A Platform for Massive Agent-Based Simulation and Its Evaluation

Yamamoto, Go; H, Tai; Mizuta, Hideyuki

doi:10.1007/978-3-540-85449-4_1

Cited by 10 publications

(3 citation statements)

References 4 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Earlier works have been done on Virtual Time (Jefferson, 1985) which explain it for discrete event simulations and multi-agent system (MAS) can be considered as discrete event simulation, if we consider an interaction as an event. Load balancing (Yamamoto et al, 2008;Logan and Theodoropoulos, 2001) is also an important issue in any distributed system, if the load between machines is not similar, the distribution will not be efficient especially for the initial state. We believe that the main concepts of multi-agents system (agents and environment) must be taken into account when we distribute some kind of applications to avoid any disproportionate load.…”

Section: Introductionmentioning

confidence: 99%

Effective Distribution of Large Scale Situated Agent-based Simulations

2014

Proceedings of the 6th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

International audienceAgent-based simulations have increasing needs in computational and memory resources when the the number of agents and interactions grows. In this paper, we are concerned with the simulation of large scale situated multi-agent systems (MAS). To be able to simulate several thousands or even a million of agents, it becomes necessary to distribute the load on a computer network. This distribution can be done in several ways and this paper presents two specific distributions: the first one is based on environment and the second one is based on agents. We illustrates the pros and cons of using both distribution types with two classical MAS applications: prey-predator and flocking behaviour models

show abstract

Section: Introductionmentioning

confidence: 99%

Effective Distribution of Large Scale Situated Agent-based Simulations

2014

Proceedings of the 6th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…The aim of this component is twofold: to speed up the simulation process and to use the computation power of several nodes in a computer network. By accessing shared computational resources across several nodes the simulation framework is even able to run massive agent based simulations (Yamamoto et al, 2007) which can not be performed on a single computer. On the other hand, the simulation framework can use the nodes to parallelize, e.g.…”

Section: System Architecture Of the Frameworkmentioning

confidence: 99%

Towards Automated Simulation of Multi Agent Based Systems

Vilenica

Lamersdorf

2010

Proceedings of the 12th International Conference on Enterprise Information Systems

View full text Add to dashboard Cite

The simulation of systems offers a viable approach to find the optimal configuration of a system with respect to time, costs or any other utility function. In order to speed up the development process and to relieve developers from doing cumbersome work that is related to the execution of simulation runs, i.e. doing the simulation management manually, it is desirable to have a framework that provides tools which perform the simulation management automatically. Therefore, this work addresses this issue and presents an approach that reduces the effort to manage simulations, i.e. it eases and automates the execution, observation, optimization and evaluation. The approach consists of a declarative simulation description language and a framework that is capable of automatically managing simulations. Thereby, this approach reduces the costs, i.e. with respect to time and money, to perform simulations. Furthermore, this work targets a special subset of simulations, i.e. multi agent based simulation, that has grown large attention in many areas of science as well as in commercial applications in the last decade. The applicability of the approach is proven by a case study called "mining ore resources" that has been conducted.

show abstract

“…DMASF [8] is a new Python toolkit that can be used to simulate a large number of agents over a distributed computer network. ZASE [9] is another approach to simulate massive multi-agent systems. It is essential for the RoboCup Rescue Simulation to scale up the numbers in order to make the simulation more realistic and these new toolkits require building of the RoboCup Rescue server from scratch.…”

Section: Related Workmentioning

confidence: 99%

Database Driven RoboCup Rescue Server

Sarika

Siddhartha

Karlapalem

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The RoboCup Rescue Simulation, a generic urban disaster simulation environment constructed on a network of computers, has been in existence for many years. The server used in the simulation league has problems of scaling up. Further, it requires considerable effort to understand the server code to make any additional changes. Therefore, it is difficult for newcomers to quickly enhance the server. The architecture and the functional design of the current server are excellent. This helps us provide a database driven architecture that can scale up the current server to 10-15 times the number of agents that can be simulated. Moreover, it is now easy for others to implement many other subsystems that can provide additional functionality. We have also shown in this paper a new scoring strategy for agent teams which can be customized to emphasize, test and evaluate different concepts and strategies employed by the agent teams.

show abstract

A Platform for Massive Agent-Based Simulation and Its Evaluation

Cited by 10 publications

References 4 publications

Effective Distribution of Large Scale Situated Agent-based Simulations

Effective Distribution of Large Scale Situated Agent-based Simulations

Towards Automated Simulation of Multi Agent Based Systems

Database Driven RoboCup Rescue Server

Contact Info

Product

Resources

About