Published December 17, 2025 | Version v1
Dataset Open

Research on microgrid resilience in highway service areas based on federated multi-agent deep reinforcement learning

Authors/Creators

Description

针对频繁极端天气事件对高速公路服务区微电网系统安全稳定运行带来的严峻挑战,本文提出了基于联邦多智能体深度强化学习(FMADRL)的综合微电网韧性优化方法。首先,通过将生成对抗网络(GAN)与蒙特卡洛模拟整合,构建了一个高精度极端天气场景生成模型。通过融合长期和短期气候数据,生成了1个时空相关的情景样本,有效捕捉极端事件的动态特征。其次,设计了一种基于联邦学习架构的多智能体协作调度机制,在保护数据隐私的同时,高效优化五个分布式服务区微电网。 随后,引入了涟漪扩散算法(RSA),建立了多目标优化框架,在经济效率、可靠性和响应等维度上产生了000个帕累托最优解,确保了稳健的决策。 最后,大规模模拟实验表明,该方法在综合系统韧性指标上得分为285.88,平均故障恢复时间从3.46分钟缩短至6.8分钟,年运营成本降低4.69%(相当于3.3万日元),实现年碳排放减少747吨。这种方法为增强分布式微电网在极端天气事件中的韧性提供了创新解决方案。

Files

Files (43.1 kB)

Name Size Download all
md5:695e317ce9f8f774138687472f3b7bc8
300 Bytes Download
md5:9e58b6710851283eb0d566acb09c5773
250 Bytes Download
md5:4a3aecf3b1403d89d87982dd1e0b3f10
3.2 kB Download
md5:7891e35648653eed6af78d9ed4dc261e
200 Bytes Download
md5:942a05545959f9ef173dacb92d8baead
600 Bytes Download
md5:2b06dc4430edb9678515114bdd65fe05
714 Bytes Download
md5:eab3f9e22764b6f111691a0d0f4589f4
3.3 kB Download
md5:5b4ae3c622a83d24d0ff30a4400f5d5b
136 Bytes Download
md5:e6a3f61e7a3f8bfef4abe1bd305ec08a
1.7 kB Download
md5:5c62ff28e3ed2d5095fe2f91ba07e661
300 Bytes Download
md5:dfa0ac595effe1bdcbae6405bef3a607
5.1 kB Download
md5:3d9ab85449957195944230c19b97679e
6.8 kB Download
md5:3cf9f3c314881f0873058da05f87c2c7
9.7 kB Download
md5:2d3f611d723d9a76deb5d72de661099c
9.9 kB Download
md5:7e76f2fa9baa77310cb3d520b83e91f9
300 Bytes Download
md5:2c132284479648fd2919fa5fcc616171
588 Bytes Download

Additional details

References

  • [1] S. Ma, L. Su, Z. Wang, F. Qiu and G. Guo, "Resilience Enhancement of Distribution Grids Against Extreme Weather Events," in IEEE Transactions on Power Systems, vol. 33, no. 5, pp. 4842-4853, Sept. 2018, doi: 10.1109/TPWRS.2018.2822295. [2] F. Chen, M. Xia, Q. Chen and L. Yang, "Resilience Enhancement Method Against Persistent Extreme Weather With Low Temperatures in Self-Sustained Highway Transportation Energy System," in IEEE Transactions on Industry Applications, vol. 60, no. 1, pp. 996-1009, Jan.-Feb. 2024, doi: 10.1109/TIA.2023.3290569. [3] J. Du, W. Hu, S. Zhang, D. Cao, W. Liu, Z. Zhang, D. Wang, Z. Chen, A distributionally robust collaborative scheduling and benefit fallocation method for interconnected microgrids considering tail risk assessment, Applied Energy, Volume 391,2025, 125910, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2025.125910. [4] Z. Zheng, B. Qian, W. Liu, Q. Zhu, H. Li, D. Dong, Y. Yuan, Enhanced schedule optimization with cross-scale coupling for microgrid with hybrid energy storage system, Energy, Volume 327, 2025, 136401, ISSN 0360-5442, https://doi.org/10.1016/j.energy.2025.136401. [5] H. Park, W. Ko, Resynchronization scheduling policy for multiple microgrids for optimal distributed system operation with enhanced flexibility, Applied Energy, Volume 399, 2025, 126491, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2025.126491. [6] Q. Huang, R. Huang, W. Hao, J. Tan, R. Fan and Z. Huang, "Adaptive Power System Emergency Control Using Deep Reinforcement Learning," in IEEE Transactions on Smart Grid, vol. 11, no. 2, pp. 1171-1182, March 2020, doi: 10.1109/TSG.2019.2933191. [7] R. Kumar, M. De, Advancement in power system resilience through deep reinforcement learning: A comprehensive review, Renewable and Sustainable Energy Reviews, Volume 222, 2025, 115951, ISSN 1364-0321, https://doi.org/10.1016/j.rser.2025.115951. [8] N. Dehghani, A. Jeddi, A. Shafieezadeh, Intelligent hurricane resilience enhancement of power distribution systems via deep reinforcement learning, Applied Energy, Volume 285, 2021, 116355, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2020.116355. [9] C. Guo, X. Wang, Y. Zheng, F. Zhang, Real-time optimal energy management of microgrid with uncertainties based on deep reinforcement learning, Energy, Volume 238, Part C, 2022, 121873, ISSN 0360-5442, https://doi.org/10.1016/j.energy.2021.121873. [10] David Domínguez-Barbero, Javier García-González, Miguel Á. Sanz-Bobi, Aurelio García-Cerrada, Energy management of a microgrid considering nonlinear losses in batteries through Deep Reinforcement Learning, Applied Energy, Volume 368, 2024, 123435, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2024.123435. [11] J. Hao et al., "Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain," in IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 7, pp. 8762-8782, July 2024, doi: 10.1109/TNNLS.2023.3236361. [12] X. Fang, Q. Zhao, J. Wang, Y. Han, Y. Li, Multi-agent Deep Reinforcement Learning for Distributed Energy Management and Strategy Optimization of Microgrid Market, Sustainable Cities and Society, Volume 74, 2021, 103163, ISSN 2210-6707, https://doi.org/10.1016/j.scs.2021.103163. [13] D. Qiu, Y. Wang, T. Zhang, M. Sun, G. Strbac, Hierarchical multi-agent reinforcement learning for repair crews dispatch control towards multi-energy microgrid resilience, Applied Energy, Volume 336, 2023, 120826, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2023.120826. [14] H. Zhang, D. Qiu, K. Kok, N. Paterakis, Reliability assessment of multi-agent reinforcement learning algorithms for hybrid local electricity market simulation, Applied Energy, Volume 389, 2025, 125789, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2025.125789. [15] G. Gao, Y. Wen and D. Tao, "Distributed Energy Trading and Scheduling Among Microgrids via Multiagent Reinforcement Learning," in IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 12, pp. 10638-10652, Dec. 2023, doi: 10.1109/TNNLS.2022.3170070. [16] D. Qiu, Y. Wang, J. Wang, N. Zhang, G. Strbac and C. Kang, "Resilience-Oriented Coordination of Networked Microgrids: A Shapley Q-Value Learning Approach," in IEEE Transactions on Power Systems, vol. 39, no. 2, pp. 3401-3416, March 2024, doi: 10.1109/TPWRS.2023.3276827. [17] D. Qiu, J. Xue, T. Zhang, J. Wang, M. Sun, Federated reinforcement learning for smart building joint peer-to-peer energy and carbon allowance trading, Applied Energy, Volume 333, 2023, 120526, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2022.120526. [18] Y. Jing, B. Guo, N. Li, R. Xu, Z. Yu, Federated multi-agent reinforcement learning: A comprehensive survey of methods, applications and challenges, Expert Systems with Applications, Volume 293, 2025, 128729, ISSN 0957-4174, https://doi.org/10.1016/j.eswa.2025.128729. [19] H. Shi, J. Li, J. Mao and K. -S. Hwang, "Lateral Transfer Learning for Multiagent Reinforcement Learning," in IEEE Transactions on Cybernetics, vol. 53, no. 3, pp. 1699-1711, March 2023, doi: 10.1109/TCYB.2021.3108237. [20] Y. Gui, Z. Zhang, D. Tang, H. Zhu, Y. Zhang, Collaborative dynamic scheduling in a self-organizing manufacturing system using multi-agent reinforcement learning, Advanced Engineering Informatics, Volume 62, Part A, 2024, 102646, ISSN 1474-0346, https://doi.org/10.1016/j.aei.2024.102646. [21] M. Panteli, C. Pickering, S. Wilkinson, R. Dawson and P. Mancarella, "Power System Resilience to Extreme Weather: Fragility Modeling, Probabilistic Impact Assessment, and Adaptation Measures," in IEEE Transactions on Power Systems, vol. 32, no. 5, pp. 3747-3757, Sept. 2017, doi: 10.1109/TPWRS.2016.2641463. [22] Bo Wang, Shu Wang, Zheng Wang, Yingying Zheng, Xin Li; A method for short-term wind power forecasting under extreme weather conditions based on meteorological factor interpretability and hybrid deep learning algorithms. AIP Advances 1 April 2025; 15 (4): 045015. https://doi.org/10.1063/5.0250465 [23] S. Hanif, M. Mukherjee, S. Poudel, M. Yu, R. Jinsiwale, T. Hardy, H. Reeve, Analyzing at-scale distribution grid response to extreme temperatures, Applied Energy, Volume 337, 2023, 120886, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2023.120886. [24] L. Chen, Z. Luo, R. Jing, K. Ye, M. Xie, Two-stage planning of integrated energy systems under copula models informed cascading extreme weather uncertainty, Applied Energy, Volume 380, 2025, 124990, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2024.124990. [25] Divyanshi Dwivedi, K. Victor Sam Moses Babu, Pradeep Kumar Yemula, Pratyush Chakraborty, Mayukha Pal, A comprehensive metric for resilience evaluation in electrical distribution systems under extreme conditions, Applied Energy, Volume 380, 2025, 125001, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2024.125001. [26] Y. Wu, W. Chiu, Y. Tsai, S. Liu, W. Hua, Multiagent reinforcement learning in enhancing resilience of microgrids under extreme weather events, Expert Systems with Applications, Volume 296, Part D, 2026, 129145, ISSN 0957-4174, https://doi.org/10.1016/j.eswa.2025.129145. [27] L. Rodriguez-Garcia, M. M. Hosseini, T. M. Mosier and M. Parvania, "Resilience Analytics for Interdependent Power and Water Distribution Systems," in IEEE Transactions on Power Systems, vol. 37, no. 6, pp. 4244-4257, Nov. 2022, doi: 10.1109/TPWRS.2022.3149463. [28] M. Soltanpour and H. Zhang, "Near-Global-Optimal Resource Allocation for Uplink SCMA Systems Based on Whale Optimization Algorithm," in IEEE Transactions on Wireless Communications, vol. 24, no. 2, pp. 1089-1103, Feb. 2025, doi: 10.1109/TWC.2024.3505192. [29] Yu, M., Xu, J., Liang, W. et al. Improved multi-strategy adaptive Grey Wolf Optimization for practical engineering applications and high-dimensional problem solving. Artif Intell Rev 57, 277 (2024). https://doi.org/10.1007/s10462-024-10821-3 [30] Mao, M., Gui, D. Enhanced adaptive-convergence in Harris' hawks optimization algorithm. Artif Intell Rev 57, 164 (2024). https://doi.org/10.1007/s10462-024-10802-6 32 [31] D. Harrold, J. Cao, Z. Fan, Renewable energy integration and microgrid energy trading using multi-agent deep reinforcement learning, Applied Energy, Volume 318, 2022, 119151, ISSN 0306-2619. https://doi.org/10.1016/j.apenergy.2022.119151. 33