范宏,徐勇杰,徐涛
FAN Hong,XU Yongjie,XU Tao

• 1:上海电力大学电气工程学院

摘要(Abstract)：

为解决风电并网后系统暂态稳定分析不准确的问题，提出一种基于ISSA（改进麻雀搜索算法）优化的MSVR（多输出支持向量回归）方法。首先，建立直驱风机并网后的能量函数，针对风机并网系统，提出利用改进的DQN（深度Q网络）算法构建出稳定性可解释的能量函数，并通过BCU（基于稳定域边界的主导不稳定平衡点）方法求解系统的不稳定平衡点，从而得到预测模型的训练集与测试集。接着，针对SSA（改进麻雀搜索算法）易陷入局部最优等缺点，引入反向学习、分段权重以及柯西变异方法对SSA进行改进，并利用ISSA对MSVR中的惩罚因子和核函数宽度两个参数进行最优化组合，通过改进的IEEE 39节点系统验证了预测方法的有效性。实验结果表明，ISSA优化后的MSVR方法相较于其他典型人工智能方法而言，预测误差更小，训练所耗时间相对较少，能够对风机并网系统的不稳定平衡点进行有效预测。
To address the issue of inaccurate transient stability analysis in power systems after wind farm integration, this paper proposes a method combining improved sparrow search algorithm(ISSA)-optimized multi-output support vector regression(MSVR). First, an energy function is established for direct-drive wind turbines integrated into the grid. For wind turbine grid-connected systems, an interpretable stability energy function is constructed using an improved Deep Q-Network(DQN) algorithm. The unstable equilibrium points(UEPs) of the system are then determined via the boundary of stability region based controlling UEP method(BCU), generating the training and testing datasets for the prediction model. Next, to overcome the limitations of the SSA algorithm, such as susceptibility to local optima, inverse learning, piecewise weighting, and Cauchy mutation are introduced to enhance SSA.The ISSA is then employed to optimally tune the penalty factor and kernel width in MSVR. The proposed method is validated on a modified IEEE 39-bus system. Experimental results demonstrate that the ISSA-MSVR approach achieves smaller prediction errors and reduced training time compared to other state-of-the-art AI methods, effectively predicting the UEPs in wind farm-integrated systems.

关键词(KeyWords)： 直驱风机并网;虚拟同步机控制;BCU;改进麻雀搜索算法;多输出支持向量回归;不稳定平衡点预测
direct-drive wind turbine integration;VSG control;BCU;ISSA;MSVR;UPE prediction

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划（2022YFA10046000）

作者(Author): 范宏,徐勇杰,徐涛
FAN Hong,XU Yongjie,XU Tao

DOI: 10.19585/j.zjdl.202505006

参考文献(References)：

• [1]秦世耀，齐琛，李少林，等.电压源型构网风电机组研究现状及展望[J].中国电机工程学报，2023,43(4):1314-1334.QIN Shiyao,QI Chen,LI Shaolin,et al. Review of the voltage-source grid forming wind turbine[J].Proceedings of the CSEE,2023,43(4):1314-1334.
• [2]汪梦军，郭剑波，马士聪，等.新能源电力系统暂态频率稳定分析与调频控制方法综述[J].中国电机工程学报，2023,43(5):1672-1694.WANG Mengjun,GUO Jianbo,MA Shicong,et al. Review of transient frequency stability analysis and frequency regulation control methods for renewable power systems[J].Proceedings of the CSEE,2023,43(5):1672-1694.
• [3]薛禹胜，赖业宁.大能源思维与大数据思维的融合（一）大数据与电力大数据[J].电力系统自动化，2016,40(1):1-8.XUE Yusheng,LAI Yening.Integration of macro energy thinking and big data thinking part one big data and power big data[J].Automation of Electric Power Systems,2016,40(1):1-8.
• [4]朱蜀，刘开培，秦亮，等.电力电子化电力系统暂态稳定性分析综述[J].中国电机工程学报，2017,37(14):3948-3962.ZHU Shu,LIU Kaipei,QIN Liang,et al.Analysis of transient stability of power electronics dominated power system:an overview[J].Proceedings of the CSEE,2017,37(14):3948-3962.
• [5]耿华，何长军，刘浴霜，等.新能源电力系统的暂态同步稳定研究综述[J].高电压技术，2022,48(9):3367-3383.GENG Hua,HE Changjun,LIU Yushuang,et al. Overview on transient synchronization stability of renewablerich power systems[J].High Voltage Engineering,2022,48(9):3367-3383.
• [6]屠竞哲，何剑，安学民，等.巴基斯坦“2023.1.23”大停电事故分析及启示[J].中国电机工程学报，2023,43(14):5319-5329.TU Jingzhe,HE Jian,AN Xuemin,et al.Analysis and lessons of Pakistan blackout event on January 23,2023[J].Proceedings of the CSEE,2023,43(14):5319-5329.
• [7]樊陈，姚建国，张琦兵，等.英国“8·9”大停电事故振荡事件分析及思考[J].电力工程技术，2020,39(4):34-41.FAN Chen,YAO Jianguo,ZHANG Qibing,et al.Reflection and analysis for oscillation of the blackout event of 9August 2019 in UK[J].Electric Power Engineering Technology,2020,39(4):34-41.
• [8]黄彦浩，于之虹，谢昶，等.电力大数据技术与电力系统仿真计算结合问题研究[J].中国电机工程学报，2015,35(1):13-22.HUANG Yanhao,YU Zhihong,XIE Chang,et al.Study on the application of electric power big data technology in power system simulation[J]. Proceedings of the CSEE,2015,35(1):13-22.
• [9]汤奕，崔晗，李峰，等.人工智能在电力系统暂态问题中的应用综述[J].中国电机工程学报，2019,39(1):2-13.TANG Yi,CUI Han,LI Feng,et al.Review on artificial intelligence in power system transient stability analysis[J].Proceedings of the CSEE,2019,39(1):2-13.
• [10]胡伟，郑乐，闵勇，等.基于深度学习的电力系统故障后暂态稳定评估研究[J].电网技术，2017,41(10):3140-3146.HU Wei,ZHENG Le,MIN Yong,et al. Research on power system transient stability assessment based on deep learning of big data technique[J].Power System Technology,2017,41(10):3140-3146.
• [11]田芳，周孝信，于之虹.基于支持向量机综合分类模型和关键样本集的电力系统暂态稳定评估[J].电力系统保护与控制，2017,45(22):1-8.TIAN Fang,ZHOU Xiaoxin,YU Zhihong.Power system transient stability assessment based on comprehensive SVM classification model and key sample set[J]. Power System Protection and Control,2017,45(22):1-8.
• [12]王琦，李峰，汤奕，等.基于物理—数据融合模型的电网暂态频率特征在线预测方法[J].电力系统自动化，2018,42(19):1-9.WANG Qi,LI Feng,TANG Yi,et al.On-line prediction method of transient frequency characteristics for power grid based on physical-statistical model[J].Automation of Electric Power Systems,2018,42(19):1-9.
• [13]童晓阳，叶圣永.数据挖掘在电力系统暂态稳定评估中的应用综述[J].电网技术，2009,33(20):88-93.TONG Xiaoyang,YE Shengyong.A survey on application of data mining in transient stability assessment of power system[J].Power System Technology,2009,33(20):88-93.
• [14]纪泰鹏，赵伟，李永达，等.基于能量函数法的含虚拟惯性控制直驱风电场内部暂态同步稳定性分析[J].电力系统保护与控制，2022,50(22):38-48.JI Taipeng,ZHAO Wei,LI Yongda,et al.Transient synchronization stability analysis of PMSG-based wind farm with virtual inertial control based on an energy function method[J].Power System Protection and Control,2022,50(22):38-48.
• [15]陈剑，杜文娟，王海风.基于动态参数等效的风电场并网系统振荡稳定性评估的数据驱动方法[J].中国电机工程学报，2022,42(19):6958-6973.CHEN Jian,DU Wenjuan,WANG Haifeng.A data-driven method for oscillation stability assessment of gridconnected wind farm based on dynamic parameters equivalent[J]. Proceedings of the CSEE,2022,42(19):6958-6973.
• [16]李永康，刘宝柱，胡俊杰.基于数据驱动与时域仿真融合的电力系统暂态稳定快速评估[J].电网技术，2023,47(11):4386-4396.LI Yongkang,LIU Baozhu,HU Junjie.Rapid evaluation of power system transient stability based on fusion of datadriven and time-domain simulation[J]. Power System Technology,2023,47(11):4386-4396.
• [17]王彤，刘九良，朱劭璇，等.基于随机森林的电力系统暂态稳定评估与紧急控制策略[J].电网技术，2020,44(12):4694-4701.WANG Tong,LIU Jiuliang,ZHU Shaoxuan,et al.Transient stability assessment and emergency control strategy based on random forest in power system[J].Power System Technology,2020,44(12):4694-4701.
• [18]武宇翔，韩肖清，牛哲文，等.基于变权重随机森林的暂态稳定评估方法及其可解释性分析[J].电力系统自动化，2023,47(14):93-104.WU Yuxiang,HAN Xiaoqing,NIU Zhewen,et al.Transient stability assessment method based on variable weight random forest and its interpretability analysis[J].Automation of Electric Power Systems,2023,47(14):93-104.
• [19] HE M,ZHANG J S,VITTAL V.Robust online dynamic security assessment using adaptive ensemble decision-tree learning[J].IEEE Transactions on Power Systems,2013,28(4):4089-4098.
• [20] ZHOU D Q,ANNAKKAGE U D,RAJAPAKSE A D.Online monitoring of voltage stability margin using an artificial neural network[J]. IEEE Transactions on Power Systems,2010,25(3):1566-1574.
• [21]马翔匀，鲍颜红，张金龙，等.基于支持向量机和决策函数的暂态稳定评估方法[J].电测与仪表，2019,56(23):48-53.MA Xiangyun,BAO Yanhong,ZHANG Jinlong,et al.Transient stability assessment based on support vector machine and decision function[J].Electrical Measurement&Instrumentation,2019,56(23):48-53.
• [22]朱轶伦，罗烨锋，高强，等.基于LSTM的电力暂态稳定在线评估及预测研究[J].电网与清洁能源，2021,37(3):38-46.ZHU Yilun,LUO Yefeng,GAO Qiang,et al.Research on online assessment and prediction of power system transient stability based on LSTM[J]. Power System and Clean Energy,2021,37(3):38-46.
• [23]崔昊杨，周坤，胡丰晔，等.基于改进LSTM的电力设备状态融合预测模型[J].电测与仪表，2023,60(1):10-15.CUI Haoyang,ZHOU Kun,HU Fengye,et al.State fusion prediction model of power equipment based on improved LSTM[J]. Electrical Measurement&Instrumentation,2023,60(1):10-15.
• [24]戴远航，陈磊，张玮灵，等.基于多支持向量机综合的电力系统暂态稳定评估[J].中国电机工程学报，2016,36(5):1173-1180.DAI Yuanhang,CHEN Lei,ZHANG Weiling,et al.Power system transient stability assessment based on multi-support vector machines[J]. Proceedings of the CSEE,2016,36(5):1173-1180.
• [25]叶圣永，王晓茹，刘志刚，等.基于支持向量机增量学习的电力系统暂态稳定评估[J].电力系统自动化，2011,35(11):15-19.YE Shengyong,WANG Xiaoru,LIU Zhigang,et al.Power system transient stability assessment based on support vector machine incremental learning method[J].Automation of Electric Power Systems,2011,35(11):15-19.
• [26]宋国杰，李国进，杨浩，等.基于李雅普诺夫函数的微电网下并网逆变器的自适应控制[J].高电压技术，2020,46(12):4455-4463.SONG Guojie,LI Guojin,YANG Hao,et al. Adaptive control of grid-connected inverter in microgrid based on Lyapunov function[J].High Voltage Engineering,2020,46(12):4455-4463.
• [27]沈赋，李施伟，王健，等.融合储能的光伏发电系统并网逆变器建模与稳定性分析[J].电力系统保护与控制，2024,52(19):131-143.SHEN Fu,LI Shiwei,WANG Jian,et al. Modeling and stability analysis of a photovoltaic grid-connected inverter integrated with an energy storage system[J].Power System Protection and Control,2024,52(19):131-143.
• [28]李东东，陈昊，姚寅，等.考虑非均匀通信延迟的多VSG功率振荡抑制[J].电力建设，2024,45(9):63-73.LI Dongdong,CHEN Hao,YAO Yin,et al.Power oscillation suppression of multi-VSG considering non-uniform communication delays[J]. Electric Power Construction,2024,45(9):63-73.
• [29]张志轩，李乐蒙，周宁，等.基于ADPSS的直驱风机半实物仿真研究[J].山东电力技术，2024,51(7):27-34.ZHANG Zhixuan,LI Lemeng,ZHOU Ning,et al. Research on semi-physical simulation of direct drive fan based on ADPSS[J].Shandong Electric Power,2024,51(7):27-34.
• [30]李琳，张晓楠，李庚银，等.考虑内外环交互作用的VSG并网振荡特性[J].电力建设，2024,45(4):66-76.LI Lin,ZHANG Xiaonan,LI Gengyin,et al.Characteristics of VSG grid-connected system oscillation considering the interaction between inner and outer loops[J].Electric Power Construction,2024,45(4):66-76.
• [31]李震，李庆生，张裕，等.一种基于数字孪生的虚拟同步机与静止同步补偿器优化协调控制策略研究[J].智慧电力，2024,52(2):115-122.LI Zhen,LI Qingsheng,ZHANG Yu,et al.A digital twinbased optimal coordinated control strategy for virtual synchronous generator and STATCOM[J]. Smart Power,2024,52(2):115-122.
• [32]朱克平，何英静，姜卫同，等.光储联合发电系统组网型控制策略对比研究[J].电力电容器与无功补偿，2023,44(5):108-115.ZHU Keping,HE Yingjing,JIANG Weitong,et al.Comparative study on grid-forming control strategies of PVstorage combined power generation system[J].Power Capacitor&Reactive Power Compensation,2023,44(5):108-115.
• [33]禹海峰，马俊杰，周年光，等.面向储能惯量支撑能力评估的新型电力系统惯性系数辨识方法[J].智慧电力，2023,51(5):1-7.YU Haifeng,MA Junjie,ZHOU Nianguang,et al. New power system inertia coefficient identification method for energy storage inertia support capability evaluation[J].Smart Power,2023,51(5):1-7.