隨著網路科技急遽的進步與發展，網際網路在傳輸速率上有著大幅度的提升，但儘管如此，遇到自然災害或緊急通訊發生時，仍有可能會造成網路系統基礎設施意外損害，進而導致網路資源負載過高。為了能夠對災後網路系統壅塞做出更良好的網路資源管理，並有效提升整體用戶的QoS服務。本研究將在災後高負載網路的情況下，透過發生的災難事件以及網路資源的變化等資訊，找出符合當下條件之場景，並藉由多場景以最適化調配網路資源。在用戶需求遠大於網路資源所能供給量，有限資源會最大化給予緊急安全用戶做救災使用。並隨著網路負載量逐漸降低時，會依照設備可用資源做調整與分配不同優先層級給其餘用戶，以達到最大化的用戶乘載。實驗結果顯示，在Stage 1，讓ESU人員能優先獲取最多網路資源，其中GU class1 下降至 19.55Mbps，而ESU class1增加至9.87Mbps、ESU class2增加至5.01Mbps、ESU class3增加至4.67Mbps。而在Stage 3，優先確保所有用戶(ESU及GU)進行通訊服務(class 1)，ESU class2 下降至 4.61Mbps、ESU class3 下降至 9.61Mbps、GU class1增加至14.22Mbps。

With the rapid advancement and development of networking technologies, the Internet has seen significant improvements in transmission speeds. However, despite these advancements, natural disasters or emergencies can still lead to unexpected damages to the network infrastructure, resulting in an overload of network resources. In order to better manage network resource congestion in post-disaster network systems and effectively improve the overall Quality of Service (QoS) for users, this study aims to identify appropriate scenarios based on the occurrence of disasters and changes in network resources in post-disaster high-load networks. It will optimize the allocation of network resources through various scenarios. In situations where user demand far exceeds available network resources, limited resources are maximized for emergency and security users involved in disaster relief efforts. As the network load gradually decreases, adjustments and allocations to other users are made based on the available resources of the devices, taking into account different priority levels, to maximize user capacity. Based on the experimental results, it is shown that in Stage 1, where ESU personnel are given priority to access the maximum network resources, GU class1 throughput decreased to 19.55 Mbps, while ESU class1 throughput increased to 9.87 Mbps, ESU class2 throughput increased to 5.01 Mbps, and ESU class3 throughput increased to 4.67 Mbps. In Stage 3, where the priority is to ensure communication services for all users (ESU and GU) in class 1, ESU class2 throughput decreased to 4.61 Mbps, ESU class3 throughput decreased to 9.61 Mbps, and GU class1 throughput increased to 14.22 Mbps .

[1] S. Ferdousi, M. Tornatore, F. Dikbiyik, C.U. Martel, S. Xu, Y. Hirota, Y. Awaji and B. Mukherjee, "Joint Progressive Network and Datacenter Recovery After Large-Scale Disasters," IEEE Transactions on Network and Service Management, vol. 17, no. 3, pp. 1501-1514, 2020.
[2] Cybersecurity and Infrastructure Security Agency, "Cyber risks to 911: telephony denial of service", 2020, [online] Available: https://montra.io/resources-old/compliance/psap-cisa/.
[3] M.Y. Selim, A. Alsharoa and A.E. Kamal, "Short-Term and Long-Term Cell Outage Compensation Using UAVs in 5G Networks," Proceedings of the IEEE Global Communications Conference, pp. 1-6, 2018.
[4] M.Y. Selim, A. Alsharoa and A.E. Kamal, "Hybrid Cell Outage Compensation in 5G Networks: Sky-Ground Approach," Proceedings of the IEEE International Conference on Communications, pp. 1-6, 2018.
[5] 5G; System Architecture for the 5G System (3GPP TS 23.501 version 15.3.0 Release 15), [online] Available: https://www.etsi.org/deliver/etsi_ts/123500_123599/123501/15.03.00_60/ts_123501v150300p.pdf.
[6] H. Remmert, "Planning Your Journey to 5G", Digi International, March 19, 2021, [online] Available: https://hub.digi.com/dp/path=/marketing/asset/planning-your-journey-to-5g-wp
[7] K. Hazra, V. K. Shah, M. Bilal, S. Silvestri, S. K. Das, S. K. Das, S. Saha, "A Novel Network Architecture for Resource-Constrained Post-Disaster Environments," proceeding of the Conference on Communication Systems & Networks, pp. 328-335, 2019.
[8] S. S. W. Lee and K. -Y. Chan, "A Traffic Meter Based on a Multicolor Marker for Bandwidth Guarantee and Priority Differentiation in SDN Virtual Networks," IEEE Transactions on Network and Service Management, vol. 16, no. 3, pp. 1046-1058, Sept. 2019.
[9] Y. Xu, G. Gui, H. Gacanin and F. Adachi, "A Survey on Resource Allocation for 5G Heterogeneous Networks: Current Research, Future Trends, and Challenges," IEEE Communications Surveys & Tutorials, vol. 23, no. 2, pp. 668-695, 2021.
[10] R. Joda, M. Elsayed, H.A. Zeid, R. Atawia, A.B. Sediq, G. Boundreau, M.E. Kantarci, "QoS-Aware Joint Component Carrier Selection and Resource Allocation for Carrier Aggregation in 5G," IEEE International Conference on Communications, Montreal, QC, Canada, 2021.
[11] S. Hendaoui, A. Mannai and N. Zangar, "Cognitive CQI/5QI Based Scheme for Software Defined 5G Hybrid Satellite-Terrestrial Network: Slicing for Ultra Reliability And Video Congestion Offloading," International Symposium on Networks, Computers and Communications, Montreal, QC, Canada, 2020.
[12] S. Das, K. M. Rege, J. R. Wullert, F. Suraci, A. Nguyen and D. Manga, "Multimedia Priority Service over Wi-Fi Networks," IEEE Communications Standards Magazine, vol. 6, no. 2, pp. 28-34, June 2022.
[13] Y. Cao, Y. Sun and B. Liu, "5G QoS Resource Allocation Optimization Mechanism for gNB," International Wireless Communications and Mobile Computing, Dubrovnik, Croatia, 2022, pp. 1194-1199, 2022.
[14] Y. -W. Chen, L. -H. Yen, W. -C. Wang, C. -A. Chuang, Y. -S. Liu and C. -C. Tseng, "P4-Enabled Bandwidth Management," Asia-Pacific Network Operations and Management Symposium, Matsue, Japan, pp. 1-5, 2019.
[15] M. Rahouti, K. Xiong, Y. Xin and N. Ghani, "A Priority-Based Queueing Mechanism in Software-Defined Networking Environments," Proceedings of the IEEE 18th Annual Consumer Communications & Networking Conference, pp. 1-2, 2021.
[16] M. Gao, B. Zhang and L. Wang, "A Dynamic Priority Packet Scheduling Scheme for Post-disaster UAV-assisted Mobile Ad Hoc network," IEEE Wireless Communications and Networking Conference, 2021.
[17] F. Niroui, K. Zhang, Z. Kashino and G. Nejat, "Deep Reinforcement Learning Robot for Search and Rescue Applications: Exploration in Unknown Cluttered Environments," IEEE Robotics and Automation Letters, vol. 4, no. 2, pp. 610-617, 2019.
[18] M.F. Ardiansyah, T. William, O.I. Abdullaziz, L.C. Wang, P.L. Tien and M.C. Yuang, "EagleEYE: Aerial Edge-enabled Disaster Relief Response System," Proceedings of the European Conference on Networks and Communications, pp. 321-325, 2020.
[19] V. Chamola, V. Hassija, S. Gupta, A. Goyal, M. Guizani and B. Sikdar, "Disaster and Pandemic Management Using Machine Learning: A Survey," IEEE Internet of Things Journal, vol. 8, no. 21, pp. 16047-16071, 2021.
[20] G. Furquim, G.P.R. Filho, R. Jalali, G. Pessin, R.W. Pazzi and J. Ueyama, "How to Improve Fault Tolerance in Disaster Predictions: A Case Study about Flash Floods Using IoT, ML and Real Data," Sensors, vol. 18, no. 3, pp. 1-20, 2018.
[21] V. Linardos, M. Drakaki, P. Tzionas and Y.L. Karnavas, "Machine Learning in Disaster Management: Recent Developments in Methods and Applications," Machine Learning and Knowledge Extraction, vol. 4, no. 2, pp. 446-473, 2022.
[22] Wilbur L. Ross, Jr., Secretary, "QPPSim A Tool for Rapid Prototyping of LTE QoS, Priority and Pre-emption", Wireless Networks Division Communications Technology Laboratory, National Institute of Standards and Technology, March 2019.