Slice Resource Allocation Technology of Cognitive Wireless Network Based on NOMA

Abstract

With the integration of industrialization and informatization, the contradiction between radio supply and demand has become increasingly prominent. To improve the utilization of spectrum resources, it is necessary to use cognitive radio technology and NOMA (NON Othogonal Multiple Access) technology. In this paper, we propose a multi-agent reinforcement learning algorithm by combining graph convolutional neural network and DQN (Deep Q Network) algorithm, which is suitable for cognitive NOMA network slice resource allocation scenario. Simulation results show that the algorithm can improve the convergence value and convergence speed.