Smart grid stability prediction using Adaptive Aquila Optimizer and ensemble stacked BiLSTM

Background: Smart grids, characterized by their ability to integrate renewable energy sources and manage the dynamic balance between supply and demand, require sophisticated prediction models to maintain stability. Traditional machine learning (ML) models often fall short in predicting the highly va...

Full description

Saved in:
Bibliographic Details
Main Authors: Safwan Mahmood Al-Selwi, Mohd Fadzil Hassan, Said Jadid Abdulkadir, Mohammed Gamal Ragab, Alawi Alqushaibi, Ebrahim Hamid Sumiea
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123024015159
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850250207858524160
author Safwan Mahmood Al-Selwi
Mohd Fadzil Hassan
Said Jadid Abdulkadir
Mohammed Gamal Ragab
Alawi Alqushaibi
Ebrahim Hamid Sumiea
author_facet Safwan Mahmood Al-Selwi
Mohd Fadzil Hassan
Said Jadid Abdulkadir
Mohammed Gamal Ragab
Alawi Alqushaibi
Ebrahim Hamid Sumiea
author_sort Safwan Mahmood Al-Selwi
collection DOAJ
description Background: Smart grids, characterized by their ability to integrate renewable energy sources and manage the dynamic balance between supply and demand, require sophisticated prediction models to maintain stability. Traditional machine learning (ML) models often fall short in predicting the highly variable nature of smart grid operations. Methods: This study introduces an ensemble stacked bidirectional Long Short-Term Memory model enhanced by a proposed Adaptive Aquila Optimizer (AAO). The AAO uses a Sigmoid Factor to balance exploration and exploitation, adapting the transition from broad searches to focused ones based on iteration progress. It is utilized for feature selection by identifying and excluding irrelevant and redundant features and methodically evaluates seven key hyperparameters to fine-tune the model's performance. Additionally, a weighted voting mechanism is employed to aggregate predictions in the ensemble model. Results: Multiple rounds of empirical experiments using different sets of optimizers and configurations, supported by the visualization capabilities of TensorBoard, demonstrate significant improvements in the performance of the AAO-BiLSTM model. The results show profound potential with accuracy, precision, recall, and F1-score rates of 99.55%, surpassing both traditional ML algorithms and state-of-the-art approaches.
format Article
id doaj-art-e3ff781fc5014e629b1de4448b0c3c02
institution OA Journals
issn 2590-1230
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-e3ff781fc5014e629b1de4448b0c3c022025-08-20T01:58:16ZengElsevierResults in Engineering2590-12302024-12-012410326110.1016/j.rineng.2024.103261Smart grid stability prediction using Adaptive Aquila Optimizer and ensemble stacked BiLSTMSafwan Mahmood Al-Selwi0Mohd Fadzil Hassan1Said Jadid Abdulkadir2Mohammed Gamal Ragab3Alawi Alqushaibi4Ebrahim Hamid Sumiea5Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, Malaysia; Center for Research in Data Science (CeRDaS), Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, Malaysia; Corresponding author at: Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, Malaysia.Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, Malaysia; Center for Research in Data Science (CeRDaS), Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, MalaysiaDepartment of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, Malaysia; Center for Research in Data Science (CeRDaS), Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, MalaysiaDepartment of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, Malaysia; Center for Research in Data Science (CeRDaS), Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, MalaysiaDepartment of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, Malaysia; Center for Research in Data Science (CeRDaS), Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, MalaysiaDepartment of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar, 32610, Perak, MalaysiaBackground: Smart grids, characterized by their ability to integrate renewable energy sources and manage the dynamic balance between supply and demand, require sophisticated prediction models to maintain stability. Traditional machine learning (ML) models often fall short in predicting the highly variable nature of smart grid operations. Methods: This study introduces an ensemble stacked bidirectional Long Short-Term Memory model enhanced by a proposed Adaptive Aquila Optimizer (AAO). The AAO uses a Sigmoid Factor to balance exploration and exploitation, adapting the transition from broad searches to focused ones based on iteration progress. It is utilized for feature selection by identifying and excluding irrelevant and redundant features and methodically evaluates seven key hyperparameters to fine-tune the model's performance. Additionally, a weighted voting mechanism is employed to aggregate predictions in the ensemble model. Results: Multiple rounds of empirical experiments using different sets of optimizers and configurations, supported by the visualization capabilities of TensorBoard, demonstrate significant improvements in the performance of the AAO-BiLSTM model. The results show profound potential with accuracy, precision, recall, and F1-score rates of 99.55%, surpassing both traditional ML algorithms and state-of-the-art approaches.http://www.sciencedirect.com/science/article/pii/S2590123024015159Aquila optimizerDeep learningFeature selectionHyperparameter tuningLSTMSmart grid
spellingShingle Safwan Mahmood Al-Selwi
Mohd Fadzil Hassan
Said Jadid Abdulkadir
Mohammed Gamal Ragab
Alawi Alqushaibi
Ebrahim Hamid Sumiea
Smart grid stability prediction using Adaptive Aquila Optimizer and ensemble stacked BiLSTM
Results in Engineering
Aquila optimizer
Deep learning
Feature selection
Hyperparameter tuning
LSTM
Smart grid
title Smart grid stability prediction using Adaptive Aquila Optimizer and ensemble stacked BiLSTM
title_full Smart grid stability prediction using Adaptive Aquila Optimizer and ensemble stacked BiLSTM
title_fullStr Smart grid stability prediction using Adaptive Aquila Optimizer and ensemble stacked BiLSTM
title_full_unstemmed Smart grid stability prediction using Adaptive Aquila Optimizer and ensemble stacked BiLSTM
title_short Smart grid stability prediction using Adaptive Aquila Optimizer and ensemble stacked BiLSTM
title_sort smart grid stability prediction using adaptive aquila optimizer and ensemble stacked bilstm
topic Aquila optimizer
Deep learning
Feature selection
Hyperparameter tuning
LSTM
Smart grid
url http://www.sciencedirect.com/science/article/pii/S2590123024015159
work_keys_str_mv AT safwanmahmoodalselwi smartgridstabilitypredictionusingadaptiveaquilaoptimizerandensemblestackedbilstm
AT mohdfadzilhassan smartgridstabilitypredictionusingadaptiveaquilaoptimizerandensemblestackedbilstm
AT saidjadidabdulkadir smartgridstabilitypredictionusingadaptiveaquilaoptimizerandensemblestackedbilstm
AT mohammedgamalragab smartgridstabilitypredictionusingadaptiveaquilaoptimizerandensemblestackedbilstm
AT alawialqushaibi smartgridstabilitypredictionusingadaptiveaquilaoptimizerandensemblestackedbilstm
AT ebrahimhamidsumiea smartgridstabilitypredictionusingadaptiveaquilaoptimizerandensemblestackedbilstm