Recurrent Neural Network for Bi-level Centralized Resource Allocation DEA Models

In this paper, the common centralized DEA models are extended to the bi-level centralized resource allocation (CRA) models based on revenue efficiency. Based on the Karush–Kuhn–Tucker (KKT) conditions, the bi-level CRA model is reduced to a one-level mathematical program subject to complementarity constraints (MPCC). A recurrent neural network is developed for solving this one-level mathematical programming problem. Under a proper assumption and utilizing a suitable Lyapunov function, it is shown that the proposed neural network is Lyapunov stable and convergent to an exact optimal solution of the original problem. Finally, an illustrative example is elaborated to substantiate the applicability and effectiveness of the proposed approach.

کلیدواژه ها:

Data envelopment analysis ، Centralized resource allocation ، Bi-level optimization ، Neural network ، Stability