Dynamic Self-Optimization of the Antenna Tilt for Best Trade-off Between Coverage and Capacity in Mobile Networks
One major factor influencing the coverage and capacity in mobile networks is related to the configuration of the antennas and especially the antenna tilt angle. By utilizing antenna tilt, signal reception within a cell can be improved and interference radiation towards other cells can be effectively reduced, which leads to a higher signal-to-interference-plus-noise ratio received by the users and increased sum data rate in the network. In this work, a method for capacity and coverage optimization using base station antenna electrical tilt in mobile networks is proposed. It has the potential to improve network performance while reducing operational costs and complexity, and to offer better quality of experience for the mobile users. Our solution is based on the application of reinforcement learning and the simulation results show that the algorithm improves significantly the overall data rate of the network, as compared to no antenna tilt optimization. The analysis in this paper focuses on the downlink of the cellular system. For the simulation experiments a multicellular and sectorized mobile network in an urban environment and randomly distributed user terminals are considered. The main contribution in this work is related to the development of a learning algorithm for automated antenna tilting.
KeywordsMobile networks Self-optimization User satisfaction Antenna tilt Coverage Capacity Machine learning Reinforcement learning
- 1.Hamalainen, S., Sanneck, H., & Sartori, C. (2011). LTE self-organising networks (SON): Network management automation for operational efficiency. Wiley.Google Scholar
- 2.Cisco (2015). Visual networking index (VNI). http://www.cisco.com/c/en/us/solutions/service-provider/visual-networking-index-vni/index.html. Aaccessed September 2015.
- 3.Yilmaz, O., Hamalainen, S., & Hamalainen, J. (2009). Comparison of remote electrical and mechanical antenna downtilt performance for 3GPP LTE. Vehicular Technology Conference Fall (VTC 2009-Fall), 2009 IEEE 70th. pp. 1–5.Google Scholar
- 4.Yilmaz, O., Hamalainen, J., & Hamalainen, S. (2010). Self-optimization of remote electrical tilt. Personal Indoor and Mobile Radio Communications (PIMRC), 2010 IEEE 21st International Symposium on. pp. 1128–1132.Google Scholar
- 6.Thampi, A., Kaleshi, D., Randall, P., Featherstone, W., & Armour, S. (2012). A sparse sampling algorithm for self-optimisation of coverage in LTE networks. Wireless Communication Systems (ISWCS), 2012 International Symposium on, pp. 909–913.Google Scholar
- 7.Razavi, R., Klein, S., & Claussen, H. (2010). Self-optimization of capacity and coverage in LTE networks using a fuzzy reinforcement learning approach. Personal Indoor and Mobile Radio Communications (PIMRC), 2010 IEEE 21st International Symposium on, pp. 1865, 1870.Google Scholar
- 9.Balanis, C. A. (2005). Antenna theory: Analysis and design, 3rd Edn. Wiley.Google Scholar
- 10.GPP. (2014). TR 36.814, technical specification group radio access network (E-UTRA). Evolved Universal Terrestrial Radio Access (E-UTRA); Further advancements for E-UTRA physical layer aspects, ver. 1.7.0, Release 9. http://www.3gpp.org/ftp/Specs/archive/36_series/36.814/36814-170.zip. Accessed July 2015.
- 11.Kathrein (2015). Antenna type 742215 technical specification. https://www.kathrein.de/svg/download/9364238a.pdf. Accessed August 2015.
- 12.Gunnarsson, F., Johansson, M. N., Furuskar, A., Lundevall, M., Simonsson, A., Tidestav, C., & Blomgren, M. (2008). Downtilted base station antennas—a simulation model proposal and impact on HSPA and LTE performance. Vehicular Technology Conference, 2008. VTC 2008-Fall. IEEE 68th, pp. 1–5.Google Scholar
- 13.Mohri, M., Rostamizadeh, A., & Talwalkar, A. (2012). Foundations of machine learning. The MIT Press.Google Scholar
- 14.Sutton, R., & Barto, A. (1998). Introduction to reinforcement learning, 1st edn. MIT Press.Google Scholar