Optimizing load demand forecasting in educational buildings using quantum-inspired particle swarm optimization (QPSO) with recurrent neural networks (RNNs):a seasonal approach

Abstract This study uses Quantum Particle Swarm Optimization (QPSO) optimized Recurrent Neural Networks (RNN), standard RNN, and autoregressive integrated moving average (ARIMA) models to anticipate educational building power demand accurately. Energy efficiency, cost reduction, and resource allocat...

Full description

Saved in:
Bibliographic Details
Main Authors: Sunawar Khan, Tehseen Mazhar, Tariq Shahzad, Tariq Ali, Muhammad Ayaz, Yazeed Yasin Ghadi, EL-Hadi M. Aggoune, Habib Hamam
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-04301-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434218725113856
author Sunawar Khan
Tehseen Mazhar
Tariq Shahzad
Tariq Ali
Muhammad Ayaz
Yazeed Yasin Ghadi
EL-Hadi M. Aggoune
Habib Hamam
author_facet Sunawar Khan
Tehseen Mazhar
Tariq Shahzad
Tariq Ali
Muhammad Ayaz
Yazeed Yasin Ghadi
EL-Hadi M. Aggoune
Habib Hamam
author_sort Sunawar Khan
collection DOAJ
description Abstract This study uses Quantum Particle Swarm Optimization (QPSO) optimized Recurrent Neural Networks (RNN), standard RNN, and autoregressive integrated moving average (ARIMA) models to anticipate educational building power demand accurately. Energy efficiency, cost reduction, and resource allocation depend on accurate load forecasts. The study evaluates model performance using year-long load data from seasonal, daily, and hourly fluctuations. Performance indicators, including Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), were used to assess the models. The QPSO-optimized RNN outperformed traditional RNN and ARIMA models with the lowest MAE of 15.2, MSE of 520.15, and RMSE of 22.8. Comparative investigation shows the QPSO-RNN’s capacity to capture complicated load data patterns, especially during peak demand. This study shows that hybrid optimization can improve forecasting accuracy, making it a powerful tool for energy management in dynamic contexts.
format Article
id doaj-art-cb8897c8fd9f4468a475bd48020273fc
institution Kabale University
issn 2045-2322
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-cb8897c8fd9f4468a475bd48020273fc2025-08-20T03:26:44ZengNature PortfolioScientific Reports2045-23222025-06-0115111910.1038/s41598-025-04301-zOptimizing load demand forecasting in educational buildings using quantum-inspired particle swarm optimization (QPSO) with recurrent neural networks (RNNs):a seasonal approachSunawar Khan0Tehseen Mazhar1Tariq Shahzad2Tariq Ali3Muhammad Ayaz4Yazeed Yasin Ghadi5EL-Hadi M. Aggoune6Habib Hamam7School of Computer Science, National College of Business Administration and Economics School of Computer Science, National College of Business Administration and Economics Department of Computer Engineering, COMSATS University IslamabadArtificial Intelligence and Sensing Technologies (AIST) Research Centre, University of TabukArtificial Intelligence and Sensing Technologies (AIST) Research Centre, University of TabukDepartment of Computer Science and Software Engineering, Al Ain UniversityArtificial Intelligence and Sensing Technologies (AIST) Research Centre, University of TabukSchool of Electrical Engineering, University of JohannesburgAbstract This study uses Quantum Particle Swarm Optimization (QPSO) optimized Recurrent Neural Networks (RNN), standard RNN, and autoregressive integrated moving average (ARIMA) models to anticipate educational building power demand accurately. Energy efficiency, cost reduction, and resource allocation depend on accurate load forecasts. The study evaluates model performance using year-long load data from seasonal, daily, and hourly fluctuations. Performance indicators, including Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), were used to assess the models. The QPSO-optimized RNN outperformed traditional RNN and ARIMA models with the lowest MAE of 15.2, MSE of 520.15, and RMSE of 22.8. Comparative investigation shows the QPSO-RNN’s capacity to capture complicated load data patterns, especially during peak demand. This study shows that hybrid optimization can improve forecasting accuracy, making it a powerful tool for energy management in dynamic contexts.https://doi.org/10.1038/s41598-025-04301-zLoad demand forecastingTime series forecastingSeasonal adjustmentEducational buildingsEnergy management
spellingShingle Sunawar Khan
Tehseen Mazhar
Tariq Shahzad
Tariq Ali
Muhammad Ayaz
Yazeed Yasin Ghadi
EL-Hadi M. Aggoune
Habib Hamam
Optimizing load demand forecasting in educational buildings using quantum-inspired particle swarm optimization (QPSO) with recurrent neural networks (RNNs):a seasonal approach
Scientific Reports
Load demand forecasting
Time series forecasting
Seasonal adjustment
Educational buildings
Energy management
title Optimizing load demand forecasting in educational buildings using quantum-inspired particle swarm optimization (QPSO) with recurrent neural networks (RNNs):a seasonal approach
title_full Optimizing load demand forecasting in educational buildings using quantum-inspired particle swarm optimization (QPSO) with recurrent neural networks (RNNs):a seasonal approach
title_fullStr Optimizing load demand forecasting in educational buildings using quantum-inspired particle swarm optimization (QPSO) with recurrent neural networks (RNNs):a seasonal approach
title_full_unstemmed Optimizing load demand forecasting in educational buildings using quantum-inspired particle swarm optimization (QPSO) with recurrent neural networks (RNNs):a seasonal approach
title_short Optimizing load demand forecasting in educational buildings using quantum-inspired particle swarm optimization (QPSO) with recurrent neural networks (RNNs):a seasonal approach
title_sort optimizing load demand forecasting in educational buildings using quantum inspired particle swarm optimization qpso with recurrent neural networks rnns a seasonal approach
topic Load demand forecasting
Time series forecasting
Seasonal adjustment
Educational buildings
Energy management
url https://doi.org/10.1038/s41598-025-04301-z
work_keys_str_mv AT sunawarkhan optimizingloaddemandforecastingineducationalbuildingsusingquantuminspiredparticleswarmoptimizationqpsowithrecurrentneuralnetworksrnnsaseasonalapproach
AT tehseenmazhar optimizingloaddemandforecastingineducationalbuildingsusingquantuminspiredparticleswarmoptimizationqpsowithrecurrentneuralnetworksrnnsaseasonalapproach
AT tariqshahzad optimizingloaddemandforecastingineducationalbuildingsusingquantuminspiredparticleswarmoptimizationqpsowithrecurrentneuralnetworksrnnsaseasonalapproach
AT tariqali optimizingloaddemandforecastingineducationalbuildingsusingquantuminspiredparticleswarmoptimizationqpsowithrecurrentneuralnetworksrnnsaseasonalapproach
AT muhammadayaz optimizingloaddemandforecastingineducationalbuildingsusingquantuminspiredparticleswarmoptimizationqpsowithrecurrentneuralnetworksrnnsaseasonalapproach
AT yazeedyasinghadi optimizingloaddemandforecastingineducationalbuildingsusingquantuminspiredparticleswarmoptimizationqpsowithrecurrentneuralnetworksrnnsaseasonalapproach
AT elhadimaggoune optimizingloaddemandforecastingineducationalbuildingsusingquantuminspiredparticleswarmoptimizationqpsowithrecurrentneuralnetworksrnnsaseasonalapproach
AT habibhamam optimizingloaddemandforecastingineducationalbuildingsusingquantuminspiredparticleswarmoptimizationqpsowithrecurrentneuralnetworksrnnsaseasonalapproach