A new control laboratory using parallel programming

This paper discusses how to use parallel processing methods to solve control algorithms in real-time in the field of Control Engineering education. It is a well known fact that some types of control problems can not be dealt with in just one practical session in the lab because of their huge computational load. However, the use of low-cost clusters of workstations (COWs) and passing-message software let students program their own control algorithms and visualize the results in real-time without waiting for a long time. In this paper we describe the control of a pH-neutralization process using dynamic programming algorithms. The pH-neutralization process has been recognized as one of the most difficult single loop in process control. For this reason, this process has been used as an experiment in control teaching to show up the results obtained by using parallel techniques. Thus, this heavy-computational-load example represents a meaningful case study to demonstrate the suitableness of using parallel computing techniques to include new experiments in the control lab. Index terms Dynamic programming, optimal control, clusters of workstations, PVM, laboratory, pHneutralization process, real-time.

[1]  R. E. Larson,et al.  A dynamic programming successive approximations technique with convergence proofs , 1970 .

[2]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[3]  J. A. Youssefi,et al.  A course in parallel processing , 1997 .

[4]  T. Hintz.  Introducing undergraduates to parallel processing , 1993 .

[5]  George Karypis,et al.  Introduction to Parallel Computing , 1994 .

[6]  B. Gluss.  AN INTRODUCTION TO DYNAMIC PROGRAMMING , 1961 .

[7]  Jan M. Maciejowski,et al.  Predictive control : with constraints , 2002 .

[8]  李幼升,et al.  Ph , 1989 .

[9]  Edison Tse,et al.  Parallel Processing Algorithms for the Optimal Control of Nonlinear Dynamic Systems , 1973, IEEE Transactions on Computers.

[10]  Christopher H. Nevison.  An undergraduate parallel processing laboratory , 1988, SIGCSE '88.

[11]  Rajkumar Buyya,et al.  High Performance Cluster Computing , 1999 .

[12]  Jack Dongarra,et al.  MPI: The Complete Reference , 1996 .

[13]  Sean R Eddy,et al.  What is dynamic programming? , 2004, Nature Biotechnology.

[14]  P. Altena,et al.  In search of clusters , 2007 .

[15]  P. B. Coaker,et al.  Applied Dynamic Programming , 1964 .

[16]  Fernando Morilla,et al.  Dynamic Programming Predictive Control , 1996 .

[17]  A. Assad,et al.  Principles of Dynamic Programming, Part II: Advanced Theory and Applications. , 1983 .

[18]  Antonio F. Díaz,et al.  Performance of Message-Passing MATLAB Toolboxes , 2002, VECPAR.

[19]  Leopoldo Acosta,et al.  Design of algorithms for spatial-time reduction complexity of dynamic programming , 1992 .

[20]  Jack Dongarra,et al.  PVM: Parallel virtual machine: a users' guide and tutorial for networked parallel computing , 1995 .

[21]  B. Wilkinson,et al.  A state-wide senior parallel programming course , 1999 .

[22]  Robert E. Larson,et al.  Principles of Dynamic Programming , 1978 .

[23]  F. Morilla,et al.  Reduction of the dimensionality of dynamic programming: a case study , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).