Integrated energy system load forecasting based on SEResNet-BiLSTM network

宋峥峥; 辛 锐; 赵黎媛; 王经书; 张鹏飞; 李士林

doi:10.3969/j.issn.1009-1831.2025.03.009

您当前的位置：

首页 >

文章列表页 >

Integrated energy system load forecasting based on SEResNet-BiLSTM network

更新时间：2026-03-05

- Integrated energy system load forecasting based on SEResNet-BiLSTM network
- Vol. 27, Issue 3, (2025)
- 作者机构：
  
  1. 国网河北省电力有限公司信息通信分公司,石家庄,050000
  2. 电工装备可靠性与智能化国家重点实验室（河北工业大学）,天津,300401
  3. 河北工业大学人工智能与数据科学学院,天津,300401
  4. 国网河北省电力有限公司,石家庄,050000
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1009-1831.2025.03.009
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
宋峥峥, 辛锐, 赵黎媛, et al. Integrated energy system load forecasting based on SEResNet-BiLSTM network[J]. 2025, 27(3).
DOI：

宋峥峥, 辛锐, 赵黎媛, et al. Integrated energy system load forecasting based on SEResNet-BiLSTM network[J]. 2025, 27(3). DOI： 10.3969/j.issn.1009-1831.2025.03.009.

摘要

准确预测多能源负荷对综合能源系统的优化调度和经济运行至关重要。针对区域综合能源系统随机性强和多能源耦合关系等特点，提出一种基于SEResNet-BiLSTM网络和注意力机制的多任务短期负荷预测模型。首先，采用压缩与激励网络与残差网络相结合的模型（squeeze-and-excitation networks-residual network，SEResNet）作为高维特征提取单元，挖掘多能源之间的耦合关系，实现多能源负荷数据的高维特征提取；然后，利用双向长短期记忆网络捕获数据之间的时序特征，实现对负荷数据的预测；通过硬权重共享的方式实现多任务负荷学习，从而实现多元负荷预测。最后，通过仿真实验验证了所提方法的有效性，所提出的方法在精度方面相比于其他模型有明显的提升。

Abstract

Accurate prediction of multi-energy load is crucial for the optimal scheduling and economic operation of integrated energy systems（IES）. Aiming at the strong randomness of regional IES and the coupling relationship between multi-energy sources

a multi-task short-term load prediction model based on SEResNet-BiLSTM network and attention mechanism is proposed. Firstly

the model of squeezeand-excitation networks-residual network（SEResNet）is used as the high-dimensional feature extraction unit to mine the coupling relationship between multiple energy sources. The high-dimensional feature extraction of multi-energy load data is realized. Then

bidirectional long short-term memory（BiLSTM）network is used to capture the time series characteristics between data to realize the prediction of load data. Multi-task load learning is realized by hard weight sharing to realize multivariate load forecasting. Finally

the effectiveness of proposed method is verified by simulation experiments

and the accuracy of the proposed method is significantly improved compared with other models.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Optimal scheduling of integrated energy system considering heat-electricity-gashydrogen-carbon coupling and the source-load response

Low-carbon economy optimization scheduling of integrated energy system considering the uncertainty of differentiated demand response

Master-slave game optimization scheduling of integrated energy system considering peak regulation ancillary service

Coordinated and optimized operation of multi-agent integrated energy system with electric vehicle shared energy storage characteristics

Short-term wind speed prediction model based on wavelet transform and bidirectional neural networks

Related Author

吕东

冒烨颖

丁敏

赵安新

张智晟

王作玮

张真源

杜月芳

Related Institution

国网江苏省电力有限公司苏州供电分公司

青岛大学电气工程学院

电子科技大学广东电子信息工程研究院

电子科技大学机械与电气工程学院

内蒙古工业大学能源与动力工程学院

AI问答

⁰