Hotspot Localization and Prediction for Broadband Multimedia Services in 5G Networks

Due to the generation of hotspots and the rapid change of hotspot location, 5G wireless network must have higher flexibility. How to accurately predict the future traffic load is a prominent problem. In this paper, we use Gaussian Random Field (GRF)-based to fit the distribution of spatial traffic density and then locate the hotspots for broadband multimedia services. At the same time, the Long Short-Term Memory (LSTM) model is trained to predict the next moment traffic value by using the actual traffic data collected from base stations. Finally, the model is used to predict the future traffic data of base stations and locate the hotspots. Through analysis and evaluation, numerical results show that the method can effectively locate hotspots.

[1]  Liang Gong,et al.  Integrating network function virtualization with SDR and SDN for 4G/5G networks , 2015, IEEE Network.

[2]  Hans D. Schotten,et al.  Mobility context awareness to improve Quality of Experience in traffic dense cellular networks , 2017, 2017 24th International Conference on Telecommunications (ICT).

[3]  Lutz Ewe,et al.  Mobile User Hotspot Detection in LTE Networks by Moving Pseudo Pico Cells , 2016 .

[4]  Yiyan Wu,et al.  Cloud Transmission: A New Spectrum-Reuse Friendly Digital Terrestrial Broadcasting Transmission System , 2012, IEEE Transactions on Broadcasting.

[5]  Sofie Pollin,et al.  Joint Sum-Rate and Power Gain Analysis of an Aerial Base Station , 2016, 2016 IEEE Globecom Workshops (GC Wkshps).

[6]  Halim Yanikomeroglu,et al.  Efficient 3-D placement of an aerial base station in next generation cellular networks , 2016, 2016 IEEE International Conference on Communications (ICC).

[7]  Xiang Zhang,et al.  Hotspot localization and prediction in wireless cellular networks via spatial traffic fitting , 2018, NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium.

[8]  Hiroki Endo,et al.  Broadcast and broadband reception quality field experiment to validate the effectiveness of Media-Unifying platform , 2017, 2017 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB).

[9]  Zhisheng Niu,et al.  Spatial modeling of Scalable Spatially-correlated Log-normal distributed traffic inhomogeneity and energy-efficient network planning , 2013, 2013 IEEE Wireless Communications and Networking Conference (WCNC).

[10]  Li Li,et al.  Using LSTM and GRU neural network methods for traffic flow prediction , 2016, 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC).