综合智慧能源 ›› 2023, Vol. 45 ›› Issue (7): 48-60.doi: 10.3969/j.issn.2097-0706.2023.07.006

• 优化运行与控制 • 上一篇    下一篇

基于多STA-GLN集成模型的电力系统暂态稳定评估方法

杨波1,2(), 李成雲1,2(), 吕浩轩3(), 周博文1,2(), 李广地1,2(), 谷鹏1,2()   

  1. 1.东北大学 信息科学与工程学院,沈阳 110819
    2.辽宁省综合能源优化与安全运行重点实验室(东北大学),沈阳 110819
    3.国网辽宁省电力有限公司铁岭供电公司,辽宁 铁岭 112099
  • 收稿日期:2023-04-25 修回日期:2023-06-28 接受日期:2023-07-11 出版日期:2023-07-25 发布日期:2023-07-25
  • 作者简介:杨波(1976),男,高级工程师,从事新能源、物联网、电气控制和电力通信等方面的研究,yangbo@ise.neu.edu.cn
    李成雲(1998),女,在读博士研究生,从事电力系统数字孪生建模方面的研究,17367911495@163.com
    吕浩轩(1995),男,硕士,从事电力系统稳定性分析方面的研究,18641036168@163.com
    周博文(1987),男,副教授,硕士生导师,博士,从事电力系统运行、稳定与控制,电动汽车与电网互动,储能,需求响应,虚拟储能,可再生能源,能源互联网,人工智能与电力系统等方面的研究,zhoubowen@ise.neu.edu.cn
    李广地(1989),男,讲师,博士,从事新能源并网发电、高频软开关技术等方面的研究,liguangdi@ise.neu.edu.cn
    谷鹏(1992),男,讲师,博士,从事综合能源系统、无线电能传输技术及其在电力系统中的应用、新型电力系统电磁暂态分析等方面的研究,gupeng@mail.neu.edu.cn
  • 基金资助:
    国家自然科学基金项目(U22 B20115);辽宁省科学技术计划项目(2022-MS-110);广东省基础与应用基础研究基金项目(2021A1515110778)

Power system transient stability assessment method based on multiple STA-GLN ensemble models

YANG Bo1,2(), LI Chengyun1,2(), LYU Haoxuan3(), ZHOU Bowen1,2(), LI Guangdi1,2(), GU Peng1,2()   

  1. 1. College of Information Science and Engineering, Northeastern University, Shenyang 110819,China
    2. Key Laboratory of Integrated Energy Optimization and Secure Operation of Liaoning Province (Northeastern University), Shenyang 110819,China
    3. Tieling Power Supply Company,State Grid Liaoning Electric Power Supply Company Limited,Tieling 112099, China
  • Received:2023-04-25 Revised:2023-06-28 Accepted:2023-07-11 Online:2023-07-25 Published:2023-07-25
  • Supported by:
    National Natural Science Foundation of China(U22 B20115);Liaoning Science and Technology Project(2022-MS-110);Guangdong Basic and Applied Basic Research Foundation Project(2021A1515110778)

摘要:

随着高比例可再生能源的不断接入和电力电子化程度的提高,电力系统结构日益复杂,导致电力系统稳定性受威胁。针对基于人工智能的暂态稳定评估(TSA)方法存在的拓扑适应能力差、失稳样本学习困难和模型训练耗时长等缺陷,提出了基于图形卷积和长短时记忆组合网络的空间和时间双注意力机制(STA-GLN)集成电力系统TSA方法。搭建了电力系统仿真模型,在全接线、N-1断线和N-2断线3种拓扑结构下设置不同线路故障,获取原始样本集,基于STA-GLN的TSA方法对系统拓扑变化表现出更强的适应性和评估准确性;构建了基于自适应增强(AdaBoost)算法和迁移学习的集成STA-GLN多任务TSA模型,解决了失稳误判问题并加快了模型的响应速度。最后通过新英格兰10机39节点系统仿真分析验证了该方法的有效性。

关键词: 电力系统, 可再生能源, 暂态稳定评估, 人工智能, 集成学习, 迁移学习, 多任务模型, 电力电子化

Abstract:

With the continuous access of high-proportion renewable energy to the power grid and advancing of power electronization, power systems are becoming increasingly complex in structure, which threats of systems' stability. To address the poor topology adaptability, difficulty in learning instability samples, and long model training time of the transient stability assessment (TSA) method based on artificial intelligence(AI),an ensemble TSA method based on Spatial-Temporal Attention Mechanism, Graph Convolution and Long Short-Term Memory Network(STA-GLN) is proposed. A power system simulation model is built, in which different line faults are set under three topologies, full connection, N-1 disconnection and N-2 disconnection, and the original sample sets are obtained. The TSA method based on STA-GLN shows stronger adaptability and accuracy to the variation of the system's topologies. Then, Adaptive Boosting (AdaBoost) and transfer learning are integrated into the multi-task TSA model based on STA-GLN, which reduces the false judgment and accelerates the response speed of the model. The effectiveness of the method is verified by the simulation analysis of a New England 10-generator 39-node system.

Key words: power system, renewable energy, transient stability assessment, AI, ensemble learning, transfer learning, multi-task model, power electronization

中图分类号: