近年來，隨著無線行動通訊系統快速發展，為滿足用戶無線通訊的服務品質(QoS)需求，由大、小型基地台整合構成的異質網路被廣泛討論。異質網路可提高頻譜效率，但也由於大小細胞共用頻段資源，伴隨嚴重的細胞間互干擾問題，因此3GPP Release 10 標準制定增強型細胞間互干擾協調(enhance Inter-cell Interference Coordination, eICIC)技術以紓解此問題，其中包含空白子訊框(Almost Blank Subframe, ABS)與細胞涵蓋展延(Cell Range Expansion, CRE)兩種技術。此外，由於小細胞密度增加，導致行動用戶頻繁且不必要之細胞間交接(handover)程序，也引發系統複雜性提高及整體服務品質降低之疑慮。
本論文針對多細胞異質網路系統的eICIC機制，除探討ABS資源配置對整體系統性能的影響外，主要採用人工智慧的模糊Q學習技術以尋求適用於行動通訊多細胞異質網路的CIO (Cell Individual Offset)及ABS ratio設定。此外，為減少行動用戶的不必要細胞間交接，本論文也探討以用戶將於目標基地台的逗留時間作為啓動交接程序的判斷準則，尋求在不會造成嚴重通話中斷率的前提下有效降低不必要之換手。

With the rapid development of wireless mobile communication systems, in order to meet the quality of service (QoS) requirements of most users, heterogeneous network (HetNet), which is composed of macro cells and small cells, has been widely discussed. HetNet can improve spectrum efficiency, but it is also accompanied with severe inter-cell interference. Therefore, the 3GPP Release 10 standard proposes the enhanced Inter-cell Interference Coordination (eICIC) mechanism to resolve this problem. The eICIC contains two technologies: Almost Blank Subframe (ABS) and Cell Range Expansion (CRE). On the other hand, as the increase of small cell density, users’ unnecessary handovers among cells usually result in higher complexity and lower quality of service. Hence, this thesis is denoted to the study on the eICIC mechanism of multi-cell heterogeneous networks. In addition to discussing the impact of ABS resource allocation on the system performance, we adopt the Fuzzy Q-learning, a technology of artificial intelligence, to determine the setting of CIO and ABS ratio for the mobile multi-cell heterogeneous network. Furthermore, we make use of a time-of-stay (ToS) based handover decision criterion to reduce the unnecessary handover rate without causing higher call-drop rate (CDR).

[1] 3GPP TR 36.839, “Mobility enhancements in heterogeneous networks,” 2012.
[2] 3GPP, “Radio Resource Control (RRC)," TS 36.331 V11.2.0, Dec, 2012.
[3] 3GPP, “Requirements for support of radio resource management,” TS 36.133 V10.6.0, Mar. 2012.
[4] 3GPP TS 36.300, “Overall description; Stage 2,” 2009.
[5] 3GPP TR 36.839, “Mobility enhancements in heterogeneous networks,” 2012
[6] 3GPP TSG RAN WG1 R1-083813, ”Range expansion for efficient support of heterogeneous networks,” Qualcomm Europe, RAN1 #54bis,September 2008.
[7] 3GPP TR 36.814, “Further advancements for E-UTRA physical layer aspects” 2010.
[8] 3GPP TR 36.942, "Radio Frequency (RF) system scenarios," 2012.
[9] 3GPP TR 36.931, “Radio Frequency (RF) requirements for LTE Pico Node B,” 2011.
[10] M. Simsek, M. Bennis, and I. Guvenc, “Learning based frequency-and time-domain inter-cell interference coordination in hetnets,” IEEE Trans. Vehicular Technol, 2015.
[11] S. Deb, P. Monogioudis, J. Miernik, and J. P. Seymour, “Algorithms for enhanced inter-cell interference coordination (eicic) in lte hetnets,” IEEE/ACM Transactions on Networking (TON), vol. 22, no. 1, pp. 137–150, 2014.
[12] A. Liu, V. K. Lau, L. Ruan, J. Chen, and D. Xiao, “Hierarchical radio resource optimization for heterogeneous networks with enhanced inter-cell interference coordination (eicic),” Signal Processing, IEEE Transactions on, vol. 62, no. 7, pp. 1684–1693, 2014.
[13] M. Simseki, M. Bennis, A. Czylwiki, "Dynamic Inter-Cell Interference Coordination in HetNets: A Reinforcement Learning Approach", IEEE Global Communications Conference (GLOBECOM), pp. 5446-5450, December 2012.
[14] Pin-Hau Lin, “Adaptive Adjustment for Enhanced Inter-Cell Interference Coordination using Machine Learning in LTE Heterogeneous Networks,” MS Thesis, National Cheng Kung University, 2020.
[15] Choong-Hee Lee; Jae-Hyun Kim, “Time-of-Stay Estimation-Based Cell Selection Scheme in Multitier Heterogeneous Mobile Networks,” IEEE Communications Letters ( Volume: 19, Issue: 9, Sept. 2015), pp. 1596 – 1599, April 2015.
[16] Mohanad Alhabo; Li Zhang; Obinna Oguejiofor, “Inbound Handover Interference-Based Margin for Load Balancing in Heterogeneous Networks,” International Symposium on Wireless Communication Systems (ISWCS), 2017.
[17] Mohanad Alhabo, Li Zhang, “Load-Dependent Handover Margin for Throughput Enhancement and Load Balancing in HetNets,” IEEE Access, vol. 6, pp. 67718-67731, 2018.
[18] Kai-Cheng Lin, “A Time-of-Stay Estimation-Based Handover Algorithm for Heterogeneous LTE Systems,” MS Thesis, National Cheng Kung University, January 2017.
[19] D. Pandey and P. Pandey, ”Approximate Q-Learning: An Introduction”, Second International Conference on Machine Learning and Computing (ICML), 2010.
[20] P.Y. Glorennec, L. Jouffe, “Fuzzy Q-learning,” Proceedings of the Sixth IEEE International Conference on Fuzzy Systems, Volume:2 , 1997
[21] C.J.C.H. Watkins, “Learning from Delayed Rewards,” PhD dissertation, Cambridge University, Cambridge, England.