Abstract
The emergence of agent oriented systems has provided an alternative approach to address many complex problems that require distributed behavior, local decisions, and emerging global behavior from the interactions of their basic elements. There are several natural, artificial and social phenomena that present these features. However, despite providing a suitable tool for modeling complex distributed systems, implementations of multi-agent systems are limited by the available hardware architecture. A recent possibility to circumvent this problem is the use of graphics cards to implement such systems. Nevertheless, these devices reach the optimal performance when agents have homogeneous and simple behavior, which might not be the case of many problems. Systems such as simulators of the immune system, in addition to having a large number of agents with complex behavior, those agents communicate massively, indirectly, through dissemination of various substances in their environment. Diffusion of substances is something easily simulated in modern current graphics cards, but the problem is to provide the results of those simulations to thousands (or millions) of agents simultaneously. This paper presents a benchmarking conducted to determine a suitable software/hardware architecture to implement such a system. The results show that a heterogeneous system can have a better performance.
A. de Paiva Oliveira—The author receives grant from capes, process n.0449/15-6.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shoham, Y.: Agent-oriented programming. Artif. Intell. 60(1), 51–92 (1993)
Chen, W., Ward, K., Li, Q., Kecman, V., Najarian, K., Menke, N.: Agent based modeling of blood coagulation system: implementation using a gpu based high speed framework. In: 2011 Annual International Conference of the IEEE on Engineering in Medicine and Biology Society, EMBC, pp. 145–148. IEEE (2011)
Richmond, P., Walker, D., Coakley, S., Romano, D.: High performance cellular level agent-based simulation with flame for the gpu. Briefings Bioinform. 11(3), 334–347 (2010)
Dewri, R., Chakraborti, N.: Simulating recrystallization through cellular automata and genetic algorithms. Modell. Simul. Mater. Sci. Eng. 13(2), 173 (2005)
North, M.J., Collier, N.T., Ozik, J., Tatara, E.R., Macal, C.M., Bragen, M., Sydelko, P.: Complex adaptive systems modeling with repast simphony. Complex adapt. syst. model. 1(1), 1–26 (2013)
Kiran, M., Richmond, P., Holcombe, M., Chin, L.S., Worth, D., Greenough, C.: Flame: simulating large populations of agents on parallel hardware architectures. In: Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems, vol. 1, pp. 1633–1636. International Foundation for Autonomous Agents and Multiagent Systems (2010)
Acknowledgments
This research is supported in part by the funding agencies FAPEMIG, CNPq, and CAPES.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Martins, F.R., de Paiva Oliveira, A., Ferreira, R.S., Cerqueira, F.R. (2016). Hardware Architecture Benchmarking for Simulation of Human Immune System by Multi-agent Systems. In: Rovatsos, M., Vouros, G., Julian, V. (eds) Multi-Agent Systems and Agreement Technologies. EUMAS AT 2015 2015. Lecture Notes in Computer Science(), vol 9571. Springer, Cham. https://doi.org/10.1007/978-3-319-33509-4_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-33509-4_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-33508-7
Online ISBN: 978-3-319-33509-4
eBook Packages: Computer ScienceComputer Science (R0)