CFP last date
22 April 2024
Reseach Article

Long Term Evolution Anomaly Detection and Root Cause Analysis for Data Throughput Optimization

by Simon Mbogo, Evans Miriti
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 175 - Number 35
Year of Publication: 2020
Authors: Simon Mbogo, Evans Miriti
10.5120/ijca2020920907

Simon Mbogo, Evans Miriti . Long Term Evolution Anomaly Detection and Root Cause Analysis for Data Throughput Optimization. International Journal of Computer Applications. 175, 35 ( Dec 2020), 27-32. DOI=10.5120/ijca2020920907

@article{ 10.5120/ijca2020920907,
author = { Simon Mbogo, Evans Miriti },
title = { Long Term Evolution Anomaly Detection and Root Cause Analysis for Data Throughput Optimization },
journal = { International Journal of Computer Applications },
issue_date = { Dec 2020 },
volume = { 175 },
number = { 35 },
month = { Dec },
year = { 2020 },
issn = { 0975-8887 },
pages = { 27-32 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume175/number35/31678-2020920907/ },
doi = { 10.5120/ijca2020920907 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:40:22.088516+05:30
%A Simon Mbogo
%A Evans Miriti
%T Long Term Evolution Anomaly Detection and Root Cause Analysis for Data Throughput Optimization
%J International Journal of Computer Applications
%@ 0975-8887
%V 175
%N 35
%P 27-32
%D 2020
%I Foundation of Computer Science (FCS), NY, USA
Abstract

There is a growing demand for mobile network data services which is driven by high number of smartphones and web content search as multimedia. Network operators have tried to provide enough capacity and meet the data speeds that the customer needs. This has led to introduction of new technology and expansion of the mobile networks making them complex to manage. Detecting anomalies that affect data throughput and investigating the root causes in mobile networks is challenging as mobile environments are increasingly complex, heterogeneous, and evolving. There is need to automate network management activities to improve network management processes and prevent revenue loss. Self-Organizing network is a standard introduced by third Generation Partnership Program (3GPP) to automate network management. However, the standard is still not fully developed. This project focused on implementing an anomaly detection and root cause analysis model that helps in the process of data throughput optimization in Long-term evolution (LTE) networks. The model used Density Based Spatial Clustering of Applications with Noise (DBSCAN) for anomaly detection, K-Nearest Neighbour (KNN) for root cause analysis and real network performance data from a Kenyan operator. Proposed anomaly detection model achieved a silhouette coefficient of 0.451 showing a good separation of existing clusters in the dataset and was able to detect anomalies with both positive and negative impact on data throughput. The root cause analysis model achieved an accuracy of 94.59% and was able to identify the root cause of detected anomalies that had a negative impact on data throughput.

References
  1. Zhang, T., Zhu, K., & Hossain, E. (2019). Data-Driven Machine Learning Techniques for Self-healing in Cellular Wireless Networks: Challenges and Solutions. Retrieved from https://arxiv.org
  2. Kostas, K. (2018). Anomaly Detection in Networks Using Machine Learning. Retrieved from https://www.researchgate.net
  3. Alvarez, S. L. (2018). Anomaly Detection and Root Cause Analysis for LTE Radio Base Stations. Retrieved from https://pdfs.semanticscholar.org.
  4. Andrades, G., Muñoz, P., Serrano, I., & Barco R, (2016). Automatic root cause analysis for LTE networks based on unsupervised techniques. Retrieved from https://www.researchgate.net
  5. Mobolize. (2014). Can Mobile Networks Keep Up with Data Demand? Retrieved from https://www.mobolize.com/2014/09/30/can-mobile-networks-keep-up-with-demand/
  6. Duan, H., Wei, Y., Liu, P. & Yin, H. (2019). A Novel Ensemble Framework Based on K-Means and Resampling for Imbalanced Data. Retrieved from https://doi.org/10.3390/app10051684
  7. Josefsson, T. (2017). Root-cause analysis through machine learning in the cloud. Retrieved from http://www.diva-portal.org.
  8. Wang, Y., Zhu, K., Sun, M., & Deng, Y. (2019). An Ensemble Learning Approach for Fault Diagnosis in Self-Organizing Heterogeneous Networks. Retrieved from https://ieeexplore.ieee.org
Index Terms

Computer Science
Information Sciences

Keywords

Density based spatial clustering of applications with noises (DBSCAN) K-Nearest neighbour (KNN) Long-term evolution (LTE) throughput