.png){kind=icon}
返回
Service-Oriented SAGIN With Pervasive Intelligence for Resource-Constrained Users
.png){kind=icon}
PRE
AI
DOI：10.1109/MNET.2024.3353414.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As an indispensable architecture for future 6G communication networks, space-air-ground integrated network (SAGIN) integrates satellite networks, air networks and ground networks, greatly expanding the coverage of network space. Compared with the traditional mobile edge computing (MEC), the edge intelligence (EI) formed by combining artificial intelligence (AI) and MEC can intelligently process the edge data by embedding the AI algorithms into the edge devices with limited computing power. Therefore, this article considers applying EI to SAGIN to form the EI-driven SAGIN architecture, which can significantly enhance the communication, computing, sensing and storage capabilities of SAGIN architecture to solve the problem of efficient resource management for resource-constrained users. In this article, we first introduce the system network architecture and logical functional architecture, and give a detailed description of the components in the network architecture, and then discuss some key technologies in the system, including efficient resource utilization for microservice based on software defined network (SDN) and network function virtualization (NFV), deep reinforcement learning (DRL) based on knowledge graph for efficient storage and intelligent computing, and efficient and realtime sensing for massive information. Finally, we propose a DRL-based resource allocation and computation offloading algorithm for microservices (DRCAM) and evaluate the performance of the proposed algorithm. The simulation results show that, compared with the existing algorithms, the proposed algorithm could greatly reduce the system cost under different weights.
Keyword:
Satellites
Computer architecture
Sensors
Low earth orbit satellites
Cloud computing
Resource management
Space-air-ground integrated networks
6G mobile communication
期刊
IF:
6.3
论文数:
2.7K
被引数:
1.1W
机构
引用论文
Computing over Space-Air-Ground Integrated Networks: Challenges and Opportunities空间-空中-地面综合网络上的计算: 挑战与机遇.png)
IEEE NETWORK
IEEE NETWORKIF6.3
PREAI
分享收藏When Serverless Computing Meets Edge Computing: Architecture, Challenges, and Open Issues当无服务器计算遇到边缘计算时: 架构、挑战和开放问题
PREAI
分享收藏AI-SPACE: A Cloud-Edge Aggregated Artificial Intelligent Architecture for Tiansuan Constellation-Assisted Space-Terrestrial Integrated NetworksIEEE NETWORK
IEEE NETWORKIF6.3
PREAI
分享收藏A Continuous Actor-Critic Deep Q-Learning-Enabled Deployment of UAV Base Stations: Toward 6G Small Cells in the Skies of Smart Cities持续的演员评论家深度q-learning支持的无人机基站部署: 智能城市天空中的6g小型蜂窝
OAAI
OAAI分享收藏Incorporating Distributed DRL Into Storage Resource Optimization of Space-Air-Ground Integrated Wireless Communication Network将分布式DRL融入空地一体化无线通信网存储资源优化OAAI
OAAI分享收藏HEAWS: An Accelerator for Homomorphic Encryption on the Amazon AWS FPGAHiaws: Amazon AWS FPGA上的同态加密加速器
OAAI
OAAI分享收藏
查看更多内容