Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Machine learning based call drop healing in 5G

Mudaliyar, Janani Ramaswamy LU (2020) EITM02 20201
Department of Electrical and Information Technology
Abstract
Self-Organizing Network (SON) functions include self-configuration, dynamic optimization and self-healing of networks. In the era of 5G, mobile operators are increasingly exploring areas of SON through Machine Learning (ML) techniques. It is seen that 5G packet switched networks are often hit with radio link failures, an important Key Performance Indicator (KPI). Reasons for a dropped call ranges from a failed handover to coverage/capacity issues. In current networks, such issues are resolved by KPI analysis, but these metrics are not always service/user specific. The aim with this master’s thesis work is to investigate how well ML techniques can be applied to predict a call drop in real-time networks.
In the thesis, ML techniques, namely... (More)
Self-Organizing Network (SON) functions include self-configuration, dynamic optimization and self-healing of networks. In the era of 5G, mobile operators are increasingly exploring areas of SON through Machine Learning (ML) techniques. It is seen that 5G packet switched networks are often hit with radio link failures, an important Key Performance Indicator (KPI). Reasons for a dropped call ranges from a failed handover to coverage/capacity issues. In current networks, such issues are resolved by KPI analysis, but these metrics are not always service/user specific. The aim with this master’s thesis work is to investigate how well ML techniques can be applied to predict a call drop in real-time networks.
In the thesis, ML techniques, namely neural networks and logistic regression were used to classify the link status. Initially, the parameters which characterize a link connection, e.g. the Reference Signal Received Power (RSRP), Block Error Rate (BLER) and similar parameters were investigated. This was followed by applying ML to the selected parameter(s) and classifying a bad link (with failure) from a good link (without failure), this was the first phase of the thesis. The next phase was forecasting a radio link failure before one occurs. This forms phase two of the thesis and the start of the self heal process where, counter measures could be taken to avoid a radio link failure. Counter measures for self-healing was not covered in the thesis. This thesis only focuses on phase one and two of predicting a radio link failure. (Less)
Popular Abstract
Today with the increasing use of cellular networks, there’s an expected sharp increase in network traffic. An interesting fact is that phone calls are getting longer. Call drops i.e. calls that are ”dropped” (terminated) without any of the parties intentionally interrupting the calls are commonly experienced in networks. Avoiding call drops helps improve quality of service. Self organized network is a technology which helps simplify complex networks and ensures better service. Machine learning plays a key role in it. With human limitations in place, machine learning, a subset of artificial intelligence helps to visualize behaviours and see patterns beyond human recognition.
In the thesis, machine learning approaches are used to predict a... (More)
Today with the increasing use of cellular networks, there’s an expected sharp increase in network traffic. An interesting fact is that phone calls are getting longer. Call drops i.e. calls that are ”dropped” (terminated) without any of the parties intentionally interrupting the calls are commonly experienced in networks. Avoiding call drops helps improve quality of service. Self organized network is a technology which helps simplify complex networks and ensures better service. Machine learning plays a key role in it. With human limitations in place, machine learning, a subset of artificial intelligence helps to visualize behaviours and see patterns beyond human recognition.
In the thesis, machine learning approaches are used to predict a radio link failure. A network may transfer (hand over), a user connection from the current cell to another cell, so that the user terminal will experience higher signal strength. This process is called a handover and an interruption here causes radio link failure. So it is important to minimize radio link failure in cellular networks for a better user experience. Deteriorating signal strength is one of the key indicators investigated in the thesis in determining a radio link failure. Real time data from live networks may seem unpredictable but machine learning approaches discussed in this thesis helps predict whether a connection would experience a link failure or not. There are a number of parameters causing a link failure, these parameters are inputs to the machine learning models and the result is a classified output which is - link failure or not. This thesis also involves a time series analysis which helps forecast a radio link failure much ahead of time. If a failure is forecast, it is possible to take counter action and prevent the same, this forms parts of the self healing process. This thesis mainly focuses on the classification and forecast of a radio link failure. (Less)
Please use this url to cite or link to this publication:
author
Mudaliyar, Janani Ramaswamy LU
supervisor
organization
course
EITM02 20201
year
type
H2 - Master's Degree (Two Years)
subject
report number
LU/LTH-EIT 2020-796
language
English
id
9032141
date added to LUP
2020-11-24 16:05:25
date last changed
2020-11-26 11:26:59
@misc{9032141,
  abstract     = {{Self-Organizing Network (SON) functions include self-configuration, dynamic optimization and self-healing of networks. In the era of 5G, mobile operators are increasingly exploring areas of SON through Machine Learning (ML) techniques. It is seen that 5G packet switched networks are often hit with radio link failures, an important Key Performance Indicator (KPI). Reasons for a dropped call ranges from a failed handover to coverage/capacity issues. In current networks, such issues are resolved by KPI analysis, but these metrics are not always service/user specific. The aim with this master’s thesis work is to investigate how well ML techniques can be applied to predict a call drop in real-time networks.
In the thesis, ML techniques, namely neural networks and logistic regression were used to classify the link status. Initially, the parameters which characterize a link connection, e.g. the Reference Signal Received Power (RSRP), Block Error Rate (BLER) and similar parameters were investigated. This was followed by applying ML to the selected parameter(s) and classifying a bad link (with failure) from a good link (without failure), this was the first phase of the thesis. The next phase was forecasting a radio link failure before one occurs. This forms phase two of the thesis and the start of the self heal process where, counter measures could be taken to avoid a radio link failure. Counter measures for self-healing was not covered in the thesis. This thesis only focuses on phase one and two of predicting a radio link failure.}},
  author       = {{Mudaliyar, Janani Ramaswamy}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Machine learning based call drop healing in 5G}},
  year         = {{2020}},
}