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
  • [31] Blockchain-based 6G task offloading and cooperative computing resource allocation study
    Tian, Shujie
    Zhang, Yuexia
    Bi, Yanxian
    Yuan, Taifu
    JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS, 2024, 13 (01):
  • [32] Computing Resource Allocation Based on Multi-base Station and Multi-user Scenario in Mobile Edge Computing
    Zhong, Yaozhang
    Du, Yingkui
    Zhao, Jing
    Gao, Qinghang
    Zou, Yujuan
    Luo, Yong
    Chao, Kailin
    Yin, Ziyu
    MOBILE INTERNET SECURITY, MOBISEC 2023, 2024, 2095 : 37 - 48
  • [33] Task Scheduling Based on Priority and Resource Allocation in Multi-User Multi-Task Mobile Edge Computing System
    Paymard, Pouria
    Mokari, Nader
    Orooji, Mehdi
    2019 IEEE 30TH ANNUAL INTERNATIONAL SYMPOSIUM ON PERSONAL, INDOOR AND MOBILE RADIO COMMUNICATIONS (PIMRC), 2019, : 265 - 271
  • [34] Deep Reinforcement Learning-Based Computation Offloading for Mobile Edge Computing in 6G
    Sun, Haifeng
    Wang, Jiawei
    Yong, Dongping
    Qin, Mingwei
    Zhang, Ning
    IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2024, 70 (04) : 7482 - 7493
  • [35] Deep-Learning-Based Resource Allocation for 6G NOMA-Assisted Backscatter Communications
    Tuong, Van Dat
    Cho, Sungrae
    IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (19): : 32234 - 32243
  • [36] Non-Orthogonal Multiple Access Enabled Mobile Edge Computing in 6G Communications: A Systematic Literature Review
    Ogundokun, Roseline Oluwaseun
    Awotunde, Joseph Bamidele
    Imoize, Agbotiname Lucky
    Li, Chun-Ta
    Abdulahi, AbdulRahman Tosho
    Adelodun, Abdulwasiu Bolakale
    Sur, Samarendra Nath
    Lee, Cheng-Chi
    SUSTAINABILITY, 2023, 15 (09)
  • [37] Cooperative End-Edge-Cloud Computing and Resource Allocation for Digital Twin Enabled 6G Industrial IoT
    Wang, Yuao
    Fang, Jingjing
    Cheng, Yao
    She, Hao
    Guo, Yongan
    Zheng, Gan
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2024, 18 (01) : 124 - 137
  • [38] HMF Based QoS aware Recommended Resource Allocation System in Mobile Edge Computing for IoT
    Das, Puja
    Jamader, Asik Rahaman
    Acharya, Biswa Ranjan
    Das, Himansu
    PROCEEDINGS OF THE 2019 INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND CONTROL SYSTEMS (ICCS), 2019, : 444 - 449
  • [39] Multi-agent Reinforcement Learning for Joint Wireless and Computational Resource Allocation in Mobile Edge Computing System
    Zhang, Yawen
    Xia, Weiwei
    Yan, Feng
    Cheng, Huaqing
    Shen, Lianfeng
    AD HOC NETWORKS, ADHOCNETS 2019, 2019, 306 : 149 - 161
  • [40] Algorithm for Resource Allocation and Computing Offloading in 6G Networks: Deep Reinforcement Learning-based
    Saeed, Mamoon M.
    Saeed, Rashid A.
    Ali, Elmustafa Sayed
    Mokhtar, Rania A.
    Khalifa, Othman O.
    9TH INTERNATIONAL CONFERENCE ON MECHATRONICS ENGINEERING, ICOM 2024, 2024, : 188 - 193