Abstract
A new methodology based on Support Vector Machine (SVM) for the detection of handover-related radio link failures was presented. After analyzing the characteristics of three abnormal handovers, five handover-related events are extracted to describe abnormal HOs and five time points are set in HO procedure for ease of quantifying these events. Based on these data, the classification performance of the SVM-AID algorithm was tested and the effects of the parameters in SVM on the classification were analyzed. The experimental results show that the parameters should be chosen carefully because they have great effects on the classification. The simulation results also demonstrate that the proposed approach achieves the best efficiency and accuracy with Polynomial kernel function. This study provides a new idea and a basis of application for anomaly detection in Self-Organizing Networks (SON).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
3GPP TS 36.300, v11.3.0, Evolved Universal Terrestrial Radio Access (E-UTRA) and Evolved Universal Terrestrial Radio Access Network (E-UTRAN) Overall description (2011)
Zhang, Y., Zhou, W., Wald-Hauser, R.: Method of determining a radio link failure associated with a handover of a user equipment from a source access node to a target access node, access node for determining a radio link failure associated with a handover of a user equipment from a source access node to a target access node, and user equipment. China Patent Agent (H.K.)Ltd. (2011)
Vapnik, V.N.: The nature of statistical learning theory, 2nd edn. Springer, Heidelberg (2000)
Begg, R.K., Palaniswami, M., Owen, B.: Support vector machines for automated gait recognition. IEEE Transactions on Biomedical Engineering 52, 828–838 (2005)
Kecman, V.: Learning and Soft Computing — Support Vector Machines, Neural Networks, Fuzzy Logic Systems. The MIT Press, Cambridge (2001)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer (1995)
Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines Software (2001), http://www.csie.ntu.edu.tw/~cjlin/libsvm
4G Americas. Self-Optimizing Networks - The Benefits of SON in LTE (July 2011)
de Morsier, F., Tuia, D., Borgeaud, M., Gass, V., Thiran, J.-P.: Semi-Supervised Novelty Detection Using SVM Entire Solution Path. IEEE Transactions on Geoscience and Remote Sensing PP(99), 1–12 (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Qin, W., Teng, Y., Man, Y., Yu, S., Zhang, Y. (2014). A Detection Method for Handover-Related Radio Link Failures Based on SVM. In: Zu, Q., Vargas-Vera, M., Hu, B. (eds) Pervasive Computing and the Networked World. ICPCA/SWS 2013. Lecture Notes in Computer Science, vol 8351. Springer, Cham. https://doi.org/10.1007/978-3-319-09265-2_49
Download citation
DOI: https://doi.org/10.1007/978-3-319-09265-2_49
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09264-5
Online ISBN: 978-3-319-09265-2
eBook Packages: Computer ScienceComputer Science (R0)