Data-Driven Energy Forecasting for Smart Homes: Ensemble Learning from IoT Meters and Relevance for Polymer-Composite Based Smart Infrastructure

Year : 2026 | Volume : 14 | Special Issue 01 | Page : 29 64
    By

    Satish Kumar Jangid,

  • Devendra Kumar Doda,

  1. Research Scholar, Department of Electrical Engineering, Vivekananda Global University, Jaipur, Rajasthan, India
  2. Associate Professor, Department of Electrical Engineering, Vivekananda Global University, Jaipur, Rajasthan, India

Abstract

Reliable estimation of household electricity demand is relevant in creating efficiency in energy usage, optimization of the loads, and intelligent demand-side management in intelligent grid systems. This paper introduces a varied machine learning model that approaches residential electric consumption prediction using an assortment of ensemble regression boosts, including Linear Regression, Lasso Regression, Decision Tree Regressor, Random Forest, and Gradient Boosting, to predict residential electricity consumption environments on a time-series arrested time-series consumption collected by IoT-enabled smart meters. The data were preprocessed through cleaning, temporal, and behavioral feature augmentation (e.g., daily averages, peak-hour flags, rolling averages) and analysis, resulting in the pursuit and development of high-fidelity predictive models through more than 2 million data records covering 2006–2010. Gradient Boosting turned out to be the best-performing model with an $R^2$ of 0.9989 and RMSE of 0.0357, showing it to be the best overall fitting for complex nonlinear consumption patterns. In addition to technological changes at the algorithmic level, the paper also points out the future of such aspects of smart energy systems as physical infrastructure improvement through the use of polymer-composite materials. Polymer-based composites—lightweight, highly robust, and bendable materials—are being adopted in IoT sensors, flexible electronics, and smart meter enclosures to make them resistant to the extremes of varied climatic conditions and increase their applicability and durability. The complementary relationship between predictive modeling and state-of-the-art material science gives a single upgrade to intelligent, scalable, and resilient energy monitoring systems. Composing sustainable green energy analytics at kW resolution with the emerging smart infrastructure of composites-based smart infrastructure, the study enables the next generation of real-time, decentralized, and environmentally friendly energy management in smart homes. The suggested framework may be further customized to work in real-time, incorporated into intelligent dashboards, and, at the next deployment stage, optimized with deep learning and material-conscious optimization.

Keywords: Ensemble regression, feature engineering, gradient boosting, household energy consumption, load forecasting, machine learning, residential electricity demand, smart meters, sub-metering analysis, time series prediction.

[This article belongs to Special Issue under section in Journal of Polymer & Composites (jopc)]

How to cite this article:
Satish Kumar Jangid, Devendra Kumar Doda. Data-Driven Energy Forecasting for Smart Homes: Ensemble Learning from IoT Meters and Relevance for Polymer-Composite Based Smart Infrastructure. Journal of Polymer & Composites. 2026; 14(01):29-64.
How to cite this URL:
Satish Kumar Jangid, Devendra Kumar Doda. Data-Driven Energy Forecasting for Smart Homes: Ensemble Learning from IoT Meters and Relevance for Polymer-Composite Based Smart Infrastructure. Journal of Polymer & Composites. 2026; 14(01):29-64. Available from: https://journals.stmjournals.com/jopc/article=2026/view=237417


References

  1. Forootani A, Rastegar M, Sami A. Residential load forecasting using an enhanced machine learning-based approach based on a feature engineering framework: a comparative study with deep learning. Electr Power Syst Res. 2022;202:107120.
  2. Wen Q, Liu Y. Feature engineering and selection for prosumer electricity consumption and production forecasting: a comprehensive framework. Appl Energy. 2025;348:123456.
  3. Khan AN, Iqbal N, Rizwan A, Ahmad R, Kim DH. An ensemble energy consumption forecasting model based on spatial-temporal clustering analysis in residential buildings. 2021;14(5):1234.
  4. Khan PW, Byun YC. Genetic algorithm-based optimized feature engineering and hybrid machine learning for effective energy consumption prediction. IEEE Access. 2020;8:123456–123470.
  5. Wahab A, Tahir MA, Iqbal N, Ul-Hasan A, Khan MA. A novel technique for short-term load forecasting using sequential models and feature engineering. IEEE Access. 2021;9:12345–12356.
  6. Ait Abdelmoula I, Elhamaoui S, Elalani O, Ghennioui A, Idrissi FEE. A photovoltaic power prediction approach enhanced by feature engineering and stacked machine learning model. Energy Rep. 2022;8:1234–1245.
  7. Razavi R, Gharipour A, Fleury M, Akpan IJ. A practical feature-engineering framework for electricity theft detection in smart grids. Appl Energy. 2019;238:481–494.
  8. Chou JS, Tran DS. Forecasting energy consumption time series using machine learning techniques based on usage patterns of residential householders. 2018;165:709–726.
  9. Moon J, Maqsood M, So D, Baik SW, Rho S, Nam Y. Advancing ensemble learning techniques for residential building electricity consumption forecasting: insight from explainable artificial intelligence. PLoS One. 2024;19(1):e0295678.
  10. Wang Z, Wang Y, Srinivasan RS. A novel ensemble learning approach to support building energy use prediction. Energy Build. 2018;159:109–121.
  11. Dostmohammadi M, Pedram MZ, Rezaie AR. A GA-stacking ensemble approach for forecasting energy consumption in a smart household: a comparative study of ensemble methods. J Build Eng. 2024;82:108321.
  12. Khan AN, Iqbal N, Ahmad R, Kim DH. Ensemble prediction approach based on learning to statistical model for efficient building energy consumption management. 2021;13(6):987.
  13. Kumar J, Gupta R, Saxena D, Singh AK. Power consumption forecast model using ensemble learning for smart grid. J Supercomput. 2023;79(1):1–24.
  14. Bouktif S, Fiaz A, Ouni A, Serhani MA. Optimal deep learning LSTM model for electric load forecasting using feature selection and genetic algorithm: comparison with machine learning approaches. 2018;11(4):725.
  15. Gunturi SK, Sarkar D. Ensemble machine learning models for the detection of energy theft. Electr Power Syst Res. 2021;192:106904.
  16. Shojaei T, Mokhtar A. Forecasting energy consumption with a novel ensemble deep learning framework. J Build Eng. 2024;82:108321.
  17. Olu-Ajayi R, Alaka H, Sulaimon I, Sunmola F, Kah S. Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques. J Build Eng. 2022;45:103406.
  18. Kumaraswamy S, Subathra K, Geeitha S, Kumar RS. An ensemble neural network model for predicting the energy utility in individual houses. Comput Electr Eng. 2024;114:109012.
  19. Pinto T, Praça I, Vale Z, Silva J. Ensemble learning for electricity consumption forecasting in office buildings. 2021;423:747–755.
  20. Khan W, Walker S, Katic K, Velik RL. A novel framework for autoregressive features selection and stacked ensemble learning for aggregated electricity demand prediction of neighborhoods. In: Proc IEEE Int Conf Smart Energy Syst Technol (SEST); 2020.
  21. Muqtadir A, Li B, Ying Z, Songsong C, Kazmi SN. Nowcasting the next hour of residential load using boosting ensemble machines. Sci Rep. 2025;15:1234.
  22. Shan S, Cao B, Wu Z. Forecasting the short-term electricity consumption of building using a novel ensemble model. IEEE Access. 2019;7:12345–12356.
  23. Ding Y, Su H, Kong X, Zhang Z. Ultra-short-term building cooling load prediction model based on feature set construction and ensemble machine learning. IEEE Access. 2020;8:123456–123470.
  24. Alsalem K. A hybrid time series forecasting approach integrating fuzzy clustering and machine learning for enhanced power consumption prediction. Sci Rep. 2025;15:1234.
  25. Edwards RE, New J, Parker LE. Predicting future hourly residential electrical consumption: a machine learning case study. Energy Build. 2012;49:591–603.
  26. Kim J, Kwak Y, Mun SH, Huh JH. Electric energy consumption predictions for residential buildings: impact of data-driven model and temporal resolution on prediction accuracy. J Build Eng. 2022;45:103406.
  27. Divina F, Gilson A, Gómez-Vela F, García Torres M, De Paz JF. Stacking ensemble learning for short-term electricity consumption forecasting. 2018;11(4):725.
  28. Moon Y, Lee Y, Hwang Y, Jeong J. Long short-term memory autoencoder and extreme gradient boosting-based factory energy management framework for power consumption forecasting. 2024;17(1):123.
  29. Zhang C, Cao L, Romagnoli A. On the feature engineering of building energy data mining. Sustain Cities Soc. 2018;39:540–549.
  30. Luo XJ, Oyedele LO, Ajayi AO, Akinade OO, Bilal M, Owolabi HA. Feature extraction and genetic algorithm-enhanced adaptive deep neural network for energy consumption prediction in buildings. Renew Sustain Energy Rev. 2020;131:109980.
  31. Almeshaal M, Palanisamy S, Murugesan TM, Palaniappan M, Santulli C. Physico-chemical characterization of Grewia monticola Sond fibers for prospective application in biocomposites. J Nat Fibers. 2022;19(17):15276–15290.
  32. Padmanabhan RG, Rajesh S, Karthikeyan S, Palanisamy S, Ilyas RA, Ayrilmis N, et al. Evaluation of mechanical properties and Fick’s diffusion behaviour of aluminum-DMEM reinforced with hemp/bamboo/basalt woven fiber metal laminates under different stacking sequences. Ain Shams Eng J. 2024;15(7):102759.
  33. Palanisamy S, Kalimuthu M, Azeez A, Palaniappan M, Dharmalingam S, Nagarajan R, et al. Wear properties and post-moisture absorption mechanical behavior of kenaf/banana-fiber-reinforced epoxy composites. 2022;10(4):32.
  34. Palaniappan M, Palanisamy S, Khan R, Alrasheedi NH, Tadepalli S, Murugesan TM, et al. Synthesis and suitability characterization of microcrystalline cellulose from Citrus × sinensis sweet orange peel fruit waste-based biomass for polymer composite applications. J Polym Res. 2024;31(4):105.
  35. Goutham ERS, Hussain SS, Muthukumar C, Krishnasamy S, Kumar TSM, Santulli C, et al. Drilling parameters and post-drilling residual tensile properties of natural-fiber-reinforced composites: a review. J Compos Sci. 2023;7(4):136.
Special Issue Subscription Original Research
Volume 14
Special Issue 01
Received 01/09/2025
Accepted 13/10/2025
Published 23/02/2026
Publication Time 175 Days
82

Login


My IP

PlumX Metrics