本文深入探讨了软件定义的空间地面集成网络（SD-STIN）的架构，面临的挑战以及潜在的解决方案。文章涵盖虚拟化的QoS驱动的频谱分配、多媒体混合云计算协议、异构STIN对物联网的架构影响，以及边缘网络中无标签学习的流量控制等主题。此外，还讨论了移动边缘缓存的深度强化学习、5G核心网络可扩展性的交通预测以及用于车辆赛博物理系统的SDN启用深度学习架构。
1 Software Defined Space-Terrestrial Integrated Networks: Architecture, Challenges, and Solutions
Figure 1.
The architecture of SD-STIN.
Figure 2.
The logical structure of SD-STIN.
Figure 3.
SDN-based resource management and traffic steering.
2. Virtualized QoS-Driven Spectrum Allocation in Space-Terrestrial Integrated Networks (频谱分配)
Figure 1.
The proposed architecture for STIN.
Figure 2.
The virtual cell construction.
Figure 3.
The reconstruction of a virtual cell.
3.MHCP: Multimedia Hybrid Cloud Computing Protocol and Architecture for Mobile Devices
4. Heterogeneous Space and Terrestrial Integrated Networks for IoT: Architecture and Challenges
5 Label-less Learning for Traffic Control in an Edge Network
Figure 1.
An illustration of traffic control in edge cloud.
Figure 2.
The trade-off among cloud intelligence, data amount, and resource consumption.
Figure 3.
Label-less learning-based traffic control in the edge cloud.
Figure 4.
System testbed.
6. Deep Reinforcement Learning for Mobile Edge Caching: Review, New Features, and Open Issues
7. Improving Traffic Forecasting for 5G Core Network Scalability: A Machine Learning Approach
8. SeDaTiVe: SDN-Enabled Deep Learning Architecture for Network Traffic Control in Vehicular Cyber-Physical Systems
9.
10. NDN Construction for Big Science: Lessons Learned from Establishing a Testbed
Figure 1.
Data fetching scenario using Interest and Data symmetrical forwarding in NDN network.
Figure 2.
NDN testbed established between continents for climate modeling application.
扫一扫
2251
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
