基于微分代数神经网络的含新能源区域电网端口动态特性学习方法

doi:10.11930/j.issn.1004-9649.202208009

中国电力 ›› 2023, Vol. 56 ›› Issue (2): 23-31.DOI: 10.11930/j.issn.1004-9649.202208009

• 多元负荷用能感知及友好互动 • 上一篇下一篇

基于微分代数神经网络的含新能源区域电网端口动态特性学习方法

曹斌^1,2, 苏珂¹, 原帅¹, 肖谭南³, 陈颖³

1. 内蒙古电力（集团）有限责任公司内蒙古电力科学研究院分公司，内蒙古呼和浩特　010020;
2. 浙江大学电气工程学院，浙江杭州　310027;
3. 清华四川能源互联网研究院，四川成都　610200

收稿日期:2022-08-01 修回日期:2022-09-13 出版日期:2023-02-28 发布日期:2023-02-23
作者简介:曹斌（1970—），男，硕士，高级工程师，从事电网电磁暂态、新能源并网发电相关研究，E-mail：caobinbd@163.com;肖谭南（1991—），男，博士，博士后，从事电力系统暂态分析与控制、高性能计算、人工智能等研究，E-mail：ee_xiaoxh@foxmail.com;陈颖（1979—），男，通信作者，博士，研究员，博士生导师，从事并行计算与分布式计算、电磁暂态仿真、信息物理系统建模、信息物理安全等研究，E-mail：chen_ying@tsinghua.edu.cn
基金资助:
内蒙古电力（集团）有限责任公司科技项目（基于国产电磁暂态仿真器的内蒙古全网电磁暂态数字仿真平台技术研究，2021-33）；国家自然科学基金资助项目（51877115）。

Portal Dynamics Learning Method for Renewable-integrated Regional Power Networks Based on Neural Differential-Algebraic Equations

CAO Bin^1,2, SU Ke¹, YUAN Shuai¹, XIAO Tannan³, CHEN Ying³

1. Inner Mongolia Power Research Institute Branch, Inner Mongolia Power (Group) Co., Ltd., Hohhot 010020, China;
2. College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China;
3. Tsinghua Sichuan Energy Internet Research Institute, Chengdu 610200, China

Received:2022-08-01 Revised:2022-09-13 Online:2023-02-28 Published:2023-02-23
Supported by:
This work is supported by Science & Technology Project of Inner Mongolia Power (Group) Co., Ltd. (Research on Electromagnetic Transient Simulation Platform of Inner Mongolia Power Grid Based on Domestic Electromagnetic Transient Simulator, No. 2021-33) and National Natural Science Foundation of China (No.51877115).

摘要/Abstract

摘要： 高比例新能源渗透背景下，建立能够准确描述复杂环境因素影响下含新能源的区域电网端口特性动态模型，对于新型电力系统动态分析至关重要。为此，提出了一种基于微分代数神经网络的含新能源区域电网端口动态特性学习方法。该方法利用微分代数神经网络，基于区域电网接入点的时序量测以及光照强度、温度等环境量测数据，学习以神经网络表达的端口特性模型。所得模型由初始状态提取模块、微分神经网络模块、代数神经网络模块组成，可直接接入电力系统暂态仿真器中，用于分析电力系统整体动态特性。在IEEE-39节点系统中对该方法进行仿真验证，测试结果表明：所得模型能够适应不同环境场景，准确率高，验证了方法的有效性。该建模方法仅依赖端口时序量测，在新型电力系统动态分析中具有较大的应用潜力。

关键词: 新能源, 端口特性建模, 微分代数方程, 神经网络, 动态仿真

Abstract: In the context of high penetration of renewables, it is very important for new power system dynamic analysis to establish a dynamic model that can accurately describe the portal dynamics of renewable-integrated regional power networks under the influence of complex environmental factors. Therefore a neural differential-algebraic equations-based portal dynamics learning method is proposed for renewable-integrated regional power networks. In this method, the differential-algebraic neural network is used to learn the portal dynamics model expressed in the form of neural network based on the time series measurements of the access point of the regional power networks and the environmental measurement data such as the radiation intensity and temperature. The learned model is composed of an initial state extracting block, a neural differential equation block and an algebraic equation block, and can be directly integrated into power system transient simulations to analyze the overall dynamics of power systems. The proposed method is tested through simulation in the IEEE-39 system, and the test results show that the obtained model can adapt to different environmental scenarios with acceptable accuracy, which verifies the effectiveness of the proposed method. The modelling method only needs portal time series measurements and has great application potential in the dynamic analysis of new power systems.

Key words: renewable energy, portal dynamics modeling, differential-algebraic equation, neural network, dynamic simulation

曹斌, 苏珂, 原帅, 肖谭南, 陈颖. 基于微分代数神经网络的含新能源区域电网端口动态特性学习方法[J]. 中国电力, 2023, 56(2): 23-31.

CAO Bin, SU Ke, YUAN Shuai, XIAO Tannan, CHEN Ying. Portal Dynamics Learning Method for Renewable-integrated Regional Power Networks Based on Neural Differential-Algebraic Equations[J]. Electric Power, 2023, 56(2): 23-31.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202208009

https://www.electricpower.com.cn/CN/Y2023/V56/I2/23

参考文献

[1] 周原冰, 杨方, 余潇潇, 等. 中国能源电力碳中和实现路径及实施关键问题[J]. 中国电力, 2022, 55(5): 1–11
ZHOU Yuanbing, YANG Fang, YU Xiaoxiao, et al. Realization pathways and key problems of carbon neutrality in China's energy and power system[J]. Electric Power, 2022, 55(5): 1–11
[2] 蔡欢, 袁旭峰, 熊炜, 等. 柔性互联配电网运行调度研究综述[J]. 智慧电力, 2022, 50(6): 92–99, 106
CAI Huan, YUAN Xufeng, XIONG Wei, et al. Review on operation scheduling of flexible interconnected distribution network[J]. Smart Power, 2022, 50(6): 92–99, 106
[3] 刘辉, 王阔. 新能源低电压穿越无功电流对暂态电压安全约束的影响[J]. 中国电力, 2022, 55(2): 152–158
LIU Hui, WANG Kuo. LVRT reactive current index of renewable units based on the constraints of transient voltage[J]. Electric Power, 2022, 55(2): 152–158
[4] 李睿智, 刘念, 延肖何. 基于势博弈的综合能源系统用户能量管理优化方法[J]. 电力科学与技术学报, 2021, 36(1): 21–31
LI Ruizhi, LIU Nian, YAN Xiaohe. An optimization method for user energy management of integrated energy system based on potential game[J]. Journal of Electric Power Science and Technology, 2021, 36(1): 21–31
[5] KUNDUR P, BALU N J, LAUBY M G. Power system stability and control: vol. 7[M]. New York: McGraw-hill, 1994.
[6] 钟璐, 熊俊, 张茜, 等. 基于光伏减载的电力系统紧急降风险控制方法[J]. 电力系统保护与控制, 2021, 49(14): 157–167
ZHONG Lu, XIONG Jun, ZHANG Xi, et al. A risk-reduction emergency control method of a power system based on photovoltaic power reserve[J]. Power System Protection and Control, 2021, 49(14): 157–167
[7] GUO S, NORRIS S, BIALEK J. Adaptive parameter estimation of power system dynamic model using modal information[J]. IEEE Transactions on Power Systems, 2014, 29(6): 2854–2861.
[8] DING F, PAN J, ALSAEDI A, et al. Gradient-based iterative parameter estimation algorithms for dynamical systems from observation data[J]. Mathematics, 2019, 7(5): 428.
[9] 李培强, 李慧, 李欣然. 基于灵敏度与相关性的综合负荷模型参数优化辨识策略[J]. 电工技术学报, 2016, 31(16): 181–188
LI Peiqiang, LI Hui, LI Xinran. Optimized identification strategy for composite load model parameters based on sensitivity and correlation analysis[J]. Transactions of China Electrotechnical Society, 2016, 31(16): 181–188
[10] ACILAN E, GOL M. Identifiability analysis for power plant parameter calibration in the presence of collinear parameters[J]. IEEE Transactions on Power Systems, 2022, 37(4): 2988–2997.
[11] YANG B, WANG J B, ZHANG X S, et al. Comprehensive overview of meta-heuristic algorithm applications on PV cell parameter identification[J]. Energy Conversion and Management, 2020, 208: 112595.
[12] HUANG R K, DIAO R S, LI Y Y, et al. Calibrating parameters of power system stability models using advanced ensemble Kalman filter[J]. IEEE Transactions on Power Systems, 2018, 33(3): 2895–2905.
[13] 朱建全, 易江文, 庄远灿, 等. 基于不敏卡尔曼粒子滤波的动态电力负荷在线建模[J]. 南方能源建设, 2017, 4(2): 51–57
ZHU Jianquan, YI Jiangwen, ZHUANG Yuancan, et al. On-line dynamic electric load modeling based on unscented Kalman particle filter[J]. Southern Energy Construction, 2017, 4(2): 51–57
[14] KHAZEIYNASAB S R, QI J J. Generator parameter calibration by adaptive approximate Bayesian computation with sequential Monte Carlo sampler[J]. IEEE Transactions on Smart Grid, 2021, 12(5): 4327–4338.
[15] NAGI R, HUAN X, CHEN Y C. Bayesian inference of parameters in power system dynamic models using trajectory sensitivities[J]. IEEE Transactions on Power Systems, 2022, 37(2): 1253–1263.
[16] AZMY A M, ERLICH I, SOWA P. Artificial neural network-based dynamic equivalents for distribution systems containing active sources[J]. IEE Proceedings-Generation, Transmission and Distribution, 2004, 151(6): 681.
[17] SHARMA P, AJJARAPU V, VAIDYA U. Data-driven identification of nonlinear power system dynamics using output-only measurements[EB/OL]. 2021: arXiv: 2110.01469.https://arxiv.org/abs/2110.01469.
[18] ZHOU Y F, ZHANG P. Neuro-reachability of networked microgrids[J]. IEEE Transactions on Power Systems, 2022, 37(1): 142–152.
[19] OSPINA L D P, SALAZAR V U, OSPINA D P. Dynamic equivalents of nonlinear active distribution networks based on Hammerstein-Wiener models: an application for long-term power system phenomena[J]. IEEE Transactions on Power Systems, 2022, 37(6): 4286–4296.
[20] 张琦, 杨健维, 向悦萍, 等. 计及气象因素的区域电动汽车充电负荷建模方法[J]. 电力系统保护与控制, 2022, 50(6): 14–22
ZHANG Qi, YANG Jianwei, XIANG Yueping, et al. Regional electric vehicle charging load modeling method considering meteorological factors[J]. Power System Protection and Control, 2022, 50(6): 14–22
[21] CHEN R T Q, RUBANOVA Y, BETTENCOURT J, et al. Neural ordinary differential equations[C]//Proceedings of the 32 nd International Conference on Neural Information Processing Systems. Montréal, Canada. New York: ACM, 2018: 6572–6583.
[22] SUN Y F, ZHANG L N, SCHAEFFER H. NeuPDE: neural network based ordinary and partial differential equations for modeling time-dependent data[C/OL]//Mathematical and Scientific Machine Learning. PMLR, 2020: 352–372.
[23] HORNIK K, STINCHCOMBE M, WHITE H. Multilayer feedforward networks are universal approximators[J]. Neural Networks, 1989, 2(5): 359–366.
[24] KAWAHARA Y. Dynamic mode decomposition with reproducing kernels for Koopman spectral analysis[C]//Proceedings of the 30 th International Conference on Neural Information Processing Systems. Barcelona, Spain. New York: ACM, 2016: 919–927.
[25] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. IEEE, 2016: 770–778.
[26] XU Y F, QIN M, HE J, et al. Modeling and operation characteristics of large-scale photovoltaic power plants based on PSASP[C]//2014 17 th International Conference on Electrical Machines and Systems (ICEMS). Hangzhou, China. IEEE, 2015: 3226–3230.
[27] XIAO T N, CHEN Y, WANG J Q, et al. Exploration of artificial intelligence oriented power system dynamic simulators[J]. Journal of Modern Power Systems and Clean Energy, 2022, PP(99): 1–10.
[28] KINGMA D P, BA J. Adam: a method for stochastic optimization [EB/OL]. 2014: arXiv: 1412.6980.https://arxiv.org/abs/1412.6980.

基于微分代数神经网络的含新能源区域电网端口动态特性学习方法

Portal Dynamics Learning Method for Renewable-integrated Regional Power Networks Based on Neural Differential-Algebraic Equations

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	张磊, 马晓伟, 王满亮, 陈力, 高丙团. 互联新能源电力系统区内AGC机组分布式协同控制策略[J]. 中国电力, 2025, 58(3): 8-19.
[2]	汪林光, 李旭涛, 任勇, 谢小荣. 基于元启发式算法的新能源电力系统振荡稳定性最差工况搜索方法[J]. 中国电力, 2025, 58(3): 65-72.
[3]	吴小忠, 肖立华, 童超, 夏向阳, 袁翎, 甘星, 江志文, 黄湘源. 基于传递熵与JS-BP神经网络的锂离子电池容量预测模型[J]. 中国电力, 2025, 58(2): 186-192, 215.
[4]	邹小燕, 张瑞宏. 考虑政府干预的可再生能源与储能企业合作模式演化博弈研究[J]. 中国电力, 2025, 58(1): 153-163.
[5]	王雨晴, 张敏, 王嘉兴, 李泊皓, 杨天阳, 曾鸣. 基于超模博弈的共享储能容量租赁价格决策[J]. 中国电力, 2025, 58(1): 164-173.
[6]	孙东磊, 王宪, 孙毅, 孟祥飞, 张涌琛, 张玉敏. 基于多面体不确定集合的电力系统灵活性量化评估方法[J]. 中国电力, 2024, 57(9): 146-155.
[7]	孙东磊, 孙毅, 刘蕊, 孙鹏凯, 张玉敏. 计及多层级配电网的分布式新能源最大消纳空间分解测算[J]. 中国电力, 2024, 57(8): 108-116.
[8]	李鲁阳, 陈龙翔, 陈磊, 孙大卫, 吴林林, 闵勇. 用于新能源一次调频的储能经济配置研究[J]. 中国电力, 2024, 57(7): 54-65.
[9]	王宇飞, 杜桐, 边伟国, 张钊, 刘慧婷, 杨丽君. 基于DTW K-medoids与VMD-多分支神经网络的多用户短期负荷预测[J]. 中国电力, 2024, 57(6): 121-130.
[10]	吴军英, 路欣, 刘宏, 张彬, 柴守亮, 刘蕴春, 王佳楠. 基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]. 中国电力, 2024, 57(6): 131-140.
[11]	李佳蔚, 张冠宇. 大规模分布式新能源接入对省级电网稳定性影响[J]. 中国电力, 2024, 57(6): 174-180.
[12]	高政南, 姜楠, 陈启鑫, 徐江, 王海利, 辛力, 徐青贵. 德国电力市场能源转型建设及启示[J]. 中国电力, 2024, 57(6): 204-214.
[13]	李咸善, 丁胜彪, 李飞, 李欣. 考虑水电调节费用补偿的风光水联盟优化调度策略[J]. 中国电力, 2024, 57(5): 26-38.
[14]	朱子民, 张锦芳, 常清, 周专, 张晓林. 大规模新能源接入弱同步支撑柔直系统的送端自适应VSG控制策略[J]. 中国电力, 2024, 57(5): 211-221.
[15]	王帅, 黄越辉, 聂元弘, 刘思扬. 基于生产模拟的受端电网新能源发展场景研究[J]. 中国电力, 2024, 57(5): 240-250.

模态框（Modal）标题

基于微分代数神经网络的含新能源区域电网端口动态特性学习方法

Portal Dynamics Learning Method for Renewable-integrated Regional Power Networks Based on Neural Differential-Algebraic Equations

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics