Dynamic Behavior of Contaminants in the Water Distribution Network of Cuernavaca Mexico, a Real Application of Multiobjective Distributed Reinforcement Learning

Comportamiento Dinámico de Contaminantes en la Red de Distribución de Agua de la Ciudad de Cuernavaca México, una Aplicación Real de Aprendizaje por Refuerzo Distribuido Multi–Objetivo

Carlos Eduardo Mariano Romero and Eduardo F. Morales Manzanares

Instituto Mexicano de Tecnología del Agua, Instituto Nacional de Astrofísica, Óptica y Electrónica e–mails: cmariano@tlaloc.imta.mx, emorales@inaoep.mx

Article received on December 20, 2006
Accepted on December 27, 2007

Abstract

Water systems often allow efficient water uses via water reuse and/or recirculation. The design of the network layout connecting water–using processes is a complex problem which involves several criteria to optimize. The use of the water pinch approach to define which of the effluents from unitary operations are most convenient to reuse is a good alternative used by some practitioners. Previously papers have presented an approach to minimize the freshwater consumption and infrastructure cost, which had been tested with real data from the Cuernavaca city water distribution network with good results (Mariano2005, Mariano2007). One of the challenges identified from previous work, was the necessity to incorporate the dynamic behavior of distribution systems. In this paper the response of the optimization model to changes in the mass charges of contaminants effluents from unitary operations is presented. The test scenario is the distribution system of the city of Cuernavaca in México.

Key words: Multiobjective optimization, water pinch, water reuse.

Resumen

El uso eficiente del agua se puede establecer a través del reuso o recirculación de efluentes. El diseño o configuración de sistemas que contemplen el uso eficiente de agua con base en el reuso se torna complejo e involucra diversos criterios a optimizar. El uso de técnicas basadas en Water Pinch permite definir los efluentes más apropiados a ser reutilizados, posicionándose como una buena alternativa para los diseñadores. En trabajos previos se presentaron resultados relacionados con la minimización del agua de primer uso suministrada y el costo de inversión sobre datos reales de la ciudad de Cuernavaca (Mariano2005, Mariano2007). Sin embargo, uno de los retos identificados a partir del la observación del comportamiento de los efluentes en la ciudad de Cuernavaca es la necesidad de representar el comportamiento dinámico de los sistemas de distribución. En esté trabajo se presenta la respuesta del modelo de optimización a los cambios medidos en los efluentes de las operaciones unitarias de las masas de contaminantes. El escenario de validación es el sistema de distribución de la ciudad de Cuernavaca en México.

Palabras clave: Optimización Multiobjetivo, water pinch, reuso de agua.

DESCARGAR ARTÍCULO EN FORMATO PDF

References

1. (Alcocer 2002) Alcocer, V. and Arreguín, F., Minimización de agua de primer uso en procesos industriales a través de técnicas de optimización. Memorias del XX Congreso Latinoamericano de Hidráulica, La Habana, Cuba, September 2002, (in spanish).        [ Links ]

2. (Alva–Argaez 1999) Alva–Argaez, A., An Automated design tool for water and wastewater minimization), PhD Thesis, Department of Process Integration University of Manchester IST, UK 1999.        [ Links ]

3. (Arreguín 2001) Arreguín, C., F., Alcocer, Y. V. Modelación sistémica del uso eficiente del agua. Revista Ingeniería Hidráulica en México). Vol. XIX, No. 3, July, 2004.        [ Links ]

4. (Mariano 2002) Coello, C. and Mariano, C., (2002) Multiple criteria optimization. state of the art annotated bibliographic surveys, Edited by Matthias Ehrgott, Xavier Gambibelux, Kluwer Academic Publishers, Chapter 6. Evolutionary Algorithms and Multiobjective Optimization, pp. 277–331.        [ Links ]

5. (Coetzer 1997) Coetzer, D., Stanley, C. and Kumana, J. Systemic Reduction of Industrial Water Use and Wastewater Generation, In Proc. of AIChE National Meeting, Houston, March 1997.        [ Links ]

6. (Dorigo 1992) Dorigo, M. (1992) Optimization, Learning and Natural Algorithms. Ph.D. Thesis, Politecnico di Milano, Italy, in Italian.        [ Links ]

7. (Dorigo 1996) Dorigo M., V. Maniezzo and A. Colorni (1996). The Ant System: Optimization by a Colony of Cooperating Agents. IEEE Transactions on Systems, Man, and Cybernetics–Part B, 26(1):29–41.        [ Links ]

8. (Farmani 2005) R. Farmani, D.A. Savic and G.A. Walters. Evolutionary multi–objective optimization in water distribution network design, Engineering Optimization, Vol. 37, No. 2, pp. 167–183, March 2005.        [ Links ]

9. (Galan 1998) Galan, B., and Grossmann, I.E., Optimal Design of Distributed Wastewater Treatment Networks, Ind. Eng. Chem. Res., 37:4036, 1998.        [ Links ]

10. (Halhal 1997) D. Halhal, G. A. Walters, D. Ouazar, and D. A. Savic. Multi–objective improvement of water distribution systems using a structured messy genetic algorithm approach, Journal of Water Resources Planning and Management ASCE, 123(3): 137–146, 1997.        [ Links ]

11. (Keedwell 2006) Edward Keedwell and Soon–Thiam Khu. A novel evolutionary meta–heuristic for the multi–objective optimization of real–world water distribution network, Engineering Optimization, Vol. 38, No. 3, pp. 319–336, April 2006.        [ Links ]

12. (Kuo 1997) Kuo, W.C. and Smith, R. Effluent treatment system design, Chem Eng. Sci., 52:4273, 1997.        [ Links ]

13. (Mann 1999) Mann, G.J. and Liu, Y.A. Industrial Water reuse and wastewater minimization McGrawHill Eds., 1999.        [ Links ]

14. (Mariano 2000) Mariano, C. and Morales, E., (2000) A new approach for the solution of multiple objective optimization problems based on reinforcement learning, Lecture Notes in Artificial Intelligence, Proceedings of the Mexican International Conference on Artificial Intelligence, pp. 212–223, Acapulco, Mex, April, 2000.        [ Links ]

15. (Mariano 2001) Mariano, C., (2001) Reinforcement learning in multiobjective optimization PhD Thesis in computer Science, Instituto Tecnologico y de Estudios Superiores de Monterrey, Campus Cuernavaca, March, 2001, Cuernavaca, Mor., Mexico.        [ Links ]

16. (Mariano 2001b) Mariano, C. and Morales, E., (2001) A new updating strategy for reinforcement learning based on Q–learning, In P. Flach and L. de Raeldt (eds.), Springer Verlag, Lecture Notes in Artificial Intelligence, vol 2167: 12th European conference on Machine Learning, pages 324–335, 2001.        [ Links ]

17. (Mariano 2005) Mariano, C., Alcocer, V., and Morales E. (2005) Diseño de sistemas hidráulicos bajo criterios de optimización de puntos de pliegue y múltiples criterios, Ingeniería hidráulica en México, vol XX, no. 3, pp. 31–42, July–September, 2005.        [ Links ]

18. (Mariano 2007) Mariano, C., Alcocer, V., and Morales, E. (2007) Multi–objective optimization of water using systems, European Journal on Operational Research, volume 181–3, September (2007), pp. 1691–1707.        [ Links ]

19. (CNA 1996) National Water Commission, Clasification study in the Apatlaco river, Sanitation and Water Quality Department from the Morelos state office, 1996 (In Spanish).        [ Links ]

20. (CNA 2000) National Water Commission, Hydro–geological update of the aquifer of Cuernavaca, state of Morelos 1999, CAN 2000, (In Spanish).        [ Links ]

21. (Putterman 1994) Putterman, M. Markov Decision Processes Discrete Stochastic Dynamic Programming, Wiley Series in Probability and Mathematical Statistic, (1994).        [ Links ]

22. (Sutton 1998) Sutton R., and Barto G. Reinforcement Learning an Introduction, MIT Press, (1998).        [ Links ]

23. (Schwefel 1995) Schwefel H., Evolution and Optimum Seeking. John Wiley and Sons, New York, USA, 1995.        [ Links ]

24. (Watkins 1992) Watkins, C., Dayan, P., (1992) Q–Learning, Machine Learning, 3:279–292, 1992.        [ Links ]