A hybrid sparse identification and convolutional neural network framework for renewable energy forecasting

In the field of renewable energy, accurate long-term time series forecasting is crucial for optimizing the operation of power systems and reducing risks. Due to the intermittency of renewable energy sources, traditional data-driven deep learning methods face challenges in capturing long-term depende...

Full description

Saved in:
Bibliographic Details
Main Authors: Junchi He, Tian Tian, Yaqing Wu, Xiaolu Liu, Mengli Wei
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Energy Research
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fenrg.2024.1461410/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850054257476108288
author Junchi He
Junchi He
Tian Tian
Yaqing Wu
Xiaolu Liu
Mengli Wei
author_facet Junchi He
Junchi He
Tian Tian
Yaqing Wu
Xiaolu Liu
Mengli Wei
author_sort Junchi He
collection DOAJ
description In the field of renewable energy, accurate long-term time series forecasting is crucial for optimizing the operation of power systems and reducing risks. Due to the intermittency of renewable energy sources, traditional data-driven deep learning methods face challenges in capturing long-term dependencies. This paper proposes a hybrid model that combines Sparse Identification (SI) with Convolutional Neural Networks (CNN) to enhance the interpretability and generalization of predictions. The SI method is utilized to extract trends, seasonality, and periodicity, while the deep neural network captures complex relationships. Experimental results demonstrate that the model exhibits high accuracy and practicality in forecasting new energy scenario data, contributing to the advancement of time series prediction methodologies.
format Article
id doaj-art-bf658a6574e8495983069baaeaaf2ea5
institution DOAJ
issn 2296-598X
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Energy Research
spelling doaj-art-bf658a6574e8495983069baaeaaf2ea52025-08-20T02:52:19ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2024-12-011210.3389/fenrg.2024.14614101461410A hybrid sparse identification and convolutional neural network framework for renewable energy forecastingJunchi He0Junchi He1Tian Tian2Yaqing Wu3Xiaolu Liu4Mengli Wei5School of Electrical Engineering, China University of Mining and Technology, Xuzhou, ChinaState Grid Lianyungang Power Supply Company, Lianyungang, ChinaState Grid Lianyungang Power Supply Company, Lianyungang, ChinaSchool of Cyber Science and Engineering, Southeast University, Nanjing, ChinaSchool of Automation, Nanjing Institute of Technology, Nanjing, ChinaSchool of Cyber Science and Engineering, Southeast University, Nanjing, ChinaIn the field of renewable energy, accurate long-term time series forecasting is crucial for optimizing the operation of power systems and reducing risks. Due to the intermittency of renewable energy sources, traditional data-driven deep learning methods face challenges in capturing long-term dependencies. This paper proposes a hybrid model that combines Sparse Identification (SI) with Convolutional Neural Networks (CNN) to enhance the interpretability and generalization of predictions. The SI method is utilized to extract trends, seasonality, and periodicity, while the deep neural network captures complex relationships. Experimental results demonstrate that the model exhibits high accuracy and practicality in forecasting new energy scenario data, contributing to the advancement of time series prediction methodologies.https://www.frontiersin.org/articles/10.3389/fenrg.2024.1461410/fulltime series forecastinglong-term predictionsparse identificationconvolutional neural networksrenewable energy
spellingShingle Junchi He
Junchi He
Tian Tian
Yaqing Wu
Xiaolu Liu
Mengli Wei
A hybrid sparse identification and convolutional neural network framework for renewable energy forecasting
Frontiers in Energy Research
time series forecasting
long-term prediction
sparse identification
convolutional neural networks
renewable energy
title A hybrid sparse identification and convolutional neural network framework for renewable energy forecasting
title_full A hybrid sparse identification and convolutional neural network framework for renewable energy forecasting
title_fullStr A hybrid sparse identification and convolutional neural network framework for renewable energy forecasting
title_full_unstemmed A hybrid sparse identification and convolutional neural network framework for renewable energy forecasting
title_short A hybrid sparse identification and convolutional neural network framework for renewable energy forecasting
title_sort hybrid sparse identification and convolutional neural network framework for renewable energy forecasting
topic time series forecasting
long-term prediction
sparse identification
convolutional neural networks
renewable energy
url https://www.frontiersin.org/articles/10.3389/fenrg.2024.1461410/full
work_keys_str_mv AT junchihe ahybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting
AT junchihe ahybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting
AT tiantian ahybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting
AT yaqingwu ahybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting
AT xiaoluliu ahybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting
AT mengliwei ahybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting
AT junchihe hybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting
AT junchihe hybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting
AT tiantian hybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting
AT yaqingwu hybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting
AT xiaoluliu hybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting
AT mengliwei hybridsparseidentificationandconvolutionalneuralnetworkframeworkforrenewableenergyforecasting