MWGrid: A System for Distributed Agent-Based Simulation in the Digital Humanities

Craenen, Bart; Murgatroyd, Philip; Theodoropoulos, Georgios; Gaffney, Vincent; Suryanarayanan, Vinoth

doi:10.1109/ds-rt.2012.24

Cited by 8 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One paper used a multi-objective simulation optimization algorithm implemented on a cloud to speed up the experimentation of medical resource allocation in emergency departments (Chen, 2014). Work in Humanities used distributed agent-based simulation to study logistics issues in historical military scenarios (Craenen, Murgatroyd, Theodoropoulos, Gaffney, & Suryanarayanan, 2012).…”

Section: Distributed Simulation Applicationsmentioning

confidence: 99%

Distributed simulation: state-of-the-art and potential for operational research

Taylor

2019

European Journal of Operational Research

View full text Add to dashboard Cite

Section: Distributed Simulation Applicationsmentioning

confidence: 99%

Distributed simulation: state-of-the-art and potential for operational research

Taylor

2019

European Journal of Operational Research

View full text Add to dashboard Cite

“…RELATED WORK Although various ABS toolkits are developed for different purposes [7,[10][11][12], there are a number of modules commonly supported by these toolkits, such as the agent management, agent interaction, visualization, and simulation result analysis. Section 3 discusses the features of GPU platforms, how these features can help to speed-up ABS on GPU, and the corresponding challenges.…”

Section: Introductionmentioning

confidence: 99%

“…Various strategies to speed up simulations have been proposed on distributed platforms [12][13][14][15] and [16]. The limitation on execution speed restricts the feasibility of executing large-scale ABS.…”

Section: Introductionmentioning

confidence: 99%

Supporting efficient execution of continuous space agent‐based simulation on GPU

Cai

Turner

2016

Concurrency and Computation

View full text Add to dashboard Cite

Using agent-based simulation (ABS) to analyze complex adaptive systems gains growing popularity over the past decades. One of the fundamental issues in ABS is to increase the execution speed. In this paper, we identify two common modules that widely exist in ABS applications, namely, the agent management module and the agent interaction module. Improving the efficiency of these two common modules can significantly speed up the ABS execution in general. GPU architecture, programming model, and memory hierarchy are studied. Effective strategies on GPU are proposed when we design the two modules. The first contribution of this work is to propose an AgentPool data structure to handle agent creation and deletion on GPU. The second contribution is an efficient agent interaction module, which is designed by carefully utilizing the GPU memory hierarchy. To demonstrate effectiveness and generality, the proposed strategies are applied to a range of ABS applications, including game-of-life, flocking boids, prey-and-predator, and the social force-based crowd simulation. The simulation results demonstrate that the proposed strategies achieve better performance than the commonly used CPU and GPU ABS framework, namely, Mason and FLAME, for ABS applications using continuous space.

show abstract

“…The framework is prototyped on top of the JADE agent infrastructure. The approach relies on a policy development process and a software toolbox supporting this process.An agent-based framework directed to the field of digital humanities is described in [20]. On-going and future work is finally pointed out in the conclusions.…”

mentioning

confidence: 99%

“…The term policy refers to strategic areas of complex decision-making with various stakeholders having conceivably diverging interests. The approach relies on a policy development process and a software toolbox supporting this process.An agent-based framework directed to the field of digital humanities is described in [20]. It integrates an agent design template, a transparent and layered mechanism to translate model-level agents actions to timestamped events and a distributed simulation kernel.…”

mentioning

confidence: 99%

Control centric framework for model continuity in time‐dependent multi‐agent systems

Cicirelli

Nigro

2016

Concurrency and Computation

View full text Add to dashboard Cite

This work centres on a control framework for general multi-agent systems, which separates the design of agents behaviours (the application layer) from crosscutting control concerns (the control layer) regulating message exchange and processing. The goal is to support modelling and execution of a multi-agent system whose evolution is transparently governed by a pluggable control structure. A library of different control structures, including pure-concurrent and time-sensitive (real-time and simulation) strategies, was developed. The paper describes the developed control framework and focusses on the achievement of control strategies compliant with agent mobility and resource availability. The control design rests on a minimal actor computational model extended with actions, which are independent computational tasks able to execute in parallel. The approach enables model continuity, that is, the same model is used from analysis by simulation to implementation and real-time execution. The framework is prototyped on top of the JADE agent infrastructure. Usability and effectiveness of the resultant approach are demonstrated by a case study based on a complex closed queue network of services. On-going and future work is finally pointed out in the conclusions. 3334F. CICIRELLI AND L. NIGRO sidering the availability of dedicated processing units. Flexibility of control design is also advocated to deal with problems of mechanism design [2] where a suitable control strategy is required to regulate/coordinate the decision process in a group of agents during the allocation of scarce resources. This paper proposes an original and flexible control framework for distributed multi-agent systems. The approach makes it possible to transparently aggregate a given control module extracted from a library to a multi-agent system. One of the challenging goals in this work is to support model continuity [3] whose aim is to favour the use of a same model from property analysis (possibly based on parallel/distributed simulation) to real-time execution. A particular implementation of the approach, devoted to the schedulability analysis of real-time systems, is described in [4].The proposed control framework purposely depends on a minimal computational actor model [5][6][7]. The actor model actually used in this paper is novel in that it owns a notion of actions, which are a key for transparently switching from simulation to real execution. Actions naturally map on to processing units (PUs) managed by a given control strategy. PUs model computational resources of the external environment of the application. Both the availability and the behaviour of processing units can affect, in an orthogonal way, the execution of the application. In particular, the evolution of a realized multi-agent system constitutes an emerging property of the interaction between the application and its environment, mediated by the provided control layer.For demonstration purpose, the framework is prototyped in JADE [8, 9]. JADE was chosen because it is a representati...

show abstract

MWGrid: A System for Distributed Agent-Based Simulation in the Digital Humanities

Cited by 8 publications

References 25 publications

Distributed simulation: state-of-the-art and potential for operational research

Distributed simulation: state-of-the-art and potential for operational research

Supporting efficient execution of continuous space agent‐based simulation on GPU

Control centric framework for model continuity in time‐dependent multi‐agent systems

Contact Info

Product

Resources

About