基于TimeMixer时序预测的电力系统宽频振荡快速辨识

赵 妍; 范彬雪; 李亚波; 刘 闯

doi:10.19783/j.cnki.pspc.260233

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于TimeMixer时序预测的电力系统宽频振荡快速辨识

应用研究 | 更新时间：2026-10-16

- 基于TimeMixer时序预测的电力系统宽频振荡快速辨识
- Fast identification of power system wideband oscillations based on TimeMixer time‑series prediction
- 电力系统保护与控制 2026年54卷第17期
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19783/j.cnki.pspc.260233
  中图分类号：
- 纸质出版：2026
- 稿件说明：
移动端阅览
赵妍, 范彬雪, 李亚波, 等. 基于TimeMixer时序预测的电力系统宽频振荡快速辨识[J]. 电力系统保护与控制, 2026,54(17).

ZHAO Yan, FAN Binxue, LI Yabo, et al. Fast identification of power system wideband oscillations based on TimeMixer time‑series prediction[J]. Power System Protection and Control, 2026, 54(17).
赵妍, 范彬雪, 李亚波, 等. 基于TimeMixer时序预测的电力系统宽频振荡快速辨识[J]. 电力系统保护与控制, 2026,54(17). DOI： 10.19783/j.cnki.pspc.260233.

ZHAO Yan, FAN Binxue, LI Yabo, et al. Fast identification of power system wideband oscillations based on TimeMixer time‑series prediction[J]. Power System Protection and Control, 2026, 54(17). DOI： 10.19783/j.cnki.pspc.260233.

摘要

传统电力系统宽频振荡辨识方法基于全实测数据，存在固有延时，难以满足新型电力系统对低延迟实时防控的需求。为此，提出一种融合 TimeMixer 时序预测的宽频振荡快速辨识方法。该方法首先通过多尺度分解模块生成适配多频段的多尺度时序序列。然后由过去可分解混合模块 (past‑decomposable‑mixing

PDM) 对多尺度特征进行季节‑趋势分解与跨尺度双向混合，从而获得综合特征。最后由未来多重预测器混合模块 (future‑multipredictor‑mixing

FMM) 独立预测并自适应加权融合，生成高精度短时未来波形。通过将预测波形数据动态补全未来时序数据，构建实测‑预测融合序列，该方法即可在数据采集阶段提前启动参数辨识计算，实现数据等待时间与计算时间的有效重叠。电网仿真实验表明，该方法在保证辨识精度的前提下显著缩短端到端延迟，有效提升了宽频振荡在线分析的实时性。

Abstract

Conventional wideband oscillation identification methods for power systems rely exclusively on measured data

resulting in inherent delays that make them unsuitable for the low‑latency

real‑time monitoring and control requirements of new power systems. To address this limitation

this paper proposes a fast wideband oscillation identification method integrated with TimeMixer time‑series prediction. First

a multi‑scale decomposition module is employed to generate multi‑scale time‑series representations suitable for different frequency bands. The past‑decomposable mixing (PDM) module then conducts seasonal‑trend decomposition and bidirectional cross‑scale feature mixing to obtain comprehensive temporal representations. Finally

the future multi‑predictor mixing (FMM) module executes independent per‑scale prediction and adaptive weighted fusion to produce high‑precision short‑term future waveforms. By dynamically extending measured data with predicted waveforms

a hybrid measured‑predicted time series is constructed

enabling parameter identification to be initiated during the data acquisition process. Consequently

the waiting time for data collection overlaps with the computation time for parameter estimation

significantly reducing the overall identification latency. Simulation results on a power system test network demonstrate that the proposed method substantially reduces the end‑to‑end latency without sacrificing identification accuracy

thereby significantly improving the real‑time capability of online wideband oscillation analysis.

关键词

Keywords

references

RAFAQ M S, JUNG J W. A comprehensive review of state‑of‑the‑art parameter estimation techniques for permanent magnet synchronous motors in wide speed range[J]. IEEE Transactions on Industrial Informatics, 2020, 16(7): 4747-4758.

HU Jianxiong, WANG Qi, YE Yujian, et al. Toward online power system model identification: a deep reinforcement learning approach[J]. IEEE Transactions on Power Systems, 2023, 38(3): 2580-2593.

RUAN Mengjie, CHENG Yifan, ZHANG Tietao, et al. Improved Prony method for high‑frequency‑resolution harmonic and interharmonic analysis[C] // 2019 IEEE 2nd International Conference on Electronics Technology (ICET), May 10‑13, 2019, Chengdu, China: 585‑589.

ZHANG Hao, SUN Hanlei, KANG Le, et al. Prediction of health level of multiform lithium sulfur batteries based on incremental capacity analysis and an improved LSTM[J]. Protection and Control of Modern Power Systems, 2024, 9(2): 21‑31.

ZHANG Jiquan, FU Xiaobiao, FU Jieyue, et al. Multi‑ time resolution load unified prediction method based on improved TimeMixer[C] // 2024 IEEE 6th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), October 23‑25, 2024, Hangzhou, China: 1171‑1176.

TANG Wejie, CHEN Jiayan, CHEN Dongjiao. Predicting EV battery state of health using long short term degradation feature extraction and FEA TimeMixer[J]. Scientific Reports, 2025, 15(1).

LUDOLFINGER U, HAMACHER T, MARTENS M. An analysis of prediction techniques for model predictive control in smart energy storage systems[C] // 2025 IEEE Kiel PowerTech, June 29‑July 3, 2025, Kiel, Germany: 1‑6.

SAAD H, FILLION Y, DESCHANVRES S, et al. On resonances and harmonics in HVDC‑MMC station connected to AC grid[J]. IEEE Transactions on Power Delivery, 2017, 32(3): 1565‑1573.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于YOLOv8的轻量化变电设备红外图像故障区域分割方法

基于双层优化迭代模数并联双驱的电力系统负荷建模方法

基于单相背靠背变流器的不对称串并联混合扰动注入型阻抗测量装置

基于主动探测式的双端弱馈交流系统模型识别纵联保护

基于负序电压幅值差的配电网单相断线接地复合故障区段定位方法