Design and Optimization of Human-Computer Interaction Interface for Smart Home Energy Management System Based on Machine Learning Load Forecasting

JianYi  Li; YingJie  Bai; YiJin  Chen

doi:10.6180/jase.202608_31.061

Design and Optimization of Human-Computer Interaction Interface for Smart Home Energy Management System Based on Machine Learning Load Forecasting

Computer Science and Information Engineering

JianYi Li¹, YingJie Bai², and YiJin Chen²This email address is being protected from spambots. You need JavaScript enabled to view it.

¹School of Art, Hubei Polytechnic University, Huangshi, Hubei, 435005 China

²School of Design, Guangxi Normal University, Guilin, Guangxi, 541006, China

Received: November 11, 2025
Accepted: February 22, 2026
Publication Date: March 21, 2026

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202608_31.061

To address the challenges of insufficient load forecasting accuracy and poor human-computer interaction in smart home energy management systems, this study proposes a short-term load forecasting model that integrates a TCN-GRU-Attention framework with a dynamic energy management strategy and a user-centric human-computer interface. This model utilizes a temporal convolutional network (TCN) to capture long-term dependencies and a gated recurrent unit (GRU) to learn short-term fluctuations. The model, combined with an attention mechanism, dynamically weights key features to achieve multi-scale load forecasting. Based on the forecast results, a dynamic energy management strategy is generated that targets electricity cost, comfort deviation, and peak load. The interface, utilizing the React framework and the Echarts visualization library, supports real-time user adjustment and feedback on the strategy. Experimental results demonstrate that the load forecasting model achieves a mean absolute percentage error (MAPE) of 5.2% and a root mean square error (RMSE) of 0.76kW. The interface also performs well in a multi-device environment, and user satisfaction ratings indicate an average functional completeness score of 8.97. This provides a collaborative optimization solution for smart home energy management.

Keywords: load forecasting; human-computer interaction; TCN-GRU-Attention; smart home energy management; dynamic energy management; machine learning

[1] A. C. Jose and R. Malekian, (2017) “Improving smart home security: Integrating logical sensing into smart home" IEEE Sensors Journal 17(13): 4269–4286. DOI: 10.1109/JSEN.2017.2705045.
[2] A. Q. H. Badar and A. Anvari-Moghaddam, (2022) “Smart home energy management system– a review" Advances in Building Energy Research 16(1): 118–143. DOI: 10.1080/17512549.2020.1806925.
[3] E. A. Affum, K. Agyeman-Prempeh, C. Adumatta, et al., (2021) “Smart home energy management system based on the Internet of Things (IoT)" International Journal of Advanced Computer Science and Applications 12(2): 722–730. DOI: 10.14569/IJACSA.2021.0120290.
[4] M. Razghandi, H. Zhou, M. Erol-Kantarci, et al., (2023) “Smart home energy management: VAE-GAN syn thetic dataset generator and Q-learning" IEEE Transactions on Smart Grid 15(2): 1562–1573. DOI: 10.1109/TSG.2023.3288824.
[5] C. Huang, H. Zhang, L. Wang, et al., (2022) “Mixed deep reinforcement learning considering discrete continuous hybrid action space for smart home energy management" Journal of Modern Power Systems and Clean Energy 10(3): 743–754. DOI: 10.35833/MPCE.2021.000394.
[6] M. Khan, B. N. Silva, O. Khattab, et al., (2022) “A transfer reinforcement learning framework for smart home energy management systems" IEEE Sensors Journal 23(4): 4060–4068. DOI: 10.35833/MPCE.2021.000394.
[7] B. Singh, R. Ray, J. S. Bhadoriya, et al., (2024) “Techno economic feasibility analysis with energy storage and demand response program for the smart home energy management" Electrical Engineering 106(4): 5133–5152. DOI: 10.1007/s00202-024-02274-2.
[8] A. Chatterjee, S. Paul, and B. Ganguly, (2022) “Multi objective energy management of a smart home in real time environment" IEEE Transactions on Industry Applications 59(1): 138–147. DOI: 10.1109/TIA.2022.3209170.
[9] G. Kumar, L. Kumar, and S. Kumar, (2023) “Multi objective control-based home energy management system with smart energy meter" Electrical Engineering 105(4): 2095–2105. DOI: 10.1007/s00202-023-01790-x.
[10] S. P. Ramalingam and P. K. Shanmugam, (2022) “Investigation on optimization algorithms for smart home energy management with different electricity pricing" International Journal of Electrical and Electronic Engineering & Telecommunications 11(6): 435–449. DOI: 10.18178/ijeetc.11.6.435-449.
[11] T. Ganesan and R. Hemnath, (2018) “Lightweight AI for smart home security: IoT sensor-based automated bot net detection" International Journal of Engineering Research and Science & Technology 14(1):
[12] S. Sohrabi, Y. Darestani, W. J. Pringle, D. M. Dow den, and P. Dehghanian, (2025) “Life cyclecostanaly sis of prestressed concrete poles subjected to wind, surges, and waves" Journal of Structural Engineering 151(7): 04025069. DOI: 10.1061/JSENDH.STENG-13840.
[13] N. Cheng, L. Yang, X. Zhu, and R. Gomes, (2025) “The role and future applications of human-computer interaction in enhancing residential energy efficiency" International Conference on Human-Computer Inter action: 202–215. DOI: 10.1007/978-3-031-94165-8_22.
[14] R. Fitriyan and S. Syafii, (2025) “Solar-assisted IoT based smart home for energy efficiency and hazard prevention toward sustainable living" Andalasian International Journal of Applied Science, Engineering and Technology 5(3): 321–328. DOI: 10.25077/aijaset.v5i3. 262.
[15] P. Gonzalez-Gil, J. A. Martinez, and A. Skarmeta, (2022) “A prosumer-oriented, interoperable, modular and secure smart home energy management system architecture" Smart Cities 5(3): 1054–1078. DOI: 10.3390/smartcities5030053.
[16] A. B. Naeini, A. G. Mahdipour, and R. Dorri, (2023) “Using eye tracking to measure overall usability of online grocery shopping websites" International Journal of Mobile Computing and Multimedia Communications (IJMCMC) 14(1): 1–24. DOI: 10.4018/IJMCMC.326129.
[17] Y. H. Lin, (2022) “An advanced smart home energy management system considering identification of ADLs based on non-intrusive load monitoring" Electrical Engineering 104(5): 3391–3409. DOI: 10.1007/s00202-022 01546-z.
[18] R. Elazab, O. Saif, A. M. A. Metwally, et al., (2022) “New smart home energy management systems based on inclining block-rate pricing scheme" Clean Energy 6(3): 503–511. DOI: 10.1093/ce/zkac016.
[19] G. Wei, M. Chi, Z. W. Liu, et al., (2023) “Deep reinforce ment learning for real-time energy management in smart home" IEEE Systems Journal 17(2): 2489–2499. DOI: 10.1109/JSYST.2023.3247592.
[20] P. C. Siswipraptini, R. N. Aziza, R. R. A. Siregar, et al., (2024) “Smart home energy management systems: A systematic review of architecture, communication, and algorithmic trends" Journal of System and Management Sciences 14(11): 129–146. DOI: 10.33168/JSMS. 2024.1108.
[21] N.Jain, (2024) “Optimizing smart home energy management for sustainability using machine learning" International Journal of Novel Research and Development 9(1): d325–d336. DOI: 10.1007/s43621-024-00681-w.
[22] A. Bhatia, M. K. Lee, and J. T. Hancock, (2025) “Miti gating memory power asymmetry in long-term human–AI collaboration" arXiv arXiv:2512.06616: DOI: 10.48550/arXiv.2512.06616.
[23] H. Youssef, S. Kamel, and M. H. Hassan, (2025) “Smart home energy management with long-term memory artificial rabbit algorithm for cost and load optimization" Cluster Computing 28(5): 1–28. DOI: 10.1007/s10586-024-04968-5.
[24] R. Yueh, J. Lim, Y. Li, and R. Dorri, (2025) “How motivational cues and contextual demands moderate the cognitive effects of accelerated information delivery" Frontiers in Psychology 16: 1664580. DOI: 10.3389/fpsyg.2025.1664580.
[25] M. Jouyban, S. Hosseini, and M. Khorashadizade, (2025) “The dynamical model of information diffusion in social networks considering the effects of user behavior" Discrete Dynamics in Nature and Society 2025(1): 5876933. DOI: 10.1155/ddns/5876933.