Water reservoirs management under uncertainty by approximating networks and learning from data

Topics on System Analysis and Integrated Water Resources Management

Volumn , Issue , 2007, Pages 117-139

  Baglietto, Marco ^a   Cervellera, Cristiano ^b   Sanguineti, Marcello ^a   Zoppoli, Riccardo ^a  

^a UNIVERSITY OF GENOA   (Italy)

^b INSTITUTE OF INTELLIGENT SYSTEMS FOR AUTOMATION   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 84882555334     PISSN: None     EISSN: None     Source Type: Book    
DOI: 10.1016/B978-008044967-8/50006-3     Document Type: Chapter

References (45)

1. Alessandri A., Sanguineti M. Optimization of approximating networks for optimal fault diagnosis. Optim. Method. Softw. 2005, 20:235-260.
2. Alessandri, A., M. Cuneo, S. Pagnan and M. Sanguineti (to appear). A recursive algorithm for nonlinear least-squares problems. Comput. Optim. Appl.
3. Alessandri A., Sanguineti M., Maggiore M. Optimization-based learning with bounded error for feedforward neural networks. IEEE T. Neural Networ. 2002, 13:261-273.
4. Archibald T.W., McKinnon K.I.M., Thomas L.C. An aggregate stochastic dynamic programming model of multireservoir systems. Water Resour. Res. 1997, 33:333-340.
5. Baglietto M., Sanguineti M., Zoppoli R. Facing the curse of dimensionality by the extended Ritz method in stochastic functional optimization: dynamic routing in traffic networks. High Performance Algorithms and Software for Nonlinear Optimization 2003, 23-56. Kluwer Academic Publishers. G. Di Pillo, A. Murli (Eds.).
6. Baglietto M., Parisini T., Zoppoli R. Distributed-information neural control: the case of dynamic routing in traffic networks. IEEE T. Neural Networ. 2001, 12:485-502.
7. Barron A.R. Universal approximation bounds for superpositions of a sigmoidal function. IEEE T. Inform. Theory 1993, 39:930-945.
8. Barron A.R. Approximation and estimation bounds for artificial neural networks. Mach. Learn. 1994, 14:115-133.
9. Bellman R. Dynamic Programming 1957, Princeton University Press, Princeton, NJ.
10. Bellman R., Kalaba R., Kotkin B. Polynomial approximation-a new computational technique in dynamic programming. Math. Comput. 1963, 17:155-161.
11. Bertsekas D.P., Tsitsiklis J.N. Neuro-Dynamic Programming 1996, Athena Scientific, Bel- mont, MA.
12. Cervellera C., Muselli M. Deterministic design for neural network learning: An ap-proach based on discrepancy. IEEE T. Neural Networ. 2004, 15:533-544.
13. Chen V.C.P., Ruppert D., Shoemaker C.A. Applying experimental design and regres-sion splines to high-dimensional continuous-state stochastic dynamic programming. Oper. Res. 1999, 47:38-53.
14. Fang K.-T., Wang Y. Number-Theoretic Methods in Statistics 1994, Chapman & Hall, Lon- don, UK.
15. Foufoula-Georgiou E., Kitanidis P.K. Gradient dynamic programming for stochastic optimal control of multidimensional water resources systems. Water Resour. Res. 1988, 24:1345-1359.
16. Gelfand I.M., Fomin S.V. Calculus of Variations 1963, Prentice-Hall, Englewood Cliffs, NJ.
17. Girosi F., Jones M., Poggio T. Regularization theory and neural networks architectures. Neural Comput. 1995, 7:219-269.
18. Giulini, S., M. Sanguineti and R. Zoppoli (to appear). Approximation schemes for functional optimization problems. Journal of Optimization Theory and Applicat.
19. Grippo L. Convergent on-line algorithms for supervised learning in neural networks. IEEE T. Neural Networ. 2000, 11:1284-1299.
20. Jacobson D., Mayne D. Differential Dynamic Programming 1970, Academic Press, New York, NY.
21. Johnson S.A., Stedinger J.R., Shoemaker C., Li Y, Tejada-Guibert J.A. Numerical solution of continuous-state dynamic programs using linear and spline interpolation. Oper. Res. 1993, 41:484-500.
22. Kainen P.C., Kurková V., Sanguineti M. Minimization of error functionals over variable-basis functions. SIAM J. Optimiz. 2003, 14:732-742.
23. Kurková V., Sanguineti M. Bounds on rates of variable-basis and neural-network ap-proximation. IEEE T Inform. Theory 2001, 47:2659-2665.
24. Kurková V., Sanguineti M. Comparison of worst case errors in linear and neural net-work approximation. IEEE T. Inform. Theory 2002, 48:264-275.
25. Kurková V., Sanguineti M. Error estimates for approximate optimization by the ex-tended Ritz method. SIAM J. Optimiz. 2005, 15:461-487.
26. Kurková V., Sanguineti M. Learning with generalization capability by kernel methods of bounded complexity. J. Complexity 2005, 21:350-367.
27. Kushner H.J., Yin G.G. Stochastic Approximation Algorithms and Applications 1997, Springer-Verlag, New York, NY.
28. Larson R. State Increment Dynamic Programming 1968, Elsevier, New York, NY.
29. Leshno M., Ya V., Pinkus A., Schocken S. Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks 1993, 6:861-867.
30. Niederreiter H. Random Number Generation and Quasi-Monte Carlo Methods 1992, SIAM, Philadelphia, MA.
31. Niyogi P., Girosi F. On the relationship between generalization error, hypothesis com-plexity, and sample complexity for radial basis functions. Neural Comput. 1996, 8:819-842.
32. Nussbaum M. On nonparametric estimation of a regression function that is smooth in a domain on. Rk. Theor. Probab. Appl. 1986, 31:118-125.
33. Parisini T., Zoppoli R. Neural networks for feedback feedforward nonlinear control systems. IEEE T. Neural Networ. 1994, 5:436-449.
34. Parisini T., Zoppoli R. Neural approximations for multistage optimal control of non-linear stochastic systems. IEEE T. Automat. Contr. 1996, 41:889-895.
35. Parisini T., Zoppoli R. Neural approximations for infinite-horizon optimal control of nonlinear stochastic systems. IEEE T. Neural Networ. 1998, 9:1388-1408.
36. Park J., Sandberg I.W. Universal approximation using radial-basis-function networks. Neural Comput. 1991, 3:246-257.
37. Philbrick C.R., Kitanidis P.K. Improved dynamic programming methods for optimal control of lumped-parameter stochastic systems. Oper. Res. 1999, 49:398-412.
38. Sobol' I.M. The distribution of points in a cube and the approximate evaluation of integrals. Zh. Vychisl. Mat. i Mat. Fiz. 1967, 7:784-802.
39. Soncini-Sessa R., Castelletti A., Weber E. Integrated and Participatory Water Re- sources Management. Theory 2007, to appear, Elsevier, Amsterdam, NL.
40. Turgeon A. A decomposition method for the long-term scheduling of reservoirs in series. Water Resour. Res. 1981, 17:1565-1570.
41. Vapnik V.N. The Nature of Statistical Learning Theory 1995, Springer-Verlag, New York, NY.
42. Yakowitz S. Dynamic programming applications in water resources. Water Resour. Res. 1982, 18:673-696.
43. Zoppoli R., Parisini T. Learning techniques and neural networks for the solution of n-stage nonlinear nonquadratic optimal control problems. Systems, Models and Feedback: Theory and Applications 1992, 193-210. Birkhäuser, Boston. A. Isidori, T.J. Tarn (Eds.).
44. Zoppoli R., Parisini T., Sanguineti M. Approximating networks and extended Ritz method for the solution of functional optimization problems. J. Optimiz. Theory Appl. 2001, 112:403-440.
45. Zoppoli, R., M. Sanguineti, M. Baglietto and T. Parisini (to appear). Neural Approximations for Optimal Control and Decision. Springer-Verlag, London, "Cont Communications Systems Series".