A Short-term Power Load Forecasting Method Combining Extreme Gradient Boosting Decision Tree with an Improved Informer

YU Sheng; SUN Ke; CAI Hua; LIU Jian; GU Yilei; JIANG Yunpeng

doi:10.11930/j.issn.1004-9649.202412004

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

A Short-term Power Load Forecasting Method Combining Extreme Gradient Boosting Decision Tree with an Improved Informer

更新时间：2025-10-29

- A Short-term Power Load Forecasting Method Combining Extreme Gradient Boosting Decision Tree with an Improved Informer
- Vol. 58, Issue 10, Pages: 195-205(2025)
- 作者机构：
  
  1. 国网电力科学研究院有限公司,江苏,南京,211106
  2. 国网浙江省电力有限公司,浙江,杭州,310007
  3. 国网浙江省电力有限公司杭州供电公司,浙江,杭州,311201
- 作者简介：
- 基金信息：
- DOI：10.11930/j.issn.1004-9649.202412004
  CLC：
- Published Online：23 October 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
俞胜, 孙可, 蔡华, 刘剑, 顾益磊, 姜昀芃. 结合极端梯度提升决策树与改进Informer的短期电力负荷预测方法[J]. 中国电力, 2025, 58(10): 195-205.

YU Sheng, SUN Ke, CAI Hua, et al. A Short-term Power Load Forecasting Method Combining Extreme Gradient Boosting Decision Tree with an Improved Informer[J]. 2025, 58(10): 195-205.
俞胜, 孙可, 蔡华, 刘剑, 顾益磊, 姜昀芃. 结合极端梯度提升决策树与改进Informer的短期电力负荷预测方法[J]. 中国电力, 2025, 58(10): 195-205. DOI： 10.11930/j.issn.1004-9649.202412004.

YU Sheng, SUN Ke, CAI Hua, et al. A Short-term Power Load Forecasting Method Combining Extreme Gradient Boosting Decision Tree with an Improved Informer[J]. 2025, 58(10): 195-205. DOI： 10.11930/j.issn.1004-9649.202412004.

摘要

准确筛选影响短期电力负荷预测的特征因素是提高预测准确性的有效手段。针对多维数据集中非关键特征易引起预测模型拟合能力不佳，从而降低模型准确性的问题，提出了一种基于极端梯度提升（eXtreme gradient boosting，XGBoost）决策树与改进Informer模型相结合的短期电力负荷预测方法。首先，为了从多维历史负荷数据中评估特征因素重要性，采用XGBoost决策树覆盖率作为评估特征重要性的指标，准确筛选参与模型训练的特征因素。然后，构建了改进Informer短期负荷预测模型，通过对位置编码开展优化设计，将筛选出的关键特征联合不同时间尺度的位置标记信息作为编码器的输入向量。再次，设计消融实验对不同时间尺度下的模型收敛速度与预测精度开展对比分析。最后，开展算例分析进行验证，结果表明，与其他模型相比，XGB-Informer模型在短期电力负荷预测精度和收敛速度上均表现出明显优势，验证了所提方法的有效性和优越性。

Abstract

Accurately identifying the key feature factors that influence short-term power load forecasting is an effective means for enhancing forecast accuracy. To address the issue in multidimensional datasets where non-critical features can easily lead to poor fitting capability of prediction models

consequently reducing model accuracy

this paper proposes a short-term power load forecasting method that combines the eXtreme Gradient Boosting (XGBoost) decision tree with an improved Informer model. Firstly

to evaluate the importance of feature factors from multi-dimensional historical load data

the coverage metric of XGBoost decision tree is adopted as an indicator to assess feature importance

thereby enabling accurate screening of the feature factors participating in model training. Subsequently

an improved Informer short-term load forecasting model is constructed. By optimizing the positional encoding design

the selected key features are combined with positional markers of different time scales to form input vectors for the encoder. Finally

ablation experiments are designed to conduct a comparative analysis of model convergence speed and prediction accuracy across different time scales. Experimental results indicate that

compared to other models

the XGB-Informer model demonstrates significant advantages in both prediction accuracy and convergence speed

verifying the effectiveness and superiority of the proposed method.

关键词

Keywords

references

1韩富佳, 王晓辉, 乔骥, 等. 基于人工智能技术的新型电力系统负荷预测研究综述[J]. 中国电机工程学报, 2023, 43 (22): 8569- 8592.

HAN Fujia, WANG Xiaohui, QIAO Ji, et al. Review on artificial intelligence based load forecasting research for the new-type power system[J]. Proceedings of the CSEE, 2023, 43 (22): 8569- 8592.

2陈宋宋, 王阳, 周颖, 等. 基于客户用电数据的多时空维度负荷预测综述[J]. 电网与清洁能源, 2023, 39 (12): 28- 40. DOI

CHEN Songsong, WANG Yang, ZHOU Ying, et al. A review of multi-time-space load forecasting based on customer electricity consumption data[J]. Power System and Clean Energy, 2023, 39 (12): 28- 40. DOI

3杨佳泽, 王灿, 王增平. 新型电力系统背景下的智能负荷预测算法研究综述[J]. 华北电力大学学报(自然科学版), 2025, 52 (3): 54- 67.

YANG Jiaze, WANG Can, WANG Zengping. Review on intelligent load forecasting algorithms for the new-type power system[J]. Journal of North China Electric Power University (Natural Science Edition), 2025, 52 (3): 54- 67.

4朱明, 夏宇栋, 常凯, 等. 基于粒子群优化算法的空调负荷灰箱模型辨识[J]. 电力科学与技术学报, 2023, 38 (04): 214- 221.

ZHU Ming, XIA Yudong, CHANG Kai, et al. Identification of grey box model for air conditioning load based on particleswarm optimization algorithm[J]. Journal of Electric Power Science and Technology, 2023, 38 (04): 214- 221.

5刘杰, 从兰美, 夏远洋, 等. 基于DBO-VMD和IWOA-BILSTM神经网络组合模型的短期电力负荷预测[J]. 电力系统保护与控制, 2024, 52 (8): 123- 133.

LIU Jie, CONG Lanmei, XIA Yuanyang, et al. Short-term power load prediction based on DBO-VMD and an IWOA-BILSTMneural network combination model[J]. Power System Protection and Control, 2024, 52 (8): 123- 133.

6邓皓云, 陈卓. 基于EEMD-IWOA-TCN的电网短期负荷预测[J]. 电力信息与通信技术, 2024, 22 (1): 70- 76.

DENG Haoyun, CHEN Zhuo. Short-term load forecasting of power gird based on EEMD-IWOA-TCN[J]. Electric Power Information and Communication Technology, 2024, 22 (1): 70- 76.

7张大海, 孙锴, 和敬涵. 基于相似日与多模型融合的短期负荷预测[J]. 电网技术, 2023, 47 (5): 1961- 1970.

ZHANG Dahai, SUN Kai, HE Jinghan. Short-term load forecasting based on similar day and multi-model fusion[J]. Power System Technology, 2023, 47 (5): 1961- 1970.

8苗磊, 李擎, 蒋原, 等. 深度学习在电力系统预测中的应用[J]. 工程科学学报, 2023, 45 (4): 663- 672.

MIAO Lei, LI Qing, JIANG Yuan, et al. A survey of power system prediction based on deep learning[J]. Chinese Journal of Engineering, 2023, 45 (4): 663- 672.

9沈赋, 刘思蕊, 徐潇源, 等. 基于多尺度特征提取的IES多元负荷短期联合预测[J]. 高电压技术, 2024, 50 (7): 2918- 2930.

SHEN Fu, LIU Sirui, XU Xiaoyuan, et al. Multi-load short-term joint forecasting of integrated energy system based on multi-scale feature extraction[J]. High Voltage Engineering, 2024, 50 (7): 2918- 2930.

10邵必林, 纪丹阳. 基于VMD-SE的电力负荷分量的多特征短期预测[J]. 中国电力, 2024, 57 (4): 162- 170. DOI

SHAO Bilin, JI Danyang. Multi-feature short-term prediction of power load components based on VMD-SE[J]. Electric Power, 2024, 57 (4): 162- 170. DOI

11VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. arXiv: 1706.03762.

12吴军英, 路欣, 刘宏, 等. 基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]. 中国电力, 2024, 57 (6): 131- 140.

WU Junying, LU Xin, LIU Hong, et al. Ultra-short-term multi-region power load forecasting based on Spearman-GCN-GRU model[J]. Electric Power, 2024, 57 (6): 131- 140.

13方娜, 余俊杰, 李俊晓, 等. 基于CNN-BIGRU-ATTENTION的短期电力负荷预测[J]. 计算机仿真, 2022, 39 (2): 40- 44, 82. DOI

FANG Na, YU Junjie, LI Junxiao, et al. Short-term power load forecasting based on CNN-BIGRU-ATTENTION[J]. Computer Simulation, 2022, 39 (2): 40- 44, 82. DOI

14王宇飞, 杜桐, 边伟国, 等. 基于DTW K-medoids与VMD-多分支神经网络的多用户短期负荷预测[J]. 中国电力, 2024, 57 (6): 121- 130.

WANG Yufei, DU Tong, BIAN Weiguo, et al. Short-term load forecasting based on DTW K-medoids and VMD multi-branch neural network for multiple users[J]. Electric Power, 2024, 57 (6): 121- 130.

15钟吴君, 李培强, 涂春鸣. 基于EEMD-CBAM-Bi LSTM的牵引负荷超短期预测[J]. 电工技术学报, 2024, 39 (21): 6850- 6864.

ZHONG Wujun, LI Peiqiang, TU Chunming. Traction load ultra-short-term forecasting framework based on EEMD-CBAM-BiLSTM[J]. Transactions of China Electrotechnical Society, 2024, 39 (21): 6850- 6864.

16杨胡萍, 余阳, 汪超, 等. 基于VMD-CNN-BIGRU的电力系统短期负荷预测[J]. 中国电力, 2022, 55 (10): 71- 76. DOI

YANG Huping, YU Yang, WANG Chao, et al. Short-term load forecasting of power system based on VMD-CNN-BIGRU[J]. Electric Power, 2022, 55 (10): 71- 76. DOI

17葛亚明, 仇晨光, 谢丽荣, 等. 基于K-means聚类与LSTM模型的多能源耦合电力负荷预测[J]. 现代电力, 2025, 42 (2): 369- 376.

GE Yaming, QIU Chenguang, XIE Lirong, et al. Research on multi-energy coupled power load prediction based on K-means clustering and LSTM model[J]. Modern Electric Power, 2025, 42 (2): 369- 376.

18郝文斌, 孟志高, 张勇, 等. 基于SOM特征聚类及RBF神经网络的电力负荷预测方法研究[J]. 电力需求侧管理, 2024, 26 (2): 49- 54. DOI

HAO Wenbin, MENG Zhigao, ZHANG Yong, et al. Research on power load forecasting method based on feature clustering of SOM and RBF neural network[J]. Power Demand Side Management, 2024, 26 (2): 49- 54. DOI

19冉启武, 张宇航. 基于模态分解及GRU-XGBoost短期电力负荷预测[J]. 电网与清洁能源, 2024, 40 (4): 18- 27, 34. DOI

RAN Qiwu, ZHANG Yuhang. Short-term power load forecasting based on modal decomposition and GRU-XGBoost[J]. Power System and Clean Energy, 2024, 40 (4): 18- 27, 34. DOI

20刘明, 尚尚. 基于K_means++聚类与RF_GRU组合模型的电力负荷预测方法研究[J]. 计算机与数字工程, 2024, 52 (6): 1662- 1667, 1702. DOI

LIU Ming, SHANG Shang. Research on power load forecasting method based on K_means++ clustering and RF_GRU combined model[J]. Computer & Digital Engineering, 2024, 52 (6): 1662- 1667, 1702. DOI

21张峻凯, 胡旭光, 刘要博, 等. 基于动态关联图注意力网络的虚拟电厂居民短期负荷预测[J]. 电力系统自动化, 2024, 48 (21): 120- 128. DOI

ZHANG Junkai, HU Xuguang, LIU Yaobo, et al. Short-term residential load forecasting based on dynamic association graph attention networks for virtual power plant[J]. Automation of Electric Power Systems, 2024, 48 (21): 120- 128. DOI

22李甲祎, 赵兵, 刘宣, 等. 基于DWT-Informer的台区短期负荷预测[J]. 电测与仪表, 2024, 61 (3): 160- 166, 191.

LI Jiayi, ZHAO Bing, LIU Xuan, et al. Short-term substation load forecasting based on DWT-Informer model[J]. Electrical Measurement & Instrumentation, 2024, 61 (3): 160- 166, 191.

23石卓见, 冉启武, 徐福聪. 基于聚合二次模态分解及Informer的短期负荷预测[J]. 电网技术, 2024, 48 (6): 2574- 2583.

SHI Zhuojian, RAN Qiwu, XU Fucong. Short-term load forecasting based on aggregated secondary decomposition and informer[J]. Power System Technology, 2024, 48 (6): 2574- 2583.

24任晟岐, 宋伟. 基于GGInformer模型的多维时间序列特征提取与预测研究[J]. 计算机工程与科学, 2024, 46 (4): 590- 598. DOI

REN Shengqi, SONG Wei. Feature extraction and prediction of multidimensional time series based on GGInformer model[J]. Computer Engineering & Science, 2024, 46 (4): 590- 598. DOI

25CHEN T Q, GUESTRIN C. XGBoost: a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California USA. ACM, 2016: 785-794.

26ZHOU H Y, ZHANG S H, PENG J Q, et al. Informer: beyond efficient transformer for long sequence time-series forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35 (12): 11106- 11115. DOI

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-stage Optimization Forecast of Short-term Power Load Based on VMD and PSO-SVR

Short-Term Power Load Forecasting Method based on Glowworm Swarm Optimization Algorithm

Related Author

Wenwu LI

Qiang SHI

Dan LI

Qunyong HU

Yun TANG

Jinchao MEI

Haihong FAN

Related Institution

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

Hubei Key Laboratory of Cascaded Hydropower Stations Operation & Control (China Three Gorges University)

Zhongshan Power Supply Bureau of Guangdong Power Grid Co., Ltd.

China Energy Materials Company Limited

AI问答

⁰