Genetic Algorithms for Optimal Operation of Soil Aquifer Treatment Systems

The genetic algorithm (GA) is a nonconventional search technique which is patterned after the biological processes of natural selection and evolution. It has the ability to search large and complex decision spaces and handle nonconvexities. In this paper, the genetic algorithm is investigated and applied to solve the optimal operation problem of soil aquifer treatment (SAT) systems. This problem involves finding optimal water application time and drying time which maximize infiltration for a predetermined starting influent rate of waste water and subject to various physical and operational constraints. A new scaling method is developed and some improvements on the evolution procedure are presented. A comprehensive GA–SAT computer model was developed and applied to an example SAT problem. The results are encouraging, when compared with using the successive approximation linear quadratic regulator algorithm. It was found that genetic algorithms are easy to program and interface with large complicated simulators.

[1]  C. Shoemaker,et al.  Dynamic optimal control for groundwater remediation with flexible management periods , 1992 .

[2]  White,et al.  MSTS Multiphase Subsurface Transport Simulator User's Guide and Reference , 1993 .

[3]  Larry W. Mays,et al.  Development of methodology for the optimal operation of soil aquifer treatment systems , 1995 .

[4]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[5]  S. Ranjithan,et al.  Using genetic algorithms to solve a multiple objective groundwater pollution containment problem , 1994 .

[6]  Leo F. Cournoyer,et al.  Operation and Maintenance of Recharge Facilities , 1988 .

[7]  Q. J. Wang.  The Genetic Algorithm and Its Application to Calibrating Conceptual Rainfall-Runoff Models , 1991 .

[8]  David Q. Mayne,et al.  Differential dynamic programming , 1972, The Mathematical Gazette.

[9]  J. Eheart,et al.  Using Genetic Algorithms to Solve a Multiobjective Groundwater Monitoring Problem , 1995 .

[10]  Hojjat Adeli,et al.  Machine Learning: Neural Networks, Genetic Algorithms, and Fuzzy Systems , 1994 .

[11]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[12]  W. Müller.  JACOBSON, D. H. and D. Q. MAYNE: Differential dynamic programming. Modern analytic and computational methods in Science and Mathematics, No. 24. American Elsevier Publ. Co., Inc., New York 1970. XVI, 208 S., 17 Abb., Dfl. 51.50. , 1973 .

[13]  Thomas Bäck,et al.  Evolutionary Algorithms in Theory and Practice , 1996 .

[14]  Graeme C. Dandy,et al.  Genetic algorithms compared to other techniques for pipe optimization , 1994 .

[15]  D. McKinney,et al.  Genetic algorithm solution of groundwater management models , 1994 .

[16]  Larry W. Mays,et al.  Optimum Operation of Recharge Basins , 1994 .

[17]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[18]  N. G. F. Sancho,et al.  A new algorithm for the solution of multi-state dynamic programming problems , 1975, Math. Program..