基于多智能体深度强化学习的分布式干扰协调

Tingting Liu; Yi'nan Luo; Chenyang Yang

doi:10.11959/j.issn.1000-436x.2020149

基于多智能体深度强化学习的分布式干扰协调

Translated title of the contribution: Distributed interference coordination based on multi-agent deep reinforcement learning

School of Electronic and Information Engineering

Beihang University

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

4 Scopus citations

Abstract

A distributed interference coordination strategy based on multi-agent deep reinforcement learning was investigated to meet the requirements of file downloading traffic in interfe-rence networks. By the proposed strategy transmission scheme could be adjusted adaptive-ly based on the interference environment and traffic requirements with limited amount of information exchanged among nodes. Simulation results show that the user satisfaction loss of the proposed strategy from the optimal strategy with perfect future information does not exceed 11% for arbitrary number of users and traffic requirements.

Translated title of the contribution	Distributed interference coordination based on multi-agent deep reinforcement learning
Original language	Chinese (Traditional)
Pages (from-to)	38-48
Number of pages	11
Journal	Tongxin Xuebao/Journal on Communications
Volume	41
Issue number	7
DOIs	https://doi.org/10.11959/j.issn.1000-436x.2020149
State	Published - 25 Jul 2020

Access to Document

10.11959/j.issn.1000-436x.2020149

Cite this

@article{d0296cacd6634cc9994d91f817b1a046,

title = "基于多智能体深度强化学习的分布式干扰协调",

abstract = "A distributed interference coordination strategy based on multi-agent deep reinforcement learning was investigated to meet the requirements of file downloading traffic in interfe-rence networks. By the proposed strategy transmission scheme could be adjusted adaptive-ly based on the interference environment and traffic requirements with limited amount of information exchanged among nodes. Simulation results show that the user satisfaction loss of the proposed strategy from the optimal strategy with perfect future information does not exceed 11\% for arbitrary number of users and traffic requirements.",

keywords = "Distributed in-terference coordination, Multi-agent deep reinforcement learning, Non-realtime traffic, Ultra-dense network",

author = "Tingting Liu and Yi'nan Luo and Chenyang Yang",

year = "2020",

month = jul,

day = "25",

doi = "10.11959/j.issn.1000-436x.2020149",

language = "繁体中文",

volume = "41",

pages = "38--48",

journal = "Tongxin Xuebao/Journal on Communications",

issn = "1000-436X",

publisher = "Editorial Board of Journal on Communications",

number = "7",

}

TY - JOUR

T1 - 基于多智能体深度强化学习的分布式干扰协调

AU - Liu, Tingting

AU - Luo, Yi'nan

AU - Yang, Chenyang

PY - 2020/7/25

Y1 - 2020/7/25

N2 - A distributed interference coordination strategy based on multi-agent deep reinforcement learning was investigated to meet the requirements of file downloading traffic in interfe-rence networks. By the proposed strategy transmission scheme could be adjusted adaptive-ly based on the interference environment and traffic requirements with limited amount of information exchanged among nodes. Simulation results show that the user satisfaction loss of the proposed strategy from the optimal strategy with perfect future information does not exceed 11% for arbitrary number of users and traffic requirements.

AB - A distributed interference coordination strategy based on multi-agent deep reinforcement learning was investigated to meet the requirements of file downloading traffic in interfe-rence networks. By the proposed strategy transmission scheme could be adjusted adaptive-ly based on the interference environment and traffic requirements with limited amount of information exchanged among nodes. Simulation results show that the user satisfaction loss of the proposed strategy from the optimal strategy with perfect future information does not exceed 11% for arbitrary number of users and traffic requirements.

KW - Distributed in-terference coordination

KW - Multi-agent deep reinforcement learning

KW - Non-realtime traffic

KW - Ultra-dense network

UR - https://www.scopus.com/pages/publications/85089287631

U2 - 10.11959/j.issn.1000-436x.2020149

DO - 10.11959/j.issn.1000-436x.2020149

M3 - 文章

AN - SCOPUS:85089287631

SN - 1000-436X

VL - 41

SP - 38

EP - 48

JO - Tongxin Xuebao/Journal on Communications

JF - Tongxin Xuebao/Journal on Communications

IS - 7

ER -

基于多智能体深度强化学习的分布式干扰协调

Abstract

Access to Document

Other files and links

Fingerprint

Cite this