Performance Models Preventing Multi-Agent Systems from Overloading Computational Resources
Automation, Control and Intelligent Systems
Volume 2, Issue 6, December 2014, Pages: 105-111
Received: Nov. 12, 2014;
Accepted: Nov. 27, 2014;
Published: Dec. 5, 2014
Views 2373 Downloads 132
Petr Kadera, Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, CZ-169 00, Prague, Czech Republic
Petr Novak, Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, CZ-169 00, Prague, Czech Republic; Christian Doppler Laboratory for Software Engineering Integration for Flexible Automation Systems, Vienna University of Technology, A-1040, Vienna, Austria
Vaclav Jirkovsky, Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, CZ-169 00, Prague, Czech Republic; Rockwell Automation Research and Development Center, CZ-150 00, Prague, Czech Republic
Pavel Vrba, Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, CZ-169 00, Prague, Czech Republic
Multi-Agent Systems (MASs) suffer from low immunity against burst of arrival requests which can result in a permanent outage of such systems. This factor limits the suitability of MASs for control of real-world manufacturing systems with strict requirements on performance and reliability. This manuscript explains the origins of the performance degradation of MASs based on Contract-Net Protocol and proposes a method that protects the systems against the destructive effect of temporal overloads. The proposed method continuously observes the communication among agents and analyzes it in order to identify possible saturation of a system resource. If triggering a new action saturates a system resource, the carrying out of the action will be postponed. The impacts of the method are demonstrated on a test-bed consisted of six mini-computers Raspberry Pi. It shows that the proposed method avoids overloading of the system and thus guarantees a specific system throughput effectively and efficiently.
Performance Models Preventing Multi-Agent Systems from Overloading Computational Resources, Automation, Control and Intelligent Systems.
Vol. 2, No. 6,
2014, pp. 105-111.
M. Pěchouček, S. Thompson, J. Baxter, G. Horn, K. Kok, C. Warmer, R. Kamphuis, V. Mařík, P. Vrba, K. Hall, F. Maturana, K. Dorer, M. Calisti, Agents in industry: the best from the AAMAS 2005 industry track, IEEE Transactions on Intelligent Systems, 21(2), 86 (2006). DOI 10.1109/MIS.2006.19J.
P. Vrba, V. Mařík, P. Siano, P. Leitao, G. Zhabelova, V. Vyatkin, T. Strasser, A Review of Agent and Service-oriented Concepts applied to Intelligent Energy Systems, IEEE Transactions on Industrial Informatics (99), 1 (2014). DOI 10.1109/TII.2014.2326411
O. Yildirim, G. Kardas, A multi-agent system for minimizing energy costs in cement production, Computers in Industry 65(7), 1076 (2014). DOI 10.1016/j.compind.2014.05.002
P. Kadera, P. Tichý, Chilled water system control, simulation, and visualization using Java multi-agent systém, Information Control Problems in Manufacturing, vol. 13 (2009), vol. 13, pp. 1808-1813
R.G. Smith, The Contract Net Protocol: High-Level Communication and Control in a Distributed Problem Solver, IEEE Transactions on Computers (12), 1104 (1980)
P. Kadera, P. Tichy, Plan, commit, execute protocol in multi-agent systems, Holonic and multi-agent systems for manufacturing (Springer, 2009), pp. 155 – 164
H.V. Brussel, J. Wyns, P. Valckenaers, L. Bongaerts, P. Peeters, Reference architecture for holonic manufacturing systems: PROSA, Computers in Industry 37(3), 255 (1998). DOI 10.1016/S0166-3615(98)00102-X
P. Leitao, F. Restivo, ADACOR: A holonic architecture for agile and adaptive manufacturing control, Computers in Industry 57(2), 121 (2006). DOI 10.1016/j.compind.2005.05.005
A. Giret, V. Botti, Engineering Holonic Manufacturing Systems, Computers in Industry 60(6), 428 (2009). DOI 10.1016/j.compind.2009.02.007
M. Wooldridge, M. Fisher, M.P. Huget, S. Parsons, Model checking multi-agent systems with MABLE, in Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 2 (ACM, 2002), pp. 952-959
S. Schliecker, J. Rox, M. Negrean, K. Richter, M. Jersak, R. Ernst, System Level Performance Analysis for Real-Time Automotive Multicore and Network Architectures, IEEE Transactions on Computer-Aided Design of integrated Circuits and Systems, 28(7), 979 (2009)
K. Richter, M. Jersak, R. Ernst, A formal approach to MpSoC performance verification, Computer 36(4), 60 (2003)
R. L. Cruz, A calculus for network delay, IEEE Transactions on Information Theory, 37(1), 114 (1991)
L. Thiele, S. Chakraborty, M. Naedele, Real-time calculus for scheduling hard real-time systems, in Proceedings of IEEE International Symposium on Circuits and Systems, vol. 4 (2000), pp. 101-104
P. Leitao, N. Rodrigues, Modelling and validating the multi-agent system behaviour for a washing machine production line, in Proceedings of IEEE International Symposium on Industrial Electronics (ISIE) (2012), pp. 1203-1208. DOI 10.1109/ISIE.2012.6237260
J. Kubalík, P. Tichý, R. Šindelář, R.J. Staron, Clustering Methods for Agent Distribution Optimization, IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 40(1), 78 (2010)
FIPA. Fipa ACL message structure specification (2002)
P.J. Denning, J.P. Buzen, The operational analysis of queueing network models, ACM Computing Surveys (CSUR) 10(3), 225 (1978)
V. Cortellesa, A. D. Marco, P. Inverardi, Model-based software performance analysis, Springer, 2011
G. Casale, G. Serazzi, Bottlenecks identification in multiclass queueing networks using convex polytopes, in Proceedings of The IEEE Computer Society's 12th Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, 2004. pp. 223-230.