An agentbased framework for performance modeling of an optimistic parallel discrete event simulator
 Aditya Kurve,
 Khashayar Kotobi,
 George Kesidis
 … show all 3 hide
Abstract
Purpose
The performance of an optimistic parallel discrete event simulator (PDES) in terms of the total simulation execution time of an experiment depends on a large set of variables. Many of them have a complex and generally unknown relationship with the simulation execution time. In this paper, we describe an agentbased performance model of a PDES kernel that is typically used to simulate largesized complex networks on multiple processors or machines. The agentbased paradigm greatly simplifies the modeling of system dynamics by representing a component logical process (LP) as an autonomous agent that interacts with other LPs through event queues and also interacts with its environment which comprises the processor it resides on.
Method
We model the agents representing the LPs using a “base” class of an LP agent that allows us to use a generic behavioral model of an agent that can be extended further to model more details of LP behavior. The base class focuses only on the details that most likely influence the overall simulation execution time of the experiment.
Results
We apply this framework to study a local incentive based partitioning algorithm where each LP makes an informed local decision about its assignment to a processor, resulting in a system akin to a self organizing network. The agentbased model allows us to study the overall effect of the local incentivebased cost function on the simulation execution time of the experiment which we consider to be the global performance metric.
Conclusion
This work demonstrates the utility of agentbased approach in modeling a PDES kernel in order to evaluate the effects of a large number of variable factors such as the LP graph properties, load balancing criteria and others on the total simulation execution time of an experiment.
 Proceedings of the, First International Workshop on MultiAgent Systems and AgentBased Simulation.
 Agrawal, VD, Chakradhar, ST (1992) Performance analysis of synchronized iterative algorithms on multiprocessor systems. IEEE Trans, Parallel Distributed Syst 3: pp. 739746 CrossRef
 Axelrod, R (1997) The dissemination of culture a model with local convergence and global polarization. J Confl Resolution 41: pp. 203226 CrossRef
 Bagrodia, R, Meyer, R, Takai, M, Chen, Y, Zeng, X, Martin, J, Song, HY (1998) Parsec: a parallel simulation environment for complex systems. Computer 31: pp. 7785 CrossRef
 Borshchev, A, Filippov, A (2004) From system dynamics and discrete event to practical agent based modeling: reasons, techniques, tools. Proceedings of the 22nd International Conference of the System Dynamics Society.
 Bu, T, Towsley, D (2002) On distinguishing between internet power law topology generators. Proceedings of the 21st, Annual Joint Conference of the IEEE Computer and Communications Societies INFOCOM. pp. 638647
 Carl, G, Kesidis, G (2008) Largescale testing of the Internet’s Border Gateway Protocol (BGP) via topological scaledown. ACM Trans Model, Comput Simul (TOMACS) 18: pp. 130 CrossRef
 Chandy, KM, Misra, J (1981) Asynchronous distributed simulation via a sequence of parallel computations. Commun ACM 24: pp. 198206 CrossRef
 Chertov, R, Fahmy, S (2011) Forwarding devices: From measurements to simulations. ACM Trans Model and, Comput Simul (TOMACS) 21: pp. 12
 Dimitropoulos, X, Krioukov, D, Vahdat, A, Riley, G (2009) Graph annotations in modeling complex network topologies. ACM Trans Model, Comput Simul (TOMACS) 19: pp. 17
 Dorigo, M, Birattari, M, Stutzle, T (2006) Ant colony optimization. Comput Intell, Mag, IEEE 1: pp. 2839
 Gupta, D, Vishwanath, KV, Vahdat, A (2008) Diecast: testing distributed systems with an accurate scale model. Proc. 5th USENIX Symposium on Networked Systems Design and Implementation. pp. 407422
 Jefferson, DR (1985) Virtual time. ACM Trans Program, Languages Syst (TOPLAS) 7: pp. 404425 CrossRef
 Jennings NR, Commun ACM: An agentbased approach for building complex software systems. 2001,44(4):35–41.
 Karypis, G, Kumar, V (1996) Parallel multilevel kway partitioning scheme for irregular graphs. Proc. 1996 ACM/IEEE Conference on Supercomputing.
 Kurve, A, Griffin, C, Kesidis, G (2011a) A graph partitioning game for distributed simulation of networks. Proceedings of the 2011 International Workshop on, Modeling, Analysis, and Control of Complex Networks. pp. 916
 Iterative partitioning scheme for distributed simulation of dynamic networks. Proc. 16th IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD). pp. 9296 CrossRef
 Kurve, A, Griffin, C, Miller, DJ, Kesidis, G (2013) Optimizing Cluster Formation in SuperPeer Networks via Local Incentive Design.
 Monderer, D, Shapley, LS (1996) Potential games. Games Econ, Behav 14: pp. 124143 CrossRef
 Niazi, M, Hussain, A (2011) Agentbased computing from multiagent systems to agentbased models a visual survey. Scientometrics 89: pp. 479499 CrossRef
 Nicol, D, Fujimoto, R (1994) Parallel simulation today. Ann Oper, Res 53: pp. 249285 CrossRef
 Nikolai, C, Madey, G (2007) Anatomy of a toolkit: A comprehensive compensium of various agentbased modeling. Proceedings of the Agent 2007 Conference on Complex Interaction and Social Emergence. pp. 8792
 North, M, Howe, T, Collier, N, Vos, J (2007) A declarative model assembly infrastructure for verification and validation. Advancing Social, Simulation: The First World Congress. pp. 129140 CrossRef
 Pothen, A, Simon, HD, Liou, KPetal (1990) Partitioning sparse matrices with eigenvectors of graphs. SIAM J Matrix Anal Appl 11: pp. 430452 CrossRef
 Psounis, K, Pan, R, Prabhakar, B, Wischik, D (2003) The scaling hypothesis: Simplifying the prediction of network performance using scaleddown simulations. ACM SIGCOMM Comput Commun, Rev 33: pp. 3540 CrossRef
 Reynolds, R (1987) Flocks, herds and schools: a distributed behavioral model. ACM SIGGRAPH Comput Graph. pp. 2534
 Sriram, K, Montgomery, D, Borchert, O, Kim, O, Kuhn, DR (2006) Study of BGP peering session attacks and their impacts on routing performance. IEEE J Selected Areas, Commun 24: pp. 19011915 CrossRef
 Tisue, S, Wilensky, U (2004) Netlogo: A simple environment for modeling complexity. Proc. International Conference on Complex Systems. pp. 1621
 Van Den Bout, DE, Thomas Miller III, TK (1990) Graph partitioning using annealed neural networks. IEEE Trans Neural Netw 1: pp. 192203 CrossRef
 Xu, J, Chung, MJ (2004) Predicting the performance of synchronous discrete event simulation. IEEE Trans Parallel, Distributed Syst 15: pp. 11301137 CrossRef
 Zeigler, B, Praehofer, H, Kim, TG (2000) Theory of modeling and simulation: integrating discrete event and continuous complex dynamic systems. Academic Pr.
 Zhang, L (2013) Internet topology data.
 Title
 An agentbased framework for performance modeling of an optimistic parallel discrete event simulator
 Open Access
 Available under Open Access This content is freely available online to anyone, anywhere at any time.
 Journal

Complex Adaptive Systems Modeling
1:12
 Online Date
 April 2013
 DOI
 10.1186/21943206112
 Online ISSN
 21943206
 Publisher
 Springer Berlin Heidelberg
 Additional Links
 Topics
 Keywords

 Agentbased modeling
 Parallel simulation
 Self organizing system
 Game theory
 Load balancing
 Authors

 Aditya Kurve ^{(1)}
 Khashayar Kotobi ^{(1)}
 George Kesidis ^{(2)}
 Author Affiliations

 1. EE Department, The Pennsylvania State University, University Park, PA, 16802, USA
 2. CSE and EE Department, The Pennsylvania State University, University Park, PA, 16802, USA