由於製造商正在開發用於性能和應用集成的 5G NR 基站 (BS)，當前的
解決方案主要基於傳統的技術規範，發展智能無線資源管理技術可以優
化當前小蜂窩系統的傳輸性能。為了在 O-RAN Near-RT RIC 中構建用於
鏈路自適應的 xApp，我們使用提供的 API 來完成傳輸觀察和參數自適
應等基本功能，然後採用深度強化學習。智能代理(Agent)以收到訊息作
為狀態(State)，可以動態選擇最佳的鏈路適配參數，實現高效傳輸。儘
管如此，我們將此功能打包到 xApp 中並在現實的 O-RAN 系統上進行測
試，觀察到了不錯的結果。
另一方面在超可靠低時延通信（URLLC）應用中，我們嘗試使用 5G
ns-3 模擬 IIoT 工廠場景，有別於傳統的上行方式， Grant-free（GF）可以在減少延遲下，同時保持一定的可靠性。在不同的傳輸條件下，我們開發了不同的 RL 方法來動態選擇 GF，最終在數值結果中也可以看到滿意率的良好趨勢。

As manufacturers are developing 5G NR base stations (BS) for performance and application integration, current solutions are mainly based on conventional technical specifications. Developing intelligent wireless resource management
technology could optimize and refine the current small cell system transmission performance. To build an xApp in O-RAN Near-RT RIC for link adaptation, we use the provided API to complete essential functions such as transmission
observation and parameter adaptation. Then the deep reinforcement learning is adopted. Using the indication report as the state, the smart agent can dynamically select the best link adaptation parameters to achieve high-efficiency transmission. Nevertheless, we pack the agent into an xApp and test on a realistic O-RAN system with encouraging results observed.
In the ultra reliable low latency communication (URLLC) application, we try to use 5G ns-3 simulation and simulate the IIoT factory scenario, which is different from the traditional uplink method. Grant-free (GF) can reduce the
delay while maintaining certain reliability. Under various transmission conditions, we developed different reinforcement learning (RL) methods used to select mode dynamically. Finally, a promising trend in satisfaction rate can also be seen in the numerical result.

[1] C. Li and A. Akman, “O-RAN Use Cases and Deployment Scenarios,” O-RAN White Paper, feb 2020.
[2] S. Niknam, A. Roy, H. S. Dhillin, S. Singh, R. Banerji, J. H. Reed, N. Saxena, and S. Yoon, “Intelligent O-RAN for beyond 5G and 6G wireless networks,” arXiv:2005.08374, pp. 1–7, may 2020.
[3] O-RAN Alliance, “O-RAN working group 2: AI/ML workflow description and requirements,” mar 2019.
[4] A. Huff, M. Hiltunen, and E. P. Duarte, “Rft: Scalable and fault-tolerant microservices for the o-ran control plane,” pp. 402–409, 2021.
[5] S. K. Singh, R. Singh, and B. Kumbhani, “The evolution of radio access network towards open-ran: Challenges and opportunities,” in 2020 IEEE Wireless Communications and Networking Conference Workshops (WCNCW), 2020, pp. 1–6.
[6] O-RAN Alliance, “O-RAN: Towards an Open and Smart RAN,” O-RAN White Paper, oct 2018.
[7] H. Lee, J. Cha, D. Kwon, M. Jeong, and I. Park, “Hosting ai/ml workflows on o-ran
ric platform,” in 2020 IEEE Globecom Workshops (GC Wkshps, 2020, pp. 1–6.
[8] S. A. T. Kawahara and A. U. R. Matsukawa, “O-ran alliance standardization trends,” 2019.
[9] S. Lagen, L. Giupponi, A. Hansson, and X. Gelabert, “Modulation compression in next generation ran: Air interface and fronthaul trade-offs,” IEEE Communications
Magazine, vol. 59, no. 1, pp. 89–95, 2021.
[10] C. Yu, L. Yu, Y. Wu, Y. He, and Q. Lu, “Uplink Scheduling and Link Adaptation for Narrowband Internet of Things Systems,” IEEE Access, vol. 5, pp. 1724–1734,2017.
[11] J. Wang, C. Xu, Y. Huangfu, R. Li, Y. Ge, and J. Wang, “Deep reinforcement learning for scheduling in cellular networks,” 2019 11th International Conference on Wireless Communications and Signal Processing (WCSP), pp. 1–6, 2019.
[12] Y. Liu, Y. Deng, M. Elkashlan, A. Nallanathan, and G. K. Karagiannidis, “Analyzing grant-free access for urllc service,” IEEE Journal on Selected Areas in Communications, vol. 39, no. 3, pp. 741–755, 2021.
[13] T. Jacobsen, R. Abreu, G. Berardinelli, K. Pedersen, P. Mogensen, I. Z. Kovacs, and T. K. Madsen, “System level analysis of uplink grant-free transmission for urllc,” in
2017 IEEE Globecom Workshops (GC Wkshps), 2017, pp. 1–6.
[14] N. Ye, X. Li, H. Yu, A. Wang, W. Liu, and X. Hou, “Deep learning aided grantfree noma toward reliable low-latency access in tactile internet of things,” IEEE
Transactions on Industrial Informatics, vol. 15, no. 5, pp. 2995–3005, 2019.
[15] Institute for Information Industry, “5G Technology Workshop with RIC Theme Description,” jun 2021.
[16] C.-L. I and S. Katti, “O-RAN: Towards an Open and Smart RAN,” O-RAN White Paper, oct 2018.
[17] Institute for Information Industry, “xApp Manual of Developer-V2,” aug 2021.
[18] N. Patriciello, S. Lagen, L. Giupponi, and B. Bojovic, “An improved mac layer for the 5g nr ns-3 module,” in Proceedings of the 2019 Workshop on Ns-3, ser. WNS3 2019. New York, NY, USA: Association for Computing Machinery, 2019, p. 41–48. [Online]. Available: https://doi.org/10.1145/3321349.3321350
[19] S. Lagen, K. Wanuga, H. Elkotby, S. Goyal, N. Patriciello, and L. Giupponi, “New radio physical layer abstraction for system-level simulations of 5g networks,” in ICC 2020 - 2020 IEEE International Conference on Communications (ICC), 2020, pp. 1–7.
[20] T. Jiang, J. Zhang, P. Tang, L. Tian, Y. Zheng, J. Dou, H. Asplund, L. Raschkowski, R. D’Errico, and T. Jams ¨ a, “3gpp standardized 5g channel model for iiot scenarios: ¨
A survey,” IEEE Internet of Things Journal, vol. 8, no. 11, pp. 8799–8815, 2021.
[21] “Study on channel model for frequencies from 0.5 to 100 ghz, v16.1.0,” 3GPP, Sophia Antipolis, France, Rep. TR 38.901, Dec 2019.
[22] A. T. Z. Kasgari and W. Saad, “Model-free ultra reliable low latency communication (urllc): A deep reinforcement learning framework,” in ICC 2019 - 2019 IEEE
International Conference on Communications (ICC), 2019, pp. 1–6.