TY - JOUR
T1 - Fault management in software-defined networking
T2 - A survey
AU - Yu, Yinbo
AU - Li, Xing
AU - Leng, Xue
AU - Song, Libin
AU - Bu, Kai
AU - Chen, Yan
AU - Yang, Jianfeng
AU - Zhang, Liang
AU - Cheng, Kang
AU - Xiao, Xin
N1 - Funding Information:
Manuscript received October 9, 2017; revised March 22, 2018 and July 1, 2018; accepted September 1, 2018. Date of publication September 6, 2018; date of current version February 22, 2019. This work was supported in part by the National Key Research and Development Program of China under Grant 2016YFC0106301, in part by the Huawei HARP under Grant HO2016050002CH, and in part by the Provincial Science and Technology Pillar Program of Hubei under Grant 2017AAA027, Grant 2017AAA042, and Grant 2017AHB048. (Corresponding author: Jianfeng Yang.) Y. Yu and J. Yang are with the School of Electronic Information, Wuhan University, Wuhan 430072, China (e-mail: yyb@whu.edu.cn; yjf@whu.edu.cn).
Publisher Copyright:
© 2018 IEEE.
PY - 2019/1/1
Y1 - 2019/1/1
N2 - Software-defined networking (SDN) has emerged as a new network paradigm that promises control/data plane separation and centralized network control. While these features simplify network management and enable innovative networking, they give rise to persistent concerns about reliability. The new paradigm suffers from the disadvantage that various network faults may consistently undermine the reliability of such a network, and such faults are often new and difficult to resolve with existing solutions. To ensure SDN reliability, fault management, which is concerned with detecting, localizing, correcting and preventing faults, has become a key component in SDN networks. Although many SDN fault management solutions have been proposed, we find that they often resolve SDN faults from an incomplete perspective which may result in side effects. More critically, as the SDN paradigm evolves, additional fault types are being exposed. Therefore, comprehensive reviews and constant improvements are required to remain on the leading edge of SDN fault management. In this paper, we present the first comprehensive and systematic survey of SDN faults and related management solutions identified through advancements in both the research community and industry. We apply a systematic classification of SDN faults, compare and analyze existing SDN fault management solutions in the literature, and conduct a gap analysis between solutions developed in an academic research context and practical deployments. The current challenges and emerging trends are also noted as potential future research directions. This paper aims to provide academic researchers and industrial engineers with a comprehensive survey with the hope of advancing SDN and inspiring new solutions.
AB - Software-defined networking (SDN) has emerged as a new network paradigm that promises control/data plane separation and centralized network control. While these features simplify network management and enable innovative networking, they give rise to persistent concerns about reliability. The new paradigm suffers from the disadvantage that various network faults may consistently undermine the reliability of such a network, and such faults are often new and difficult to resolve with existing solutions. To ensure SDN reliability, fault management, which is concerned with detecting, localizing, correcting and preventing faults, has become a key component in SDN networks. Although many SDN fault management solutions have been proposed, we find that they often resolve SDN faults from an incomplete perspective which may result in side effects. More critically, as the SDN paradigm evolves, additional fault types are being exposed. Therefore, comprehensive reviews and constant improvements are required to remain on the leading edge of SDN fault management. In this paper, we present the first comprehensive and systematic survey of SDN faults and related management solutions identified through advancements in both the research community and industry. We apply a systematic classification of SDN faults, compare and analyze existing SDN fault management solutions in the literature, and conduct a gap analysis between solutions developed in an academic research context and practical deployments. The current challenges and emerging trends are also noted as potential future research directions. This paper aims to provide academic researchers and industrial engineers with a comprehensive survey with the hope of advancing SDN and inspiring new solutions.
KW - Fault classification
KW - Fault diagnosis
KW - Fault recovery and repair
KW - Fault tolerance
KW - SDN faults
KW - SDN reliability
KW - Software-defined networking (SDN)
KW - System monitoring
UR - http://www.scopus.com/inward/record.url?scp=85052851954&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85052851954&partnerID=8YFLogxK
U2 - 10.1109/COMST.2018.2868922
DO - 10.1109/COMST.2018.2868922
M3 - Review article
AN - SCOPUS:85052851954
SN - 1553-877X
VL - 21
SP - 349
EP - 392
JO - IEEE Communications Surveys and Tutorials
JF - IEEE Communications Surveys and Tutorials
IS - 1
M1 - 8456508
ER -