User Association and Resource Allocation in Large Language Model Based Mobile Edge Computing System over 6G Wireless Communications

被引:0
|
作者
Qian, Liangxin [1 ]
Zhao, Jun [1 ]
机构
[1] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore
关键词
6G; Large language model; mobile edge computing; wireless communications; resource allocation;
D O I
10.1109/VTC2024-SPRING62846.2024.10683177
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In the rapidly evolving landscape of large language models (LLMs) and mobile edge computing for 6G, the need for efficient service delivery to mobile users with constrained computational resources has become paramount. Addressing this, our paper delves into a collaborative framework for model training where user data and model adapters are shared with servers to optimize performance. Within this framework, users initially update the first several layers of the adapters while freezing the other layers of them, leveraging their local datasets. Once this step is complete, these partially trained parameters are transmitted to servers. The servers, equipped with more robust computational capabilities, then update the subsequent layers. After this training, they send the enhanced parameters back to the users. This collaborative training approach ensures that mobile users with limited computational capacities can still benefit from advanced LLM services without being burdened by exhaustive computations. Central to our methodology is the DASHF algorithm, which encapsulates the Dinkelbach algorithm, alternating optimization, semidefinite relaxation (SDR), the Hungarian method, and a pioneering fractional programming technique from a recent IEEE JSAC paper [1]. The crux of DASHF is its capability to reformulate an optimization problem as Quadratically Constrained Quadratic Programming (QCQP) via meticulously crafted transformations, making it solvable by SDR and the Hungarian algorithm. Through extensive simulations, we demonstrate the effectiveness of the DASHF algorithm, offering significant insights for the advancement of collaborative LLM service deployments.
引用
收藏
页数:7
相关论文
共 50 条
  • [21] Hybrid NOMA Based MIMO Offloading for Mobile Edge Computing in 6G Networks
    Yunus Dursun
    Fang Fang
    Zhiguo Ding
    China Communications, 2022, 19 (10) : 12 - 20
  • [22] Hybrid NOMA Based MIMO Offloading for Mobile Edge Computing in 6G Networks
    Dursun, Yunus
    Fang, Fang
    Ding, Zhiguo
    CHINA COMMUNICATIONS, 2022, 19 (10) : 12 - 20
  • [23] EdgeGO: A Mobile Resource-Sharing Framework for 6G Edge Computing in Massive IoT Systems
    Cong, Rong
    Zhao, Zhiwei
    Min, Geyong
    Feng, Chenyuan
    Jiang, Yuhong
    IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (16) : 14521 - 14529
  • [24] Large Language Model Enhanced Multi-Agent Systems for 6G Communications
    Jiang, Feibo
    Peng, Yubo
    Dong, Li
    Wang, Kezhi
    Yang, Kun
    Pan, Cunhua
    Niyato, Dusit
    Dobre, Octavia A.
    IEEE WIRELESS COMMUNICATIONS, 2024, 31 (06) : 48 - 55
  • [25] Flexible Physical Layer based Resource Allocation for Machine Type Communications Towards 6G
    Sadi, Yalcin
    Erkucuk, Serhat
    Panayirci, Erdal
    2020 2ND 6G WIRELESS SUMMIT (6G SUMMIT), 2020,
  • [26] IRS/UAV-Based Edge-Computing/Traffic-Offloading Over RF-Powered 6G Mobile Wireless Networks
    Wang, Fei
    Zhang, Xi
    2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), 2022, : 1272 - 1277
  • [27] Research on resource allocation of vocal music teaching system based on mobile edge computing
    Sun, Jian
    COMPUTER COMMUNICATIONS, 2020, 160 (160) : 342 - 350
  • [28] Edge Computing-Based Mobile Health System: Network Architecture and Resource Allocation
    Lin, Di
    Tang, Yu
    IEEE SYSTEMS JOURNAL, 2020, 14 (02): : 1716 - 1727
  • [29] Joint User Clustering, Resource Allocation and Power Control for NOMA-based Mobile Edge Computing
    Diao, Xianbang
    Zheng, Jianchao
    Cai, Yueming
    Dong, Xinsong
    Zhang, Xiaoyi
    2018 10TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS AND SIGNAL PROCESSING (WCSP), 2018,
  • [30] A Double Auction-Based Approach for Multi-User Resource Allocation in Mobile Edge Computing
    Yue, Yanlin
    Sun, Wen
    Liu, Jiajia
    2018 14TH INTERNATIONAL WIRELESS COMMUNICATIONS & MOBILE COMPUTING CONFERENCE (IWCMC), 2018, : 805 - 810