| Popis: |
Cellular networks evolve from generation to generation aiming at faster transmission, lower latency, and better usage of channel resources. How to design intelligent resource provisioning mechanisms is a critical issue in cellular networks, especially in the next-generation ultra-dense networks. In this dissertation, we focus on solving two of the communication resource provisioning issues. We first study the communication channels’ insufficient problem and solve it by proposing a deep learning-based channel availability prediction schema with Cognitive Radio (CR). Moreover, we study the mobile data transmission delay problem owing to the frequent handoff between the ultra-dense base stations (BS) in the next-generation cellular networks. We solve this issue by proposing another deep learning model to learn mobile users’ data usage patterns, aiming at making predictions on the mobile users’ traffic and mobile data flow amount. Based on the prediction result, the target BS can reserve sufficient bandwidth for the specific mobile user.Specifically, cognitive radio (CR) technology enables secondary users (SUs) to opportunistically access unused licensed spectrum owned by primary users (PUs). It has the potential to significantly enhance communication capacity and has attracted intensive attention. One of the key issues in cognitive radio communications is to detect spectrum availability. Traditional approaches rely on spectrum sensing techniques to address this problem, which, however, consume considerable energy and time, and require complex prior information from PUs. In this dissertation, we develop a hierarchical spectrum learning system that takes advantage of the fine-tuned convolutional neural network (CNN) and the gated recurrent unit network (GRU), which is called the dual CNN and GRU (DCG), for spectrum availability prediction. Particularly, this model performs accurate predictions on spectrum occupation patterns without any prior information of PUs. The performance of the proposed system is demonstrated through extensive and thorough simulations. On the other hand, knowing their spectrum availability does not necessarily enable two SUs to successfully communicate on the same channel. This is a challenging problem and has been largely ignored by previous studies designing learning models for CR communications. Towards this goad, we design an enhanced DCG model called EDCG to enable two SUs to find the same channel to communicate with each other by performing channel selection prediction. The performance of the designed DCG and EDCG models is demonstrated through extensive and thorough simulations. The results show that our designed models achieve high prediction accuracy with limited training overhead.In the meantime, the BSs in the next-generation cellular networks are deployed ultra-densely. The movement between those dense BSs will lead to frequent service handoffs, which causes the data transmission delay or even congestions. Towards this issue, the traffic modeling and prediction are at the heart of providing high-quality telecommunication services in next-generation cellular networks and attract much attention. However, it has been approved as an extremely challenging task. Due to the diverse network demand of Internet-based apps, the cellular traffic from an individual user can have a wide dynamic range. Most existing methods, on the other hand, model traffic patterns as probabilistic distributions or stochastic processes and impose stringent assumptions over these models. Such assumptions may be beneficial at providing closed-form formula in evaluating prediction performances but fall short for practice use. In this dissertation, we propose STEP, a Spatio-temporal fine-granular user traffic prediction mechanism for cellular networks. A deep graph convolution network, called GCGRN, is constructed. It is a novel combination of the graph convolution network (GCN) and gated recurrent units (GRU), which exploits graph neural network to learn an efficient Spatio-temporal model from a user’s massive dataset for traffic prediction. The prototype of the STEP has been implemented. Extensive experimental results demonstrate that our model outperforms the state-of-the-art time-series based approaches. Besides, STEP merely incurs mild energy consumption, communication overhead, and system resource occupancy to mobile devices. Moreover, NS-3 based simulations validate the efficacy of STEP in reducing session dropping ratio in cellular networks. |
