基于快速核学习的新能源高渗透电网频率风险评估Frequency Risk Assessment for Power Grid with High-penetration Renewable Integration Based on Fast Kernel Learning
董炜,华文,王冠中,王龙飞,王博文,叶承晋
DONG Wei,HUA Wen,WANG Guanzhong,WANG Longfei,WANG Bowen,YE Chengjin
摘要(Abstract):
新能源高渗透电网在功率扰动后,频率响应轨迹更容易呈现出频率偏差大和变化速率高的特性,导致频率保护动作受到明显影响。为准确预测强随机运行方式下的系统频率响应特性,利用基于核矩阵广义逆运算的快速核学习算法,结合共模频率解析所得关键特征量,提出一种新能源高渗透电网的频率风险评估方法。该方法通过一组相互独立的采样数据,运用核矩阵广义逆运算构造出正则项函数,避免了一般机器学习算法迭代求解所带来的收敛性问题,并且不降低学习结果的泛化能力。在IEEE 39节点测试系统中进行的算例分析验证了所提方法的有效性。
In the aftermath of power disturbance in power grid with high-penetration renewable integration,the frequency response trajectory is more likely to present large frequency deviation and high rate of change,which leads to a significant effect on frequency protection action. In order to accurately predict the frequency response characteristics of the system under the strong random operation mode,this paper uses the fast kernel learning algorithm based on the pseudo-inverse of the kernel matrix and integrates the key feature quantities obtained from the common mode frequency analysis to propose a frequency risk assessment method for power grid with high-penetration renewable integration. This method uses a set of mutually independent sample data to directly construct the regular term function through the pseudo-inverse operation of the kernel matrix,avoiding the convergence problems caused by the iterative solution of general machine learning algorithms without reducing the generalization ability of the learning results. The analysis of an example in the IEEE 39-node system verifies the effectiveness of the proposed method.
关键词(KeyWords):
频率特性;核学习;核矩阵;广义逆;风险评估
frequency characteristics;kernel learning;kernel matrix;pseudo-inverse;risk evaluation
基金项目(Foundation): 国网浙江省电力有限公司科技项目(B311DS21000N)
作者(Author):
董炜,华文,王冠中,王龙飞,王博文,叶承晋
DONG Wei,HUA Wen,WANG Guanzhong,WANG Longfei,WANG Bowen,YE Chengjin
参考文献(References):
- [1]方勇杰.英国“8·9”停电事故对频率稳定控制技术的启示[J].电力系统自动化,2019,43(24):1-5.
- [2]孙华东,许涛,郭强,等.英国“8·9”大停电事故分析及对中国电网的启示[J].中国电机工程学报,2019,39(21):6183-6192.
- [3]李兆伟,吴雪莲,庄侃沁,等.“9·19”锦苏直流双极闭锁事故华东电网频率特性分析及思考[J].电力系统自动化,2017,41(7):149-155.
- [4]国家市场监督管理总局,国家标准化管理委员会.电力系统安全稳定导则:GB/T 38755—2019[S].北京:中国标准出版社,2019.
- [5]张剑云,李明节.新能源高渗透的电力系统频率特性分析[J].中国电机工程学报,2020,40(11):3498-3507.
- [6]高晖胜,辛焕海,黄林彬,等.新能源电力系统的共模频率分析及其特征量化[J].中国电机工程学报,2021,41(3):890-900.
- [7]张恒旭,薛禹胜.转速的简化处理对暂态稳定仿真的影响[J].电力系统自动化,2003,27(17):8-10.
- [8]张怡,张恒旭,李常刚,等.深度学习在电力系统频率分析与控制中的应用综述[J].中国电机工程学报,2021,41(10):3392-3406.
- [9]温佳鑫,卜思齐,陈麒宇,等.基于数据学习的新能源高渗透电网频率风险评估[J].发电技术,2021,42(1):40-47.
- [10]朱岚康,单宝旭,隋本刚.光伏电站参与电网频率调节技术的研究[J].浙江电力,2019,38(6):118-122.
- [11]毛亚非.风电接入下基于“源-源”协调的系统频率控制研究[J].浙江电力,2015,34(10):1-5.
- [12]朱轶伦,张东波,陈新建,等.计及频率特性的高比例可再生能源电力系统概率潮流分析[J].浙江电力,2021,40(5):7-13.
- [13] POOLLA B K,BOLOGNANI S,D?RFLER F.Optimal placement of virtual inertia in power grids[J].IEEE Transactions on Automatic Control,2017,62(12):6209-6220.
- [14] LIN S B,ZENG J S.Fast learning with polynomial kernels[J].IEEE transactions on cybernetics,2019,49(10):3780-3792.
- [15]赵友国,刘尚伟,王冠中,等.基于正交分解的电力系统状态估计可观性分析[J].浙江电力,2021,40(7):1-5.
- [16]杨志文.新疆地区新能源引发次同步振荡典型案例分析[J].电力大数据,2021,24(8):83-92.
- [17]皇甫成,邱婷,梁吉,等.一种考虑电力系统频率安全的新能源并网限值评估方法[J].电网与清洁能源,2021,37(2):85-90.
- [18]赵熙临,姚业佩,何晶晶,等.考虑风机分组的风储联合辅助调频双目标预测优化方法[J].电网与清洁能源,2021,37(10):59-66.
- [19]刘颖明,陈亮,王晓东,等.混合储能参与风电集群一次调频的容量配置优化[J].电器与能效管理技术,2020(10):55-63.
- [20]王俊杰,孙嘉,徐猛,等.电源侧储能参与电网调频的容量配置研究[J].电器与能效管理技术,2020(10):84-89.