A Multiscale Lightweight Deep Learning Approach for Short-Term Multi-Energy Load Forecasting in Integrated Energy Systems

Jingshu Wang; Liyuan Zhao; Junhua Gu; Ying Lei

doi:10.1049/esi2.70048

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 >

A Multiscale Lightweight Deep Learning Approach for Short-Term Multi-Energy Load Forecasting in Integrated Energy Systems

更新时间：2026-10-08

- A Multiscale Lightweight Deep Learning Approach for Short-Term Multi-Energy Load Forecasting in Integrated Energy Systems
- A Multiscale Lightweight Deep Learning Approach for Short-Term Multi-Energy Load Forecasting in Integrated Energy Systems
- IET Energy Systems Integration 2026年8卷第1期
- 作者机构：
  
  1. School of Artificial Intelligence, Hebei University of Technology,Tianjin,China
  2. State Key Laboratory of Smart Power Distribution Equipment and System, Hebei University of Technology,Tianjin,China
  3. ,and
  4. Junhua Gu
  5. Liyuan Zhao
- 作者简介：
- 基金信息：
- DOI：10.1049/esi2.70048
  中图分类号：
- 纸质出版：2026
- 稿件说明：
移动端阅览
Jingshu Wang, Liyuan Zhao, Junhua Gu, 等. A Multiscale Lightweight Deep Learning Approach for Short-Term Multi-Energy Load Forecasting in Integrated Energy Systems[J]. IET Energy Systems Integration, 2026,8(1).

Jingshu Wang, Liyuan Zhao, Junhua Gu, et al. A Multiscale Lightweight Deep Learning Approach for Short-Term Multi-Energy Load Forecasting in Integrated Energy Systems[J]. IET Energy Systems Integration, 2026, 8(1).
Jingshu Wang, Liyuan Zhao, Junhua Gu, 等. A Multiscale Lightweight Deep Learning Approach for Short-Term Multi-Energy Load Forecasting in Integrated Energy Systems[J]. IET Energy Systems Integration, 2026,8(1). DOI： 10.1049/esi2.70048.

Jingshu Wang, Liyuan Zhao, Junhua Gu, et al. A Multiscale Lightweight Deep Learning Approach for Short-Term Multi-Energy Load Forecasting in Integrated Energy Systems[J]. IET Energy Systems Integration, 2026, 8(1). DOI： 10.1049/esi2.70048.

摘要

Abstract

Accurate multi-energy load forecasting plays a vital role in the optimal scheduling of integrated energy systems (IES). However

existing forecasting methods face two major challenges: insufficient extraction of complex features within load data

which limits prediction accuracy

and ever-increasing model complexity

which leads to a sharp rise in computational resource demands. To tackle the above-mentioned challenges

this research introduces a load forecasting scheme derived from multiscale lightweight deep learning. First

the dynamic coupling characteristics of load data are analysed using correlation coefficients to determine model-specific input configurations. Then

an improved variant channel multiscale bottleneck residual network (VC-MBResNet) is proposed to obtain high-dimensional load feature data. Finally

by leveraging shared underlying parameters and an enhanced adaptive loss function for each subtask-using both soft and hard weight-sharing strategies—the extracted features are integrated into a multi-task learning (MTL) framework. A bidirectional long short-term memory (BiLSTM) network is employed as the shared layer

with an attention mechanism embedded in its hidden layers to enhance the focus on critical temporal features. Experimental results demonstrate that the proposed approach surpasses existing models in terms of both prediction accuracy and computational efficiency.

关键词

Keywords

references

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

Modelling and Optimisation of Integrated Energy Supply System for Deep-Sea Offshore Oil and Gas Field Considering Intelligent Scheduling Factors

Neural Network Surrogate for Multi-Criteria Coordinated Model Predictive Control of Vanadium Redox Flow Battery Stations With Bound Tightening

Research on Rural Integrated Energy Systems With Economic–Energy Efficiency Synergistic Optimisation

IEC 62056-Compliant Interoperable Smart Metering and Load Management for Indian Distribution Utilities

Physics-Guided Transformer for Distributed Photovoltaic Power Forecasting Based on Copula Asymmetric Dependence Analysis