自然灾害会导致地面基站大面积损毁，引发移动通信网络服务中断，严重影响应急救援效率。为快速恢复灾后移动通信网络性能，设计了一种面向应急移动通信网络的空地基站协同部署与资源调度优化方法。首先，建立了灾后地面基站损毁模型，该模型综合考虑地震强度、基站分布与基站建筑特征，可准确刻画地面基站残存概率。同时，设计了用户动态汇聚模型刻画灾后用户迁移规律，获得准确的灾后用户分布特征。在此基础上，结合灾区应急设备及无人机续航时间有限等问题，以最小化空中基站的总能耗为优化目标，对空地基站的发射功率、空中基站位置及资源分配策略进行联合优化。为满足灾后快速部署需求，将原始的非凸混合整数规划问题拆分成地面侧子问题与空中侧子问题，并设计了数值优化与强化学习嵌套的两阶段协同算法。该算法通过将数值优化嵌入深度神经网络的反馈学习过程，降低了传统数值优化算法复杂度，并大幅加快强化学习训练速率。仿真结果表明，相较于对比算法，所提方法在高震级场景下，使用68％的总能耗即可完成通信覆盖恢复并使用户平均速率提升约29%。
Natural disasters can cause large-scale damage to terrestrial base stations, leading to mobile network service disruptions and severely degrading the efficiency of emergency rescue operations. To rapidly restore post-disaster mobile network performance, this paper proposes an optimization method for coordinated air–ground base-station deployment and resource scheduling in emergency mobile communication networks. First, a post-disaster terrestrial base-station damage model is developed, which jointly considers earthquake intensity, base-station distribution, and structural characteristics of base-station buildings, enabling accurate characterization of the survival probability of terrestrial base stations. Meanwhile, a dynamic user aggregation model is designed to capture post-disaster user mobility patterns, yielding accurate post-disaster user distribution features. On this basis, considering practical constraints such as limited emergency equipment availability and finite UAV endurance in disaster areas, the total energy consumption of aerial base stations is minimized by jointly optimizing the transmit power of air–ground base stations, the placement of aerial base stations, and resource allocation strategies. To meet the requirement of rapid post-disaster deployment, the original non-convex mixed-integer programming problem is decomposed into a terrestrial-side subproblem and an aerial-side subproblem, and a two-stage collaborative algorithm is devised by nesting numerical optimization within reinforcement learning. By embedding numerical optimization into the feedback learning process of deep neural networks, the proposed algorithm reduces the complexity of conventional numerical optimization and significantly accelerates reinforcement learning training. Simulation results show that, compared with baseline algorithms, in high-magnitude earthquake scenarios, the proposed method restores communication coverage using only 68% of the total energy consumption while improving the average user rate by approximately 29%.
[1] 李诗尧. 落地通信基站地震易损性及功能失效概率评估[D]. 黑龙江:中国地震局工程力学研究所,2017.pp.9-19
[2] Singh R, Thompson M, Mathews S A, et al. Aerial base stations for enabling cellular communications during emergency situation[C] 2017 International Conference on Vision, Image and Signal Processing (ICVISP). IEEE, 2017: 103-108
[3] Yang B, Xiong X, Liu H, et al. Unmanned aerial vehicle assisted post-disaster communication coverage optimization based on internet of things big data analysis[J]. Sensors, 2023, 23(15): 6795
[4] Li Z, Chen Q, Huang Y, et al. Post-Disaster Emergency Communications Enhanced by Drones and Non-Orthogonal Multiple Access: Three Dimensional De-ployment Optimization and Spectrum Alloca-tion[J]. Drones, 2024, 8(2): 63.
[5] Ma B, Zhang J, Zhang Z, et al. Time-efficient joint UAV-BS deployment and user association based on machine learning[J]. IEEE Internet of Things Journal, 2023, 10(14): 13077-13094.
[6] Cao Y, Luo Y, Yang H, et al. UAV-based emergency communications: An iterative two-stage multiagent soft actor–critic approach for optimal association and dynamic deployment[J]. IEEE Internet of Things Journal, 2023, 11(16): 26610-26622.
[7] Khalil A, Zhang T, Wu L, et al. Optimizing Disaster Response through Efficient Path Planning of Mobile Aerial Base Station with Genetic Algorithm[J]. Drones, 2024, 8(6): 272.
[8] Mozaffari M, Saad W, Bennis M, et al. Mobile un-manned aerial vehicles for energy-efficient Internet of Things communications [J]. IEEE Journal on Selected Areas in Communications, 2017, 35(5): 1136-1150.
[9] X. Tang, F. Chen, F. Wang and Z. Jia Disaster-Resilient Emergency Communication With Intelligent Air–Ground Cooperation[J]. IEEE Internet of Things Journal, vol. 11, no. 3, pp. 5331-5346
[10] 周中红,孙艳萍,朱瑞. 基于新型地震烈度快速评估方法的震后人员压埋估计[J]. 地球科学,2024,49(2):437-450. DOI:10.3799/dqkx.2023.178.
[11] 中国地震烈度表 GB/T 17742-2020
[12] Nakashima T, Okada S. Seismic strengthening strategy for wood frame dwellings targeting to minimize the death toll from a view point of temporal variation[J]. J. of Structural and Construction Engineering, 2008, 73(623): 79-86.
[13] S. Mitsui and H. Nishiyama, A Bandwidth Allocation Algorithm Mitigating Unfairness Issues in a UAV-Aided Flying Base Station Used for Disaster Recovery [C] 2023 IEEE 98th Vehicular Technology Conference Hong Kong, Hong Kong, 2023, pp. 1-6
[14] Shakhatreh H, Hayajneh K, Bani-Hani K, et al. Cell on Wheels‐Unmanned Aerial Vehicle System for Providing Wireless Coverage in Emergency Situations[J]. Complexity, 2021, 2021(1): 8669824.
[15] Deruyck M, Wyckmans J, Joseph W, et al. Designing UAV-aided emergency networks for large-scale disaster scenarios[J]. EURASIP Journal on Wireless Communications and Networking, 2018, 2018(1): 1-12.
[16] Hamid H, Begh G R. Clustering based strategic 3D deployment and trajectory optimization of UAVs with A-star algorithm for enhanced disaster response[J]. Physical Communication, 2024, 67: 102536.
[17] H. Qu, W. Zhang, J. Zhao, Z. Luan and C. Chang, Rapid Deployment of UAVs Based on Bandwidth Resources in Emergency Scenarios[C] 2020 Information Communication Technologies Conference (ICTC), Nanjing, China, 2020, pp. 86-90
[18] G. Peng, Y. Xia, X. Zhang and L. Bai, UAV-aided Networks for Emergency Communications in Areas with Unevenly Distributed Users[C], 2018 IEEE International Conference on Communication Systems (ICCS), Chengdu, China, 2018, pp. 25
[19] Nabanita Das, Souvik Basu, and Sipra Das Bit. 2018. Hm2Sc: Human Movement Model for Post Disaster Scenario in Smart City.[C] In Proceedings of the 1st Workshop on Complex Networked Systems for Smart Infrastructure (CNetSys '18). Association for Computing Machinery, New York, NY, USA, 7–12.
[20] Merwaday A, Tuncer A, Kumbhar A, et al. Improved throughput coverage in natural disasters: Unmanned aerial base stations for public-safety communications[J]. IEEE vehicular technology magazine, 2016, 11(4): 53-60.
[21] J. Li, D. Lu, G. Zhang, J. Tian and Y. Pang, Post-Disaster Unmanned Aerial Vehicle Base Station Deployment Method Based on Artificial Bee Colony Algorithm [J] in IEEE Access, vol. 7, pp. 168327-168336, 2019
[22] Fujimoto S, Van Hoof H , Meger D .Addressing Function Approximation Error in Actor-Critic Methods[J]. 2018.DOI:10.48550/arXiv.1802.09477.
[23] ZHAO H, WANG H, WU W, et al. Deployment Algorithms for UAV Airborne Networks Toward On-Demand Coverage [J]. IEEE Journal on Selected Areas in Communications, 2018, 36(9): 2015-31.
CJA