GainNet: Coordinates the Odd Couple of Generative AI and 6G Networks

被引:1
作者
Chen, Ning [1 ]
Yang, Jie [2 ]
Cheng, Zhipeng [3 ]
Fan, Xuwei [1 ]
Liu, Zhang [1 ]
Huang, Bangzhen [1 ]
Zhao, Yifeng [1 ]
Huang, Lianfen [1 ]
Du, Xiaojiang [4 ]
Guizani, Mohsen [5 ]
机构
[1] Xiamen Univ, Sch Informat, Xiamen 361005, Peoples R China
[2] Xiamen Univ, Natl Inst Data Sci Hlth & Med, Xiamen 361102, Peoples R China
[3] Soochow Univ, Sch Future Sci & Engn, Suzhou 215006, Peoples R China
[4] Stevens Inst Technol, Dept Elect & Comp Engn, Hoboken, NJ 07030 USA
[5] Mohamed bin Zayed Univ Artificial Intelligence, Machine Learning Dept, Abu Dhabi, U Arab Emirates
来源
IEEE NETWORK | 2024年 / 38卷 / 05期
关键词
6G mobile communication; Computational modeling; Data models; Artificial intelligence; Knowledge engineering; Sensors; Optimization; 6G; generative AI; collaborative cloud-edge-end intelligence; resource orchestration; integrated sensing; communication; computing; ORCHESTRATION;
D O I
10.1109/MNET.2024.3418671
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
The rapid expansion of AI-generated content (AIGC) reflects the iteration from assistive AI towards generative AI (GAI). Meanwhile, the 6G networks will also evolve from the Internet-of-Everything to the Internet-of-Intelligence. However, they seem to be an odd couple, due to the contradiction of data and resources. To achieve a better-coordinated interplay between GAI and 6G, the GAI-native Networks (GainNet), a GAI-oriented collaborative cloud-edge-end intelligence framework, is proposed in this article. By deeply integrating GAI with 6G network design, GainNet realizes the positive closed-loop knowledge flow and sustainable-evolution GAI model optimization. On this basis, the GAI-oriented generic Resource Orchestration Mechanism with Integrated Sensing, Communication, and Computing (GaiRomISCC) is proposed to guarantee the efficient operation of GainNet. Two simple case studies demonstrate the effectiveness and robustness of the proposed schemes. Finally, we envision the key challenges and future directions concerning the interplay between GAI models and 6G networks.
引用
收藏
页码:56 / 65
页数:10
相关论文
共 15 条
[1]  
Cao Zequn, 2024, IEEE Internet Things J.
[2]   Resource Provisioning for Mitigating Edge DDoS Attacks in MEC-Enabled SDVN [J].
Deng, Yuchuan ;
Jiang, Hao ;
Cai, Peijing ;
Wu, Tong ;
Zhou, Pan ;
Li, Beibei ;
Lu, Hao ;
Wu, Jing ;
Chen, Xin ;
Wang, Kehao .
IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (23) :24264-24280
[3]   Standing on the Shoulders of Giants: Cross-Slice Federated Meta Learning for Resource Orchestration to Cold-Start Slice [J].
Dong, Tianjian ;
Qi, Qi ;
Wang, Jingyu ;
Zhuang, Zirui ;
Sun, Haifeng ;
Liao, Jianxin ;
Han, Zhu .
IEEE-ACM TRANSACTIONS ON NETWORKING, 2023, 31 (02) :828-845
[4]   Autonomous Lifecycle Management for Resource-Efficient Workload Orchestration for Green Edge Computing [J].
Guim, Francesc ;
Metsch, Thijs ;
Moustafa, Hassnaa ;
Verrall, Timothy ;
Carrera, David ;
Cadenelli, Nicola ;
Chen, Jiang ;
Doria, David ;
Ghadie, Chadie ;
Prats, Raul Gonzalez .
IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING, 2022, 6 (01) :571-582
[5]   A DDPG Hybrid of Graph Attention Network and Action Branching for Multi-Scale End-Edge-Cloud Vehicular Orchestrated Task Offloading [J].
He, Yejun ;
Zhong, Xiaoxu ;
Gan, Youhui ;
Cui, Haixia ;
Guizani, Mohsen .
IEEE WIRELESS COMMUNICATIONS, 2023, 30 (04) :147-153
[6]   A Global DAG Task Scheduler Using Deep Reinforcement Learning and Graph Convolution Network [J].
Lee, Hyunsung ;
Cho, Sangwoo ;
Jang, Yeongjae ;
Lee, Jinkyu ;
Woo, Honguk .
IEEE ACCESS, 2021, 9 :158548-158561
[7]   GNN-Based Hierarchical Deep Reinforcement Learning for NFV-Oriented Online Resource Orchestration in Elastic Optical DCIs [J].
Li, Baojia ;
Zhu, Zuqing .
JOURNAL OF LIGHTWAVE TECHNOLOGY, 2022, 40 (04) :935-946
[8]   Deep-Graph-Based Reinforcement Learning for Joint Cruise Control and Task Offloading for Aerial Edge Internet of Things (EdgeIoT) [J].
Li, Kai ;
Ni, Wei ;
Yuan, Xin ;
Noor, Alam ;
Jamalipour, Abbas .
IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (21) :21676-21686
[9]   Graph-Reinforcement-Learning-Based Task Offloading for Multiaccess Edge Computing [J].
Sun, Zhenchuan ;
Mo, Yijun ;
Yu, Chen .
IEEE INTERNET OF THINGS JOURNAL, 2023, 10 (04) :3138-3150
[10]   Dependent Task Offloading for Edge Computing based on Deep Reinforcement Learning [J].
Wang, Jin ;
Hu, Jia ;
Min, Geyong ;
Zhan, Wenhan ;
Zomaya, Albert Y. ;
Georgalas, Nektarios .
IEEE TRANSACTIONS ON COMPUTERS, 2022, 71 (10) :2449-2461