| 引用本文: | 李华瑞,李文博.交直流混联受端电网直流闭锁多资源紧急控制两阶段优化[J].电力自动化设备,2025,45(2):217-224. |
| LI Huarui,LI Wenbo.Multi-resource emergency control two-stage optimization of AC-DC hybrid receiving-end power grid for HVDC blocking[J].Electric Power Automation Equipment,2025,45(2):217-224. |
|
| 摘要: |
| 针对直流闭锁等严重功率扰动事件下现有离线决策方法无法对实际运行方式进行精准控制的情况，综合应用时域仿真和机器学习技术，提出一种包含预优化和在线优化两阶段的紧急控制方案优化方法。在预优化阶段，生成反映系统未来可能运行方式的典型场景，使用轨迹灵敏度和机器学习方法优化各场景下的多资源协调紧急控制方案，并将其存入知识库。在在线优化阶段，获取系统实际运行方式信息，基于度量学习从知识库中选择适当的控制方案作为初值，快速迭代优化得到实际运行方式下的优化控制方案。以某多直流馈入受端系统为例，验证了所提方法的有效性。 |
| 关键词: 新能源 多资源协调 紧急控制 两阶段优化 频率安全 |
| DOI：10.16081/j.epae.202411009 |
| 分类号:TM73 |
| 基金项目:江苏省基础研究计划(自然科学基金)项目(BK20230167) |
|
| Multi-resource emergency control two-stage optimization of AC-DC hybrid receiving-end power grid for HVDC blocking |
|
LI Huarui, LI Wenbo
|
|
Electric Power Research Institute of State Grid Jiangsu Electric Power Co.,Ltd.,Nanjing 211100, China
|
| Abstract: |
| In view of the fact that the existing offline decision making methods cannot accurately control the actual operation mode under severe power disturbance events such as DC blocking, a two-stage optimization method of emergency control scheme including pre-optimization and online optimization is proposed by comprehensively applying the time domain simulation and machine learning technology. In the pre-optimization stage, the typical scenarios reflecting the possible future system operation mode are generated, and multi-resource coordination emergency control schemes under each scenario are optimized by using trajectory sensitivity and machine learning methods, which are stored in the knowledge base. In the online optimization stage, the information of actual system operation mode is obtained, the appropriate control scheme is selected from the knowledge base as the initial value based on the metric learning, and the optimal control scheme under actual operation mode is obtained by rapid iterative optimization. A multi-DC infeed recei-ving-end system is taken as an example to verify the effectiveness of the proposed method. |
| Key words: new energy multi-resource coordination emergency control two-stage optimization frequency security |
