Proactive failure detection learning generation patterns of large-scale network logs

Kimura, Toshikiro; Watanabe, Akio; Toyono, Tsuyoshi; Ishibashi, Keisuke

doi:10.1109/cnsm.2015.7367332

Cited by 62 publications

(44 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…White box models such as Bayesian networks [32,19,9,31,27] use the network dependency graph to pinpoint faulty components and black box Artificial Intelligence (AI) techniques can be applied to detect a faulty state [35,36,20]. The second phase is the recovery process.…”

Section: Fault Managementmentioning

confidence: 99%

LUMEN: A global fault management framework for network virtualization environments

Cherrared

Imadali

Fabre

et al. 2018

2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)

View full text Add to dashboard Cite

The advent of 5G and its ever increasing stringent requirements for bandwidth, latency, and quality of service pushes the boundaries of what is feasible with legacy Mobile Network Operators' technologies. Network Function Virtualization (NFV) is one promising attempt at solving some of those challenges that were widely adopted by the industry and the standardization bodies. At its essence, NFV is about running network functions as software workloads on commodity hardware to optimize deployment costs and simplify the life-cycle management of network functions. However, it introduces new fault management challenges including dynamic topology, multi-tenant fault isolation and data consistency and ambiguity; that we propose to define in this paper. To tackle those challenges, we extend the classical fault management process to the virtualized functions by introducing LUMEN: a Global Fault Management Framework. Our approach aims at providing the availability and reliability of the virtualized 5G end-to-end service chain. LUMEN includes the canonical steps of the fault management process and proposes a monitoring solution for all types of Network virtualization Environments. Our framework is based on open source solutions and could easily be integrated with other existing autonomic management models.

show abstract

Section: Fault Managementmentioning

confidence: 99%

LUMEN: A global fault management framework for network virtualization environments

Cherrared

Imadali

Fabre

et al. 2018

2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN)

View full text Add to dashboard Cite

show abstract

“…Zhang et al presented a log‐driven failure prediction system for complex IT systems, which automatically extracted features from IT system logs and enables earlier failure predictions through the LSTM approach on discovering the long‐range structure in history data. Kimura et al adopted a supervised machine learning technique to associate network failures with the network log data that appeared in the past using network trouble ticket data and developed an online template extraction method and a future extraction method that characterizes the abnormality of logs based on the generation patterns of logs. Kimura et al proposed a modeling and event extraction method on network log data using a tensor factorization approach.…”

Section: Related Workmentioning

confidence: 99%

“…Long short time memory (LSTM) is designed to improve storing and accessing information compared with classical RNNs by introducing a purpose‐built memory cell. Long short time memory has recently been successfully applied in a variety of sequence modeling tasks . Thus, we apply an LSTM‐based network to build the predictive maintenace model.…”

Section: Predictive Maintenance Modelmentioning

confidence: 99%

A feature extraction method for predictive maintenance with time‐lagged correlation–based curve‐registration model

Zhang

Liu

et al. 2018

Int J Network Mgmt

View full text Add to dashboard Cite

With the prevalent development and use of predictive maintenance models for Internet‐of‐Things scenarios, the deep learning technology is gaining momentum. Feature extraction helps to increase efficiency in training the deep‐learning–based predictive maintenance model. However, there are common situations of time‐lagged correlations among industrial sensor data, resulting in reduction the effect of feature extraction. In this paper, we propose a feature extraction method for multisensors data with time‐lagged correlation. A curve‐registration method of correlation maximization algorithm is used to solve the problem of time‐lagged correlation for multi sensors. Then we apply a recurrent neural network, namely, long short‐term memory to develop a lightweight predictive maintenance model with the help of proposed feature extraction method. The effectiveness of the proposed feature extraction approach is demonstrated by examining real cases in a power plant. The experimental results indicate that our method can (1) effectively improve the accuracy of prediction and (2) improve the performance of the prediction model.

show abstract

“…However, this paper only deals with linear clustering and the entire process is not automated. "Proactive Failure Detection Learning Generation Patterns of Large-scale Network Logs" [4] deals with concepts like Feature Extraction, Log Template. The algorithm used automatically learns the relationship between critical failures and log messages without using any previous knowledge.…”

Section: Literature Surveymentioning

confidence: 99%

Prediction Framework for Fault Resolution in Networks

Sushma¹

2017

IJRASET

View full text Add to dashboard Cite

The continued increase in the size and complexity of modern networks has led to a commensurate increase in the size of their logs. To ensure high availability and correct operation of networks, it is essential that failures be detected promptly and quickly, their causes have to be diagnosed and remedial actions taken. Router logs are an invaluable resource to systems administrators during fault resolution. A lot of time spent in fault resolution is in sifting through large volumes of information, which includes router logs, to find the root cause of the problem. Therefore, the ability to analyse log files automatically and accurately will lead to significant savings in the time and cost of downtime events for any organization. The automatic search, analysis and prediction of errors using router logs is the primary motivation for the work carried out in this project. Different supervised machine learning techniques are compared and it is shown that a prediction model framework using RandomForest Algorithm can be used for automated fault detection as it has more accuracy and efficiency.

show abstract

Proactive failure detection learning generation patterns of large-scale network logs

Cited by 62 publications

References 11 publications

LUMEN: A global fault management framework for network virtualization environments

LUMEN: A global fault management framework for network virtualization environments

A feature extraction method for predictive maintenance with time‐lagged correlation–based curve‐registration model

Prediction Framework for Fault Resolution in Networks

Contact Info

Product

Resources

About