TY - JOUR
T1 - A Novel Framework for Optical Layer Device Board Failure Localization in Optical Transport Network
AU - Jiao, Yan
AU - Ho, Pin Han
AU - Lu, Xiangzhu
AU - Tapolcai, Janos
AU - Peng, Limei
N1 - Publisher Copyright:
© 2004-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - This paper presents a novel framework called Failure-Alarm Correlation Tree based Failure Localization (FACT-FL), designed to localize failed optical layer device boards in an Optical Transport Network (OTN). Specifically, FACT-FL aims to construct a set of FACTs by correlating the failed boards and alarms, where each FACT takes one failed board and its correlated alarms as the root and leaves, respectively. Furthermore, a FACT consists of a suite of kth order Failure-Alarm Correlation Chains (k-FACCs) with different order values of k. Each k-FACC indicates the chain-like correlation established by k alarms due to one common failed board. To identify all previously undetected k-FACCs, a set of binary classifiers is trained that characterizes each k-FACC from various dimensions, including time, network topology, traffic distribution, and board/alarm attributes. Eventually, an integer linear programming (ILP) problem is formulated to extract the most likely FACT(s) from those k-FACCs. Extensive case studies demonstrate the superior results of FACT-FL in terms of metrics evaluating the identified failed boards and root alarms. We also analyze its performance under different maximum order values of k and environmental changes, including failure scenarios, network topologies, traffic distributions, and noise alarms.
AB - This paper presents a novel framework called Failure-Alarm Correlation Tree based Failure Localization (FACT-FL), designed to localize failed optical layer device boards in an Optical Transport Network (OTN). Specifically, FACT-FL aims to construct a set of FACTs by correlating the failed boards and alarms, where each FACT takes one failed board and its correlated alarms as the root and leaves, respectively. Furthermore, a FACT consists of a suite of kth order Failure-Alarm Correlation Chains (k-FACCs) with different order values of k. Each k-FACC indicates the chain-like correlation established by k alarms due to one common failed board. To identify all previously undetected k-FACCs, a set of binary classifiers is trained that characterizes each k-FACC from various dimensions, including time, network topology, traffic distribution, and board/alarm attributes. Eventually, an integer linear programming (ILP) problem is formulated to extract the most likely FACT(s) from those k-FACCs. Extensive case studies demonstrate the superior results of FACT-FL in terms of metrics evaluating the identified failed boards and root alarms. We also analyze its performance under different maximum order values of k and environmental changes, including failure scenarios, network topologies, traffic distributions, and noise alarms.
KW - Optical transport network (OTN)
KW - alarm correlation
KW - failure localization
KW - integer linear programming (ILP)
UR - http://www.scopus.com/inward/record.url?scp=85194817293&partnerID=8YFLogxK
U2 - 10.1109/TNSM.2024.3405901
DO - 10.1109/TNSM.2024.3405901
M3 - Article
AN - SCOPUS:85194817293
SN - 1932-4537
VL - 21
SP - 5374
EP - 5383
JO - IEEE Transactions on Network and Service Management
JF - IEEE Transactions on Network and Service Management
IS - 5
ER -