近年來行動通訊的資訊傳輸量快速的提升，為了滿足用戶的需求，異質網路在LTE中被拿出來討論。異質網路系統可減低發射功率、提高頻譜效率，進而提升總體資訊傳送量，但其附隨的行動用戶頻繁細胞間交接(handover)處理也引發系統複雜性及整體服務品質降低的疑慮。
在行動通訊網路中，用戶很少會剛好均勻的分佈在整個網路中，當一個基地台超載時，附近的基地台通常都還有空閒的資源，這就造成基地台負載不平衡的問題。
本論文即探討在LTE系統下的異質網路，利用交接演算法來改善負載不平衡的問題，提出使用Fuzzy Q-learning方法來實現適應性交接演算法，除了考慮基地台負載之外，同時考慮通話阻斷率與通話中斷率來學習調整handover參數，使系統能夠根據基地台的負載狀況來做調整，將用戶移動至鄰近基地台以降負載，並探討不同參數的調整及不同的模擬情境下對系統效能的影響。

In order to satisfy user traffic demand which has increased rapidly in recent years. Heterogeneous Network (HetNet) is a good solution in LTE systems. Users are rarely uniformly distributed in mobile communication networks. There are available neighbor base stations when a base state is overloaded. This cause loading unbalancing problem. In this thesis, we propose a fuzzy Q-learning approach load balancing algorithm in dense small cells system. In addition to considering loading of base station, we take call drop rate and call block rate into account to adjust handover parameters. When performing the simulations, the various parameters will be adjusted to identify the impact of various parameters on the handover process.

[1] 3GPP TR 36.942, "Radio Frequency (RF) system scenarios," 2012.
[2] 3GPP TS 36.331, "Radio Resource Control (RRC);Protocol specification," 2012.
[3] P. Y. Glorennec, "Fuzzy Q-learning," Proceedings of the Sixth IEEE International Conference on Fuzzy Systems, vol. 2, pp. 659 - 662, 1997.
[4] 3GPP TR 36.839, "Mobility enhancements in heterogeneous networks," 2012.
[5] 3GPP TS 36.133, "Requirements for support of radio resource management," 2012.
[6] D. López-Pérez, I. Güvenc and X. Chu, "Mobility management challenges in 3GPP heterogeneous networks," IEEE Communications Magazine, vol. 50, pp. 70 - 78, Dec. 2012.
[7] J. Andrews, "Seven Ways that HetNets Are a Cellular Paradigm Shift," IEEE Communications Magazine, vol. 51, pp. 136 - 144, Mar. 2013.
[8] A. Ghosh;, N. Mangalvedhe, R. Ratasuk and B. Mond, "Heterogeneous Cellular Networks: From Theory to Practice," IEEE Communications Magazine, vol. 50, pp. 54 - 64, June 2012.
[9] J. Andrews, H. Claussen, M. Dohler and S. Rangan, "Femtocells: Past, Present, and Future," IEEE Journal on Selected Areas in Communications, vol. 30, pp. 497 - 508, April 2012.
[10] V. Chandrasekhar, J. Andrews and A. Gatherer, "Femtocell networks: a survey," IEEE Communications Magazine, vol. 46, pp. 59 - 67, Sep. 2008.
[11] D. Xenakis, N. Passas, L. Merakos and C. Verikoukis, "Mobility Management for Femtocells in LTE-Advanced-Key Aspects and Survey of Handover Decision Algorithms," IEEE Communications Surveys & Tutorials, vol. 16, pp. 64 - 91, July 2013.
[12] S. S. Mwanje and A. Mitschele-Thiel, "A Q-Learning Strategy for LTE Mobility Load Balancing," IEEE 24th International Symposium on Personal, Indoor and Mobile Radio Communications: Mobile and Wireless Networks, pp. 2154 - 2158, 2013.
[13] S. S. Mwanje and A. Mitschele-Thiel, "Minimizing Handover Performance Degradation due to LTE Self Organized Mobility Load Balancing," IEEE 77thVehicular Technology Conference (VTC Spring), pp. 1-5, june 2013.
[14] P. Munoz, R. Barco, I. de la Bandera, M. Toril and S. Luna-Ramírez, "Optimization of a Fuzzy Logic Controller for Handover-based Load Balancing," IEEE 73rd Vehicular Technology Conference (VTC Spring), pp. 1-5, 2011.
[15] P. Muñoz, R. Barco, J. M. Ruiz-Avilés, A. Aguilar and Isabel de la Bandera, "Fuzzy Rule-Based Reinforcement Learning for Load Balancing Techniques in Enterprise LTE Femtocells," IEEE Transactions on Vehicular Technology, vol. 62, no. 5, pp. 1962 - 1973, 2013.
[16] C. Watkins, "Learning from Delayed Rewards".PhD thesis, Cambridge University, Cambridge, England.
[17] E. Even-dar, S. Mannor and Y. Mansour, "PAC bounds for multi-armed bandit and Markov decision processes," Proceedings of 15th Annual Conference on Computational Learning Theory, July 2002.