2021/01/17 by Dibakar Das, Das, Dibakar, Mohammad Fahad Imteyaz +5
Engineering · #Advanced Optical Network Technologies #Advanced Photonic Communication Systems #FOS: Computer and information sciences #Networking and Internet Architecture (cs.NI) #Optical Network Technologies
paper · pdf · doi:10.48550/arxiv.2101.06661
openalex publication_date 2021/01/17 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Failures in optical network backbone can lead to major disruption of internet\ndata traffic. Hence, minimizing such failures is of paramount importance for\nthe network operators. Even better, if the network failures can be predicted\nand preventive steps can be taken in advance to avoid any disruption in\ntraffic. Various data driven and machine learning techniques have been proposed\nin literature for failure prediction. Most of these techniques need real time\ndata from the networks and also need different monitors to measure key optical\nparameters. This means provision for failure prediction has to be available in\nnetwork nodes, e.g., routers and network management systems. However, sometimes\ndeployed networks do not have failure prediction built into their initial\ndesign but subsequently need arises for such mechanisms. For such systems,\nthere are two key challenges. Firstly, statistics of failure distribution,\ndata, etc., are not readily available. Secondly, major changes cannot be made\nto the network nodes which are already commercially deployed. This paper\nproposes a novel implementable non-intrusive failure prediction mechanism for\ndeployed network nodes using information from log files of those devices.\nNumerical results show that the mechanism has near perfect accuracy in\npredicting failures of individual network nodes.\n