CellPAD: Detecting Performance Anomalies in Cellular Networks via Regression Analysis

Wu, Jun; Lee, Patrick P. C.; Li, Qi; Pan, Lujia; Zhang, Jianfeng

doi:10.23919/ifipnetworking.2018.8697027

Cited by 33 publications

(20 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following a network trouble, the engineers identified 80 cells with an unusually high number of anomalies in 15 key business related KPIs which were chosen in accordance with the network experts’ directives ( Table 1 ). These cells had a mean of 12% anomalous samples, whereas mobile networks have a mean of about 3–4% anomalous samples in real-world scenarios [ 7 ]. In this way, 300 more cells have been labeled until the mean of anomalous samples from all labeled cells was consistent with this data.…”

Section: Evaluation Methodologymentioning

confidence: 99%

“…Due to the lack of anomalies labeled by network experts, most studies add synthetic anomalies in one of these two stages. In this sense, the authors of [ 7 ] proposed a system trained with synthetic anomalies, based on regression analysis. Multiple correlated KPIs are needed to detect anomalies, so this technique cannot be applied to different KPIs separately.…”

Section: Related Workmentioning

confidence: 99%

“…However, historical data are usually not labeled, excluding those cases of interest that have been studied and analyzed in depth by the operator. Therefore, a large proportion of published studies add synthetic anomalies to obtain datasets with classified samples [ 7 , 8 ]. Nonetheless, these fictitious anomalies do not faithfully coincide with the real cases.…”

Section: Introductionmentioning

confidence: 99%

“…This is even more challenging for high-cost computing techniques [ 13 ]. To reduce computational costs, some approaches decide whether a cell is anomalous or not based on a combination of a reduced set of KPIs [ 7 , 14 ]. However, they do not differentiate between KPIs that function normally and those that do not.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Online Anomaly Detection System for Mobile Networks

Burgueño

de-la-Bandera

Mendoza

et al. 2020

Sensors

View full text Add to dashboard Cite

The arrival of the fifth generation (5G) standard has further accelerated the need for operators to improve the network capacity. With this purpose, mobile network topologies with smaller cells are currently being deployed to increase the frequency reuse. In this way, the number of nodes that collect performance data is being further risen, so the number of metrics to be managed and analyzed is being highly increased. Therefore, it is fundamental to have tools that automatically inform the network operator of the relevant information within the vast amount of metrics collected. The continuous monitoring of the performance indicators and the automatic detection of anomalies is especially important for network operators to prevent the network degradation and user complaints. Therefore, this paper proposes a methodology to detect and track anomalies in the mobile networks performance indicators online, i.e., in real time. The feasibility of this system was evaluated with several performance metrics and a real LTE Advanced dataset. In addition, it was also compared with the performances of other state-of-the-art anomaly detection systems.

show abstract

Section: Evaluation Methodologymentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Online Anomaly Detection System for Mobile Networks

Burgueño

de-la-Bandera

Mendoza

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The high similarity of network performance data at the corresponding time of day has been described in [11]. In order to describe the strong seasonality of performance of NEs, we define the period T = 24×60 ∆ .…”

Section: A Relationship Modelingmentioning

confidence: 99%

A Factorization Machine-Based Approach to Predict Performance Under Different Parameters in Cellular Networks

2020

View full text Add to dashboard Cite

The performance of network elements depends heavily on their parameter setting in cellular networks. Current practice of parameter setting relies largely on expert experience and self-organizing networks, which is often suboptimal. Therefore, how to find the optimal parameter combinations automatically is increasingly concerned by mobile network operators. In this article, a collaborative learning approach is proposed to meet this demand by predicting the performance of network elements under different parameter combinations before setting. The proposed approach captures the time-aware correlation between different network elements and their parameter combinations based on factorization machine to boost the prediction accuracy. Extensive experiment results demonstrate that the proposed approach outperforms the existing prediction approaches on a large-scale real-world network dataset from a metropolitan LTE network.

show abstract

LSTM Recurrent Neural Network (RNN) for Anomaly Detection in Cellular Mobile Networks

Mamun¹,

Beyaz²

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

CellPAD: Detecting Performance Anomalies in Cellular Networks via Regression Analysis

Cited by 33 publications

References 22 publications

Online Anomaly Detection System for Mobile Networks

Online Anomaly Detection System for Mobile Networks

A Factorization Machine-Based Approach to Predict Performance Under Different Parameters in Cellular Networks

LSTM Recurrent Neural Network (RNN) for Anomaly Detection in Cellular Mobile Networks

Contact Info

Product

Resources

About