Abstract：With the continuous increase of high-penetration renewable energy, power system stability issues concerning small-signal and transient security have become increasingly prominent. Current studies critically lack a coordinated optimization framework that jointly enforces multiple stability constraints and integrates multiple types of devices. As a result, unmodeled stability metrics are often not validated for security compliance, posing potential operational risks, while device deployment remains largely confined to single-type configurations, hindering economic optimality. Moreover, existing transient analyses still model renewable generators as conventional impedance-voltage-source equivalents, which fail to accurately capture their true fault response characteristics and may lead to assessment results that deviate significantly from real behavior. Compounding these issues, the optimization models and solution algorithms employed often struggle to achieve an effective balance between computational efficiency and solution accuracy. To address these challenges, this paper proposes a coordinated resource allocation strategy based on supervised learning enabled constraint linearization. Initially, the impact mechanism of modeling renewable energy as voltage-controlled current sources on stability indices is thoroughly analyzed. Subsequently, an optimization model for the coordinated configuration of synchronous condensers and energy storage is constructed. Furthermore, a supervised learning-based nonlinear constraint linearization method is introduced to reformulate the original problem as a mixed-integer linear programming (MILP) model, accompanied by theoretical analysis of the fitted model in terms of convergence of the linearization coefficients, model complexity, and approximation accuracy. Finally, mathematical simulations are conducted to validate the proposed optimization strategy. Simulation results demonstrate that, throughout the entire time horizon, the system stability metrics satisfy all security constraints, with the average values of gSCR and SCC increased to 3.48(pu) and 5.95(pu), providing safety margins of 6.33% and 2.40% relative to their respective thresholds. Under this optimization strategy, the total system economic cost is significantly reduced, and the system’s economic sensitivity to parameter variations is effectively mitigated. Moreover, the proposed model exhibits linear convergence and obtains the optimal solution within 32.67 min. Compared with existing models, it achieves up to a 7-fold reduction in computational time and improves fitting accuracy by a factor of 5.6, with no violations of stability constraints observed across all test scenarios, demonstrating strong applicability and scalability in large-scale systems. The following conclusions can be drawn from the analysis: (1) In terms of security and stability, the proposed strategy ensures that all system buses satisfy both small-signal and transient stability constraints throughout the entire scheduling horizon, with no violations observed. This effectively mitigates the safety risks associated with single-constraint optimization, where neglecting one stability dimension may compromise overall system security. (2) In terms of an economic perspective, the coordinated configuration significantly reduces the total system cost and eliminates resource allocation redundancy arising from decoupled planning. Furthermore, the resulting economic cost demonstrates strong robustness to variations in key parameters, such as renewable penetration levels and stability thresholds, rendering the approach well suited for electricity market operation scenarios which require comprehensive economic considerations. (3) Compared with existing methods, the proposed model demonstrates superior performance in convergence, solution accuracy, computational efficiency, and applicability; furthermore, the supervised learning-based constraint reconstruction step accounts for only 20% of the total computation time, imposing negligible overhead on solution efficiency.
铉子逸, 李永刚, 郭潇镁, 张峰睿, 周一辰. 基于监督学习的资源协同优化配置在高比例新能源场站中的应用[J]. 电工技术学报, 2026, 41(19): 6584-6599.
Xuan Ziyi, Li Yonggang, Guo Xiaomei, Zhang Fengrui, Zhou Yichen. Resource Coordinated Optimal Allocation in High-Penetration Renewable Energy Power Stations Based on Supervised Learning-Constrained Linearization. Transactions of China Electrotechnical Society, 2026, 41(19): 6584-6599.
[1] 江一航, 赵书强, 王慧, 等. 计及风电、调相机支撑特性的频率安全约束分布鲁棒机组组合调度方法[J]. 电工技术学报, 2025, 40(1): 80-95. Jiang Yihang, Zhao Shuqiang, Wang Hui, et al.Distributionally robust frequency constrained unit commitment with frequency support of wind power and synchronous condenser[J]. Transactions of China Electrotechnical Society, 2025, 40(1): 80-95. [2] 周瑀涵, 辛焕海, 鞠平. 基于广义短路比的多馈入系统强度量化原理与方法: 回顾、探讨与展望[J]. 中国电机工程学报, 2023, 43(10): 3794-3810. Zhou Yuhan, Xin Huanhai, Ju Ping.System strength quantification principle and method of multi-infeed systems based on generalized short-circuit ratio: reviews, discussions and outlooks[J]. Proceedings of the CSEE, 2023, 43(10): 3794-3810. [3] 刘昊霖, 贾科, 毕天姝, 等. 计及新能源耦合特性的柔直换流站短路电流解析[J]. 电工技术学报, 2025, 40(15): 4835-4844. Liu Haolin, Jia Ke, Bi Tianshu, et al.Analysis of short-circuit current in flexible DC converter stations considering the coupling characteristics of new energy sources[J]. Transactions of China Electrotechnical Society, 2025, 40(15): 4835-4844. [4] 郭强, 李志强. 同步调相机发展综述[J]. 中国电机工程学报, 2023, 43(15): 6050-6063. Guo Qiang, Li Zhiqiang.Summarization of synchronous condenser development[J]. Proceedings of the CSEE, 2023, 43(15): 6050-6063. [5] 李军徽, 潘雅慧, 穆钢, 等. 高比例风电系统中储能集群辅助火电机组调峰分层优化控制策略[J]. 电工技术学报, 2025, 40(7): 2127-2145. Li Junhui, Pan Yahui, Mu Gang, et al.Hierarchical optimal control strategy for storage cluster-assisted thermal unit peaking in high-ratio wind power system[J]. Transactions of China Electrotechnical Society, 2025, 40(7): 2127-2145. [6] 杨浩, 刘虎, 丁肇豪, 等. 计及短路比提升与暂态过电压抑制的含高比例风电送端电网两阶段式调相机优化配置[J]. 电网技术, 2024, 48(2): 540-551. Yang Hao, Liu Hu, Ding Zhaohao, et al.Two-stage optimal configuration of condenser for high-proportion wind power sending-end power grid considering short circuit ratio increase and transient overvoltage suppression[J]. Power System Technology, 2024, 48(2): 540-551. [7] 单永鹏, 刘昕宇, 汪莹, 等. 基于等效同步机的新能源基地同步调相机暂态功角失稳机理和稳定裕度分析[J]. 电工技术学报, 2025, 40(17): 5448-5463. Shan Yongpeng, Liu Xinyu, Wang Ying, et al.Transient power angle instability mechanism and stability margin analysis of synchronous condenser co-located with renewable energy base based on equivalent synchronous generator[J]. Transactions of China Electrotechnical Society, 2025, 40(17): 5448-5463. [8] Hadavi S, Saunderson J, Mehrizi-Sani A, et al.A planning method for synchronous condensers in weak grids using semi-definite optimization[J]. IEEE Transactions on Power Systems, 2023, 38(2): 1632-1641. [9] Chu Zhongda, Teng Fei.Voltage stability constrained unit commitment in power systems with high penetration of inverter-based generators[J]. IEEE Transactions on Power Systems, 2023, 38(2): 1572-1582. [10] Wang Jiaxin, Zhang Jiawei, Hou Qingchun, et al.Synchronous condenser placement for multiple HVDC power systems considering short-circuit ratio requirements[J]. IEEE Transactions on Power Systems, 2025, 40(1): 765-779. [11] Liu Xinyu, Xin Huanhai, Zheng Di, et al.Transient stability of synchronous condenser co-located with renewable power plants[J]. IEEE Transactions on Power Systems, 2024, 39(1): 2030-2041. [12] Ramos A F, Ahmad I, Habibi D, et al.Placement and sizing of utility-size battery energy storage systems to improve the stability of weak grids[J]. International Journal of Electrical Power & Energy Systems, 2023, 144: 108427. [13] 赵冬梅, 宋晨铭, 冯向阳, 等. 100%新能源场景下考虑频率稳定约束的源网荷储一体化系统储能优化配置[J]. 电工技术学报, 2025, 40(7): 2146-2161. Zhao Dongmei, Song Chenming, Feng Xiangyang, et al.The optimal configuration of energy storage in the source-grid-load-storage integrated system considering frequency stability constraints in 100%New energy scenarios[J]. Transactions of China Electrotechnical Society, 2025, 40(7): 2146-2161. [14] Zhang Xi, Liu Youbo, Zhao Junbo, et al.Short-circuit current constrained unit commitment and transmission switching model for improving renewable integration: an MILP formulation[J]. IET Generation, Transmission & Distribution, 2022, 16(9): 1743-1755. [15] Chu Zhongda, Teng Fei.Short circuit current constrained UC in high IBG-penetrated power systems[J]. IEEE Transactions on Power Systems, 2021, 36(4): 3776-3785. [16] 马鑫, 薛飞, 顾文波, 等. 考虑多场站短路比约束的构网型储能及分布式调相机优化配置方法[J]. 电力自动化设备, 2025, 45(5): 40-46, 64. Ma Xin, Xue Fei, Gu Wenbo, et al.Optimal configuration method of grid-forming energy storage and distributed synchronous condenser considering constrain[J]. Electric Power Automation Equipment, 2025, 45(5): 40-46, 64 [17] 赵天骐, 郭金鹏, 张海燕, 等. 考虑调相机的风电场稳态-暂态无功协同优化控制[J]. 电力系统自动化, 2024, 48(24): 54-65. Zhao Tianqi, Guo Jinpeng, Zhang Haiyan, et al.Steady state-transient state reactive power cooperative optimization control of wind farm considering synchronous condensers[J]. Automation of Electric Power Systems, 2024, 48(24): 54-65. [18] Shao Weihua, Wu Ruizhu, Ran Li, et al.A power module for grid inverter with in-built short-circuit fault current capability[J]. IEEE Transactions on Power Electronics, 2020, 35(10): 10567-10579. [19] Kim H, Oh H, Park J, et al. High-speed control and navigation for quadrupedal robots on complex and discrete terrain[J]. Science Robotics, 2025, 10(102): eads6192. [20] Lee J, Hwangbo J, Wellhausen L, et al. Learning quadrupedal locomotion over challenging terrain[J]. Science Robotics, 2020, 5(47): eabc5986. [21] 张伯明. 电力系统分析[M]. 北京: 清华大学出版社, 2001. [22] Yang Jingwei, Zhang Ning, Kang Chongqing, et al.A state-independent linear power flow model with accurate estimation of voltage magnitude[J]. IEEE Transactions on Power Systems, 2017, 32(5): 3607-3617. [23] Vollenweider E, Bjelonic M, Klemm V, et al.Advanced skills through multiple adversarial motion priors in reinforcement learning[C]//2023 IEEE International Conference on Robotics and Automation (ICRA), London, United Kingdom, 2023: 5120-5126. [24] 戴华. 矩阵论[M]. 北京: 科学出版社, 2001. [25] Stewart G W, Sun Jiguang.Matrix Perturbation Theory[M]. Boston: Academic Press, 1990. [26] 国家能源局. 新型电力系统发展蓝皮书[R]. 北京: 国家能源局, 2023. [27] 索之闻, 李晖, 王智冬, 等. 计及边际贡献的新能源场站分布式调相机投资收益评估方法[J]. 电力系统自动化, 2025, 49(8): 66-75. Suo Zhiwen, Li Hui, Wang Zhidong, et al.Evaluation method for investment revenue of distributed synchronous condensers in renewable energy station considering marginal contribution[J]. Automation of Electric Power Systems, 2025, 49(8): 66-75. [28] 铉子逸, 李永刚. 高比例光伏送端系统分布式调相机优化配置研究[J/OL]. 华北电力大学学报(自然科学版), 2024: 1-10[2025-04-07]. http://kns.cnki.net/kcms/detail/13.1212.TM.20241204.1443.002.html. Xuan Ziyi, Li Yonggang. Research on optimal allocation of distributed synchronous condensers in high-proportion photovoltaic sending-end systems [J/OL]. Journal of North China Electric Power University (Natural Science Edition), 2024: 1-10[2025-04-07]. http://kns.cnki.net/kcms/detail/13.1212.TM.20241204.1443.002.html. [29] Hu Jingwei, Xu Xiaoyuan, Ma Hongyan, et al.Distributionally robust co-optimization of transmission network expansion planning and penetration level of renewable generation[J]. Journal of Modern Power Systems and Clean Energy, 2022, 10(3): 577-587. [30] 李庆扬, 王能超, 易大义. 数值分析[M]. 5版. 北京: 清华大学出版社, 2023.
2026, Vol. 41 
