Lightweight Models for Per-PC Energy Consumption Forecasting: Comparative Study with ML and DL Approaches

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 17 | 01 | Page :
    By

    Akanksha Patel,

  • Banafsha Patel,

  • Shweta Waghmare,

  1. Research Scholar, MCA Thakur Institute of Management Studies, Career Development & Research (TIMSCDR) Mumba, Maharashtra, India
  2. Research Scholar, MCA Thakur Institute of Management Studies, Career Development & Research (TIMSCDR) Mumba, Maharashtra, India
  3. Assistant Professor, MCA Thakur Institute of Management Studies, Career Development & Research (TIMSCDR) Mumba, Maharashtra, India

Abstract

We have collected primary data from automated logging of parameters like CPU utilization, estimated power, active or idle state, user logging activity, and the type of day. Additionally, survey data showed user awareness, energy-saving behaviour, and PC usage patterns. The data is pre-processed and merged by applying processes such as data cleaning, normalization, and feature extraction, i.e., determining the peak active timings and downtime. Developed lightweight prediction models based on Support Vector Regression (SVR) measuring them in terms of performance metrics like MAE, RMSE and R2. The goal of this research is to show that light models are able to predict accurately with low resource requirements, which becomes appropriate for small environments such as labs or other individual cases. The results will help to contribute towards future research in sustainable computing by contrasting large-scale forecasting studies with small-scale personal computing scenarios.

Keywords: Energy consumption forecasting, Personal computer, Lightweight machine learning, Support Vector Regression, Random Forest, LightGBM,LSTM,GRU, Model efficiency, Small-scale computing environments.

How to cite this article:
Akanksha Patel, Banafsha Patel, Shweta Waghmare. Lightweight Models for Per-PC Energy Consumption Forecasting: Comparative Study with ML and DL Approaches. Journal of Alternate Energy Sources & Technologies. 2026; 17(01):-.
How to cite this URL:
Akanksha Patel, Banafsha Patel, Shweta Waghmare. Lightweight Models for Per-PC Energy Consumption Forecasting: Comparative Study with ML and DL Approaches. Journal of Alternate Energy Sources & Technologies. 2026; 17(01):-. Available from: https://journals.stmjournals.com/joaest/article=2026/view=241088


References

  1. Alsamraee A, Khanna S. High-resolution energy consumption forecasting of a university campus power plant based on advanced machine learning techniques. Energy Strategy Rev. 2025;52:101235.
  2. Anonto HZ, Hossain MI, Momo M, Shufian A, Roy AK, Ashraf MS. Optimizing energy consumption prediction using hybrid LightGBM and XGBoost: integrating heterogeneous data for smart grid management. In: Proc IEEE Region 10 Symp (TENSYMP); 2025. p. 895–900.
  3. Dai Z, Huang W. Improving energy management practices through accurate building energy consumption prediction: analyzing the performance of LightGBM, RF, and XGBoost models with advanced optimization strategies. Electr Eng. 2025.
  4. Chen G, et al. A systematic review of building energy consumption prediction strategies. Appl Sci. 2025;15(6).
  5. Bashynska I, Khaustova Y. Using machine learning algorithms to analyze energy consumption data and optimize management processes at smart enterprises. Front Manuf Technol. 2025:125–141.
  6. Alizadegan H, Malki BR. Comparative study of long short-term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction. Energy Explor Exploit. 2025.
  7. Abdulameer YH, Ibrahim AA. Forecasting of electrical energy consumption using hybrid models of GRU, CNN, LSTM, and ML regressors. J Wirel Mob Netw Ubiquitous Comput Appl. 2025.
  8. Wang Y, et al. A lightweight method of integrated local load forecasting. Sci Rep. 2024.
  9. Munir S, Pradhan MR, Abbas S, Khan MA. Energy consumption prediction based on LightGBM empowered with explainable artificial intelligence. IEEE Access. 2024;12:115203–115214.
  10. Alba EL, Oliveira GA, Ribeiro MHDM, Rodrigues ÉO. Electricity consumption forecasting: an approach using cooperative ensemble learning with SHapley additive exPlanations. Forecasting. 2024;6(1):1–15.
  11. Shin J, Moon H, Chun CJ, Sim T, Kim E, Lee S. Enhanced data processing and machine learning techniques for energy consumption forecasting. Electronics. 2024;13(2):345.
  12. Cai W, Wen X, Li C, Shao J, Xu J. Predicting the energy consumption in buildings using the optimized support vector regression model. Energy. 2023;278:126059.
  13. Faiq M, Tan KG, Liew CP, Hossain F, Tso CP, Lim LL, et al. Prediction of energy consumption in campus buildings using long short-term memory. Alex Eng J. 2023;62:123–134.
  14. Altayeb M, Arabiat A. A sustainable system for predicting appliance energy consumption based on machine learning. J Environ Manage. 2025;362:122094.
  15. Slowik M, Urban W. Machine learning short-term energy consumption forecasting for microgrids in a manufacturing plant. Energies. 2022;15(9):3382.
  16. Li Y, Tong Z, Tong S, Westerdahl D. A data-driven interval forecasting model for building energy prediction using attention-based LSTM and fuzzy information granulation. Sustain Cities Soc. 2022;80:103791.
  17. Olu-Ajayi R, Alaka H, Sulaimon I, Sunmola F, Ajayi S. Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques. J Build Eng. 2022;52:104438.
  18. Ngo NT, Pham AD, Truong TTH, Truong NS, Huynh NT, Pham TM. An ensemble machine learning model for enhancing the prediction accuracy of energy consumption in buildings. Energy Build. 2022.
  19. Wang H, Li H, Gao S, Zhou L, Lao Z. Multigranularity building energy consumption prediction method based on convolutional recurrent neural network. J Electr Comput Eng. 2022;2022:8524034.
  20. Madhukumar M, Sebastian A, Liang X, Jamil M, Shabbir MNSK. Regression model-based short-term load forecasting for university campus load. In: Proc IEEE Int Conf Power Electron Smart Grid Renew Energy (PESGRE); 2022. p. 1–6.
  21. Tu M, Mallik A, et al. Unveiling energy efficiency in deep learning: measurement, prediction and scoring across edge devices. arXiv. 2023.
  22. Amasyali K, El-Gohary N. A review of data-driven building energy consumption prediction studies. Renew Sustain Energy Rev. 2018;81:1192–1205.
  23. Candanedo LM, Feldheim V, Deramaix D. Data driven prediction models of energy use of appliances in a low-energy house. Energy Build. 2017;140:81–97.
  24. Runge J. A review of deep learning techniques for forecasting energy use in buildings. Energies. 2021;14(3):608.
Ahead of Print Subscription Review Article
Volume 17
01
Received 09/04/2026
Accepted 27/04/2026
Published 27/04/2026
Publication Time 18 Days
1

Login


My IP

PlumX Metrics