIGSIM-PADS articles) were peer reviewed again by at least three reviewers, making the quality of the final submissions very high. The topics were varied, ranging from automation in parallel simulation in multicore architectures, generation of simulation models, management of activity in simulation, heterogeneous parallel simulation, and theory and emergent behavior. We also received articles on agent-based simulation, simulation with hardware-in-the-loop, and varied applications including networking and communications, logistics, and biology. The articles presented in this issue can be categorized, based on their research area, into the following areas: modeling methodologies, parallel and distributed simulation, and network simulation and emulation.
{"title":"Editorial for Principles of Advanced Discrete Simulation","authors":"Gabriel A. Wainer","doi":"10.1145/2845147","DOIUrl":"https://doi.org/10.1145/2845147","url":null,"abstract":"Modeling and simulation has witnessed a surge of advanced methods and tools to improve the tasks of the simulation users, ranging from advanced methodologies, software development methods, middleware, visualization tools, analytics, Cloud computing, standards, and others. Within this context, the new ACM SIGSIM Conference on Principles of Advanced Discrete Simulation (SIGSIM-PADS) has allowed sharing and discussing new methods, tools and applications in this field. The new SIGSIM-PADS conference was rebuilt upon 26 years of history and the reputation for high-quality papers of the traditional PADS Workshop (Workshop on Principles of Advanced and Distributed Simulation). The objective of this new conference is now the intersection of computer science and modeling and simulation. The inaugural conference attracted 75 full paper submissions from 27 countries around the world. From the 29 papers accepted, the top 10 were invited to submit extended versions. There was also a call for papers for articles related to this field of research. The numerous articles (some of which were new, and others were extended versions of the original SIGSIM-PADS articles) were peer reviewed again by at least three reviewers, making the quality of the final submissions very high. The topics were varied, ranging from automation in parallel simulation in multicore architectures, generation of simulation models, management of activity in simulation, heterogeneous parallel simulation, and theory and emergent behavior. We also received articles on agent-based simulation, simulation with hardware-in-the-loop, and varied applications including networking and communications, logistics, and biology. The articles presented in this issue can be categorized, based on their research area, into the following areas: modeling methodologies, parallel and distributed simulation, and network simulation and emulation.","PeriodicalId":50943,"journal":{"name":"ACM Transactions on Modeling and Computer Simulation","volume":"3 1","pages":"1e:1-1e:3"},"PeriodicalIF":0.9,"publicationDate":"2015-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89330024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：