隨著物聯網（IoT）設備在智慧環境中的快速部署，如智慧校園和城市，對於異質網路的服務品質（QoS）管理需求日益增長。在本論文中，我們將網路數位孿生（NDT）的概念擴展到網路化的物聯網設備，提出了一種增強智慧環境功能和性能的網路數位孿生控制器（NDTC）。我們的NDTC通過創建實體孿生（PT）的數位孿生（DT）、同步它們的狀態以及進行與QoS相關的假設分析，解決了關鍵挑戰。具體而言，我們利用開源軟體定義網路（SDN）控制器構建了一個DT支持的物聯網儀器化智慧環境。我們使用我們提出的最佳更新（OU）和梯度驅動更新（GU）演算法來解決狀態同步問題，通過調整更新頻率和資料粒度，在給定的網路頻寬預算內最小化DT/PT狀態偏差。我們還通過使用最佳選擇（OS）演算法選擇最優的假設分析器來解決假設分析問題，以在給定的計算時間預算內進行最準確的QoS預測。我們在真實測試平台上進行的實驗展示了我們所提出解決方案的優點：（i）我們開發的NDTC和演算法滿足功能需求，（ii）我們的OU和GU演算法顯著減少了PT與DT之間的狀態偏差，（iii）我們的OS演算法大幅減少了假設分析的預測誤差，（iv）所有我們提出的演算法均帶來可接受的資源消耗。

The rapid deployment of Internet-of-Things (IoT) devices in smart environments such as smart campuses and cities necessitates robust Quality-of-Service (QoS) management across heterogeneous networks. In this thesis, we extend the concept of Network Digital Twin (NDT) to networked IoT devices, presenting a Network Digital Twin Controller (NDTC) that enhances the functionality and performance of smart environments. Our NDTC addresses key challenges by creating Digital Twins (DTs) of Physical Twins (PTs), synchronizing their states, and performing QoS-related what-if analysis. Specifically, we build a DT-enabled IoT-instrumented smart environment by utilizing an open-source Software-Defined Network (SDN) controller. We formulate and solve the state synchronization problem using our proposed Optimal Update (OU) and Gradient-driven Update (GU) algorithms, carefully adjusting the update frequency and data granularity to minimize DT/PT state deviation within given network bandwidth budgets. We also formulate and address the what-if analysis problem by selecting optimal what-if analyzers using our Optimal Selection (OS) algorithm for the most accurate QoS predictions under a given computing time budget.
Our extensive experiments on a real testbed demonstrate the merits of our proposed solution: (i) our developed NDTC and algorithms meet the functional requirements, (ii) our OU and GU algorithms significantly reduce the state deviation between PTs and DTs, (iii) our OS algorithm largely reduces the prediction errors of what-if analysis, and (iv) all our proposed algorithms incur acceptable overhead.

[1] A. Al-Fuqaha, M. Guizani, M. Mohammadi, M. Aledhari, and M. Ayyash. Internet of things: A survey on enabling technologies, protocols, and applications. IEEE communications surveys & tutorials, 17(4):2347–2376, June 2015.
[2] K. Alanezi and S. Mishra. Towards a Scalable Architecture for Building Digital Twins at the Edge. In Proc. of IEEE/ACM Symposium on Edge Computing (SEC), pages 325–329, Wilmington, DE, USA, December 2023.
[3] P. Almasan, M. Ferriol-Galm´es, J. Paillisse, J. Su´arez-Varela, D. Perino, D. L´opez, A. A. P. Perales, P. Harvey, L. Ciavaglia, L. Wong, et al. Network digital twin: Context, enabling technologies, and opportunities. IEEE Communications Magazine, 60(11):22–27, 2022.
[4] A. Bencz´ur, L. Kocsis, and R. P´alovics. Online machine learning in big data streams. arXiv preprint arXiv:1802.05872, pages 1–40, 2018.
[5] H. Chen, T. Todd, D. Zhao, and G. Karakostas. Digital Twin Model Selection for Feature Accuracy. IEEE Internet of Things Journal, 11(7):11415 – 11426, 2023.
[6] Y. Dai, K. Zhang, S. Maharjan, and Y. Zhang. Deep reinforcement learning for stochastic computation offloading in digital twin networks. IEEE Transactions on Industrial Informatics, 17(7):4968–4977, 2020.
[7] Y. Edalat, J.-S. Ahn, and K. Obraczka. Smart experts for network state estimation. IEEE Transactions on Network and Service Management, 13(3):622–635, 2016.
[8] A. El Saddik, F. Laamarti, and M. Alja’Afreh. The potential of digital twins. IEEE Instrumentation and Measurement Magazine, 24(3):36–41, May 2021.
[9] M. Ferriol-Galm´es, J. Su´arez-Varela, J. Pailliss´e, X. Shi, S. Xiao, X. Cheng, P. Barlet-Ros, and A. Cabellos-Aparicio. Building a digital twin for network optimization using graph neural networks. Elsevier Computer Networks, 217:109329, 2022.
[10] Free Software Foundation. GLPK, 2012. https://www.gnu.org/software/glpk/.
[11] A. Fuller, Z. Fan, C. Day, and C. Barlow. Digital twin: Enabling technologies, challenges and open research. IEEE access, 8:108952–108971, May 2020.
[12] C. G¨uemes-Palau, P. Almasan, S. Xiao, X. Cheng, X. Shi, P. Barlet-Ros, and A. Cabellos-Aparicio. Accelerating deep reinforcement learning for digital twin network optimization with evolutionary strategies. In Proc. of IEEE/IFIP Network Operations and Management Symposium (NOMS), pages 1–5, Budapest, Hungary, April 2022.
[13] C. Hoi, D. Sahoo, J. Lu, and P. Zhao. Online learning: A comprehensive survey. Elsevier Neurocomputing, 459:249–289, 2021.
[14] H. Hong, Q. Wu, F. Dong, W. Song, R. Sun, T. Han, C. Zhou, and H. Yang. Netgraph: An intelligent operated digital twin platform for data center networks. In Proc. of the ACM SIGCOMM workshop on network-application integration, pages 26–32, Virtual Event, USA, August 2021.
[15] International Business Machines Corporation (IBM). CPLEX, 2024. https://www.ibm.com/products/ilog-cplex-optimization-studio.
[16] ITU-T. Digital twin network – Requirements and architecture, 2022. https://www.itu.int/rec/T-REC-Y.3090s.
[17] M. Jafari, A. Kavousi-Fard, T. Chen, and M. Karimi. A review on digital twin technology in smart grid, transportation system and smart city: Challenges and future. IEEE Access, 11:17471 – 17484, February 2023.
[18] e. a. Jin, Jiong. Network architecture and QoS issues in the Internet of things for a smart city. In Proc. of IEEE International Symposium on Communications and Information Technologies (ISCIT), pages 956–961, October 2012.
[19] D. Kreutz, F. M. Ramos, P. E. Verissimo, C. E. Rothenberg, S. Azodolmolky, and S. Uhlig. Software-defined networking: A comprehensive survey. Proceedings of the IEEE, 103(1):14–76, December 2014.
[20] G. Li, T. Luan, X. Li, J. Zheng, C. Lai, Z. Su, and K. Zhang. Breaking down data sharing barrier of smart city: A digital twin approach. IEEE Network, pages 1 – 9, May 2023.
[21] J. Li, J. Wang, Q. Chen, Y. Li, and A. Zomaya. Digital twin-enabled service satisfaction enhancement in edge computing. In Proc. of IEEE INFOCOM Conference on Computer Communications, pages 1–10, New York City, NY, USA, May 2023.
[22] G. Lin, J. Gel, Y. Wu, H. Li, and L. Li. Digital twin networks: learning dynamic network behaviors from network flows. In Proc. of IEEE Symposium on Computers and Communications (ISCC), pages 1–6, Rhodes, Greece, June 2022.
[23] Linux Foundation. OpenvSwitch, 2016. https://www.openvswitch.org/.
[24] Q. Liu, L. Tang, T. Wu, and Q. Chen. Deep reinforcement learning for resource demand prediction and virtual function network migration in digital twin network. IEEE Internet of Things Journal, 10(21):19102 – 19116, 2023.
[25] P. Major, G. Li, H. Hildre, and H. Zhang. The use of a data-driven digital twin of a smart city: A case study of ˚Alesund, norway. IEEE Instrumentation & Measurement Magazine, 24(7):39–49, 2021.
[26] O. Marai, T. Taleband, and J. Song. Roads infrastructure digital twin: A step toward smarter cities realization. IEEE Network, 35(2):136–143, March-April 2021.
[27] K. Mayer, R. Pinto, J. Soares, D. Arantes, C. Rothenberg, V. Cavalcante, L. Santos, F. Moraes, and D. Mello. Demonstration of ML-assisted soft-failure localization based on network digital twins. IEEE Journal of Lightwave Technology, 40(14):4514–4520, 2022.
[28] R. Minerva and N. Crespi. Digital twins: Properties, software frameworks, and application scenarios. IT Professional, 23(1):51–55, April 2021.
[29] G. Mylonas, A. Kalogeras, G. Kalogeras, C. Anagnostopoulos, C. Alexakos, and L. Mu˜noz. Digital twins from smart manufacturing to smart cities: A survey. IEEE Access, 9:143222–143249, October 2021.
[30] Y. Nabil, H. ElSawy, S. Al-Dharrab, H. Mostafa, and H. Attia. Data aggregation in regular large-scale IoT networks: Granularity, reliability, and delay tradeoffs. IEEE Internet of Things Journal, 9(18):17767–17784, 2022.
[31] H. Nguyen, R. Trestian, D. To, and M. Tatipamula. Digital twin for 5G and beyond. IEEE Communications Magazine, 59(2):10–15, February 2021.
[32] NS3 Network Simulator , 2011. https://www.nsnam.org/.
[33] Ontje L¨unsdorf. Simpy, 2023. https://simpy.readthedocs.io/en/latest/.
[34] M. Polverini, I. Germini, A. Cianfrani, F. G. Lavacca, and M. Listanti. A Digital Twin based Framework to Enable “What-If” Analysis in BGP Optimization. In Proc. of IEEE/IFIP Network Operations and Management Symposium (NOMS), pages 1–6, Miami, FL, USA, May 2023.
[35] M. Polverini, F. Lavacca, J. Gal´an-Jim´enez, D. Aureli, A. Cianfrani, and M. Listanti. Digital twin manager: A novel framework to handle conflicting network applications. In Proc. of IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN), pages 85–88, Phoenix, AZ, USA, November 2022.
[36] K. Poularakis, Q. Qin, L. Ma, S. Kompella, K. K. Leung, and L. Tassiulas. Learning the optimal synchronization rates in distributed SDN control architectures. In Proc. of IEEE INFOCOM 2019 Conference on Computer Communications, pages 1099–1107, Paris, France, April 2019.
[37] L. Raes, P. Michiels, T. Adolphi, C. Tampere, A. Dalianis, S. McAleer, and P. Kogut. Duet: A framework for building interoperable and trusted digital twins of smart cities. IEEE Internet Computing, 26(3):43–50, May 2022.
[38] D. Raj, T. Ahmed, A. Hirwe, P. Tammana, and K. Kataoka. Building a digital twin network of sdn using knowledge graphs. IEEE Access, 11:63092 – 63106, 2023.
[39] A. Rasheed, O. San, and T. Kvamsdal. Digital twin: Values, challenges and enablers from a modeling perspective. IEEE Access, 8:21980–22012, January 2020.
[40] A. Ridwan, M. Radzi, F. Abdullah, and Y. Jalil. Applications of machine learning in networking: a survey of current issues and future challenges. IEEE access, 9:52523–52556, 2021.
[41] M. M. Rosell´o, V. Cancela, I. Quintana, and M. Lorenzo. Network Digital Twin for Non-Public Networks. In Proc. of IEEE 24th International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM), pages 495–500, Boston, MA, USA, June 2023.
[42] K. Rusek, J. Su´arez-Varela, A. Mestres, P. Barlet-Ros, and A. Cabellos-Aparicio. Unveiling the potential of graph neural networks for network modeling and optimization in sdn. In Proceedings of the 2019 ACM Symposium on SDN Research, pages 140–151, 2019.
[43] Ryu SDN Framework Community. Ryu, 2017. https://ryu-sdn.org/.
[44] N. Savage. Virtual duplicates. Commun. ACM, 65(2):14–16, January 2022.
[45] K. Sood, K. K. Karmakar, S. Yu, V. Varadharajan, S. R. Pokhrel, and Y. Xiang. Alleviating heterogeneity in SDN-IoT networks to maintain QoS and enhance security. IEEE Internet of Things Journal, 7(7):5964–5975, December 2019.
[46] M. Talebkhah, A. Sali, M. Marjani, M. Gordan, S. J. Hashim, and F. Z. Rokhani. Iot and big data applications in smart cities: recent advances, challenges, and critical issues. IEEE Access, 9:55465–55484, April 2021.
[47] F. Tang, X. Chen, K. Rodrigues, M. Zhao, and N. Kato. Survey on digital twin edge networks (DITEN) toward 6G. IEEE Open Journal of the Communications Society, 3:1360–1381, August 2022.
[48] G. Tangari, D. Tuncer, M. Charalambides, Y. Qi, and G. Pavlou. Self-adaptive decentralized monitoring in software-defined networks. IEEE Transactions on Network and Service Management, 15(4):1277–1291, 2018.
[49] S. Taylor, B. Johansson, S. Jeon, L. Lee, P. Lendermann, and G. Shao. Using simulation and digital twins to innovate: Are we getting smarter? In 2021 Winter Simulation Conference (WSC), pages 1–13, December 2021.
[50] M. Vaezi, K. Noroozi, T. Todd, D. Zhao, G. Karakostas, H. Wu, and X. Shen. Digital twins from a networking perspective. IEEE Internet of Things Journal, 9(23):23525–23544, 2022.
[51] R. Vilalta, L. Gifre, R. Casellas, R. Mu˜noz, R. Mart´ınez, A. Mozo, A. Pastor, D. L´opez, and J. P. Fern´andez-Palacios. Applying digital twins to optical networks with cloud-native sdn controllers. IEEE Communications Magazine, 61(12):128 – 134, 2023.
[52] H. Wang, Y. Wu, G. Min, and W. Miao. A graph neural network-based digital twin for network slicing management. IEEE Transactions on Industrial Informatics, 18(2):1367–1376, 2020.
[53] Y. Wang, Z. Su, S. Guo, M. Dai, T. H. Luan, and Y. Liu. A survey on digital twins: Architecture, enabling technologies, security and privacy, and future prospects. IEEE Internet of Things Journal, 10(17):14965–14987, 2023.
[54] J. Wen, B. Gabrys, and K. Musial. Toward digital twin oriented modeling of complex networked systems and their dynamics: A comprehensive survey. Ieee Access, 10:66886–66923, 2022.
[55] J. Wieme, M. Baert, and J. Hoebeke. Managing a QoS-enabled Bluetooth Mesh network using a Digital Twin Network: An experimental evaluation. Elsevier Internet of Things, 25:101023, 2024.
[56] Y. Wu, K. Zhang, and Y. Zhang. Digital twin networks: A survey. IEEE Internet of Things Journal, 8(18):13789–13804, 2021.
[57] M. Yannuzzi, F. van Lingen, A. Jain, O. L. Parellada, M. M. Flores, D. Carrera, J. L. P´erez, D. Montero, P. Chacin, A. Corsaro, et al. A new era for cities with fog computing. IEEE Internet Computing, 21(2):54–67, 2017.
[58] P. Yu, J. Zhang, H. Fang, W. Li, L. Feng, F. Zhou, P. Xiao, and S. Guo. Digital twin driven service self-healing with graph neural networks in 6g edge networks. IEEE Journal on Selected Areas in Communications, 41(11):3607 – 3623, 2023.
[59] A. Zanella, N. Bui, A. Castellani, L. Vangelista, and M. Zorzi. Internet of things for smart cities. IEEE Internet of Things journal, 1(1):22–32, August 2014.
[60] L. Zhu, M. M. Karim, K. Sharif, C. Xu, F. Li, X. Du, and M. Guizani. SDN controllers: A comprehensive analysis and performance evaluation study. ACM Computing Surveys (CSUR), 53(6):1–40, December 2020.