Issue

Vol. 11, No. 3, August 2026 (Article in Progress)

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Federated Ensemble Learning with SHAP–LIME Interpretability for Smart Home Energy Prediction

https://doi.org/10.22219/kinetik.v11i3.2665
Rahma Puspitasari
Universitas Negeri Malang
Siti Sendari
Universitas Negeri Malang
Muhammad Arif Hermawan
Universitas Negeri Malang
Joshua Andrian
Universitas Negeri Malang
Ira Kumala Sari
Universitas Negeri Malang

Corresponding Author(s) : Rahma Puspitasari

rahma.puspitasari.2505348@students.um.ac.id

Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, Vol. 11, No. 3, August 2026 (Article in Progress)

Abstract

The increased adoption of IoT-based Smart Home systems in Indonesia has resulted in a growing volume of device-level energy data, opening up opportunities for the development of predictive models to support efficient household electricity consumption. However, challenges related to accuracy, interpretability, and data privacy remain a major concern, especially when data is distributed across multiple devices. This study evaluates the performance of four tree-based ensemble models, namely Random Forest, Gradient Boosting, XGBoost, and LightGBM, in centralized learning and federated learning scenarios using the Indonesia Smart Home Dataset. After undergoing feature preprocessing and refinement, including the removal of Sofa Pressure and Bed Pressure due to high noise, each model was trained and evaluated using MAE, MSE, and RMSE metrics. Federated learning was implemented through the Federated Averaging (FedAvg) algorithm to maintain data privacy without the need to transfer raw data between devices. The results show that LightGBM consistently provides the best performance in both scenarios and demonstrates resilience to data fragmentation and heterogeneity. Although there was a slight increase in error in federated learning, the error values remained within an acceptable range. SHAP and LIME analyses revealed that high-power devices such as air conditioners, water pumps, rice cookers, lights, and refrigerators had the greatest contribution.

Keywords

Smart Home Energy Prediction Federated Learning Ensemble Models SHAP–LIME Interpretability IoT Energy Data
Puspitasari, R., Sendari, S. ., Hermawan, M. A., Andrian, J. ., & Sari, I. K. (2026). Federated Ensemble Learning with SHAP–LIME Interpretability for Smart Home Energy Prediction. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, 11(3). https://doi.org/10.22219/kinetik.v11i3.2665
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
References
  1. D. I. Quintana and J. M. Cansino, “Residential Energy Consumption-A Computational Bibliometric Analysis,” Buildings, vol. 13, no. 6. p. 1525, 2023. doi: 10.3390/buildings13061525.
  2. T. Wang, Q. Zhao, W. Gao, and X. He, “Research on energy consumption in household sector : a comprehensive review based on bibliometric analysis,” no. January, pp. 1–22, 2024, doi: 10.3389/fenrg.2023.1209290.
  3. N. A. Pambudi et al., “Renewable Energy in Indonesia: Current Status, Potential, and Future Development,” Sustainability, vol. 15, no. 3. p. 2342, 2023. doi: 10.3390/su15032342.
  4. I. Fitriana, J. Santosa, A. Sugiyono, and I. Rahardjo, The role of energy conservation in the household sector to achieve net zero emission (NZE) conditions in Indonesia by using optimization energy model. 2024. doi: 10.1063/5.0206660.
  5. D. Novianto, M. Koerniawan, M. Munawir, and D. Sekartaji, “Impact of lifestyle changes on home energy consumption during pandemic COVID-19 in Indonesia,” Sustain. Cities Soc., vol. 83, p. 103930, May 2022, doi: 10.1016/j.scs.2022.103930.
  6. L. Endriana, D. Hartono, Khoirunurrofik, and I. F. U. Muzayanah, “Does education affect energy behavior? Investigating the influence of educational attainment in Indonesia,” Soc. Sci. Humanit. Open, vol. 11, p. 101612, 2025, doi: https://doi.org/10.1016/j.ssaho.2025.101612.
  7. M. K. Nallakaruppan, M. Lawanyashri, R. K. Dhanaraj, S. Fuladi, D. Pamucar, and V. Simic, “Reliable power management and predictive analysis of domestic appliances with insights of XAI,” Energy Reports, vol. 14, pp. 3704–3718, 2025, doi: https://doi.org/10.1016/j.egyr.2025.10.036.
  8. M. Poyyamozhi, B. Murugesan, N. Rajamanickam, M. Shorfuzzaman, and Y. Aboelmagd, “IoT—A Promising Solution to Energy Management in Smart Buildings: A Systematic Review, Applications, Barriers, and Future Scope,” Buildings, vol. 14, no. 11. p. 3446, 2024. doi: 10.3390/buildings14113446.
  9. Y. Liu, B. Qiu, X. Fan, H. Zhu, and B. Han, “Review of Smart Home Energy Management Systems,” Energy Procedia, vol. 104, pp. 504–508, Dec. 2016, doi: 10.1016/j.egypro.2016.12.085.
  10. R. Munadi, M. Fuady, R. Noer, M. A. Kevin, M. R. Farrel, and Buraida, “Towards Net-Zero-Energy Buildings in Tropical Climates: An IoT and EDGE Simulation Approach,” Sustainability, vol. 17, no. 21. p. 9538, 2025. doi: 10.3390/su17219538.
  11. I. Priyadarshini, S. Sahu, R. Kumar, and D. Taniar, “A machine-learning ensemble model for predicting energy consumption in smart homes,” Internet of Things, vol. 20, p. 100636, 2022, doi: https://doi.org/10.1016/j.iot.2022.100636.
  12. J. D. Billanes, Z. G. Ma, and B. N. Jørgensen, “Data-Driven Technologies for Energy Optimization in Smart Buildings: A Scoping Review,” Energies, vol. 18, no. 2. p. 290, 2025. doi: 10.3390/en18020290.
  13. P. Nie, M. Roccotelli, M. P. Fanti, Z. Ming, and Z. Li, “Prediction of home energy consumption based on gradient boosting regression tree,” Energy Reports, vol. 7, pp. 1246–1255, 2021, doi: https://doi.org/10.1016/j.egyr.2021.02.006.
  14. S. Twum, R. Sarpong, A. Adomako, A. Agusah, B. Poornima, and K. Diallo, “Smart Home Energy Optimization Using Big Data and Predictive Modelling,” INTERANTIONAL J. Sci. Res. Eng. Manag., vol. 09, p. 12, Apr. 2025, doi: 10.55041/IJSREM45148.
  15. Y. Liu, G. Wu, W. Zhang, and J. Li, “Federated Learning-Based Intrusion Detection on Non-IID Data,” 2023, pp. 313–329. doi: 10.1007/978-3-031-22677-9_17.
  16. S. Kaur, A. Bala, and A. Parashar, “Explainable deep learning approach to predict residential electricity demand,” Int. J. Syst. Assur. Eng. Manag., vol. 16, May 2025, doi: 10.1007/s13198-025-02821-5.
  17. I. Givisis, D. Kalatzis, C. Christakis, and Y. Kiouvrekis, “Comparing Explainable AI Models: SHAP, LIME, and Their Role in Electric Field Strength Prediction over Urban Areas,” Electronics, vol. 14, no. 23. p. 4766, 2025. doi: 10.3390/electronics14234766.
  18. T. Magara and Y. Zhou, “Internet of Things (IoT) of Smart Homes: Privacy and Security,” J. Electr. Comput. Eng., vol. 2024, Apr. 2024, doi: 10.1155/2024/7716956.
  19. S. Zhu et al., “Personalized federated learning for household electricity load prediction with imbalanced historical data,” Appl. Energy, vol. 384, p. 125419, 2025, doi: https://doi.org/10.1016/j.apenergy.2025.125419.
  20. M. H. Widianto, A. Agung, S. Gunawan, and Y. Heryadi, “Identifying the Dominant Features in Indonesia Smart Home Dataset by Interpreting Electrical Energy Consumption Prediction Results,” no. 9, 2024.
  21. B. Niroomand, S. Pirhadi, and M. Shirazi, A Comparative Analysis of Ensemble Learning Methods for Classification Tasks on Benchmark Datasets. 2024. doi: 10.13140/RG.2.2.30835.64809.
  22. Y. Yu, L. Wang, H. Huang, and W. Yang, “An Improved Random Forest Algorithm,” J. Phys. Conf. Ser., vol. 1646, p. 12070, Sep. 2020, doi: 10.1088/1742-6596/1646/1/012070.
  23. D. Kho, H. Purnomo, and H. Hendry, “Performance Analysis of Gradient Boosting Models Variants in Predicting the Direction of Stock Closing Prices on the Idonesian Stock Exchange,” BAREKENG J. Ilmu Mat. dan Terap., vol. 19, pp. 1393–1408, Apr. 2025, doi: 10.30598/barekengvol19iss2pp1393-1408.
  24. S. Hakkal and A. A. Lahcen, “XGBoost To Enhance Learner Performance Prediction,” Comput. Educ. Artif. Intell., vol. 7, p. 100254, 2024, doi: https://doi.org/10.1016/j.caeai.2024.100254.
  25. T. O. Omotehinwa, D. O. Oyewola, and E. G. Moung, “Optimizing the light gradient-boosting machine algorithm for an efficient early detection of coronary heart disease,” Informatics Heal., vol. 1, no. 2, pp. 70–81, 2024, doi: https://doi.org/10.1016/j.infoh.2024.06.001.
  26. W. Xie, R. Xiong, J. Zhang, J. Jin, and J. Luo, “Federated variational generative learning for heterogeneous data in distributed environments,” J. Parallel Distrib. Comput., vol. 191, p. 104916, 2024, doi: https://doi.org/10.1016/j.jpdc.2024.104916.
  27. F. Liu, Z. Zheng, Y. Shi, Y. Tong, and Y. Zhang, “A survey on federated learning : a perspective from multi-party computation,” vol. 18, no. 1, 2024.
  28. S. Saha, A. Hota, A. K. Chattopadhyay, A. Nag, and S. Nandi, learning : progress , challenges , and opportunities, vol. 57, no. 7. Springer Netherlands, 2024. doi: 10.1007/s10462-024-10766-7.
  29. V. Mothukuri, R. M. Parizi, S. Pouriyeh, Y. Huang, A. Dehghantanha, and G. Srivastava, “A survey on security and privacy of federated learning,” Futur. Gener. Comput. Syst., vol. 115, pp. 619–640, 2021, doi: https://doi.org/10.1016/j.future.2020.10.007.
  30. R. Gosselin, L. Vieu, F. Loukil, and A. Benoit, “Privacy and Security in Federated Learning: A Survey,” Applied Sciences, vol. 12, no. 19. p. 9901, 2022. doi: 10.3390/app12199901.
  31. P. Qi, D. Chiaro, A. Guzzo, M. Ianni, G. Fortino, and F. Piccialli, “Model aggregation techniques in federated learning: A comprehensive survey,” Futur. Gener. Comput. Syst., vol. 150, pp. 272–293, 2024, doi: https://doi.org/10.1016/j.future.2023.09.008.
  32. Y. Gao, G. Lu, J. Gao, and J. Li, “A High-Performance Federated Learning Aggregation Algorithm Based on Learning Rate Adjustment and Client Sampling,” Mathematics, vol. 11, no. 20. p. 4344, 2023. doi: 10.3390/math11204344.
  33. M. Usman, M. L. Bernardi, and M. Cimitile, “Introducing a Quality-Driven Approach for Federated Learning,” Sensors, vol. 25, no. 10. p. 3083, 2025. doi: 10.3390/s25103083.
  34. T. O. Hodson, “Root-mean-square error ( RMSE ) or mean absolute error ( MAE ): when to use them or not,” no. 2, pp. 5481–5487, 2022.
  35. V. Demir, “Evaluation of Solar Radiation Prediction Models Using AI: A Performance Comparison in the High-Potential Region of Konya, Türkiye,” Atmosphere (Basel)., vol. 16, p. 398, Mar. 2025, doi: 10.3390/atmos16040398.
  36. A. Mohamed, K. Abdelqader, and K. Shaalan, “Explainable Artificial Intelligence: A systematic Review of Progress and Challenges,” Intell. Syst. with Appl., vol. 28, p. 200595, 2025, doi: https://doi.org/10.1016/j.iswa.2025.200595.
  37. M. T. Ribeiro and C. Guestrin, “‘ Why Should I Trust You ?’ Explaining the Predictions of Any Classifier,” 2016.
  38. A. Gramegna and P. Giudici, “SHAP and LIME : An Evaluation of Discriminative Power in Credit Risk,” vol. 4, no. September, pp. 1–6, 2021, doi: 10.3389/frai.2021.752558.
  39. S. M. Lundberg et al., “From local explanations to global understanding with explainable AI for trees,” Nat. Mach. Intell., vol. 2, no. 1, pp. 56–67, 2020, doi: 10.1038/s42256-019-0138-9.
  40. X. Ma, M. Hou, J. Zhan, and Z. Liu, “Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME Techniques,” Energies, vol. 16, no. 9. p. 3653, 2023. doi: 10.3390/en16093653.
Read More
Author biographies is not available.
Download this PDF file
Statistic
Read Counter : 0

Downloads

Download data is not yet available.