Collaborative Forecasting of Multiple Energy Loads in Integrated Energy Systems Based on Feature Extraction and Deep Learning

Accurate load forecasting is crucial for the safe, stable, and economical operation of integrated energy systems. However, directly applying single models to predict coupled cooling, heating, and electric loads under complex influencing factors often yields unsatisfactory results. This paper propose...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhe Wang, Jiali Duan, Fengzhang Luo, Xiaoyu Qiu
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/5/1048
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030377187409920
author Zhe Wang
Jiali Duan
Fengzhang Luo
Xiaoyu Qiu
author_facet Zhe Wang
Jiali Duan
Fengzhang Luo
Xiaoyu Qiu
author_sort Zhe Wang
collection DOAJ
description Accurate load forecasting is crucial for the safe, stable, and economical operation of integrated energy systems. However, directly applying single models to predict coupled cooling, heating, and electric loads under complex influencing factors often yields unsatisfactory results. This paper proposes a collaborative load forecasting method based on feature extraction and deep learning. First, the complete ensemble empirical mode decomposition with adaptive noise algorithm decomposes load data, and a dynamic time warping-based k-medoids clustering algorithm reconstructs subsequences aligned with system load components. Second, a correlation analysis identifies the key influencing factors for model input. Then, a multi-task parallel learning framework combining a regression convolutional neural network and long short-term memory networks is developed to predict reconstructed subsequences. Case studies demonstrate that the proposed model achieves mean absolute percentage errors (MAPE) of 2.24%, 2.75%, and 1.69% for electricity, cooling, and heating loads on summer workdays, with mean accuracy (MA) values of 97.76%, 97.25%, and 98.31%, respectively. For winter workdays, the MAPE values are 2.92%, 1.66%, and 2.87%, with MA values of 97.08%, 98.34%, and 97.13%. Compared to traditional single-task models, the weighted mean accuracy (WMA) improves by 2.01% and 2.33% in summer and winter, respectively, validating its superiority. This method provides a high-precision tool for the planning and operation of integrated energy systems.
format Article
id doaj-art-de7c8cd6235049f39db31c41848ced5f
institution DOAJ
issn 1996-1073
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-de7c8cd6235049f39db31c41848ced5f2025-08-20T02:59:14ZengMDPI AGEnergies1996-10732025-02-01185104810.3390/en18051048Collaborative Forecasting of Multiple Energy Loads in Integrated Energy Systems Based on Feature Extraction and Deep LearningZhe Wang0Jiali Duan1Fengzhang Luo2Xiaoyu Qiu3State Grid Tianjin Electric Power Company, Tianjin 300010, ChinaState Grid Tianjin Electric Power Company, Tianjin 300010, ChinaKey Laboratory of Smart Grid of Ministry of Education, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Smart Grid of Ministry of Education, Tianjin University, Tianjin 300072, ChinaAccurate load forecasting is crucial for the safe, stable, and economical operation of integrated energy systems. However, directly applying single models to predict coupled cooling, heating, and electric loads under complex influencing factors often yields unsatisfactory results. This paper proposes a collaborative load forecasting method based on feature extraction and deep learning. First, the complete ensemble empirical mode decomposition with adaptive noise algorithm decomposes load data, and a dynamic time warping-based k-medoids clustering algorithm reconstructs subsequences aligned with system load components. Second, a correlation analysis identifies the key influencing factors for model input. Then, a multi-task parallel learning framework combining a regression convolutional neural network and long short-term memory networks is developed to predict reconstructed subsequences. Case studies demonstrate that the proposed model achieves mean absolute percentage errors (MAPE) of 2.24%, 2.75%, and 1.69% for electricity, cooling, and heating loads on summer workdays, with mean accuracy (MA) values of 97.76%, 97.25%, and 98.31%, respectively. For winter workdays, the MAPE values are 2.92%, 1.66%, and 2.87%, with MA values of 97.08%, 98.34%, and 97.13%. Compared to traditional single-task models, the weighted mean accuracy (WMA) improves by 2.01% and 2.33% in summer and winter, respectively, validating its superiority. This method provides a high-precision tool for the planning and operation of integrated energy systems.https://www.mdpi.com/1996-1073/18/5/1048integrated energy systemload forecastingempirical mode decompositionk-medoids clusteringmulti-task learning
spellingShingle Zhe Wang
Jiali Duan
Fengzhang Luo
Xiaoyu Qiu
Collaborative Forecasting of Multiple Energy Loads in Integrated Energy Systems Based on Feature Extraction and Deep Learning
Energies
integrated energy system
load forecasting
empirical mode decomposition
k-medoids clustering
multi-task learning
title Collaborative Forecasting of Multiple Energy Loads in Integrated Energy Systems Based on Feature Extraction and Deep Learning
title_full Collaborative Forecasting of Multiple Energy Loads in Integrated Energy Systems Based on Feature Extraction and Deep Learning
title_fullStr Collaborative Forecasting of Multiple Energy Loads in Integrated Energy Systems Based on Feature Extraction and Deep Learning
title_full_unstemmed Collaborative Forecasting of Multiple Energy Loads in Integrated Energy Systems Based on Feature Extraction and Deep Learning
title_short Collaborative Forecasting of Multiple Energy Loads in Integrated Energy Systems Based on Feature Extraction and Deep Learning
title_sort collaborative forecasting of multiple energy loads in integrated energy systems based on feature extraction and deep learning
topic integrated energy system
load forecasting
empirical mode decomposition
k-medoids clustering
multi-task learning
url https://www.mdpi.com/1996-1073/18/5/1048
work_keys_str_mv AT zhewang collaborativeforecastingofmultipleenergyloadsinintegratedenergysystemsbasedonfeatureextractionanddeeplearning
AT jialiduan collaborativeforecastingofmultipleenergyloadsinintegratedenergysystemsbasedonfeatureextractionanddeeplearning
AT fengzhangluo collaborativeforecastingofmultipleenergyloadsinintegratedenergysystemsbasedonfeatureextractionanddeeplearning
AT xiaoyuqiu collaborativeforecastingofmultipleenergyloadsinintegratedenergysystemsbasedonfeatureextractionanddeeplearning