Mobility Robustness Optimization for Self-Organizing Networks: A Deep Reinforcement Learning Approach

Kihoon Kim; Eunsok Lee; Sangheon Pack

doi:10.1109/ICTC58733.2023.10393337

Mobility Robustness Optimization for Self-Organizing Networks: A Deep Reinforcement Learning Approach

Kihoon Kim, Eunsok Lee, Sangheon Pack

School of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Self-organizing network (SON) has emerged as a promising solution to manage dynamic and complex wireless/mobile networks without excessive manual intervention. As a key function of SON, mobility robustness optimization (MRO) aims to prevent radio link failure (RLF) for user equipment (UE) by adjusting handover-related parameters. Although there are several existing studies on MRO, previous studies have limitations in coping with various UE mobility patterns. Additionally, since parameter adjustments are performed on a per-cell basis, detailed adjustments based on individual UE situations become unfeasible. To overcome these limitations, we propose a deep reinforcement learning (DRL)-based MRO scheme where parameter adjustment sets are evaluated by a multi-agent double deep Q-network (MA-DDQN). Evaluation results demonstrate that the proposed DRL-based MRO scheme can reduce RLFs by up to 45. 7% compared to other MRO schemes and completely prevent handover ping-pong events.

Original language	English
Title of host publication	ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence
Subtitle of host publication	Exploring the Frontiers of ICT Innovation
Publisher	IEEE Computer Society
Pages	511-513
Number of pages	3
ISBN (Electronic)	9798350313277
DOIs	https://doi.org/10.1109/ICTC58733.2023.10393337
Publication status	Published - 2023
Event	14th International Conference on Information and Communication Technology Convergence, ICTC 2023 - Jeju Island, Korea, Republic of Duration: 2023 Oct 11 → 2023 Oct 13

Publication series

Name	International Conference on ICT Convergence
ISSN (Print)	2162-1233
ISSN (Electronic)	2162-1241

Conference

Conference	14th International Conference on Information and Communication Technology Convergence, ICTC 2023
Country/Territory	Korea, Republic of
City	Jeju Island
Period	23/10/11 → 23/10/13

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Deep Reinforcement Learning
Handover Ping-Pong
Mobility Robustness Optimization
Radio Link Failure
Self-Organizing Networks

ASJC Scopus subject areas

Information Systems
Computer Networks and Communications

Access to Document

10.1109/ICTC58733.2023.10393337

Cite this

Kim, K., Lee, E., & Pack, S. (2023). Mobility Robustness Optimization for Self-Organizing Networks: A Deep Reinforcement Learning Approach. In ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation (pp. 511-513). (International Conference on ICT Convergence). IEEE Computer Society. https://doi.org/10.1109/ICTC58733.2023.10393337

Mobility Robustness Optimization for Self-Organizing Networks: A Deep Reinforcement Learning Approach. / Kim, Kihoon; Lee, Eunsok; Pack, Sangheon.
ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation. IEEE Computer Society, 2023. p. 511-513 (International Conference on ICT Convergence).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kim, K, Lee, E & Pack, S 2023, Mobility Robustness Optimization for Self-Organizing Networks: A Deep Reinforcement Learning Approach. in ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation. International Conference on ICT Convergence, IEEE Computer Society, pp. 511-513, 14th International Conference on Information and Communication Technology Convergence, ICTC 2023, Jeju Island, Korea, Republic of, 23/10/11. https://doi.org/10.1109/ICTC58733.2023.10393337

Kim K, Lee E, Pack S. Mobility Robustness Optimization for Self-Organizing Networks: A Deep Reinforcement Learning Approach. In ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation. IEEE Computer Society. 2023. p. 511-513. (International Conference on ICT Convergence). doi: 10.1109/ICTC58733.2023.10393337

Kim, Kihoon ; Lee, Eunsok ; Pack, Sangheon. / Mobility Robustness Optimization for Self-Organizing Networks : A Deep Reinforcement Learning Approach. ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation. IEEE Computer Society, 2023. pp. 511-513 (International Conference on ICT Convergence).

@inproceedings{6ecf7bbcec0c4109a6f737ce1c1f216e,

title = "Mobility Robustness Optimization for Self-Organizing Networks: A Deep Reinforcement Learning Approach",

abstract = "Self-organizing network (SON) has emerged as a promising solution to manage dynamic and complex wireless/mobile networks without excessive manual intervention. As a key function of SON, mobility robustness optimization (MRO) aims to prevent radio link failure (RLF) for user equipment (UE) by adjusting handover-related parameters. Although there are several existing studies on MRO, previous studies have limitations in coping with various UE mobility patterns. Additionally, since parameter adjustments are performed on a per-cell basis, detailed adjustments based on individual UE situations become unfeasible. To overcome these limitations, we propose a deep reinforcement learning (DRL)-based MRO scheme where parameter adjustment sets are evaluated by a multi-agent double deep Q-network (MA-DDQN). Evaluation results demonstrate that the proposed DRL-based MRO scheme can reduce RLFs by up to 45. 7% compared to other MRO schemes and completely prevent handover ping-pong events.",

keywords = "Deep Reinforcement Learning, Handover Ping-Pong, Mobility Robustness Optimization, Radio Link Failure, Self-Organizing Networks",

author = "Kihoon Kim and Eunsok Lee and Sangheon Pack",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 14th International Conference on Information and Communication Technology Convergence, ICTC 2023 ; Conference date: 11-10-2023 Through 13-10-2023",

year = "2023",

doi = "10.1109/ICTC58733.2023.10393337",

language = "English",

series = "International Conference on ICT Convergence",

publisher = "IEEE Computer Society",

pages = "511--513",

booktitle = "ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence",

}

TY - GEN

T1 - Mobility Robustness Optimization for Self-Organizing Networks

T2 - 14th International Conference on Information and Communication Technology Convergence, ICTC 2023

AU - Kim, Kihoon

AU - Lee, Eunsok

AU - Pack, Sangheon

PY - 2023

Y1 - 2023

N2 - Self-organizing network (SON) has emerged as a promising solution to manage dynamic and complex wireless/mobile networks without excessive manual intervention. As a key function of SON, mobility robustness optimization (MRO) aims to prevent radio link failure (RLF) for user equipment (UE) by adjusting handover-related parameters. Although there are several existing studies on MRO, previous studies have limitations in coping with various UE mobility patterns. Additionally, since parameter adjustments are performed on a per-cell basis, detailed adjustments based on individual UE situations become unfeasible. To overcome these limitations, we propose a deep reinforcement learning (DRL)-based MRO scheme where parameter adjustment sets are evaluated by a multi-agent double deep Q-network (MA-DDQN). Evaluation results demonstrate that the proposed DRL-based MRO scheme can reduce RLFs by up to 45. 7% compared to other MRO schemes and completely prevent handover ping-pong events.

AB - Self-organizing network (SON) has emerged as a promising solution to manage dynamic and complex wireless/mobile networks without excessive manual intervention. As a key function of SON, mobility robustness optimization (MRO) aims to prevent radio link failure (RLF) for user equipment (UE) by adjusting handover-related parameters. Although there are several existing studies on MRO, previous studies have limitations in coping with various UE mobility patterns. Additionally, since parameter adjustments are performed on a per-cell basis, detailed adjustments based on individual UE situations become unfeasible. To overcome these limitations, we propose a deep reinforcement learning (DRL)-based MRO scheme where parameter adjustment sets are evaluated by a multi-agent double deep Q-network (MA-DDQN). Evaluation results demonstrate that the proposed DRL-based MRO scheme can reduce RLFs by up to 45. 7% compared to other MRO schemes and completely prevent handover ping-pong events.

KW - Deep Reinforcement Learning

KW - Handover Ping-Pong

KW - Mobility Robustness Optimization

KW - Radio Link Failure

KW - Self-Organizing Networks

UR - http://www.scopus.com/inward/record.url?scp=85184574471&partnerID=8YFLogxK

U2 - 10.1109/ICTC58733.2023.10393337

DO - 10.1109/ICTC58733.2023.10393337

M3 - Conference contribution

AN - SCOPUS:85184574471

T3 - International Conference on ICT Convergence

SP - 511

EP - 513

BT - ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence

PB - IEEE Computer Society

Y2 - 11 October 2023 through 13 October 2023

ER -

Mobility Robustness Optimization for Self-Organizing Networks: A Deep Reinforcement Learning Approach

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this