臺灣博碩士論文加值系統

毫米波在未來的通訊系統中扮演重要的角色。然而，毫米波收發器的密集佈建會對於管理無線接取網路帶來沈重的負擔，這項問題讓使用智慧網路管理技術的需求增加。由於邊緣運算的技術出現，基於機器學習的網路管理演算法和延遲敏感的使用者應用程式可以運行在邊緣伺服器上。然而，因為邊緣伺服器上的資源有限，必須要開發一個協調智慧網路管理和使用者應用程式的機制。在本論文中，我們提出一個資源管理框架，在運行智慧網路管理算法和使用者應用程式的邊緣運算平台中，對使用者體驗品質進行優化。具體上，我們採用的情境是毫米波通訊系統配置有基於機器學習的毫米波波束追蹤算法，而系統中的使用者會請求行動遊戲服務。我們制定基於使用者體驗之協調問題，並且證明其NP難度。為了降低計算複雜度，我們將原本問題分解成遊戲服務放置以及毫米波波束追蹤設定選擇和放置兩個子問題。接著，我們使用啟發式演算法依序解決兩個子問題。模擬結果表明我們提出的協調機制的有效性。

Millimeter wave (mmWave) is a crucial component in 5G and beyond 5G communications. However, the dense deployment of mmWave transceivers would impose a heavy burden on the management of the radio access network (RAN). This issue increases the need for leveraging intelligent network management techniques. Thanks to edge computing, ML-based network management algorithms and other delay-sensitive user applications can operate at the network edge. However, due to limited resources on the edge servers, it is necessary to develop an orchestration scheme for intelligent network management and user applications. In this research, we provide an edge-centric resource management framework for intelligent RAN management and applications with the awareness of the users' QoE. Specifically, we consider the scenario of a mmWave communication system equipped with an ML-based mmWave beam tracking algorithm, and the users under this system request for mobile edge gaming service. We formulate a game QoE aware orchestration problem as a non-linear integer programming and prove its NP-hardness. To reduce the complexity, we decompose the original problem into two subproblems, named the service placement problem for mobile edge gaming and the configuration selection and placement problem for mmWave beam tracking. Then, we solve the two subproblems consecutively with heuristic approaches. Simulation results demonstrate the effectiveness of the proposed orchestration scheme.

Chapter 1 Introduction 1
1.1 General Background . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Research Scope . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.3 Contribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
Chapter 2 Related Works 5
2.1 Machine Learning Based mmWave Beam Tracking . . . . . . . . . . 5
2.2 Edge Computing Assisted Game Streaming Services . . . . . . . . . 6
2.3 Orchestration of Edge Intelligence . . . . . . . . . . . . . . . . . . . 7
Chapter 3 System Model 9
3.1 System Description . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3.2 Communication Model . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.3 Computing Model . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
Chapter 4 Problem Formulation 14
4.1 User Requests and Service Placement . . . . . . . . . . . . . . . . . 14
4.2 Configuration Selection and Placement of Beam Tracking . . . . . . 15
4.3 Game QoE Model . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
4.4 Optimization Problem . . . . . . . . . . . . . . . . . . . . . . . . . 19
4.5 Problem Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
Chapter 5 Proposed Solutions 24
5.1 Algorithm for the Service Placement of Mobile Edge Gaming . . . . 24
5.2 Algorithm for the Configuration Selection and Placement of Beam
Tracking . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
5.3 Complexity Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . 27
Chapter 6 Evaluation Results 29
6.1 Environmental Settings . . . . . . . . . . . . . . . . . . . . . . . . . 29
6.1.1 Testbed . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
6.1.2 Gaming . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
6.1.3 Millimeter-wave Beam Tracking Model . . . . . . . . . . . . . . . 31
6.1.4 Benchmarks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
6.2 Numerical Simulations . . . . . . . . . . . . . . . . . . . . . . . . . 33
6.2.1 Computation Time . . . . . . . . . . . . . . . . . . . . . . . . . . 34
6.2.2 Number of Users . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
6.2.3 Available GPU Memory . . . . . . . . . . . . . . . . . . . . . . . 37
6.2.4 Available GPU Utilization . . . . . . . . . . . . . . . . . . . . . . 37
6.2.5 Distribution of User Request . . . . . . . . . . . . . . . . . . . . . 38
Chapter 7 Conclusions 39
References 40

[1] O-RAN Alliance. (2018) O-ran whitepaper - building the next generation ran. [Online]. Available: https://www.o-ran.org/resources
[2] A. Ly and Y.-D. Yao, “A review of deep learning in 5g research: Channel coding, massive mimo, multiple access, resource allocation, and network security,” IEEE Open Journal of the Communications Society, vol. 2, pp. 396–408, 2021.
[3] Y. Zhang, J.-H. Liu, C.-Y. Wang, and H.-Y. Wei, “Decomposable intelligence on cloud-edge iot framework for live video analytics,” IEEE Internet of Things Journal, vol. 7, no. 9, pp. 8860–8873, 2020.
[4] Y. Zhang and H.-Y. Wei, “Risk-aware cloud-edge computing framework for delay-sensitive industrial iots,” IEEE Transactions on Network and Service Management, vol. 18, no. 3, pp. 2659–2671, 2021.
[5] Y.-T. Yang and H.-Y. Wei, “Edge computing and networking resource management for decomposable deep learning: An auction-based approach,” in 2021 22nd Asia-PacificNetwork OperationsandManagementSymposium(APNOMS). IEEE, 2021, pp. 108–113.
[6] M. Alrabeiah, J. Booth, A. Hredzak, and A. Alkhateeb, “Viwi vision-aided mmwave beam tracking: Dataset, task, and baseline solutions,” arXiv preprint arXiv:2002.02445, 2020.
[7] H. Luo and H.-Y. Wei, “Machine learning based mmwave orchestration for edge gaming qoe enhancement,” in Proc. IEEE 94th Vehicular Technology Conference (VTC2021-Fall). IEEE, 2021, pp. 1–6.
[8] Y. Tian, G. Pan, and M.-S. Alouini, “Applying deep-learning-based computer vision to wireless communications: Methodologies, opportunities, and challenges,” IEEE Open Journal of the Communications Society, vol. 2, pp. 132–143, 2020.
[9] Z. Hu and C. Han, “Image and index fused sequence-to-sequence algorithm for vision-aided millimeter-wave beam tracking,” in Proceedings of the 5th ACM Workshop on Millimeter-Wave and Terahertz Networks and Sensing Systems, 2021, pp. 7–12.
[10] Y. Tian and C. Wang, “Vision-aided beam tracking: Explore the proper use of camera images with deep learning,” in 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall). IEEE, 2021, pp. 01–05.
[11] S. Jiang and A. Alkhateeb, “Computer vision aided beam tracking in a real-world millimeter wave deployment,” arXiv preprint arXiv:2111.14803, 2021.
[12] S. Choy, B. Wong, G. Simon, and C. Rosenberg, “A hybrid edge-cloud architecture for reducing on-demand gaming latency,” Multimedia systems, vol. 20, no. 5, pp. 503–519, 2014.
[13] X. Zhang, H. Chen, Y. Zhao, Z. Ma, Y. Xu, H. Huang, H. Yin, and D. O. Wu, “Improving cloud gaming experience through mobile edge computing,” IEEE Wireless Communications, vol. 26, no. 4, pp. 178–183, 2019.
[14] T. Cao, Z. Qian, K. Wu, M. Zhou, and Y. Jin, “Service placement and bandwidth allocation for mec-enabled mobile cloud gaming,” in 2021 IEEE 22nd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM). IEEE, 2021, pp. 179–188.
[15] A. Alkhateeb, S. Alex, P. Varkey, Y. Li, Q. Qu, and D. Tujkovic, “Deep learning coordinated beamforming for highly-mobile millimeter wave systems,” IEEE Access, vol. 6, pp. 37328–37348, 2018.
[16] C.-Y. Huang, K.-T. Chen, D.-Y. Chen, H.-J. Hsu, and C.-H. Hsu, “Gaminganywhere: The first open source cloud gaming system,” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), vol. 10, no. 1s, pp. 1–25, 2014.
[17] X. Wang, Y. Han, V. C. Leung, D. Niyato, X. Yan, and X. Chen, “Convergence of edge computing and deep learning: A comprehensive survey,” IEEE Communications Surveys & Tutorials, vol. 22, no. 2, pp. 869–904, 2020.
[18] S. Wang and S. Dey, “Modeling and characterizing user experience in a cloud server based mobile gaming approach,” in Proc. IEEE Global Commun. Conf. (GLOBECOM), 2009, pp. 1–7.
[19] K.-T. Chen, Y.-C. Chang, P.-H. Tseng, C.-Y. Huang, and C.-L. Lei, “Measuring the latency of cloud gaming systems,” in Proceedings of the 19th ACM international conference on Multimedia, 2011, pp. 1269–1272.
[20] Huawei. (2016) Mobile networks with the best gaming experience. [Online]. Available: https://gsacom.com/paper/mobile-networks-best-gaming-experience/
[21] J. Klaue, B. Rathke, and A. Wolisz, “Evalvid–a framework for video transmission and quality evaluation,” in Proc. International conference on modelling techniques and tools for computer performance evaluation. Springer, 2003, pp. 255–272.
[22] H. D. Sherali and W. P. Adams, A reformulation-linearization technique for solving discrete and continuous nonconvex problems. Springer Science & Business Media, 2013, vol. 31.
[23] Y. Song, C. Zhang, and Y. Fang, “Multiple multidimensional knapsack problem and its applications in cognitive radio networks,” in Proc. IEEE Military Communications Conference (MILCOM). IEEE, 2008, pp. 1–7.
[24] M. Hifi, M. Michrafy, and A. Sbihi, “Heuristic algorithms for the multiple-choice multidimensional knapsack problem,” Journal of the Operational Research Society, vol. 55, no. 12, pp. 1323–1332, 2004.
[25] J. Liu, Q. Yang, G. Simon, and W. Cui, “Migration-based dynamic and practical virtual streaming agent placement for mobile adaptive live streaming,” IEEE Transactions on Network and Service Management, vol. 15, no. 2, pp. 503–515, 2017.
[26] M. Amiri, H. A. Osman, S. Shirmohammadi, and M. Abdallah, “Toward delay-efficient game-aware data centers for cloud gaming,” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), vol. 12, no. 5s, pp. 1–19, 2016.
[27] M. Alrabeiah, A. Hredzak, Z. Liu, and A. Alkhateeb, “Viwi: A deep learning dataset framework for vision-aided wireless communications,” in Proc. IEEE 91st Vehicular Technology Conference (VTC2020-Spring), 2020, pp. 1–5.
[28] M. Alrabeiah, A. Hredzak, and A. Alkhateeb, “Millimeter wave base stations with cameras: Vision-aided beam and blockage prediction,” in Proc. IEEE 91st Vehicular Technology Conference (VTC2020-Spring). IEEE, 2020, pp. 1–5.
[29] Gurobi Optimization. (2015) Gurobi optimizer reference manual. [Online]. Available: https://www.gurobi.com
[30] S. Diamond and S. Boyd, “CVXPY: A Python-embedded modeling language for convex optimization,” Journal of Machine Learning Research, vol. 17, no. 83, pp.1–5, 2016.
[31] R. S. Camati, A. Calsavara, and L. Lima Jr, “Solving the virtual machine placement problem as a multiple multidimensional knapsack problem,” in Proc. The Thirteenth International Conference on Networks (ICN), 2014, p. 264.