Abstract
Short-term residential electricity load forecasting is the basis of economic dispatch, spinning reserve scheduling, and demand-side management in the operation of grid. Existing deep learning approaches depend on manual hyperparameter selection, introducing researcher bias and limiting reproducibility. In this paper, we propose PSO–LSTM–DNN, an optimisation-driven framework where Particle Swarm Optimisation jointly tunes all hyperparameters of a stacked LSTM–DNN architecture. On the public IHEPC dataset benchmarked with a rolling-origin cross-validation protocol over five non-overlapping seasonal folds and ten repeated runs (50 evaluations per model), the proposed framework yields average RMSE of \(0.0213\pm 0.0018\) kW, MAE of \(0.0147\pm 0.0013\) kW, and \(R^{2}\) of \(0.9997\pm 0.0001\), on the single-household IHEPC benchmark; generalisation to other households, climatic regions, or grid environments has not been validated and requires independent assessment, yielding an 11.6 % reduction in RMSE relative to a DNN–LSTM baseline and 35.5 % relative to the most recent attention-enhanced model on the IHEPC benchmark, under the experimental conditions described herein. Differences are assessed by ANOVA, Wilcoxon signed-rank tests with Holm–Bonferroni correction, and Cohen’s d effect sizes, computed exclusively on models evaluated on identical folds and identical test observations. All results pertain to a single household from the IHEPC benchmark under the protocol described; generalisation across residential users, climatic regions, or utility systems is not established.
Data Availability
The dataset used is publicly available from the UCI Machine Learning Repository (https://doi.org/10.24432/C58K54
References
Morcillo-Jiménez R, Criado J, Cortés A (2024) Deep learning for prediction of energy consumption: an applied use case in an office building. Appl Intell 54(7):5813–5825. https://doi.org/10.1007/s10489-024-05382-7
Hosseini E, Mehdinejad M, Mohammadi-Ivatloo B, Marzband M (2025) Optimized deep neural network architectures for energy consumption and PV production forecasting. Energy Strat Rev 59:101704. https://doi.org/10.1016/j.esr.2025.101704
Al-Ghamdi M, Al-Ghamdi AA-M, Ragab M (2023) A hybrid DNN multilayered LSTM model for energy consumption prediction. Appl Sci 13(20):11408. https://doi.org/10.3390/app132011408
Boroojeni KG, Amini MH, Bahrami S, Iyengar SS, Sarwat AI, Karabasoglu O (2017) A novel multi-time-scale modeling for electric power demand forecasting: from short-term to medium-term horizon. Electr Power Syst Res 142:58–73. https://doi.org/10.1016/j.epsr.2016.08.031
Braun MR, Altan H, Beck SBM (2014) Using regression analysis to predict the future energy consumption of a supermarket in the UK. Appl Energy 130:305–313. https://doi.org/10.1016/j.apenergy.2014.05.062
Fumo N, Rafe Biswas MA (2015) Regression analysis for energy prediction in residential buildings. Renew Sustain Energy Rev 47:332–343. https://doi.org/10.1016/j.rser.2015.03.035
Bikcora C, Verheijen L, Weiland S (2018) Density forecasting of daily electricity demand with ARMA-GARCH, CAViaR, and CARE models. Sustain Energy Grids Netw 13:148–156. https://doi.org/10.1016/j.segan.2017.12.003
Alsharekh MF, Habib S, Dewi DA, Albattah W, Islam M, Albahli S (2022) Improving the efficiency of multistep short-term electricity load forecasting via R-CNN with ML-LSTM. Sensors 22(18):6913. https://doi.org/10.3390/s22186913
Khan ZA, Hussain T, Baik SW (2022) Boosting energy harvesting via deep learning-based renewable power generation prediction. J King Saud Univ Sci 34(3):101815. https://doi.org/10.1016/j.jksus.2021.101815
Kong W, Dong ZY, Hill DJ, Luo F, Xu Y (2019) Short-term residential load forecasting based on an LSTM recurrent neural network. IEEE Trans Smart Grid 10(1):841–851. https://doi.org/10.1109/TSG.2017.2753802
Bouktif S, Fiaz A, Ouni A, Serhani MA (2020) Multi-sequence LSTM-RNN deep learning and metaheuristics for electric load forecasting. Energies 13(2):391. https://doi.org/10.3390/en13020391
Kaur S, Bala A, Parashar A (2026) A hybrid PSO-LSTM-based electricity prediction and optimization technique for home appliances. Sci Technol Energy Transit 81:13
Hyndman RJ, Athanasopoulos G (2021) Forecasting: principles and practice, 3rd edn. OTexts, Melbourne, Australia. https://otexts.com/fpp3/
Bergmeir C, Hyndman RJ, Koo B (2018) A note on the validity of cross-validation for evaluating autoregressive time series prediction. Comput Stat Data Anal 120:70–83. https://doi.org/10.1016/j.csda.2017.11.003
Diebold FX, Mariano RS (1995) Comparing predictive accuracy. J Bus Econ Stat 13(3):253–263. https://doi.org/10.1080/07350015.1995.10524599
Holm S (1979) A simple sequentially rejective multiple test procedure. Scand J Stat 6(2):65–70
Cohen J (1988) Statistical power analysis for the behavioral sciences, 2nd edn. Lawrence Erlbaum Associates, Hillsdale, NJ
Zhan Y, Wang X, Xu Y, Li W (2026) A hybrid TCN-LSTM-attention framework for multi-scenario short-term photovoltaic power forecasting incorporating physics-informed neural network strategy. Energy 139968
Cao G, Wu L (2016) Support vector regression with fruit fly optimization algorithm for seasonal electricity consumption forecasting. Energy 115:734–745. https://doi.org/10.1016/j.energy.2016.09.035
Chen Y, Xu P, Chu Y, Li W, Wu Y, Ni L, Bao Y, Wang K (2017) Short-term electrical load forecasting using the SVR model to calculate the demand response baseline for office buildings. Appl Energy 195:659–670. https://doi.org/10.1016/j.apenergy.2017.03.077
Zhong H, Wang J, Jia H, Mu Y, Lv S (2019) Vector field-based support vector regression for building energy consumption prediction. Appl Energy 242:403–414. https://doi.org/10.1016/j.apenergy.2019.03.078
Li C, Ding Z, Zhao D, Yi J, Zhang G (2018) Building energy consumption prediction: an extreme deep learning approach. Energies 11(6):1525. https://doi.org/10.3390/en11061525
Li S, Wang P, Goel L (2016) A novel wavelet-based ensemble method for short-term load forecasting with hybrid neural networks and feature selection. IEEE Trans Power Syst 31(3):1788–1798. https://doi.org/10.1109/TPWRS.2015.2438322
Shi H, Xu M, Li R (2018) Deep learning for household load forecasting—a novel pooling deep RNN. IEEE Trans Smart Grid 9(5):5271–5280. https://doi.org/10.1109/TSG.2017.2686012
Tsekouras GJ, Hatziargyriou ND, Dialynas EN (2006) An optimized adaptive neural network for annual midterm energy forecasting. IEEE Trans Power Syst 21(1):385–391. https://doi.org/10.1109/TPWRS.2005.860922
Wang Y, Xia Q, Kang C (2011) Secondary forecasting based on deviation analysis for short-term load forecasting. IEEE Trans Power Syst 26(2):500–507. https://doi.org/10.1109/TPWRS.2010.2054172
Tovar M, Robles M, Rashid F (2020) PV power prediction using a CNN-LSTM hybrid neural network model. Energies 13(24):6512. https://doi.org/10.3390/en13246512
Wang S, Wang X, Wang S, Wang D (2019) Bi-directional LSTM with attention mechanism and rolling update for short-term load forecasting. Int J Electr Power Energy Syst 109:470–479. https://doi.org/10.1016/j.ijepes.2019.02.022
Kim T-Y, Cho S-B (2019) Predicting residential energy consumption using CNN-LSTM neural networks. Energy 182:72–81. https://doi.org/10.1016/j.energy.2019.05.230
Ullah FUM, Ullah A, Khan MI, Hussain T, Lee MY, Baik SW (2020) Short-term prediction of residential power energy consumption via CNN and multi-layer BiLSTM. IEEE Access 8:123369–123380. https://doi.org/10.1109/ACCESS.2020.3006763
Khan ZA, Hussain T, Ullah A, Rho S, Lee MY, Baik SW (2020) Electrical energy prediction in residential buildings for short-term horizons using a hybrid deep learning strategy. Appl Sci 10(23):8634. https://doi.org/10.3390/app10238634
Chi D (2022) Research on an electricity consumption forecasting model based on the wavelet transform and a multi-layer LSTM model. Energy Rep 8:220–228. https://doi.org/10.1016/j.egyr.2021.11.119
Khan T, Choi C (2025) Attention-enhanced dual stream network with advanced feature selection for power forecasting. Appl Energy 377:124564. https://doi.org/10.1016/j.apenergy.2024.124564
Mzili T, Mzili I, Riffi ME, Papadopoulos GA (2025) Hybrid grey wolf and genetic algorithm for the flow shop scheduling problem. Int J Int Technol Inf Syst 8(3):666–686
Ramírez-Ochoa D-D, Pérez-Olmedo L-L, Espinal A, Ornelas-Tellez F (2022) PSO, a swarm intelligence-based evolutionary algorithm as a decision-making strategy: a review. Symmetry 14(3):455. https://doi.org/10.3390/sym14030455
Putra Utama AB, Sihombing P, Zamzami EM, Sitompul OS (2022) PSO-based hyperparameter tuning of CNN multivariate time series analysis. J Online Inform 7(2):193–202. https://doi.org/10.15575/join.v7i2.822
Das S, Suganthan PN (2011) Differential evolution: a survey of the state-of-the-art. IEEE Trans Evol Comput 15(1):4–31. https://doi.org/10.1109/TEVC.2010.2059031
Houdaif O, Mzili T, Ezzazi I, Mzili M (2026) Intelligent solar power forecasting using a neuro-evolutionary DE-optimized TCN-LSTM hybrid model. Int J Interact Technol Inf Syst 9(2):830–863
Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30
Hebrail G, Berard A (2023) Individual household electric power consumption dataset. UCI machine learning repository. https://doi.org/10.24432/C58K54
Funding
No funds, grants, or other financial support were received for conducting this study or for preparing this manuscript.
Author information
Authors and Affiliations
Contributions
O.H. contributed to the conceptualisation, methodology, software development, data curation, formal analysis, investigation, validation, visualisation, writing of the original draft, review and editing, and project administration. M.T. contributed to the conceptualisation, methodology, supervision, validation, formal analysis, writing—review and editing, and overall scientific guidance throughout all stages of the research. M.M. contributed to the statistical analysis, validation procedures, interpretation of results, and manuscript review, and I.E. contributed to the supervision, resources, manuscript review and editing, and final validation of the study. All authors reviewed and approved the final version of the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflict of interest to declare that are relevant to the content of this article.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Houdaif, O., Mzili, M., Mzili, T. et al. Short-term residential load forecasting via PSO-optimised hybrid LSTM–DNN with automated hyperparameter tuning. J Supercomput 82, 728 (2026). https://doi.org/10.1007/s11227-026-08859-x
Received:
Accepted:
Published:
Version of record:
DOI: https://doi.org/10.1007/s11227-026-08859-x