A neurodynamic approach for distributionally robust joint chance-constrained optimization problems
Résumé
This paper studies a dynamical neural network approach to solve joint chance-constrained distributionally robust optimization problems. We consider that the row vectors of the matrix defining the constraints are independent. The probability distributions of the row vectors are not known in advance and belong to a certain distributional uncertainty set. In our paper, we study two uncertainty sets for the unknown distributions. The main feature of our framework is to propose a neural network-based method to solve distributionally robust joint chance-constrained optimization problems without the use of standard state-of-the-art solving methods. We show the convergence and stability of the proposed neural network. In the numerical Section, we apply the proposed approach to solve a profit maximization problem to show the performances of our approach.
Origine | Fichiers produits par l'(les) auteur(s) |
---|