Space/Time Traffic Fluctuations in a Cellular Network: Measurements’ Analysis and Potential Applications
The characterization of the space/time traffic profiles in a cellular network can be of high interest for automating the operation of future networks, since the knowledge extracted from the traffic fluctuations in a cell and its neighbours can be effectively exploited by different optimisation functions. In this context, this paper takes as an input a set of real traffic measurements in a cellular network deployed in a large city and analyses, on a per cell basis, the traffic profile characteristics at different time scales (week, day, hour). Then, the analysis is extended to the space dimension by considering the traffic of one cell in relation to that of its neighbours. This allows identifying traffic complementarities between neighbour cells at different time scales that can be exploited by certain optimisation functions, as illustrated in the paper with specific examples.
KeywordsSpace/time traffic analysis Cellular networks SON Mobility Load Balancing Coverage and capacity optimisation Energy saving
This work has been supported by the EU funded H2020 5G-PPP project 5G ESSENCE under grant agreement 761592 and by the Spanish Research Council and FEDER funds under RAMSES and SONAR 5G grants (ref. TEC2013-41698-R and TEC2017-82651-R).
- 1.Cisco Visual Networking Index: Forecast and Methodology, 2016–2021, White Paper, June 2017Google Scholar
- 2.Ramiro, J., Hamied, K.: Self-Organizing Networks: Self-Planning, Self-Optimization and Self-Healing for GSM, UMTS and LTE. Wiley, Hoboken (2012)Google Scholar
- 5.Pérez-Romero, J., Sallent, O., Ferrús, R., Agustí, R.: Artificial intelligence-based 5G network capacity planning and operation. In: International Symposium on Wireless Communication Systems (ISWCS 2015), Brussels, Belgium, August 2015Google Scholar
- 7.Ma, J., Ni, W., Yin, J., Lin, S., Cui, H., Liu, R.P., Fang, B.X.: Modelling social characteristics of mobile radio networks. In: International Conference on Communications (ICC 2015), London, United Kingdom, June 2015Google Scholar
- 8.Miao, D., Sun, W., Qin, X., Wang, W.: MSFS: multiple spatio-temporal scales traffic forecasting in mobile cellular network. In: 14th International Conference on Pervasive Intelligence and Computing, Auckland, New Zealand, August 2016Google Scholar
- 11.Wang, S., Zhang, X., Zhang, J., Feng, J., Wang, W., Xin, K.: An approach for spatial-temporal traffic modeling in mobile cellular networks. In: International Teletraffic Congress (ITC), Ghent, Belgium, September 2015Google Scholar
- 13.Hammami, S.E., Afifi, H., Marot, M., Gauthier, V.: Network planning tool based on network classification and load prediction. In: IEEE Wireless Communications and Networking Conference (WCNC 2016), Doha, Qatar, April 2016Google Scholar
- 14.Pérez-Romero, J., Sánchez-González, J., Sallent, O., Agustí, R.: On learning and exploiting time domain traffic patterns in cellular radio access networks. Machine Learning and Data Mining in Pattern Recognition. LNCS (LNAI), vol. 9729, pp. 501–515. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-41920-6_40CrossRefGoogle Scholar