YSA ve GA Temelli Bir Algoritma ile Doğrusal Olmayan Optimizasyon

Bu çalışmada doğrusal olmayan optimizasyon problemlerinin çözümünde yapay sinir ağlarının ve genetik algoritmaların kullanımıyla ilgili yeni bir yaklaşım önerilmektedir. Önerilen optimizasyon metodu, kısıtları öğrenmek için yapay sinir ağları, global optimum çözüme yakınsamak için genetik algoritmayı ve özellikle bazı kısıtların olurlu çözümü ihlal ettiği durumlarda metodun sonuçlarını değerlendirmek için ise amaç programlamayı seçenek çözüm olarak sunmaktadır. Yöntemin klasik yöntemlere göre hesaplama karmaşıklığı açısından avantajları incelenerek kullanım sınırlamaları belirlenmiştir.

Optimizasyon Using an ANN and GA Based New Algorithm

In this study, a new approach is offered to nonlinear optimization problem solving by using artificial neural networks and genetic algorithms. The proposed approach utilizes Artificial Neural Network (ANN) for learning constraints, Genetic Algorithm (GA) for evolving to global optimum solution and Goal Programming for evaluating results in case of some constraints violate their boundaries near around the feasible region. The approach is compared with classical methods in terms of computational complexity advantages and usage limitations are discussed.

PDF

___

Benson, H.Y., Shanno, D.F. & Vanderbei, R.J. (2001). A Comparative Study of Large-Scale Nonlinear Optimization Algorithms, Proceedings of the Workshop on High Performance Algorithms and Software for Nonlinear Optimization, Erice, Italy.
Haupt, R.L. & Haupt, S.E. (2004). Practical Genetic Algorithm 2nd Edt., John Wiley and Sons Inc. Publication, New Jersey.
Holland, J.H. (1975). Adaptation in Natural and Artificial Systems, An Harbor, University of Michigan Press.
Kelley, C.T. (1999). Iterative Methods for Optimization, Published by SIAM
Kitano, H. (1994). Neurogenetic Learning: An Integrated Method of Designing and Training Neural Networks Using Genetic Algorithms, Physica D, 75: 225–238.
Lewis, R.M., Torczon, V. & Trosset, M.W. (2000). Direct Search Methods: Then and Now. Journal of Computational and Applied Mathematics, 124: 191-207.
Mitchell, M. (1999). An Introduction to Genetic Algorithms 5th Edt., London.
McCulloch, W.S. & Pitts, W.H. (1943). A Logical Calculus of The Ideas Immanent in Nervous Activity. Bulletin of Mathematical Biophysics, 5: 115-133.
Rodrigueza, J.F., Renaudb, J.E., Wujekc, B.A. & Tappeta, R.V. (2000). Trust region model management in multidisciplinary design optimization, Journal of Computational and Applied Mathematics, 124: 139-154.
Wah, B.W. & Chen, Y. (2001). Hybrid Constrained Simulated Annealing and Genetic Algorithms for Nonlinear Constrained Optimization, Proc. IEEE Congress on Evolutionary Computation, 925-932.
Yu, N. (2008). Numerical Methods for Semidefinite Programming, İndirilme Tarihi: 1/3/2008. WWW:Web:http://www.core.ucl.ac.be/ Doctoral Courses /Lecture1.pdf
Zanden, B.V. (2008). Analysis of Algorithms and Selection of Algorithms, İndirilme Tarihi: 1/3/2008. WWW:Web:http://www.cs.utk. edu/~bvz/bvz/classes/cs302/notes/complexity.html