A discrete-time switching neural network for quadratic programming

Sanfeng Chen, Shuai Li, Yongsheng Liang, Y. Lou

Abstract: This paper presents a discrete-time neural network with a switching structure to solve a general quadratic programming problem in real time. Compared with existing ones for solving quadratic programming problems, the proposed neural network model has a simple architecture and uses a limited number of neurons to solve the problem, irrespective of the dimension of the decision variables or the number of constraints. The global convergence of the model is proven using contraction theory. Simulations are performed to demonstrate the effectiveness of the proposed method.