Ultra-short-term traction load forecasting in plateau areas based on lightweight feature selection

LIU Xinyue; WANG Guo; MIN Yongzhi; GUO Wenkai; QIU Bohan; CHEN Qian

doi:10.19783/j.cnki.pspc.260054

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Ultra-short-term traction load forecasting in plateau areas based on lightweight feature selection

更新时间：2026-07-27

- Ultra-short-term traction load forecasting in plateau areas based on lightweight feature selection
- Power System Protection and Control Vol. 54, Issue 13, (2026)
- 作者机构：
  
  兰州交通大学自动化与电气工程学院,甘肃,兰州,730070
- 作者简介：
- 基金信息：
- DOI：10.19783/j.cnki.pspc.260054
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
LIU Xinyue, WANG Guo, MIN Yongzhi, et al. Ultra-short-term traction load forecasting in plateau areas based on lightweight feature selection[J]. Power System Protection and Control, 2026, 54(13).
DOI：

LIU Xinyue, WANG Guo, MIN Yongzhi, et al. Ultra-short-term traction load forecasting in plateau areas based on lightweight feature selection[J]. Power System Protection and Control, 2026, 54(13). DOI： 10.19783/j.cnki.pspc.260054.

摘要

针对高原牵引供电系统再生制动能量利用率低、电压波动剧烈以及缺乏实时行车指令导致负荷预测困难的问题，提出一种面向“源-网-车-储”系统日内调度与实时控制的超短期负荷预测方法。首先，构建秒级特征量化体系，并提出多阶段动态特征筛选模型，剔除冗余特征以实现模型轻量化。其次，构建融合自适应噪声完备集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise

CEEMDAN)、卷积神经网络(convolutional neural network

CNN)、双向长短期记忆网络(bidirectional long short-term memory

BiLSTM)和随机森林(random forest

RF)的混合预测模型，并引入贝叶斯优化对超参数进行自适应寻优。最后，算例结果表明所提方法能够有效提升高原牵引负荷超短期预测精度，具有较好的动态特征捕捉能力、跟踪性能和稳定性，可为实时能量管理提供可靠的前瞻性决策依据。

Abstract

To address the challenges of ultra-short-term load forecasting in plateau traction power supply systems caused by low utilization of regenerative braking energy

severe voltage fluctuations

and the lack of real-time train operation commands

this paper proposes an ultra-short-term load forecasting method for intraday dispatch and real-time control of the source-grid-train-storage system. First

a second-level feature quantification framework is established

and a multi-stage dynamic feature selection model is proposed to eliminate redundant features and achieve lightweight modeling. Then

a hybrid forecasting model integrating complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN)

convolutional neural network (CNN)

bidirectional long short-term memory (BiLSTM)

and random forest (RF) is constructed. Bayesian optimization is introduced to adaptively optimize the model hyperparameters. Finally

case study results show that the proposed method can effectively improve the accuracy of ultra-short-term forecasting for plateau traction loads

exhibiting strong dynamic feature extraction capability

tracking performance

and stability. The method provides a reliable forward-looking decision-making basis for real-time energy management.

关键词

Keywords

references

CHE Y, WANG X, GE L, et al. A review of research on traction load models and modeling methods for electrified railways[J]. Renewable and Sustainable Energy Reviews, 2025, 219.

WANG J, GAO J, WEI D. Electric load prediction based on a novel combined interval forecasting system[J]. Applied Energy, 2022, 322.

MA Q, WANG H, LUO P, et al. Ultra-short-term railway traction load prediction based on DWT-TCN-PSO_SVR combined model[J]. International Journal of Electrical Power Energy Systems, 2022, 135.

SUN J, MA K, ZHAO H. Short-term power load hybrid forecasting using GRU and SCN[J]. Energy and Buildings, 2025, 347.

ZHU S, MA H, CHEN L, et al. Short-term load forecasting of an integrated energy system based on STL-CPLE with multitask learning[J]. Protection and Control of Modern Power Systems, 2024, 9(6): 71-92.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

贝叶斯优化超参数的空时融合压缩残差网络在风速区间预测中的研究

基于MHA-CNN-SLSTM和误差补偿的短期互感器误差预测

考虑阵列间时空相关性的超短期光伏出力预测

Voltage control of single-phase grid-forming inverters based on a model-assisted extended state observer with a quasi-proportional resonant controller

Adaptive droop control of VSC-MTDC incorporating power change rate and margin feedback

Related Author

CHE Liang

LI Xiaoyong

WANG Wenye

GE Jiamin

Related Institution

CHE Liang(1. College of Electrical and Information Engineering, Hunan University

School of Environment, South China Normal University

QIU Li(1. Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station, China Three Gorges University

College of Electrical Engineering & New Energy, China Three Gorges University

National High Magnetic Field Center, Huazhong University of Science and Technology

AI问答

⁰