基于联邦学习的无线网络节点能量与信息管理策略

doi:10.19678/j.issn.1000-3428.0060825

计算机工程 ›› 2022, Vol. 48 ›› Issue (1): 188-196,203. doi: 10.19678/j.issn.1000-3428.0060825

基于联邦学习的无线网络节点能量与信息管理策略

杨文琦¹, 章阳^1,2, 聂江天³, 杨和林³, 康嘉文³, 熊泽辉⁴

1. 武汉理工大学计算机科学与技术学院, 武汉 430063;
2. 武汉理工大学交通物联网技术湖北省重点实验室, 武汉 430063;
3. 南洋理工大学计算机科学与工程学院, 新加坡 639798;
4. 新加坡科技设计大学信息系统技术与设计学院, 新加坡 487372

收稿日期:2021-02-07 修回日期:2021-04-23 发布日期:2021-05-08
作者简介:杨文琦(1996-),女,硕士研究生,主研方向为移动与分布式系统;章阳,副教授、博士;聂江天、杨和林、康嘉文,博士后;熊泽辉,助理教授、博士。
基金资助:
国家自然科学基金（62071343）。

Energy and Information Management Strategy Based on Federated Learning for Wireless Network Nodes

YANG Wenqi¹, ZHANG Yang^1,2, NIE Jiangtian³, YANG Helin³, KANG Jiawen³, XIONG Zehui⁴

1. School of Computer Science and Technology, Wuhan University of Technology, Wuhan 430063, China;
2. Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan 430063, China;
3. School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, Singapore;
4. Pillar of Information Systems Technology and Design, Singapore University of Technology and Design, Singapore 487372, Singapore

Received:2021-02-07 Revised:2021-04-23 Published:2021-05-08

摘要/Abstract

摘要： 在无线通信网络环境中，分布式客户端节点在用户隐私保护、数据传输效率、能量利用效率之间较难实现平衡。针对该问题，提出一种结合联邦学习与传统集中式学习的能量与信息管理优化策略。以覆盖性强、适用性广的移动信息采集设备作为学习服务器，将分布分散、资源受限的客户端节点作为学习参与者，通过构建马尔科夫决策模型分析客户端节点在移动信息采集过程中的状态变化和行为模式，同时采用值迭代算法和深度强化学习算法对该模型进行近似求解，获得客户端节点最优的信息传输与能量管理组合策略。仿真结果表明，相比MDP、GRE、RAN策略，该策略的长期效用较高且数据延迟较小，可实现客户端节点在信息传输过程中的数据隐私性、数据可用性与能量消耗之间的最优平衡。

关键词: 联邦学习, 无线通信网络, 信息传输, 能量管理, 马尔科夫决策过程, 深度强化学习

Abstract: To balance user privacy protection, data transmission efficiency, and energy utilization efficiency of distributed user nodes in wireless communication networks, a federated learning-based strategy for optimizing information transmission and energy management is established.The mobile information collection devices with extended coverage and applicability are deployed as servers, and the distributed user nodes with limited resources are deployed as workers.Then a Markov decision model is built to analyze the status changes and behavior patterns of nodes during mobile information collection.The Markov model is approximately solved by using a value iteration algorithm and deep reinforcement learning algorithm, so an optimal strategy for information transmission and energy management for user nodes is obtained.Simulation results show that compared with MDP, GRE and RAN strategies, the proposed strategy has better long-term utility and less data delay.It can achieve an optimal balance between data privacy, data availability and energy consumption during information transmission of user nodes.

Key words: federated learning, wireless communication network, information transmission, energy management, Markov Decision Process(MDP), Deep Reinforcement Learning(DRL)

中图分类号:

TP391

杨文琦, 章阳, 聂江天, 杨和林, 康嘉文, 熊泽辉. 基于联邦学习的无线网络节点能量与信息管理策略[J]. 计算机工程, 2022, 48(1): 188-196,203.

YANG Wenqi, ZHANG Yang, NIE Jiangtian, YANG Helin, KANG Jiawen, XIONG Zehui. Energy and Information Management Strategy Based on Federated Learning for Wireless Network Nodes[J]. Computer Engineering, 2022, 48(1): 188-196,203.

https://www.ecice06.com/CN/Y2022/V48/I1/188

图/表 10

20220108123023

20220108123027

20220108123031

20220108123039

20220108123044

20220108123048

20220108123052

20220108123055

20220108123059

20220108123103

参考文献

[1] BOUBICHE D E, PATHAN A S K, LLORET J, et al.Advanced industrial wireless sensor networks and intelligent IoT[J].IEEE Communications Magazine, 2018, 56(2):14-15.
[2] FUNG B C M, WANG K, CHEN R, et al.Privacy-preserving data publishing:a survey of recent developments[J].ACM Computing Surveys, 2010, 42(4):1-53.
[3] 陈发堂, 赵昊明, 吴晓龙, 等.移动网络用户隐私与信息安全研究[J].南京邮电大学学报(自然科学版), 2020, 40(2):35-40. CHEN F T, ZHAO H M, WU X L, et al.Privacy and information security of mobile network users[J].Journal of Nanjing University of Posts and Telecommunications (Natural Science), 2020, 40(2):35-40.(in Chinese)
[4] 刘俊旭, 孟小峰.机器学习的隐私保护研究综述[J].计算机研究与发展, 2020, 57(2):346-362. LIU J X, MENG X F.Survey on privacy-preserving machine learning[J].Journal of Computer Research and Development, 2020, 57(2):346-362.(in Chinese)
[5] YANG Q, LIU Y, CHEN T, et al.Federated machine learning:concept and applications[J].ACM Transactions on Intelligent Systems and Technology, 2019, 10(2):1-19.
[6] LIU S, QU Q, CHEN L, et al.SMC:a practical schema for privacy-preserved data sharing over distributed data streams[J].IEEE Transactions on Big Data, 2015, 1(2):68-81.
[7] MCMAHAN H B, MOORE E, RAMAGE D, et al.Communication-efficient learning of deep networks from decentralized data[EB/OL].[2021-01-05].https://arxiv.org/pdf/1602.05629.pdf.
[8] CORTES J, DULLERUD G E, HAN S, et al.Differential privacy in control and network systems[C]//Proceeding of the 55th Conference on Decision and Control.Washington D.C., USA:IEEE Press, 2016:4252-4272.
[9] LINDELL Y.General composition and universal composability in secure multi-party computation[J].Journal of Cryptology, 2009, 22:395-428.
[10] WANG Z, SONG M, ZHANG Z, et al.Beyond inferring class representatives:user-level privacy leakage from federated learning[C]//Proceedings of IEEE Conference on Computer Communications.Washington D.C., USA:IEEE Press, 2019:1-10.
[11] KONEN J, MCMAHAN H B, YU F X, et al.Federated learning:strategies for improving communication efficiency[EB/OL].[2021-01-03].https://arxiv.org/pdf/1610.05492.pdf.
[12] TRAN N H, BAO W, ZOMAYA A, et al.Federated learning over wireless networks:optimization model design and analysis[C]//Proceedings of IEEE Conference on Computer Communications.Washington D.C., USA:IEEE Press, 2019:1387-1395.
[13] JIN R, HE X, DAI H.On the design of communication efficient federated learning over wireless networks[EB/OL].[2021-01-05].https://arxiv.org/abs/2004.07351v1.
[14] NADIGER C, KUMAR A, ABDELHAK S.Federated reinforcement learning for fast personalization[C]//Proceedings of the 2nd International Conference on Artificial Intelligence and Knowledge Engineering.Washington D.C., USA:IEEE Press, 2019:123-127.
[15] CONWAY-JONES D, TUOR T, WANG S, et al.Demonstration of federated learning in a resource-constrained networked environment[C]//Proceedings of IEEE International Conference on Smart Computing.Washington, D.C., USA:IEEE Press, 2019:484-486.
[16] LI H, HAN T.An end-to-end encrypted neural network for gradient updates transmission in federated learning[C]//Proceedings of IEEE Conference on Data Compression.Washington D.C., USA:IEEE Press, 2019:589-592.
[17] 杨庚, 王周生.联邦学习中的隐私保护研究进展[J].南京邮电大学学报(自然科学版), 2020, 40(5):204-214. YANG G, WANG Z S.Survey on privacy preservation in federated learning[J].Journal of Nanjing University of Posts and Telecommunications (Natural Science), 2020, 40(5):204-214.(in Chinese)
[18] ZHANG Y, XIONG Z H, NIYATO D, et al.Toward a perpetual IoT system:wireless power management policy with threshold structure[J].IEEE Internet of Things Journal, 2018, 5(6):5254-5270.
[19] LU X, WANG P, NIYATO D, et al.Wireless networks with RF energy harvesting:a contemporary survey[J].IEEE Communications Surveys and Tutorials, 2015, 17(2):757-789.
[20] ZHU C, LEUNG V C M, SHU L, et al.Green Internet of Things for smart world[J].IEEE Access, 2015, 3:2151-2162.
[21] ANH T T, LUONG N C, NIYATO D, et al.Efficient training management for mobile crowd-machine learning:a deep reinforcement learning approach[J].IEEE Wireless Communications Letters, 2019, 8(5):1345-1348.
[22] ZHANG C, UENG Y, STUDER C, et al.Artificial intelligence for 5G and beyond 5G:implementations, algorithms, and optimizations[J].IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2020, 10(2):149-163.
[23] MOZAFFARI M, SAAD W, BENNIS M, et al.Optimal transport theory for cell association in UAV-enabled cellular networks[J].IEEE Communications Letters, 2017, 21(9):2053-2056.
[24] DUAN W, GU J, WEN M, et al.Emerging technologies for 5G-IoV networks:applications, trends and opportunities[J].IEEE Network, 2020, 34(5):283-289.
[25] ZENG Y, ZHANG R, LIM T J.Wireless communications with unmanned aerial vehicles:opportunities and challenges[J].IEEE Communications Magazine, 2016, 54(5):36-42.
[26] HE D, CHAN S, GUIZANI M.Communication security of unmanned aerial vehicles[J].IEEE Wireless Communications, 2017, 24(4):134-139.
[27] 周志华.机器学习[M].北京:清华大学出版社, 2015. ZHOU Z H.Machine learning[M].Beijing:Tsinghua University Press, 2015.(in Chinese)
[28] LIAO J, SANKAR L, TAN V Y F, et al.Hypothesis testing under mutual information privacy constraints in the high privacy regime[J].IEEE Transactions on Information Forensics and Security, 2018, 13(4):1058-1071.
[29] LUONG N C, HOANG D T, GONG S, et al.Applications of deep reinforcement learning in communications and networking:a survey[J].IEEE Communications Surveys and Tutorials, 2019, 21(4):3133-3174.

选择文件类型/文献管理软件名称

选择包含的内容

基于联邦学习的无线网络节点能量与信息管理策略

Energy and Information Management Strategy Based on Federated Learning for Wireless Network Nodes

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	潘恩元, 钟原, 李平. 联邦异质性数据下半监督颈椎MRI分割模型[J]. 计算机工程, 2024, 50(9): 367-376.
[2]	石琼, 段辉, 师智斌. 基于深度强化学习的可信任务卸载方案[J]. 计算机工程, 2024, 50(8): 142-152.
[3]	李红娇, 王宝金, 王朝晖, 胡仁豪. 基于模型相似度与本地损失的双重客户端选择算法[J]. 计算机工程, 2024, 50(8): 153-164.
[4]	顾永跟, 高凌轩, 吴小红, 陶杰. 非独立同分布下联邦半监督学习的数据分享研究[J]. 计算机工程, 2024, 50(6): 188-196.
[5]	顾永跟, 李国笑, 吴小红, 陶杰, 张艳琼. 预算约束下多任务联邦学习激励机制[J]. 计算机工程, 2024, 50(5): 149-157.
[6]	傅明建, 郭福强. 基于深度强化学习的无信号灯路口决策研究[J]. 计算机工程, 2024, 50(5): 91-99.
[7]	孙文洁, 李宗民, 孙浩淼. 基于图神经网络的多智能体强化学习值函数分解方法[J]. 计算机工程, 2024, 50(5): 62-70.
[8]	熊世强, 何道敬, 王振东, 杜润萌. 联邦学习及其安全与隐私保护研究综述[J]. 计算机工程, 2024, 50(5): 1-15.
[9]	刘少杰, 文斌, 王泽旭. 基于联邦学习的多技术融合数据交易方法[J]. 计算机工程, 2024, 50(3): 182-190.
[10]	宋华伟, 李升起, 万方杰, 卫玉萍. 非独立同分布场景下的联邦学习优化方法[J]. 计算机工程, 2024, 50(3): 166-172.
[11]	张晓均, 李兴鹏, 唐伟, 郝云溥, 薛婧婷. 云-边融合的可验证隐私保护跨域联邦学习方案[J]. 计算机工程, 2024, 50(3): 148-155.
[12]	杜海军, 余粟. 基于时空图注意力网络的服务机器人动态避障[J]. 计算机工程, 2024, 50(2): 105-112.
[13]	郑晨俊, 曾艳, 袁俊峰, 张纪林, 王鑫, 韩猛. 基于联邦学习的船舶AIS轨迹预测算法[J]. 计算机工程, 2024, 50(2): 298-307.
[14]	蔡梓越, 谭北海, 余荣, 黄旭民, 王思明. 面向6G物联网设备协同的区块链动态分片[J]. 计算机工程, 2024, 50(1): 50-59.
[15]	胡水. 基于深度强化学习的智能兵棋推演决策方法[J]. 计算机工程, 2023, 49(9): 303-312.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于联邦学习的无线网络节点能量与信息管理策略

Energy and Information Management Strategy Based on Federated Learning for Wireless Network Nodes

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献

相关文章 15

编辑推荐

Metrics

本文评价