Class imbalance learning for network fault prediction

The quality of internet connection is important in our daily life as people are becoming more dependent on it. To reduce internet connection problems, internet service providers (ISP) are proactively predicting and identifying network faults before it occurs. One of the network fault prediction meth...

Full description

Saved in:

Bibliographic Details
Main Author:	Kok, Leonard Jin Yin
Format:	Thesis
Published:	2020
Subjects:	TK5101-6720 Telecommunication Including telegraphy, telephone, radio, radar, television
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-mmu-ep.11103
record_format	uketd_dc
spelling	my-mmu-ep.111032023-04-17T08:22:28Z Class imbalance learning for network fault prediction 2020-12 Kok, Leonard Jin Yin TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television The quality of internet connection is important in our daily life as people are becoming more dependent on it. To reduce internet connection problems, internet service providers (ISP) are proactively predicting and identifying network faults before it occurs. One of the network fault prediction methods is by classifying incoming network data from Remote Authentication Dial-In User Service (RADIUS) server. Although RADIUS data provide useful accounting information such as total download, cause of termination, etc., it does not provide any indication whether the network is faulty or not. A customer trouble ticket (CTT) is often raised by network user when he/she faces an internet connection problem. In this thesis, a method is proposed to annotate network data by correlating RADIUS data and CTT using temporal interval relations. Once RADIUS data are labelled, a network fault prediction model can be trained. However, performance of the prediction model is greatly affected by class imbalance problem, where the number of faulty cases is relatively rare. One of the challenges in addressing class imbalance problems for network fault prediction is the overlapping between faulty and non-faulty classes, which mainly due to unreported network issues. This thesis proposes a method based on edited nearest neighbours (ENN), Tomek-link and SMOTE to address the class overlapping and class imbalance problems. The findings showed that RADIUS data annotated with our method achieved a higher recall and precision rate. The F1-score and AUC results showed that our proposed method has greatly improved class imbalance learning for network fault prediction. 2020-12 Thesis http://shdl.mmu.edu.my/11103/ http://erep.mmu.edu.my/ masters Multimedia University Faculty of Management EREP ID: 10280
institution	Multimedia University
collection	MMU Institutional Repository
topic	TK5101-6720 Telecommunication Including telegraphy, telephone, radio, radar, television
spellingShingle	TK5101-6720 Telecommunication Including telegraphy, telephone, radio, radar, television Kok, Leonard Jin Yin Class imbalance learning for network fault prediction
description	The quality of internet connection is important in our daily life as people are becoming more dependent on it. To reduce internet connection problems, internet service providers (ISP) are proactively predicting and identifying network faults before it occurs. One of the network fault prediction methods is by classifying incoming network data from Remote Authentication Dial-In User Service (RADIUS) server. Although RADIUS data provide useful accounting information such as total download, cause of termination, etc., it does not provide any indication whether the network is faulty or not. A customer trouble ticket (CTT) is often raised by network user when he/she faces an internet connection problem. In this thesis, a method is proposed to annotate network data by correlating RADIUS data and CTT using temporal interval relations. Once RADIUS data are labelled, a network fault prediction model can be trained. However, performance of the prediction model is greatly affected by class imbalance problem, where the number of faulty cases is relatively rare. One of the challenges in addressing class imbalance problems for network fault prediction is the overlapping between faulty and non-faulty classes, which mainly due to unreported network issues. This thesis proposes a method based on edited nearest neighbours (ENN), Tomek-link and SMOTE to address the class overlapping and class imbalance problems. The findings showed that RADIUS data annotated with our method achieved a higher recall and precision rate. The F1-score and AUC results showed that our proposed method has greatly improved class imbalance learning for network fault prediction.
format	Thesis
qualification_level	Master's degree
author	Kok, Leonard Jin Yin
author_facet	Kok, Leonard Jin Yin
author_sort	Kok, Leonard Jin Yin
title	Class imbalance learning for network fault prediction
title_short	Class imbalance learning for network fault prediction
title_full	Class imbalance learning for network fault prediction
title_fullStr	Class imbalance learning for network fault prediction
title_full_unstemmed	Class imbalance learning for network fault prediction
title_sort	class imbalance learning for network fault prediction
granting_institution	Multimedia University
granting_department	Faculty of Management
publishDate	2020
_version_	1776101395965935616

Class imbalance learning for network fault prediction

Similar Items