基于联邦学习的无线网络节点能量与信息管理策略

Wenqi Yang; Yang Zhang; Jiangtian Nie; Helin Yang; Jiawen Kang; Zehui Xiong

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

Translated title of the contribution: Energy and information management strategy based on federated learning for wireless network nodes

Wenqi Yang
, Yang Zhang^*
, Jiangtian Nie
, Helin Yang
, Jiawen Kang
, Zehui Xiong

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

4 Citations (Scopus)

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.

Translated title of the contribution	Energy and information management strategy based on federated learning for wireless network nodes
Original language	Chinese (Traditional)
Pages (from-to)	188–196,203
Journal	Jisuanji Gongcheng/Computer Engineering
Volume	48
Issue number	1
DOIs	https://doi.org/10.19678/j.issn.1000-3428.0060825
Publication status	Published - 01 Jan 2022
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2022, Editorial Office of Computer Engineering. All rights reserved.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Deep Reinforcement Learning(DRL)
Energy management
Federated learning
Information transmission
Markov Decision Process(MDP)
Wireless communication network

ASJC Scopus subject areas

Software
Hardware and Architecture
Computer Networks and Communications
Computer Graphics and Computer-Aided Design
Computational Theory and Mathematics

Access to Document

10.19678/j.issn.1000-3428.0060825Licence: Unspecified

Cite this

@article{f22c3f130e0246cfb97cce2b9e2c2df7,

title = "基于联邦学习的无线网络节点能量与信息管理策略",

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.",

keywords = "Deep Reinforcement Learning(DRL), Energy management, Federated learning, Information transmission, Markov Decision Process(MDP), Wireless communication network",

author = "Wenqi Yang and Yang Zhang and Jiangtian Nie and Helin Yang and Jiawen Kang and Zehui Xiong",

year = "2022",

month = jan,

day = "1",

doi = "10.19678/j.issn.1000-3428.0060825",

language = "Chinese (Traditional)",

volume = "48",

pages = "188–196,203",

journal = "Jisuanji Gongcheng/Computer Engineering",

issn = "1000-3428",

publisher = "Shanghai Jisuanji Xuehui/Shanghai Computer Society",

number = "1",

}

TY - JOUR

T1 - 基于联邦学习的无线网络节点能量与信息管理策略

AU - Yang, Wenqi

AU - Zhang, Yang

AU - Nie, Jiangtian

AU - Yang, Helin

AU - Kang, Jiawen

AU - Xiong, Zehui

PY - 2022/1/1

Y1 - 2022/1/1

N2 - 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.

AB - 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.

KW - Deep Reinforcement Learning(DRL)

KW - Energy management

KW - Federated learning

KW - Information transmission

KW - Markov Decision Process(MDP)

KW - Wireless communication network

U2 - 10.19678/j.issn.1000-3428.0060825

DO - 10.19678/j.issn.1000-3428.0060825

M3 - Article

AN - SCOPUS:85135928308

SN - 1000-3428

VL - 48

SP - 188–196,203

JO - Jisuanji Gongcheng/Computer Engineering

JF - Jisuanji Gongcheng/Computer Engineering

IS - 1

ER -

基于联邦学习的无线网络节点能量与信息管理策略

Abstract

Bibliographical note

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this