Abstract-Traffic learning and prediction is at the heart of the evaluation of the performance of telecommunications networks and attracts a lot of attention in wired broadband networks. Now, benefiting from the big data in cellular networks, it becomes possible to make the analyses one step further into the application level. In this paper, we firstly collect a significant amount of application-level traffic data from cellular network operators. Afterwards, with the aid of the traffic "big data", we make a comprehensive study over the modeling and prediction framework of cellular network traffic. Our results solidly demonstrate that there universally exist some traffic statistical modeling characteristics at a service or application granularity, including α-stable modeled property in the temporal domain and the sparsity in the spatial domain. But, different service types of applications possess distinct parameter settings. Furthermore, we propose a new traffic prediction framework to encompass and explore these aforementioned characteristics and then develop a dictionary learning-based alternating direction method to solve it. Finally, we examine the effectiveness and robustness of the proposed framework for different types of application-level traffic. Our simulation results prove that the proposed framework could offer a unified solution for application-level traffic learning and prediction and significantly contribute to solve the modeling and forecasting issues.
Network slicing (NS) is recognized as a key technology for the 5G mobile network in enabling the network to support multiple diversified vertical markets over a shared physical infrastructure with efficiency and flexibility. A 5G NS instance is composed of a set of virtual network function (VNF) instances to form the end-to-end (E2E) virtual network for the slice to operate independently. The deployment of a NS is a typical virtual network embedding (VNE) problem. We consider a scenario in which VNF instances can be shared across multiple slices to further enhance the utilization ratio of the underlying physical resources. For NSs with sharable VNF instances, the deployment of the slice instances is essentially the embedding of multiple virtual networks coupled by the VNFs shared among slices. Hence, we formulate this sharable-VNFs-based multiple coupled VNE problem (SVM-VNE) through an integer linear program (ILP) formulation, and design a back-tracking coordinated virtual network mapping algorithm. Simulation results demonstrate that VNF-sharing can enhance the slice acceptance ratio with the same physical network, which represents higher physical resource utilization. Moreover, our approach achieves higher acceptance ratio by comparing to a baseline algorithm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.