RETRACTED ARTICLE: Application of deep and robust resource allocation for uncertain CSI in English distance teaching

Abstract

In order to ensure that channel state information and interference channel state information can be defined at the same time in random access wireless networks, we propose a deeply robust resource allocation architecture. The resource allocation architecture regards the goal of optimizing wireless resources as a learning problem, and uses deep neural networks to learn the best resource allocation strategy. An elliptical shape is modeled for robust resources with uncertain channel state information (CSI) depth, and a network structure composed of two cascaded deep neural network (DNN) units is proposed. First, it is a resource processing unit with uncertain CSI depth and robustness, and the second is a power control unit. Then, an alternative iterative learning algorithm is proposed for joint training of two cascaded DNN units. Finally, the simulation compares the performance of the network under the robust learning strategy and the non-robust learning strategy, and verifies the effectiveness of the proposed algorithm. Due to the continuous innovation of modern education technology, when English distance teaching cannot be carried out in the classroom face-to-face teaching, online English distance teaching becomes a necessary method. The live English distance teaching on the Internet has developed rapidly in the context of globalization. The goal of teaching is to train talents according to the requirements of the society. It has played an active role in promoting the subjective initiative of students, fully demonstrating the convenience of the information society and the balance learning resources play an important role.