在即將到來的5G新無線電(New Radio, NR) 時代中，使用未授權頻段增加傳輸速度已是未來的趨勢，NR微小型基地台(small cell) 和Wi-Fi 將會被布建在同一場域或是整合至同一台機器中，並爭奪未授權頻段的使用權。由3GPP 主導的技術中LTE 許可輔助存取(Licensed Assisted Access, LAA)，導入了LBT 技術，目的在於可以更加公平的競爭，使得Wi-Fi 與LAA 可在同一種場域共存。
本論文將介紹一個評估Wi-Fi和LAA共存下吞吐量 (Throughput)的框架，分別比較DCF 與LBT 各自的特徵，修改自著名的Bianchi 模型，並加入各種網路參數，如媒體存取控制層（MAC層）物理層（PHY）通道條件等進行模擬分析，並將呈現數值分析結果。
但是，我們發現在不同802.11協定下，LAA 與Wi-Fi 競爭會讓吞吐量出現極度不平衡的關係，為了改善不平等的關係，我們在本篇論文中提出基於強化式學習下調整TXOP (Transmission Opportunity)時間，來改善次世代異質性網路得公平效能，這項技術可以安裝在微小型基地台，增進在不同異質性網路下達到公平且有效的資源分配，保護網路用戶的服務品質。

In the coming era of 5G New Radio (NR), using unlicensed frequency bands to increase the transmission speed is the future trend. NR small cells and Wi-Fi will be deployed in the same field or integrated into the same machine and contend for the right to use unlicensed bands. In the technology led by 3GPP, LTE Licensed Assisted Access (LAA), the introduction of Listen Before Talk (LBT), aims at a fairer competition. so that Wi-Fi and LAA can coexist in the same field.
This thesis will introduce a framework of evaluating the throughput under the coexistence of Wi-Fi and LAA. Compare the characteristics of DCF and LBT respectively, modify from the famous Bianchi model, and add various network parameters, such as Media Access Control (MAC) and physical layer (PHY) channel conditions, etc. For simulation and numerical analysis.
However, we found that under different 802.11 protocols, the contention between LAA and Wi-Fi will cause an extremely uneven relationship in throughput. In order to improve the unequal relationship, we propose in this paper to adjust the Transmission Opportunity (TXOP) duration based on reinforcement learning to improve the fair performance of next-generation heterogeneous networks. This research can be installed in small cell to improve the fair and effective resource allocation protect the services of each network user’s quality.

[1] 3GPP, “3rd Generation Partnership Project; Technical Specification Group Radio Access Network; Study on Licensed-Assisted Access to Unlicensed Spectrum,” 3GPP TR 36.889, V13.0.0, June 2015.
[2] B. Chen, J. Chen, Y. Gao and J. Zhang, "Coexistence of LTE-LAA and Wi-Fi on 5 GHz With Corresponding Deployment Scenarios: A Survey," in IEEE Communications Surveys & Tutorials, vol. 19, no. 1, pp. 7-32, First quarter 2017.
[3] Qualcomm Research LTE in Unlicensed Spectrum: Harmonious Coexistence with Wi-Fi, San Diego, CA, USA, Jun. 2014.
[4] R. Bajracharya et al., "LWA in 5G: State-of-the-art architecture opportunities and research challenges", IEEE Communication Mag., vol. 56, no. 10, pp. 134-141, Oct. 2018.
[5] M. Cavalcante, E. Almeida, R. D. Vieira, S. Choudhury, E. Tuomaala, K. Doppler, F. Chaves, R. C. D. Paiva, and F. Abinader, “Performance Evaluation of LTE and Wi-Fi Coexistence in Unlicensed Bands,” in IEEE 77th Vehicular Technology Conference, June 2013, pp. 1–6.
[6] V. Mushunuri, B. Panigrahi, H. K. Rath and A. Simha, "Fair and Efficient Listen Before Talk (LBT) Technique for LTE Licensed Assisted Access (LAA) Networks," 2017 IEEE 31st International Conference on Advanced Information Networking and Applications (AINA), Taipei, 2017, pp. 39-45.
[7] Junjie Tan, Sa Xiao, Shiying Han, Ying-Chang Liang, and Victor C. M. Leung, “QoS-Aware User Association and Resource Allocation in LAA-LTE/ WiFi Coexistence Systems”, IEEE Transaction on Wireless Communications, VOL. 18, NO. 4, April 2019
[8] G. Bianchi, “Performance Analysis of the IEEE 802.11 Distributed Coordination Function,” IEEE Journal of Selected Area Communications, vol. 18, no. 3, pp. 535–547, Sep. 2006.
[9] M. Mehrnoush, V. Sathya, S. Roy, and M. Ghosh, Analytical modeling of Wi-Fi and LTE-LAA coexistence: Throughput and impact of energy detection threshold, Mar. 2018, [online] Available: https://arxiv.org/abs/1803.02444.
[10] Jie Xiao; Jun Zheng; Liangyu Chu; Qilei Ren(Oct. 2018). Performance Modeling of LAA LBT with Random Backoff and a Variable Contention Window, IEEE 2018 10th International Conference on Wireless Communications and Signal Processing (WCSP), Hangzhou, China
[11] N. Bitar, M. O. Al Kalaa, S. J. Seidman, and H. H. Refai, "On the Coexistence of LTE-LAA in the Unlicensed Band: Modeling and Performance Analysis", in IEEE Access, vol. 6, pp. 52668-52681, 2018, doi: 10.1109/ACCESS.2018.2870757.
[12] J. Xiao, J. Zheng, L. Chu, and Q. Ren, "Performance Modeling and Analysis of the LAA Category-4 LBT Procedure," in IEEE Transactions on Vehicular Technology, vol. 68, no. 10, pp. 10045-10055, Oct. 2019, doi: 10.1109/TVT.2019.2933012.
[13] C. J. C. H. Watkins and P. Dayan. Q-learning. Machine Learning, 8:279–292, 1992.
[14] S. Toumi, M. Hamdi and M. Zaied, "An adaptive Q-learning approach to power control for D2D communications," 2018 International Conference on Advanced Systems and Electric Technologies (IC_ASET), Hammamet, 2018, pp. 206-209, doi: 10.1109/ASET.2018.8379860.
[15] V. Maglogiannis, D. Naudts, A. Shahid, and I. Moerman, "A Q-Learning Scheme for Fair Coexistence Between LTE and Wi-Fi in Unlicensed Spectrum," in IEEE Access, vol. 6, pp. 27278-27293, 2018, doi: 10.1109/ACCESS.2018.2829492.
[16] U. Challita, L. Dong and W. Saad, "Proactive Resource Management for LTE in Unlicensed Spectrum: A Deep Learning Perspective", IEEE Transactions on Wireless Communications, vol. 17, no. 7, pp. 4674-4689, July 2018.
[17] E. Dahlman, S. Parkvall, J. Peisa and H. Tullberg, "5G evolution and beyond", SPAWC, 2019.
[18] R. Jain, W. Hawe, D. Chiu, “A Quantitative measure of fairness and discrimination for resource allocation in Shared Computer Systems,” DEC-TR-301, September 26, 1984.
[19] S. Saadat, D. Chen, K. Luo, M. Feng and T. Jiang, "License assisted access-WiFi coexistence with TXOP backoff for LTE in unlicensed band", China Commun., vol. 14, no. 3, pp. 1-14, Mar. 2017.
[20] P. Naghavi, S. Hamed Rastegar, V. Shah-Mansouri and H. Kebriaei, "Learning RAT Selection Game in 5G Heterogeneous Networks," in IEEE Wireless Communications Letters, vol. 5, no. 1, pp. 52-55, Feb. 2016, doi: 10.1109/LWC.2015.2495123.
[19] M. Yazid, A. Ksentini, L. Bouallouche-Medjkoune and D. Aïssani, "Performance Analysis of the TXOP Sharing Mechanism in the VHT IEEE 802.11ac WLANs," in IEEE Communications Letters, vol. 18, no. 9, pp. 1599-1602, Sept. 2014.
[20] Hausknecht, M., and Stone, P. 2015. Deep recurrent Qlearning for partially observable MDPs. arXiv preprint arXiv:1507.06527.
[21] E. Pei, J. Jiang, L. Liu, Y. Li and Z. Zhang, "A Chaotic Q-learning-Based Licensed Assisted Access Scheme Over the Unlicensed Spectrum," in IEEE Transactions on Vehicular Technology, vol. 68, no. 10, pp. 9951-9962, Oct. 2019, doi: 10.1109/TVT.2019.2936510.
[22] V. Maglogiannis, D. Naudts, A. Shahid, and I. Moerman, "A Q-Learning Scheme for Fair Coexistence Between LTE and Wi-Fi in Unlicensed Spectrum," in IEEE Access, vol. 6, pp. 27278-27293, 2018, doi: 10.1109/ACCESS.2018.2829492.