Network Anomaly Detector using Machine Learning
-
2018-07-20 https://doi.org/10.14419/ijet.v7i3.12.15914
-
syslogs, detector, predictor, random forest, supervised -
Abstract
The 4G network consists of a network of routers on each tower that decides where a certain packet must be switched to. These routers like any other hardware device is subject to failure due to number of factors such as threshold violations and problems with its tuning. The routers and other relevant hardware devices undergo various maintenance cycles that can sometimes be wasteful as the hardware may be replaced even when in complete working condition. This is a measure taken to ensure the network is always up and running. This measures has proven to be expensive and alternative solutions have been looked for. To alleviate the costs involved in the maintenance of these routers, a system will be developed to perform applications such as report failures, find the root cause and implement a remedial action automatically.The prediction of failures in the routers is achieved by unsupervised machine learning while will be trained to pick up anomalies from a continuous stream of log messages sent to system which is then analyzed. The anomaly data is then used to schedule maintenance runs more effectively.
Â
Â
-
References
[1] https://nishanthu.github.io/articles/ClusteringUsingRandomForest.html
[2] https://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm#intro
[3] https://mapr.com/ebooks/spark/08-unsupervised-anomaly-detection-apache-spark.html
[4] https://labs.genetics.ucla.edu/horvath/RFclustering/RFclustering.htm
[5] https://labs.genetics.ucla.edu/horvath/RFclustering/RFclustering/RandomForestHorvath.pdf
[6] http://pages.cs.wisc.edu/~matthewb/pages/notes/pdf/ensembles/RandomForests.pdf
-
Downloads
-
How to Cite
M. Uma Maheswari, K., Pranesh, A., & Govindarajan, S. (2018). Network Anomaly Detector using Machine Learning. International Journal of Engineering & Technology, 7(3.12), 178-179. https://doi.org/10.14419/ijet.v7i3.12.15914Received date: 2018-07-20
Accepted date: 2018-07-20
Published date: 2018-07-20