Correlation-Based Cell Degradation Detection for Operational Fault Detection in Cellular Wireless Base-Stations

Asghar, Muhammad Zeeshan; Fehlmann, Richard; Ristaniemi, Tapani

doi:10.1007/978-3-319-04277-0_7

Cited by 12 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, correlation-based mechanisms have been considered applicable to this problem. In [ 20 ], the degradation was detected by the correlation between the indicators of an observed cell and a neighboring cell. In particular, this occurs when the correlation coefficient between the observed cell indicator and the neighboring healthy one drops below a certain threshold.…”

Section: Related Workmentioning

confidence: 99%

Transform-Based Multiresolution Decomposition for Degradation Detection in Cellular Networks

Fortes

Muñoz

Serrano

et al. 2020

Sensors

View full text Add to dashboard Cite

Anomaly detection in the performance of the huge number of elements that are part of cellular networks (base stations, core entities, and user equipment) is one of the most time consuming and key activities for supporting failure management procedures and ensuring the required performance of the telecommunication services. This activity originally relied on direct human inspection of cellular metrics (counters, key performance indicators, etc.). Currently, degradation detection procedures have experienced an evolution towards the use of automatic mechanisms of statistical analysis and machine learning. However, pre-existent solutions typically rely on the manual definition of the values to be considered abnormal or on large sets of labeled data, highly reducing their performance in the presence of long-term trends in the metrics or previously unknown patterns of degradation. In this field, the present work proposes a novel application of transform-based analysis, using wavelet transform, for the detection and study of network degradations. The proposed system is tested using cell-level metrics obtained from a real-world LTE cellular network, showing its capabilities to detect and characterize anomalies of different patterns and in the presence of varied temporal trends. This is performed without the need for manually establishing normality thresholds and taking advantage of wavelet transform capabilities to separate the metrics in multiple time-frequency components. Our results show how direct statistical analysis of these components allows for a successful detection of anomalies beyond the capabilities of detection of previous methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Transform-Based Multiresolution Decomposition for Degradation Detection in Cellular Networks

Fortes

Muñoz

Serrano

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…There has already been a lot of work done on the use of machine learning approaches in the cellular network domain [54][55][56][57][58][59]. In this section, we describe how SON and deep learning could play an important roles in jointly driving future cellular networks [60].…”

Section: Enabling 5g With Son and Deep Learningmentioning

confidence: 99%

Assessment of Deep Learning Methodology for Self-Organizing 5G Networks

et al. 2019

Self Cite

View full text Add to dashboard Cite

In this paper, we present an auto-encoder-based machine learning framework for self organizing networks (SON). Traditional machine learning approaches, for example, K Nearest Neighbor, lack the ability to be precisely predictive. Therefore, they can not be extended for sequential data in the true sense because they require a batch of data to be trained on. In this work, we explore artificial neural network-based approaches like the autoencoders (AE) and propose a framework. The proposed framework provides an advantage over traditional machine learning approaches in terms of accuracy and the capability to be extended with other methods. The paper provides an assessment of the application of autoencoders (AE) for cell outage detection. First, we briefly introduce deep learning (DL) and also shed light on why it is a promising technique to make self organizing networks intelligent, cognitive, and intuitive so that they behave as fully self-configured, self-optimized, and self-healed cellular networks. The concept of SON is then explained with applications of intrusion detection and mobility load balancing. Our empirical study presents a framework for cell outage detection based on an autoencoder using simulated data obtained from a SON simulator. Finally, we provide a comparative analysis of the proposed framework with the existing frameworks.

show abstract

“…Accessibility degradation prediction, which was the focus of this research, can be categorized under self-healing problems, especially detection issues. Several methods related to degradation detection have been proposed, including [5] and [6], which propose methods for implementation on cellular networks. In the first paper, a proactive approach of detecting degradation in cells is presented that utilizes the correlation between two cells as a means of identifying degraded cells and to reduce the possibility of false alarms.…”

Section: Related Research Workmentioning

confidence: 99%

“…3: Given initial state s o and its initial probability, the probability of being present in state s n after n steps can be calculated given step transition probability P ij in Eq. (5). This probability is a conditional pmf for transitions from state s i at time step n to state s j at time step (n + 1) for all i and j.…”

Section: Accessibility Key Performance Indicators (Kpis)mentioning

confidence: 99%

Accessibility Degradation Prediction on LTE/SAE Network Using Discrete Time Markov Chain (DTMC) Model

Hendrawan

2019

J. ICT Res. Appl.

View full text Add to dashboard Cite

In this paper, an algorithm for predicting accessibility performance on an LTE/SAE network based on relevant historical key performance indicator (KPI) data is proposed. Since there are three KPIs related to accessibility, each representing different segments, a method to map these three KPI values onto the status of accessibility performance is proposed. The network conditions are categorized as high, acceptable or low for each time interval of observation. The first state shows that the system is running optimally, while the second state shows that the system has deteriorated and needs full attention, and the third state indicates that the system has gone into degraded conditions that cannot be tolerated. After the state sequence has been obtained, a transition probability matrix can be derived, which can be used to predict future conditions using a DTMC model. The results obtained are system predictions in terms of probability values for each state for a specific future time. These prediction values are required for proactive health monitoring and fault management. Accessibility degradation prediction is then conducted by using measurement data derived from an eNodeB in the LTE network for a period of one month.

show abstract

Correlation-Based Cell Degradation Detection for Operational Fault Detection in Cellular Wireless Base-Stations

Cited by 12 publications

References 10 publications

Transform-Based Multiresolution Decomposition for Degradation Detection in Cellular Networks

Transform-Based Multiresolution Decomposition for Degradation Detection in Cellular Networks

Assessment of Deep Learning Methodology for Self-Organizing 5G Networks

Accessibility Degradation Prediction on LTE/SAE Network Using Discrete Time Markov Chain (DTMC) Model

Contact Info

Product

Resources

About