Load Balancing and Optimization in LTE Network Using Fuzzy Logic and Q-Learning Techniques

References

[1] Aderemi, A. A. & Matthew, K. L. (2012). Adaptive Neuro-Fuzzy Inference System for Dynamic Load Balancing in 3GPP LTE. International Journal of Advanced Research in Artificial Intelligence (IJARAI), 1(1), 11-16.

[2] Aderemi, A. A., Matthew, K. L. & Adeyemi, A. A. (2012). Neural-Encoded Fuzzy Models for Load Balancing in 3GPP LTE. International Journal of Applied Information Systems (IJAIS), 3, No. (7), 1-7.

[3] Alejandro, A. G., Raquel, B., Sergio, F. & Pablo, M. (2015). Load Balancing Mechanisms ForIndoor Temporarily Over Loaded Heterogeneous Femto Cell networks. EURASIP Journal on Wireless Communications and Networking, 1(1), 1-14.

[4] David, P. & Alan, M. (2010). Artificial Intelligence Foundations of Computational Agents. Cambridge University Press Ltd.

[5] Erik D., Stefan P., Jonan S., & Per B., (2007). Background of 3G Evolution: 3G Evolution, HSPA and LTE for Mobile Broadband (pp. 40- 41). San Diego, California: Elsevier Ltd.

[6] Fotiadis, P., Polignano, M., Laselva, D., Vejlgaard, B., Mogensen, P., Irmer, R. et al. (2012). Multi-Layer Mobility Load Balancing in a Heterogeneous LTE Network. IEEE Vehicular Technology Conference (VTC Fall). 1(1), 1-5.

[7] Houman, Z. (2014). Overview of the LTE Physical Layer: Understanding LTE with MATLB from Mathematical Modelling to Simulation and Prototyping (pp 13-46). Massachusetts, USA Willey Ltd.

[8] Hu, H., Zhang, J, Zheng, X., Yang, Y. & Wu, P. (2010). Self-Configuration and Self- Optimization for LTE Networks. IEEE Communications Magazine. 48(2), 94-100.

[9] Iana, S. & Di, Y. (2012). Load Balancing in Heterogeneous LTE: Range Optimization via Cell Offset and Load -Coupling Characterization. IEEE ICC 2012 - Communication QoS, Reliability and Modeling Symposium. 1(1), 1357-1361.

[10] Internet and Mobile Phone Users Worldwide (2015). Retrieved January 16, 2016, from: www.dazeinfo.com.

[11] Jian, L., Yifeng, H., Yun, T. & Ling, G. (2014). Optimal Load Balancing Algorithm for Multi- cell LTE Networks. International Journal of Wireless Communications and Mobile Computing. 2 (2), 23-29.

[12] Jose, M. R. A., Salvador, L. R., Matias, T. & Fernando, R. (2011). Traffic Steering by Self- tuning Controllers in Enterprise LTE Femtocells. EURASIP Journal on Wireless Communications and Networking (London, June 2011). 2012 (1), 195 -200.

[13] Kai, M., Frank, K., Rudolf, K. & Andreas, N. (2005). Studies in Fuzziness and Soft Computing. Germany: Springer Berlin Heidelberg New York. 200, 1-4.

[14] Maurizio, L. R. (2016). RSRQ to SINR Measurement. Retrieved February 3, 2016, from: www.laroccasolutions.com.

[15] Miaona, H., Suili, F. & Jun, C. (2014). A Practical Approach for Load Balancing in LTE Networks. Journal of Communications. 9(6), 490-497.

[16] Muñoz, P., Barco, R., & de la Bandera, I. (2014). Load Balancing and Handover Joint Optimization in LTE Network Using Fuzzy Logic and Reinforcement Learning. Computer Networks. 76, (1), 112-125.

[17] Nazmul, S. &Hojjat, A. (2013). Fuzzy Systems and Applications: Computational Intelligence; Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing (pp 65-101). John Wiley and Sons Ltd.

[18] Nokia, (2002). GSM Air Interface & Network Planning. Pp. 24-25 TC Finland.

[19] Osman, N. C. Y. (2010). Networks Self- Optimization of Coverage and Capacity in LTE using Adaptive Antenna Systems. Presented to AALTO UNIVERSITY for the award of masters of Science degree

[20] Ray, K. (2014). TD-LTE Power Configuration. Retrieved April 26, 2017, from: www.slideshare.net/RayKhastur/how-to- increase-your-lte-coverage-with-limited-rru- capacity.

[21] Sumita, M. & Nidhi M. (2014). Load Balancing Optimization in LTE/LTE-A Cellular Networks.

[22] Third Generation Partnership Project; Technical Specification Group Radio Access Network; (2012). Evolved Universal Terrestrial Radio Access Network (E-UTRAN); X2 general aspects and principles Release 8.

[23] Toshiaki, Y., Toshihiko, K., & Satoshi, K. (2012). Mobility Load Balancing Scheme Based on Cell Reselection. The Eighth International Conference on Wireless and Mobile Communications (ICWMC). 1(1), 381-387.

[24] Tutorials point. (2015). History of Mobile Communication. Retrieved October 20, 2015, from: www.tutorialspoint.com/umts/umts_history_of_ mobile_communication.htm.

[25] Viering, I., Dottling, M. &Lobinger, A. (2009). A mathematical Perspective of Self-Optimizing Wireless Networks. IEEE International Conference on Communications. 14-18.

[26] Wang, H. Ding, L., Wu, P., Pan, Z., Liu, N. & You, X. (2010) Dynamic Load Balancing and Throughput Optimization in 3GPP LTE Networks. Wireless Communications and Mobile Computing Conference (IWCMC).

[27] Wang, H., Liu, N., Li, Z., Wu, P., Pan, Z., and You, X., (2012). A Unified Algorithm for Mobility Load Balancing in 3GPP LTE Multi- Cell Networks. National Mobile Communications Research Laboratory, School of Information Science and Engineering, Southeast University, Nanjing 210096, China. 1(1), 1-12.

[28] Zadeh L. A., (1965). Fuzzy Sets. INFORMATION AND CONTROL Department of Electrical Engineering and Electronics Research Laboratory, University of California, Berkeley, California. 8(1), 338-353.

@article{1703913,
      author = {Daniel Samson Akpolile},
      title = {Load Balancing and Optimization in LTE Network Using Fuzzy Logic and Q-Learning Techniques},
      journal = {Iconic Research And Engineering Journals},
      year = {2022},
      volume = {6},
      number = {6},
      pages = {45-60},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1703913.pdf},
      abstract = {Long term evolution (LTE) main objectives are to provide a high data rate, low latency and packet optimized radio access technology supporting flexible bandwidth deployments. LTE network architecture is designed to support packet-switched traffic with seamless mobility and great quality of service. Notwithstanding these gains, its system performance is hampered by load imbalance due to uneven distribution among neighboring cells. As a remedy to the above stated problem, automated inter-cell optimization is required. It is necessary for the network to conduct inter-cell optimization dynamically and adaptively according to its environments. Several techniques have been proposed in the past to solve the problem of load imbalance in an LTE network. This research seeks to use fuzzy logic controller and Q-learning technique to achieve load balancing in such a network. Using as inputs to the fuzzy controller the reference receivesignal quality (RSRQ) and load difference between adjacent cells. While the output of the controller is a crispy power value use to alter the cell transmit power for a better load performance. Using Q-learning techniques, the output power is optimized to obtain the best possible power increment considering the current state of the network in terms of quality and load and also keep the transmit power within acceptable range. The results obtained showed a remarkable improvement in the load fairness index with a mean value of 0.99 all through the simulation period and a 48% reduction in the number of unsatisfied users from its unbalance state.},
      keywords = {Fuzzy logic, Load balancing, Long-term evolution, Q-learning, Self- organizing networks},
      month = {December},
  }