Improving the criteria of electricity consumptionforecasting in petrochemical industrial units based ondeep learning

Accurate forecasting of electricity consumption in petrochemical industrial units is essential for optimizing energy management and ensuring operational efficiency. This study presents a novel deep learning framework that integrates advanced feature engineering and Long Short-Term Memory (LSTM) net...

Full description

Saved in:
Bibliographic Details
Main Authors: Ehsan Tavakoli Garmaserh, Mehran Emadi
Format: Article
Language:English
Published: OICC Press 2025-06-01
Series:Majlesi Journal of Electrical Engineering
Subjects:
Online Access:https://oiccpress.com/mjee/article/view/16937
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849721331622346752
author Ehsan Tavakoli Garmaserh
Mehran Emadi
author_facet Ehsan Tavakoli Garmaserh
Mehran Emadi
author_sort Ehsan Tavakoli Garmaserh
collection DOAJ
description Accurate forecasting of electricity consumption in petrochemical industrial units is essential for optimizing energy management and ensuring operational efficiency. This study presents a novel deep learning framework that integrates advanced feature engineering and Long Short-Term Memory (LSTM) networks to address the challenges posed by irregular seasonal trends and dynamic consumption patterns. Key innovations include the use of Fourier Transform-based feature extraction for enhanced data representation and a hybrid genetic-sparse matrix optimization technique for feature selection, ensuring high predictive performance. The proposed method effectively mitigates issues related to data irregularities through preprocessing techniques, resulting in improved accuracy and stability in both univariate and multivariate time series forecasting scenarios. Experimental evaluations using benchmark datasets demonstrate significant improvements, achieving a Root Mean Square Error (RMSE) of 0.0693 and a Mean Absolute Percentage Error (MAPE) reduction of over 15% compared to state-of-the-art methods. These results highlight the robustness and practical applicability of the proposed framework for industrial energy consumption forecasting and sustainable energy management.
format Article
id doaj-art-e4c283160cad4475af782daabd6ef254
institution DOAJ
issn 2345-377X
2345-3796
language English
publishDate 2025-06-01
publisher OICC Press
record_format Article
series Majlesi Journal of Electrical Engineering
spelling doaj-art-e4c283160cad4475af782daabd6ef2542025-08-20T03:11:42ZengOICC PressMajlesi Journal of Electrical Engineering2345-377X2345-37962025-06-01192 (June 2025)10.57647/j.mjee.2025.1902.41Improving the criteria of electricity consumptionforecasting in petrochemical industrial units based ondeep learningEhsan Tavakoli GarmaserhMehran Emadi Accurate forecasting of electricity consumption in petrochemical industrial units is essential for optimizing energy management and ensuring operational efficiency. This study presents a novel deep learning framework that integrates advanced feature engineering and Long Short-Term Memory (LSTM) networks to address the challenges posed by irregular seasonal trends and dynamic consumption patterns. Key innovations include the use of Fourier Transform-based feature extraction for enhanced data representation and a hybrid genetic-sparse matrix optimization technique for feature selection, ensuring high predictive performance. The proposed method effectively mitigates issues related to data irregularities through preprocessing techniques, resulting in improved accuracy and stability in both univariate and multivariate time series forecasting scenarios. Experimental evaluations using benchmark datasets demonstrate significant improvements, achieving a Root Mean Square Error (RMSE) of 0.0693 and a Mean Absolute Percentage Error (MAPE) reduction of over 15% compared to state-of-the-art methods. These results highlight the robustness and practical applicability of the proposed framework for industrial energy consumption forecasting and sustainable energy management. https://oiccpress.com/mjee/article/view/16937Electricity Consumption ForecastingPetrochemical Industrial UnitsDeep LearningLong Short-Term Memory
spellingShingle Ehsan Tavakoli Garmaserh
Mehran Emadi
Improving the criteria of electricity consumptionforecasting in petrochemical industrial units based ondeep learning
Majlesi Journal of Electrical Engineering
Electricity Consumption Forecasting
Petrochemical Industrial Units
Deep Learning
Long Short-Term Memory
title Improving the criteria of electricity consumptionforecasting in petrochemical industrial units based ondeep learning
title_full Improving the criteria of electricity consumptionforecasting in petrochemical industrial units based ondeep learning
title_fullStr Improving the criteria of electricity consumptionforecasting in petrochemical industrial units based ondeep learning
title_full_unstemmed Improving the criteria of electricity consumptionforecasting in petrochemical industrial units based ondeep learning
title_short Improving the criteria of electricity consumptionforecasting in petrochemical industrial units based ondeep learning
title_sort improving the criteria of electricity consumptionforecasting in petrochemical industrial units based ondeep learning
topic Electricity Consumption Forecasting
Petrochemical Industrial Units
Deep Learning
Long Short-Term Memory
url https://oiccpress.com/mjee/article/view/16937
work_keys_str_mv AT ehsantavakoligarmaserh improvingthecriteriaofelectricityconsumptionforecastinginpetrochemicalindustrialunitsbasedondeeplearning
AT mehranemadi improvingthecriteriaofelectricityconsumptionforecastinginpetrochemicalindustrialunitsbasedondeeplearning