基于多通道特征提取与深度交互融合网络的IES多元负荷短期预测

郭利进; 郝书昭; 梁小龙

doi:10.19805/j.cnki.jcspe.2026.250322

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 >

基于多通道特征提取与深度交互融合网络的IES多元负荷短期预测

综合能源系统 | 更新时间：2026-09-15

- 基于多通道特征提取与深度交互融合网络的IES多元负荷短期预测
- Short-term Multi-load Forecasting of IES Based on Multi-channel Feature Extraction and Deep Interaction Fusion Network
- 动力工程学报 2026年46卷第9期页码：216-229
- 作者机构：
  
  1. 天津工业大学控制科学与工程学院,天津,300387
  2. 天津市电气装备智能控制重点实验室,天津,300387
- 作者简介：
  
  郭利进(1970—),男,湖北黄冈人,教授,博士,研究方向为过程参数的检测与控制,E-mail:Doctor_guo@tiangong.edu.cn。
- 基金信息：
  
  国家自然科学基金资助项目(52077155)
- DOI：10.19805/j.cnki.jcspe.2026.250322
  中图分类号： TM715
- 纸质出版：2026
- 稿件说明：
移动端阅览
郭利进, 郝书昭, 梁小龙. 基于多通道特征提取与深度交互融合网络的IES多元负荷短期预测[J]. 动力工程学报, 2026, 46(9): 216-229.
郭利进, 郝书昭, 梁小龙. 基于多通道特征提取与深度交互融合网络的IES多元负荷短期预测[J]. 动力工程学报, 2026, 46(9): 216-229. DOI： 10.19805/j.cnki.jcspe.2026.250322.

DOI： 10.19805/j.cnki.jcspe.2026.250322

摘要

针对综合能源系统中多能源复杂耦合关系及多变量时序的非平稳性与依赖性，提出一种基于多通道特征提取与深度交互融合的多任务学习模型。首先，结合最大互信息系数（MIC）和自相关函数（ACF）分析负荷特性并筛选关键输入特征；其次，采用多通道门控时间卷积网络（MGTCN）对各输入特征独立建模并动态提取有效信息，各通道输出通过交叉多头注意力模块实现深度交互，显式挖掘多源特征间的关联信息；然后，引入自适应路由融合（ARF）模块对各负荷与其交互信息进行全局语义建模与高效融合，接着由双向长短期记忆网络（BiLSTM）进一步捕捉融合特征的长短期时序依赖；最后，在多任务学习框架下共享负荷间耦合信息，并通过优化损失函数实现任务间平衡训练，提升预测模型的整体性能。算例分析表明：所提方法在多元负荷短期预测中具有更高的预测精度。

Abstract

To address the complex multi-energy coupling relationships

as well as the non-stationarity and dependency of multivariate time series in integrated energy systems

a multi-task learning model based on multi-channel feature extraction and deep interactive fusion was proposed. First

the maximal information coefficient (MIC) and autocorrelation function (ACF) were combined to analyze load characteristics and select key input features. Second

a multi-channel gated temporal convolutional network (MGTCN) was employed to independently model each input feature and dynamically extract effective information. The outputs of each channel achieved deep interaction through a cross multi-head attention module

explicitly mining the correlation information among multi-source features. Then

an adaptive routing fusion (ARF) module was introduced to conduct global semantic modeling and efficient fusion for each load and its interactive information

followed by a bidirectional long short-term memory (BiLSTM) network to further capture the long- and short-term temporal dependencies of the fused features. Finally

under the multi-task learning framework

the coupling information among loads was shared

and balanced training across tasks was achieved by optimizing the loss function

thereby enhancing the overall performance of the prediction model. Case analysis demonstrates that the proposed method achieves higher prediction accuracy in short-term multi-load forecasting.

关键词

Keywords

references

邹鑫, 陈丹昊, 邹爱孟, 等. 考虑多种负荷需求响应的综合能源系统优化运行[J]. 动力工程学报, 2025, 45(1): 154-164. ZOU Xin, CHEN Danhao, ZOU Aimeng, et al. Optimized operation of integrated energy systems considering multiple load demand response[J]. Journal of Chinese Society of Power Engineering, 2025, 45(1): 154-164.

肖龙, 张靖, 阚超, 等. 基于变分模态分解和组合深度神经网络的综合能源系统多元负荷预测[J]. 电网技术, 2025, 49(10): 4376-4385. XIAO Long, ZHANG Jing, KAN Chao, et al. Multivariate load forecasting for integrated energy systems based on variational modal decomposition and combined deep neural networks[J]. Power System Technology, 2025, 49(10): 4376-4385.

薛东, 段立强, 高统彤, 等. 考虑多重特征与不确定性度量的综合能源系统负荷预测研究[J]. 太阳能学报, 2024, 45(7): 379-388. XUE Dong, DUAN Liqiang, GAO Tongtong, et al. Study of integrated energy system load forecasting considering multiple characteristics and uncertainty measures[J]. Acta Energiae Solaris Sinica, 2024, 45(7): 379-388.

张玉敏, 孙猛, 吉兴全, 等. 基于模态分解与多任务学习模型的综合能源系统多元负荷短期预测[J]. 高电压技术, 2025, 51(7): 3488-3499. ZHANG Yumin, SUN Meng, JI Xingquan, et al. Short-term load forecasting of integrated energy system based on modal decomposition and multi-task learning model[J]. High Voltage Engineering, 2025, 51(7): 3488-3499.

付炳喆, 王玮, 任国瑞, 等. 考虑增强特征选择的深度卷积-时序网络短期风功率预测[J]. 动力工程学报, 2024, 44(10): 1565-1573. FU Bingzhe, WANG Wei, REN Guorui, et al. Short-term wind power prediction with deep convolutional-temporal networks considering enhanced feature selection[J]. Journal of Chinese Society of Power Engineering, 2024, 44(10): 1565-1573.

姚钦才, 向文国, 陈时熠, 等. 基于ICEEMDAN-KPCA-ICPA-LSTM的光伏发电功率预测[J]. 动力工程学报, 2025, 45(3): 374-382. YAO Qincai, XIANG Wenguo, CHEN Shiyi, et al. Photovoltaic power forecasting based on ICEEMDAN-KPCA-ICPA-LSTM[J]. Journal of Chinese Society of Power Engineering, 2025, 45(3): 374-382.

田浩含, 张智晟, 于道林. 基于改进LSTM的区域综合能源系统多元负荷短期预测研究[J]. 电力系统及其自动化学报, 2021, 33(9): 130-137. TIAN Haohan, ZHANG Zhisheng, YU Daolin. Research on multi-load short-term forecasting of regional integrated energy system based on improved LSTM[J]. Proceedings of the CSU-EPSA, 2021, 33(9): 130-137.

LIU Erjia, WANG Yuxuan, HUANG Yongzhang. Short-term forecast of multi-load of electrical heating and cooling in regional integrated energy system based on deep LSTM RNN[C]//2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2). Wuhan: IEEE, 2020: 2994-2998.

叶剑华, 曹旌, 杨理, 等. 基于变分模态分解和多模型融合的用户级综合能源系统超短期负荷预测[J]. 电网技术, 2022, 46(7): 2610-2618. YE Jianhua, CAO Jing, YANG Li, et al. Ultra short-term load forecasting of user level integrated energy system based on variational mode decomposition and multi-model fusion[J]. Power System Technology, 2022, 46(7): 2610-2618.

高晨元, 田建艳, 姬政雄, 等. 基于门控循环单元残差连接网络与多任务学习的园区综合能源系统多元负荷预测[J]. 电网技术, 2025, 49(5): 1771-1780. GAO Chenyuan, TIAN Jianyan, JI Zhengxiong, et al. Multivariate load forecasting for park-level integrated energy system based on gated recurrent unit residual connection network and multi-task learning[J]. Power System Technology, 2025, 49(5): 1771-1780.

孙庆凯, 王小君, 张义志, 等. 基于LSTM和多任务学习的综合能源系统多元负荷预测[J]. 电力系统自动化, 2021, 45(5): 63-70. SUN Qingkai, WANG Xiaojun, ZHANG Yizhi, et al. Multiple load prediction of integrated energy system based on long short-term memory and multi-task learning[J]. Automation of Electric Power Systems, 2021, 45(5): 63-70.

HAN Ruicong, JIANG He, WEI Mofan, et al. Research on joint forecasting technology of cold, heat, and electricity loads based on multi-task learning[J]. Electronics, 2024,13(22):4396-4396.

NIU Dongxiao, YU Min, SUN Lijie, et al. Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism[J]. Applied Energy, 2022, 313: 118801.

李云松, 张智晟. 基于ATT-TCGNN的综合能源系统多元负荷短期预测[J]. 电工电能新技术, 2024, 43(9): 23-32. LI Yunsong, ZHANG Zhisheng. Short-term multi-energy load short-term forecasting of integrated energy system based on ATT-TCGNN[J]. Advanced Technology of Electrical Engineering and Energy, 2024, 43(9): 23-32.

岳伟民, 刘青荣, 阮应君, 等. 基于MTL-GRU-Attention的综合能源系统多元负荷预测[J]. 电力系统及其自动化学报, 2023, 35(6): 83-89. YUE Weimin, LIU Qingrong, RUAN Yingjun, et al. Multivariate load forecasting of integrated energy system based on MTL-GRU-attention mechanism[J]. Proceedings of the CSU-EPSA, 2023, 35(6): 83-89.

WANG Yixi, GAO Wei, NING Hao, et al. An attention-BiGRU based power generation forecasting method for multi-energy systems[C]//2024 10th International Conference on Computer and Communications (ICCC). Chengdu: IEEE, 2024: 2302-2306.

SUN Qianxiang, MA Hongyuan, LI Guangdi, et al. Short-term multivariate load forecasting for integrated energy systems based on BIGRU-AM and multi-task learning[C]//2022 First International Conference on Cyber-Energy Systems and Intelligent Energy (ICCSIE). Shenyang: IEEE, 2023: 1-6.

FENG Yang, ZHU Jiashan, QIU Pengjin, et al. Short-term power load forecasting based on TCN-BiLSTM-attention and multi-feature fusion[J]. Arabian Journal for Science and Engineering, 2024, 50(8): 5475-5486.

ZHANG Wei, ZHAN Hongyi, SUN Hang, et al. Probabilistic load forecasting for integrated energy systems based on quantile regression patch time series Transformer[J]. Energy Reports, 2025, 13: 303-317.

WANG Danhao, PENG Daogang, HUANG Dongmei, et al. MMEMformer: a multi-scale memory-enhanced transformer framework for short-term load forecasting in integrated energy systems[J]. Energy, 2025, 322: 135762.

WANG Shaomin, WANG Shouxiang, CHEN Haiwen, et al. Multi-energy load forecasting for regional integrated energy systems considering temporal dynamic and coupling characteristics[J]. Energy, 2020, 195: 116964.

LI Ke, MU Yuchen, YANG Fan, et al. A novel short-term multi-energy load forecasting method for integrated energy system based on feature separation-fusion technology and improved CNN[J]. Applied Energy, 2023, 351: 121823.

杨澜倩, 郭锦敏, 田慧丽, 等. 基于CNN-LSTM-Self attention的园区负荷多尺度预测研究[J]. 综合智慧能源, 2025, 47(2): 79-87. YANG Lanqian, GUO Jinmin, TIAN Huili, et al. Research on multi-scale load prediction in parks based on CNN-LSTM-Self attention[J]. Integrated Intelligent Energy, 2025, 47(2): 79-87.

李云松, 张智晟. 基于GRU-TGTransformer的综合能源系统多元负荷短期预测[J]. 电力系统保护与控制, 2023, 51(15): 33-41. LI Yunsong, ZHANG Zhisheng. Multi load short-term forecasting of an integrated energy system based on a GRU-TGTransformer[J]. Power System Protection and Control, 2023, 51(15): 33-41.

倪建辉, 张菁. 基于多任务双层注意力优化的TCN-BiGRU综合能源负荷短期预测[J]. 控制工程, 2024, 31(11): 1924-1936. NI Jianhui, ZHANG Jing. Short-term load forecasting for integrated energy system based on TCN-BiGRU optimized by multi-task dual-layer attention[J]. Control Engineering of China, 2024, 31(11): 1924-1936.

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

芦竹与典型煤协同燃烧过程中灰成分与结渣特性研究

中高温热化学储热关键技术研究

考虑风光不确定性的风电光伏与燃气电站联合参与日前-实时市场的交易决策研究

基于半马尔可夫的风电机组自触发变桨控制

计入工业园区电热负荷需求的源网荷储优化调度方法研究