Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services

被引:54
|
作者
Xu, Minrui [1 ]
Du, Hongyang [1 ]
Niyato, Dusit [1 ]
Kang, Jiawen [2 ,3 ]
Xiong, Zehui [4 ]
Mao, Shiwen [5 ]
Han, Zhu [6 ,7 ]
Jamalipour, Abbas [8 ]
Kim, Dong In [9 ]
Shen, Xuemin [10 ]
Leung, Victor C. M. [11 ,12 ]
Poor, H. Vincent [13 ]
机构
[1] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore 639798, Singapore
[2] Guangdong Univ Technol, Sch Automat, Key Lab Intelligent Informat Proc & Syst Integrat, Minist Educ, Guangzhou 510006, Guangdong, Peoples R China
[3] Guangdong Univ Technol, Guangdong Hong Kong Macao Joint Lab Smart Discrete, Guangzhou 510006, Guangdong, Peoples R China
[4] Singapore Univ Technol & Design, Pillar Informat Syst Technol & Design, Singapore 487372, Singapore
[5] Auburn Univ, Dept Elect & Comp Engn, Auburn, AL 36849 USA
[6] Univ Houston, Dept Elect & Comp Engn, Houston, TX 77004 USA
[7] Kyung Hee Univ, Dept Comp Sci & Engn, Seoul 446701, South Korea
[8] Univ Sydney, Sch Elect & Informat Engn, Sydney, NSW 2006, Australia
[9] Sungkyunkwan Univ, Dept Elect & Comp Engn, Suwon 16419, South Korea
[10] Univ Waterloo, Dept Elect & Comp Engn, Waterloo, ON N2L 3G1, Canada
[11] Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen 518061, Peoples R China
[12] Univ British Columbia, Dept Elect & Comp Engn, Vancouver, BC V6T 1Z4, Canada
[13] Princeton Univ, Dept Elect & Comp Engn, Princeton 08544, NJ USA
来源
关键词
Computational modeling; Servers; Biological system modeling; Artificial intelligence; Generative AI; Surveys; Mobile handsets; AIGC; generative AI; mobile edge networks; communication and networking; AI training and inference; Internet technology; RESOURCE-ALLOCATION; SEMANTIC COMMUNICATIONS; DNN INFERENCE; INTELLIGENCE; BLOCKCHAIN; SMART; CHALLENGES; ENVIRONMENTS; CONVERGENCE; COMPRESSION;
D O I
10.1109/COMST.2024.3353265
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Artificial Intelligence-Generated Content (AIGC) is an automated method for generating, manipulating, and modifying valuable and diverse data using AI algorithms creatively. This survey paper focuses on the deployment of AIGC applications, e.g., ChatGPT and Dall-E, at mobile edge networks, namely mobile AIGC networks, that provide personalized and customized AIGC services in real time while maintaining user privacy. We begin by introducing the background and fundamentals of generative models and the lifecycle of AIGC services at mobile AIGC networks, which includes data collection, training, fine-tuning, inference, and product management. We then discuss the collaborative cloud-edge-mobile infrastructure and technologies required to support AIGC services and enable users to access AIGC at mobile edge networks. Furthermore, we explore AIGC-driven creative applications and use cases for mobile AIGC networks. Additionally, we discuss the implementation, security, and privacy challenges of deploying mobile AIGC networks. Finally, we highlight some future research directions and open issues for the full realization of mobile AIGC networks.
引用
收藏
页码:1127 / 1170
页数:44
相关论文
共 50 条
  • [41] Auto-Split: A General Framework of Collaborative Edge-Cloud AI
    Banitalebi-Dehkordi, Amin
    Vedula, Naveen
    Pei, Jian
    Xia, Fei
    Wang, Lanjun
    Zhang, Yong
    KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, : 2543 - 2553
  • [42] Collaborative Edge-Cloud AI for IoT Driven Secure Healthcare System
    Gupta, Lay
    2023 IEEE INTERNATIONAL SYSTEMS CONFERENCE, SYSCON, 2023,
  • [43] Reliable and Data-driven AI Applications in Edge-Cloud Environments
    Ko, In-Young
    Mrissa, Michael
    Srivastava, Abhishek
    FRONTIERS OF COMPUTER VISION, IW-FCV 2024, 2024, 2143 : 2 - 4
  • [44] A Survey on Edge and Edge-Cloud Computing Assisted Cyber-Physical Systems
    Cao, Kun
    Hu, Shiyan
    Shi, Yang
    Colombo, Armando
    Karnouskos, Stamatis
    Li, Xin
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 17 (11) : 7806 - 7819
  • [45] Task Offloading for Deep Learning Empowered Automatic Speech Analysis in Mobile Edge-Cloud Computing Networks
    Li, Xiuhua
    Xu, Zhenghui
    Fang, Fang
    Fan, Qilin
    Wang, Xiaofei
    Leung, Victor C. M.
    IEEE TRANSACTIONS ON CLOUD COMPUTING, 2023, 11 (02) : 1985 - 1998
  • [46] Accelerating Federated Learning via Parameter Selection and Pre-Synchronization in Mobile Edge-Cloud Networks
    Zhou, Huan
    Li, Mingze
    Sun, Peng
    Guo, Bin
    Yu, Zhiwen
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (11) : 10313 - 10328
  • [47] AI-Bazaar: A Cloud-Edge Computing Power Trading Framework for Ubiquitous AI Services
    Ren, Xiaoxu
    Qiu, Chao
    Wang, Xiaofei
    Han, Zhu
    Xu, Ke
    Yao, Haipeng
    Guo, Song
    IEEE TRANSACTIONS ON CLOUD COMPUTING, 2023, 11 (03) : 2337 - 2348
  • [48] Split Edge-Cloud Neural Networks for Better Adversarial Robustness
    Douch, Salmane
    Abid, Mohamed Riduan
    Zine-Dine, Khalid
    Bouzidi, Driss
    Benhaddou, Driss
    IEEE ACCESS, 2024, 12 : 158854 - 158865
  • [49] Dependency-Aware Computation Offloading for Mobile Edge Computing With Edge-Cloud Cooperation
    Chen, Long
    Wu, Jigang
    Zhang, Jun
    Dai, Hong-Ning
    Long, Xin
    Yao, Mianyang
    IEEE TRANSACTIONS ON CLOUD COMPUTING, 2022, 10 (04) : 2451 - 2468
  • [50] A Unified Framework for Guiding Generative AI With Wireless Perception in Resource Constrained Mobile Edge Networks
    Wang, Jiacheng
    Du, Hongyang
    Niyato, Dusit
    Kang, Jiawen
    Xiong, Zehui
    Rajan, Deepu
    Mao, Shiwen
    Shen, Xuemin
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (11) : 10344 - 10360