A Distribution-Based Approach to Anomaly Detection and Application to 3G Mobile Traffic

D’Alconzo, Alessandro; Coluccia, Angelo; Ricciato, Fabio; Romirer-Maierhofer, Peter

doi:10.1109/glocom.2009.5425651

Cited by 53 publications

(38 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ridoux et al [22] collect data from a CDMA2000 network, and compare the similarities and differences with wireline data traffic. The DARWIN+ group [3] collects IP packets at a GPRS/UMTS network, and analyzes various issues such as TCP performance [21] and traffic anomalies [2]. The above studies mainly analyze the data-plane performance of 3G networks.…”

Section: Related Workmentioning

confidence: 99%

A Panoramic View of 3G Data/Control-Plane Traffic: Mobile Device Perspective

He¹,

Lee²,

Pan³

et al. 2012

Networking 2012

View full text Add to dashboard Cite

Abstract. Users can access the Internet via 3G/4G cellular data networks using various types of user devices (e.g., smartphones, tablets, datacards). We conduct a detailed measurement study on the impact of different device types on the data/control-plane performance of a commercial, city-wide 3G cellular data network in China. We present a methodology that correlates different data/controlplane datasets collected at different points in the network core, and identify more than 60K devices of different types per day on average. For the devices we identify, we investigate how their commonly used Internet applications and internal heartbeat mechanisms lead to distinct data/control-plane behaviors. For example, we observe that datacard devices contribute a large volume of IP traffic in the data plane, while smartphones introduce significant resource overhead in the signaling control plane. Our measurement study provides insights for network operators to strategize pricing and resource allocation for the data/control planes of their cellular data networks with regard to the market penetrations of various device types.

show abstract

Section: Related Workmentioning

confidence: 99%

A Panoramic View of 3G Data/Control-Plane Traffic: Mobile Device Perspective

He¹,

Lee²,

Pan³

et al. 2012

Networking 2012

View full text Add to dashboard Cite

show abstract

“…The idea of the algorithm is very similar to the meta-algorithm presented in [14] and the method in [3]. First, data from datastream is taken and divided into Fig.…”

Section: Detection Algorithmmentioning

confidence: 99%

“…Then a dissimilarity measure of two probability distributions to detect a change could be applied. In many applications the Kullback-Leibler divergence is used [3,16,19], or entropy-based measures [19,20]. Sometimes more theoretical measures are proposed [14].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Context Change Detection for Resource Allocation in Service-Oriented Systems

Rygielski

Tomczak

2011

Knowlege-Based and Intelligent Information and Engineering Systems

View full text Add to dashboard Cite

Abstract. In this paper, the problem of detecting the major changes in the stream of service requests is formulated. The change of stream component varies over time and depends on, e.g., a time of a day. The underlying cause of the change is called a context. Hence, at each moment there exists a probability distribution determining the probability of requesting the system service conditioned by the context. The aim is to find such a moment in which the distributions change. To solve that problem dissimilarity measures between two probability distributions are given. Nevertheless, detecting every change is not interesting but only long-lasting changes because of the costs of the service system resources reallocation. Therefore, in the proposed algorithm an issue of sensitivity to temporary changes detection is considered.

show abstract

“…D'Alconzo et al [14] proposed an anomaly detection algorithm for 3G cellular networks that detects events that might put the stability and performance of the network at risk.…”

Section: Related Workmentioning

confidence: 99%

Detecting anomalies in cellular networks using an ensemble method

Ciocarlie

Lindqvist

Nováczki³

et al. 2013

Proceedings of the 9th International Conference on Network and Service Management (CNSM 2013)

View full text Add to dashboard Cite

Abstract-The Self-Organizing Networks (SON) concept includes the functional area known as self-healing, which aims to automate the detection and diagnosis of, and recovery from, network degradations and outages. This paper focuses on the problem of cell anomaly detection, addressing partial and complete degradations in cell-service performance, and it proposes an adaptive ensemble method framework for modeling cell behavior. The framework uses Key Performance Indicators (KPIs) to determine cell-performance status and is able to cope with legitimate system changes (i.e., concept drift). The results, generated using real cellular network data, suggest that the proposed ensemble method automatically and significantly improves the detection quality over univariate and multivariate methods, while using intrinsic system knowledge to enhance performance.

show abstract

A Distribution-Based Approach to Anomaly Detection and Application to 3G Mobile Traffic

Cited by 53 publications

References 25 publications

A Panoramic View of 3G Data/Control-Plane Traffic: Mobile Device Perspective

A Panoramic View of 3G Data/Control-Plane Traffic: Mobile Device Perspective

Context Change Detection for Resource Allocation in Service-Oriented Systems

Detecting anomalies in cellular networks using an ensemble method

Contact Info

Product

Resources

About