Abstract
The detailed Markov chain model of the dynamics of the heterogeneous computer network is presented. The stochastic control problem of optimal task distribution in computer network is formulated. Some control strategies based on the stochastic forecast and deterministic rules are presented. The system mentioned above is applied to the solution of mixed FE/FD scheme coming from the earthen dam stability analysis. Numerical tests performed on the network including different workstations, scalar LAN servers and power vector unit exhibit the behavior of different strategies for various size of data to be processed.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
V. Donaldson, F. Berman, R. Paturi, Program Speedup in Heterogeneous Computing Network, Journal of Parallel and Distributed Computing 21, 316–332 (1994).
H.S. Stone, Multiprocessor scheduling with the aid of network flow algorithms, IEEE Trans. Software Engrg. SE-3, 1 (Jan 1977), 85–93.
S.H. Bokhari, A shortest tree algorithm for optimal assignments across space and time in a distributed processor system. IEEE Trans. Software Engrg. SE-7, 6 (Nov. 1981), 583–589.
S. White, A. Alund, V.S. Sunderam, Performance of the NAS Parallel Benchmarks on PVM-Based Networks, Journal of Parallel and Distributed Computing 26, 61–71 (1995).
D.M. Nicol, D.R. O'Hallaron, Improved algorithms for mapping pipelined and parallel computations. IEEE Trans. Comput. 40, 3 (Mar. 1991), 295–306.
S. Manoharan, N.P. Topham, An assessment of assignment schemes for dependency graphs, Parallel Computing 21 (1995) 85–107.
E. Altman, Asymptotic Properties of Constrained Markov Decision Process, INRIA, Centre Sophia Antipolis, France, Raport No.1598, 1992.
E.Altman, Constrained Markov Decision Process, INRIA, Centre Sophia Antipolis, France, Raport No.2574, 1995
R. Schaefer, Numerical Models of the Prelinear Filtration, Rozprawy Habilitacyjne U.J., Vol. 212, Krakow, 1991, (in Polish)
R. Schaefer, S. Sedziwy, Semivariational Numerical Model of Prelinear Filtration with the Special Emphasis on Nonlinear Sources, CAMES, vol. 3 1996, pp. 83–96.
R. Schaefer, S. Sedziwy, Filtration in cohesive soils: modelling and solving in: Proc. of the Conf.:Finite Elements in Fluids, New Trends and Appl., Barcelona 1993, Vol. II., 887–891
J. Bear, Dynamics of Fluids in Porus Media, Elsevier, New York, 1972
K. Kant, Introduction to Computer System Performance Evaluation, Dep. of Comp. Science The Pensylvania Satet Univ. McGraw-Hill, Inc, 1992
M. Papadrakakis, S. Bitzarakis, Domain Decomposition PCG Methods For Serial and Parallel Processing, Computing Systems in Engineering, 1995
Z. Onderka, Markov Chain Based Management of Large Scale Distributed CAD Computations in preparation
H. Kuszner, Intrudaction to Sochastic Control, Holt, Reinhart and Winston, Inc., New York Copyright 1971.
Clyde P. Kruskal, Alan Weiss, Allocating Independent Subtasks on Parallel Processors, IEEE Trans. on Software Engrg. vol. SE-11, No. 10, October 1985.
Flasinski M., Schaefer R., Toporkiewicz W., Optimal Decomposition of IE-Graph Represented Structures, Proc. of the 7-th Int. Conf. on Engrg. Computer Graphics and Descriptive Geometry, pp. 405–409, ICECGDG'96, July 1996 Krakow, Poland.
Przybylski P., The Distributed Algorithm of an Unstractural Triangular Mesh Generator — Object Oriented Approach, Proc. of XII Conf. on Computer Methods in Mechanics, pp. 283–284, May 1995 Warsaw-Zegrze, Poland.
Krok J., Lezanski P., Orkisz J., Przybylski P., Schaefer R., Basic Concepts of an Open Distributed System for Cooperative Design and Structure Analysis, CAMES, vol. 3 1996, pp. 169–186.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Onderka, Z., Schaefer, R. (1997). Markov chain based management of large scale distributed computations of earthen dam leakages. In: Palma, J.M.L.M., Dongarra, J. (eds) Vector and Parallel Processing — VECPAR'96. VECPAR 1996. Lecture Notes in Computer Science, vol 1215. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62828-2_112
Download citation
DOI: https://doi.org/10.1007/3-540-62828-2_112
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62828-6
Online ISBN: 978-3-540-68699-6
eBook Packages: Springer Book Archive