Q-Learning-Based Spectrum Access for Content Delivery in Mobile Networks

By the wide development of wireless communication technology, mobile networks are becoming the promising paradigm for mobile users to access the Internet to download contents. However, transmitting contents to multiple mobile users causes excessive interference and heavy network load. Moreover, the service demands for rich contents over mobile networks have been ever-increasing, which leads serious traffic loads to the networks. To improve mobile user's quality of experience (QoE), in this paper, a Q-learning based spectrum access scheme in mobile networks is firstly proposed for mobile users to access the optimal spectrum and maximize the transmission rate. Secondly, based on the optimal spectrum decision, we present a content delivery scheme for edge nodes, device-to-device (D2D) pairs and mobile users. After that, we model the content delivery process among edge nodes, D2D pairs and mobile users as a non-cooperative Stackelberg game to improve the efficiency of content delivery. Then, the content delivery strategy algorithm is proposed to derive the Stackelberg equilibrium. Each player can obtain the maximum utility from the game based on the optimal strategy. Finally, we conduct extensive simulations to validate the performance of the proposed scheme. Simulation results demonstrate that the proposed scheme can jointly maximize the throughput of mobile networks and improve the QoE of mobile users compared with the conventional schemes.