Dynamic harmonic state estimation of an unscented Kalman filter based on long short-term memory neural networks

被引：0
|
作者：
Huang M. [1 ]
Wang T. [1 ]
Wei Z. [1 ]
Sun G. [1 ]
机构：
[1] College of Energy and Electrical Engineering, Hohai University, Nanjing
来源：
Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control | 2022年 / 50卷 / 11期
基金：
中国国家自然科学基金;
关键词：
dynamic harmonic state estimation; long short-term memory neural networks; prediction model; robustness; unscented Kalman filter;
D O I：
10.19783/j.cnki.pspc.211221
中图分类号：
学科分类号：
摘要：
The Kalman filter prediction step of traditional dynamic harmonic state estimation usually constructs the state space model with a unit matrix and assumes the system noise covariance matrix as a constant matrix. This reduces the accuracy of the estimation and affects the results of the dynamic state estimation model. In order to establish the spatial model of harmonic state accurately, this paper proposes a time series prediction method based on a long short-term memory network. The complex state transfer process is simulated by off-line training of a large number of historical data, and the harmonic state at the present moment is predicted based on the filtering estimation of historical moments. This effectively improves the accuracy of the prediction model in an unscented Kalman filter. The method in this paper is tested and analyzed on the improved IEEE 34-node three-phase unbalanced system. Compared with the traditional method, the results show that the proposed method performs better in both precision and robustness of harmonic state estimation. © 2022 Power System Protection and Control Press. All rights reserved.
引用
收藏
页码：1 / 11
页数：10
相关论文
共 26 条
  • [1] NIE Xiaohua, A new method of power quality disturbance detection based on Kalman filter, Proceedings of the CSEE, 37, 22, pp. 6649-6658, (2017)
  • [2] YANG Denghui, ZHU Mingxing, XU Bin, An analysis method for frequency and transient harmonics of isolated network under instable condition, Electric Power, 54, 8, pp. 27-34, (2021)
  • [3] LI Xinyue, LI Fengting, YIN Chunya, Et al., Transient overvoltage calculation method of HVDC sending-end system under DC bipolar blocking, Power System Protection and Control, 49, 1, pp. 1-8, (2021)
  • [4] CHEN Lei, HE Huiwen, WANG Lei, Et al., Fault isolation method of a hybrid HVDC system based on the coordination of a fault current limiter and a DC circuit breaker, Power System Protection and Control, 48, 19, pp. 119-127, (2020)
  • [5] SUN Liming, YANG Bo, Nonlinear robust fractional-order control of battery/SMES hybrid energy storage systems, Power System Protection and Control, 48, 22, pp. 76-83, (2020)
  • [6] BAI Zhixuan, XIAO Xianyong, ZHANG Yi, Et al., Identification method of harmonic source considering harmonic apparent power, Automation of Electric Power Systems, 41, 8, pp. 11-15, (2017)
  • [7] SUN Yuanyuan, LI Shurong, SHI Fang, Et al., Multiple harmonic source contribution determination in the active distribution network with distributed harmonic sources, Proceedings of the CSEE, 39, 18, pp. 5389-5398, (2019)
  • [8] LI Congshan, LIU Tianqi, LI Xingyuan, Et al., Data fusion method of WAMS/SCADA hybrid measurements in power system state estimation, High Voltage Engineering, 39, 11, pp. 2686-2691, (2013)
  • [9] ZHAO Hongshan, TIAN Tian, Dynamic state estimation for power system based on an adaptive unscented Kalman filter, Power System Technology, 38, 1, pp. 188-192, (2014)
  • [10] ZHANG Weichen, XIONG Yongxin, LI Chenghao, Et al., Continuous commutation failure suppression and coordinated recovery of multi-infeed DC system based on improved VDCOL, Power System Protection and Control, 48, 13, pp. 63-72, (2020)
123