HMM-based User Behavior Prediction Method in Heterogeneous Cellular Networks

doi:10.23940/ijpe.18.09.p25.21632174

Int J Performability Eng ›› 2018, Vol. 14 ›› Issue (9): 2163-2174.doi: 10.23940/ijpe.18.09.p25.21632174

Previous Articles Next Articles

HMM-based User Behavior Prediction Method in Heterogeneous Cellular Networks

Shanshan Tu^{a, b}, Xinyi Huang^{a, *}, Yaqin Zhang^a, Mingyang An^a, Lei Liu^c, and Yao Huang^d

^aFaculty of Information Technology, Beijing University of Technology, Beijing, 100124, China;
^bBeijing Key Laboratory of Trusted Computing, Beijing, 100124, China;
^cBeijing Electro-Mechanical Engineering Institute, Beijing, 100074, China;
^dChengdu University of Information Technology, Chengdu, 610225, China

Revised on ; Accepted on
Contact: * E-mail address: junzilanfang@126.com

Abstract

Abstract: In the heterogeneous cellular networks (HCN) environment, users travel between different cells to ensure that the network connection will not be interrupted, and there is a need for network handover management for users. In HCN, adopting the same handover strategy for different cells will reduce handover performance. Therefore, a reasonable handover management strategy needs to consider the mobile preference and mobility characteristics of users in hot spots. Aiming at the existing problems, in this study, the self-similar least-action human walk (SLAW) is analyzed and a method based on the hidden Markov model (HMM) for perceiving user behavior in hot spots is proposed. First, users’ mobile paths in hot spots are simulated based on SLAW, and user behaviors are modeled using HMM. Then, the corresponding moving time is predicted by the mobile sequence of the user. Finally, the effects of different sampling times and different base station densities on the behavior prediction are analyzed through simulation experiments, providing specific parameter settings for designing a reasonable handover management plan. Meanwhile, the prediction of user movement time can ensure that the base stations in hot spots will make effective preparations for the upcoming handover requests.

Key words: heterogeneous cellular network, hidden Markov model, self-similar least-action human walk, behavior prediction

Shanshan Tu, Xinyi Huang, Yaqin Zhang, Mingyang An, Lei Liu, and Yao Huang. HMM-based User Behavior Prediction Method in Heterogeneous Cellular Networks [J]. Int J Performability Eng, 2018, 14(9): 2163-2174.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

[1] J. G. Andrews, V. Chandrasekhar,A. Gatherer, “Femtocell Networks: A Survey,” IEEE Communications Magazine, Vol. 46, No. 9, pp. 59-67, 2008
[2] W. Q. Liu, “Study on Interference Management of Heterogeneous Cellular Networks,” University of Science and Technology of China, 2013, DOI:10.7666/d. Y2354199
[3] J. Kim and C. Lee, “Time-of-Stay Estimation-based Cell Selection Scheme in Multitier Heterogeneous Mobile Networks,” IEEE Communications Letters, Vol. 19, No. 9, pp. 1596-1599, 2015
[4] H. Kalbkhani, M. G. Shayesteh,S. Yousefi, “Adaptive Handover Algorithm in Heterogeneous Femtocellular Networks based on Received Signal Strength and Signal-to-Interference-Plus-Noise Ratio Prediction,” IET Communications, Vol. 8, No. 17, pp. 3061-3071, 2014
[5] S. Chong, S. Hong, K. Lee, I. Rhee,M. Shin, “On the Levy-walk Nature of Human Mobility,” in Proceedings of IEEE International Conference on Computer Communications, Phoenix, AZ, pp. 924-932, April 2008
[6] C. R. Das, S. Lim,C. Yu, “Clustered Mobility Model for Scale-Free Wireless Networks,” inProceedings of IEEE Conference on Local Computer Networks, pp. 231-238, Tampa, FL, November 2006
[7] E. Hyytia, P. Lassila,J. Virtamo, “A Markovian Waypoint Mobility Model with Application to Hotspot Modeling,” inProceedings of IEEE Conferences on Communications, pp. 979-986, Istanbul, Turkey, June 2006
[8] S. Hong, S. J. Kim, K. Lee, et al., “SLAW: Self-Similar Least-Action Human Walk,” IEEE/ACM Transactions on Networking, Vol. 20, No. 2, pp. 515-529, 2012
L. Barabasi, M. C. Gonzalez,C. A. Hidalgo, “Understanding Individual Human Mobility Patterns,” Nature, Vol. 453, pp. 779-782, June 2008
[9] D. Brockmann, T. Geisel,L. Hufnagel, “The Scaling Laws of Human Travel,” Nature, Vol. 439, pp. 462-465, January 2006
[10] M. Kim, S. Kim,D. Kotz, “Extracting a Mobility Model from Real User Traces,” in Proceedings of IEEE International Conference on Computer Communications, Barcelona, Spain, Apr. 2006, DOI:10/1109/INFOCOM.2006.173
Chaintreau, J. Crowcroft, C. Diot, R. Gass, P. Hui, and J. Scott, “Impact of Human Mobility on the Design of Opportunistic Forwarding Algorithms,” in Proceedings of IEEE INFOCOM, Barcelona, Spain, Apr. 2006, DOI:10.1109/INFOCOM.2006.172
[11] T. Karagiannis, J. Y.LeBoudec, and M. Vojnovic, “Power Law and Exponential Decay of Inter Contact Times Between Mobile Devices,” inProceedings of the 13^th Annual ACM International Conference on Mobile Computing and Networking, pp. 183-194, 2007
[12] M. Gu and Z. Y. Xin, “Complicated Financial Data Time Series Forecasting Analysis based on Least Square Support Vector Machine,”Journal of Tsinghua university (Natural Science Edition), No. 7, pp. 1147-1149, 2008
[13] C. Wang, X. Yang, G. C. Zhang,C. F. Zong, “Driving Intentions Identification and Behaviors Prediction in Car Lane Change,” Journal of Jilin University (Engineering and Technology Edition), Vol. 39, No. S1, pp. 27-32, 2009
[14] Y. Liu and B. Shen, “Movement Prediction Model based on HMM and Simulations,”Journal of System Simulation, No. 18, pp. 4118-4121, 2007
[15] Y. N. Chung, C. D. Liu,J. C.Pau-Choo, “An Interaction-Embedded HMM Framework for Human Behavior Understanding: With Nursing Environments as Examples,” IEEE Transactions on Information Technology in Biomedicine: A Publication of the IEEE Engineering in Medicine and Biology Society, Vol. 14, No. 5
[16] L. R. Welch, “Hidden Markov Models and the Baum-welch Algorithm,” IEEE Information Theory Society Newsletter, Vol. 53, No. 4, pp. 1-14, 2003

HMM-based User Behavior Prediction Method in Heterogeneous Cellular Networks

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 0

Recommended 0