User scheduling and power allocation strategy for cell-free networks based on federated learning

WANG Huahua; HUANG Yexia; LI Ling

doi:10.11959/j.issn.1000-436x.2024159

您当前的位置：

首页 >

文章列表页 >

User scheduling and power allocation strategy for cell-free networks based on federated learning

Papers | 更新时间：2024-10-10

- User scheduling and power allocation strategy for cell-free networks based on federated learning
- Journal on Communications Vol. 45, Issue 9, Pages: 129-143(2024)
- 作者机构：
  
  重庆邮电大学通信与信息工程学院，重庆 400065
- 作者简介：
- 基金信息：
  
  Chongqing Natural Science Foundation Innovation and Development Joint Fund (China Star Network)(CSTB2023NSCQ-LZX0114)
- DOI：10.11959/j.issn.1000-436x.2024159
  CLC： TN929.5
- Received：10 April 2024，
  
  Revised：2024-06-13，
  
  Published：25 September 2024
- 稿件说明：
移动端阅览
王华华,黄烨霞,李玲.基于FL的无蜂窝网络用户调度与功率分配策略[J].通信学报,2024,45(09):129-143.

WANG Huahua,HUANG Yexia,LI Ling.User scheduling and power allocation strategy for cell-free networks based on federated learning[J].Journal on Communications,2024,45(09):129-143.
王华华,黄烨霞,李玲.基于FL的无蜂窝网络用户调度与功率分配策略[J].通信学报,2024,45(09):129-143. DOI： 10.11959/j.issn.1000-436x.2024159.

WANG Huahua,HUANG Yexia,LI Ling.User scheduling and power allocation strategy for cell-free networks based on federated learning[J].Journal on Communications,2024,45(09):129-143. DOI： 10.11959/j.issn.1000-436x.2024159.

摘要

为解决无蜂窝网络系统中用户链路质量差异和通信、计算资源占用不平衡导致的联邦学习（FL）训练性能受限问题，设计了一个联合用户调度和功率分配的优化方案。首先，提出了一种低复杂度的基于资源优先的二次抽样用户调度（RPSS-US）算法，根据用户计算资源的可用性和链路质量选择用户，优先调度对系统容量和全局模型更新贡献较大的用户参与FL任务，提高整体训练性能。随后，提出了一种基于二分法的功率分配（BM-PA）算法，通过优化功率分配改善用户链路质量差异，以提高数据传输速率，减少FL任务的总体时延。通过交替迭代优化这2个子问题，实现系统性能的联合优化。仿真结果表明，相较于其他对比算法，所提出的算法下行吞吐量提升了47.19%，上行吞吐量提升了22.60%，FL任务时间消耗减少了57.33%，并在达到相同模型精度时的时间开销最小。

Abstract

In order to address the issue of limited training performance in federated learning (FL) due to user link quality disparities and imbalanced communication

and computing resource utilization in cell-free network systems

a joint optimization problem for user scheduling and power allocation was designed. Firstly

a low-complexity resource priority based secondary sampling user scheduling (RPSS-US) algorithm was proposed. Users were selected based on the availability of their computing resources and link quality

with priority given to those contributing more to system capacity and global model updates

thus improving overall training performance. Then

a power allocation algorithm based on the binary method (BM-PA) was proposed to optimize power allocation

improve user link quality differences

enhance data transmission rates

and reduce overall FL task delay. By iteratively optimizing these two sub-problems alternately

joint optimization of system performance was achieved. Simulation results demonstrate that compared to other comparison algorithms

the proposed algorithm achieves a 47.19% increase in downlink throughput

a 22.60% increase in uplink throughput

and a 57.33% reduction in FL task time consumption

while minimizing time overhead for achieving the same model accuracy

关键词

Keywords

references

LI T , SAHU A K , TALWALKAR A , et al . Federated learning: challenges, methods, and future directions [J ] . IEEE Signal Processing Magazine , 2020 , 37 ( 3 ): 50 - 60 .

ELHOUSHY S , IBRAHIM M , HAMOUDA W . Cell-free massive MIMO: a survey [J ] . IEEE Communications Surveys & Tutorials , 2022 , 24 ( 1 ): 492 - 523 .

KASSAM J , CASTANHEIRA D , SILVA A , et al . A review on cell-free massive MIMO systems [J ] . Electronics , 2023 , 12 ( 4 ): 1001 .

NGO H Q , ASHIKHMIN A , YANG H , et al . Cell-free massive MIMO versus small cells [J ] . IEEE Transactions on Wireless Communications , 2017 , 16 ( 3 ): 1834 - 1850 .

VU T T , NGO D T , TRAN N H , et al . Cell-free massive MIMO for wireless federated learning [J ] . IEEE Transactions on Wireless Communications , 2020 , 19 ( 10 ): 6377 - 6392 .

CHEN M Z , GÜNDÜZ D , HUANG K B , et al . Distributed learning in wireless networks: recent progress and future challenges [J ] . IEEE Journal on Selected Areas in Communications , 2021 , 39 ( 12 ): 3579 - 3605 .

XIA W C , QUEK T Q S , GUO K , et al . Multi-armed bandit-based client scheduling for federated learning [J ] . IEEE Transactions on Wireless Communications , 2020 , 19 ( 11 ): 7108 - 7123 .

ZAEEM R M , DUNCAN J C M , MARTINS W A , et al . Resource allocation and user scheduling design for user-centric cell-free massive MIMO systems [C ] // Proceedings of the 2023 IEEE 34th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) . Piscataway : IEEE Press , 2023 : 1 - 6 .

NGO H Q , TRAN L N , DUONG T Q , et al . On the total energy efficiency of cell-free massive MIMO [J ] . IEEE Transactions on Green Communications and Networking , 2018 , 2 ( 1 ): 25 - 39 .

申敏 , 裘德市 . 无蜂窝大规模MIMO系统接入点动态选择算法 [J ] . 电讯技术 , 2024 , 64 ( 3 ): 416 - 422 .

SHEN M , QIU D S . A dynamic access point selection algorithm in cell-free massive MIMO systems [J ] . Telecommunication Engineering , 2024 , 64 ( 3 ): 416 - 422 .

CHEN M Z , POOR H V , SAAD W , et al . Convergence time minimization of federated learning over wireless networks [C ] // Proceedings of the ICC 2020 - 2020 IEEE International Conference on Communications (ICC) . Piscataway : IEEE Press , 2020 : 1 - 6 .

SHI W Q , ZHOU S , NIU Z S . Device scheduling with fast convergence for wireless federated learning [C ] // Proceedings of the ICC 2020- 2020 IEEE International Conference on Communications (ICC) . Piscataway : IEEE Press , 2020 : 1 - 6 .

CHEN M Z , YANG Z H , SAAD W , et al . A joint learning and communications framework for federated learning over wireless networks [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 1 ): 269 - 283 .

VU T T , NGO H Q , NGO D T , et al . Energy-efficient massive MIMO for serving multiple federated learning groups [C ] // Proceedings of the 2021 IEEE Global Communications Conference (GLOBECOM) . Piscataway : IEEE Press , 2021 : 1 - 6 .

MAI T C , NGO H Q , TRAN L N . Energy efficiency maximization in large-scale cell-free massive MIMO: a projected gradient approach [J ] . IEEE Transactions on Wireless Communications , 2022 , 21 ( 8 ): 6357 - 6371 .

姚媛媛 , 刘忆秋 , 黄赛 , 等 . 无蜂窝大规模MIMO网络下基于联邦学习的用户接入策略及能耗优化 [J ] . 通信学报 , 2023 , 44 ( 10 ): 112 - 123 .

YAO Y Y , LIU Y Q , HUANG S , et al . Federated learning-based user access strategy and energy consumption optimization in cell-free massive MIMO network [J ] . Journal on Communications , 2023 , 44 ( 10 ): 112 - 123 .

VU T T , NGO D T , NGO H Q , et al . Joint resource allocation to minimize execution time of federated learning in cell-free massive MIMO [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 21 ): 21736 - 21750 .

BAO H , GAO B , XIONG K , et al . Joint user cooperation and scheduling for federated learning in CFmMIMO networks [C ] // Proceedings of the 2023 2nd International Conference on Smart Technologies and Systems for Next Generation Computing (ICSTSN) . Piscataway : IEEE Press , 2023 : 1 - 5 .

ALEDHARI M , RAZZAK R , PARIZI R M , et al . Federated learning: a survey on enabling technologies, protocols, and applications [J ] . IEEE Access: Practical Innovations , Open Solutions, 2020 , 8 : 140699 - 140725 .

SUN T , LI D S , WANG B . Decentralized federated averaging [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2023 , 45 ( 4 ): 4289 - 4301 .

LI X , HUANG K , YANG W , et al . On the convergence of FedAvg on non-iid data [J ] . arXiv Preprint , arXiv: 1907.02189 , 2019 .

KOOLIVAND M , BAHONAR M H , FAZEL M S . Improving energy efficiency of massive MIMO relay systems using power bisection allocation for cell-edge users [C ] // Proceedings of the 2019 27th Iranian Conference on Electrical Engineering (ICEE) . Piscataway : IEEE Press , 2019 : 1470 - 1475 .

Views

921

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

TDMA-based user scheduling policies for federated learning

Algorithm on joint optimization of power allocation and slot allocation in satellite communication systems

Dynamic compression method for federated learning based on feature information in ISAC networks

DPBR-Adapt: a hierarchically adaptive differential privacy defence scheme for federated learning

Personalized differential privacy federated learning method for collaborative spectrum sensing

Related Author

Meixia TAO

Dong WANG

Rui SUN

Naifu ZHANG

Han HAN

Ying LI

Xu DONG

Xiao-bo GUO

Related Institution

School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University

College of Communication Engineering,PLA UST

Institute of China Electronic System Engineering Corporation

Xi'an Communication Institute,,Xi'an

No.54 Research Institute of CETC

AI问答

⁰