Intelligent Network Slicing for V2X Services Toward 5G

Abstract

Benefiting from the widely deployed LTE infrastructures, the fifth generation (5G) wireless networks has been becoming a critical enabler for the emerging vehicle-to-everything (V2X) communications.However, existing LTE networks cannot efficiently support stringent but dynamic requirements of V2X services. One effective solution to overcome this challenge is network slicing, whereby different services could be supported by logically separated networks. To mitigate the increasing complexity of network slicing in 5G, we propose to leverage the recent advancement of Machine Learning (ML) technologies for automated network operation. Specifically, we propose intelligent network slicing architecture for V2X services, where network functions and multi-dimensional network resources are virtualized and assigned to different network slices. In achieving optimized slicing intelligently, several critical techniques, including mobile data collection and ML algorithm design, are discussed to tackle the related challenges.Then, we develop a simulation platform to illustrate the effectiveness of our proposed intelligent network slicing. With the integration of 5G network slicing and ML-enabled technologies, the QoS of V2X services is expected to be dramatically enhanced. Index TermsV2X services, network slicing, artificial intelligence, deep reinforcement learning Jie Mei is with the Intelligent Computing and Communication (IC 2 ) Lab, Wireless Signal Processing and Network

Characterization of Radio Signal Strength Fluctuations in Road Scenarios for Cellular Vehicular Network Planning in LTE

“…Road safety and autonomous driving impose strict requirements in terms of latency and link availability, hard to achieve in mobility scenarios [8]. To satisfy them, a combination of radio access and networking techniques have been proposed as key technology enablers (e.g., millimeter waves [9], non-orthogonal multiple access [10], link adaptation [11], joint resource allocation [12], network slicing [13], mobile edge computing [14], [15], data analytics [16], etc.). Security and privacy are also an important concern when adding connectivity to cars [17].…”

Computer wireless network integration technology in equipment state data collection

“…The experimental data are automatically stored in the operation and inspection box. After the test is completed, the operation and maintenance personnel only need to touch the tablet interface to generate a test report and realize one-click data upload automatically [10]. The use of intelligent transportation inspection boxes can significantly reduce the labor intensity of management personnel and operation and maintenance personnel.…”

An intelligent self-sustained RAN slicing framework for diverse service provisioning in 5G-beyond and 6G networks

“…In order to perform centralized control of the multicell RAN slicing, as shown in Fig. 1, a cloud-based network architecture with SDN and NFV technology is presented by integrating various network infrastructures in the multi-cell RAN [5,25] . The proposed architecture has two advantages.…”

“…Therefore, we need a paradigm shift in 5G-beyond and 6G networks from conventional network slicing schemes, in which the network merely performs network operation for specific scenarios and always requires manual intervention to resolve unforeseen situations, into a completely new intelligent network slicing framework that can autonomously self-sustain the high QoS performance of diverse services under the highly dynamic and complex network conditions, which was elaborated in our previous work [5] . Following this paradigm, in this paper, we propose a hierarchical multilayer RAN slicing framework to enable the network operation with self-sustained capability.…”