Integration of Deep Learning into Smart Distribution Panelboard at Household level with IoT Connectivity
DOI:
https://doi.org/10.4108/ew.8601Keywords:
Smart Distribution Panelboard (SDP), Internet of Things (IOT), Deep Learning, Edge computing, Power management, Blynk ApplicationAbstract
Power management systems are becoming inevitable for enhancing efficiency, reliability, and sustainability in household electricity consumption. Unlike industry which has a robust intelligent power management system for effective control. The proposed system introduces an integration of IoT with cutting edge deep learning modality using the facilitation of microcontroller as entry-exit core point edge device to receive data from the sensor modules, conveying data to a visualization platform through Wi-Fi (MQTT protocol). In order to address the concern of power wastage due to unawareness of power consumption it needs to enable the visual portal which displays the power, current and voltage consumption of the household by deploying it as an application that could be scaled and installed into local mobile phones for real time monitoring. The sensor modules are embedded onto a distribution panel board prototype sensing the sample load in various distribution nodes and circuit interpreters to shut down during abnormality. In the second phase, these data are then transmitted to a central control unit for decision-making using advanced deep learning algorithms. The comparison of various deep learning algorithms like light gradient boosting machine (LGBM), neural network (NN) and long short-term memory (LSTM) tabulating their accuracy in a more deterministic aspect using the mean absolute percentage error (MAPE) as evaluation parameter attempting to be more data centric artificial intelligence. The prediction comes under the temporal categorization of load forecasting attempting to predict on a short term basis for effective system management.
Downloads
References
[1] Hong T, Wang P, Willis HL. A review of machine learning models in load prediction. Energy AI. 2020;1:100033. doi:10.1016/j.egyai.2020.100033.
[2] Song KB, Ha SK, Park JW, Kweon DJ, Kim KH. Hybrid load forecasting method with analysis of temperature sensitivities. IEEE Trans Power Syst. 2006;21(2):869-876. doi:10.1109/TPWRS.2006.873099.
[3] Pai PF, Hong WC. Novel approach for short-term load forecasting using support vector machine. Int J Neural Syst. 2004;14(5):329-335. doi:10.1142/S0129065704002097.
[4] Charytoniuk W, Chen MS, Van Olinda P. One-hour-ahead load forecasting using neural network. IEEE Trans Power Syst. 2002;17(1):125-132. doi:10.1109/59.982211.
[5] Dongxiao N, Wang Y, Wu DD. A study of short-term load forecasting based on ARIMA-ANN. In: Proceedings of the International Conference on Machine Learning and Cybernetics; 2004. p. 3183-3187. doi:10.1109/ICMLC.2004.1382885.
[6] Monteiro C, Fernandez-Jimenez LA, Ramirez-Rosado IJ, Muñoz-Jimenez A. The daily and hourly energy con-sumption and load forecasting using artificial neu-ral network method: A case study using a set of 93 households in Portugal. Energy. 2014;62:220-229. doi:10.1016/j.energy.2013.09.050.
[7] Sandels C, Widén J, Nordström L. Forecasting household consumer electricity load profiles with a combined physi-cal and behavioral approach. Appl Energy. 2014;131:267-278. doi:10.1016/j.apenergy.2014.06.034.
[8] Brown W, Garcia O. IoT-enabled Energy Management Systems: A Review. 2020.
[9] Al Mamun A, Sohel M, Mohammad N. A comprehensive review of the load forecasting techniques using single and hybrid predictive models. IEEE Access. 2020;8:134751134769.doi:10.1109/ACCESS.2020.3010183.
[10] Smith J, Johnson E. Smart Distribution Panelboards: A Review of IoT Integration and Machine Learning Techniques for Power Management. 2020.
[11] Silfiani M, Hayati FN, Nurlaily D, Fitria I. Household electrical load forecasting: A hybrid of linear models and radial basis function neural network. J Electr Syst Inf Technol. 2021;8(1):1-15.doi:10.1186/s43067-020-00021-8.
[12] Nti IK, Teimeh M, Nyarko-Boateng O, Adekoya AF. Electricity load forecasting: A systematic review. J Electr Syst Inf Technol. 2020;7(1):1-19. doi:10.1186/s43067-020-00021-8.
[13] National Association of Regulatory Utility Commissioners (NARUC). Smart Grid and Load Forecasting Report [Internet]. Washington (DC): NARUC; [cited 2026 Jul 13]. Available from:https://pubs.naruc.org/pub.cfm?id=536E10A7-2354-D714-5191-A8AAFE45D626
[14] Zhao J, Zhang C, Mu D, Cao W. Load forecasting based on CNN-LSTM for 96 time points. In: 2022 IEEE 5th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC); 2022. p. 1749-1753. doi:10.1109/IMCEC55388.2022.10019996.
[15] Zhao J, Zhang X, Wang H, Mu D. Load trend prediction analysis based on LSTM and sliding time window. In: 2022 IEEE 5th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC); Chongqing, China; 2022. p. 1239-1242. doi:10.1109/IMCEC55388.2022.10019830.
[16] Budin L, Duilo I, Delimar M. Day-ahead multi-ple households load forecasting using deep learning and unsupervised clustering. Energies. 2022;15(9):3284. doi:10.3390/en15093284.
[17] De Ocampo ALP, Baes AMM, Ronquillo DGD. Non-intrusive load monitoring and forecasting for home appliances using artificial intelligence – A review. Results Eng. 2022;14:100465. doi:10.1016/j.rineng.2022.100465.
[18] Wilson J, Harris E. IoT-enabled Power Distribution Systems: Technologies and Applications. 2022.
[19] Grabner M, Wang Y, Wen Q, Blažič B, Štruc V. A global modeling framework for load forecasting in distribution networks. IEEE Trans Smart Grid. 2023;14(6):4927-4941. doi:10.1109/TSG.2023.3264525.
[20] Lu R, Bai R, Li R, Zhu L, Sun M, Xiao F, et al. A novel sequence-to-sequence-based deep learning model for multistep load forecasting. IEEE Trans Neural Netw Learn Syst. 2025;36(1):638-652. doi:10.1109/TNNLS.2023.3329466.
[21] International Energy Agency (IEA). Electricity 2024: Executive Summary [Internet]. Paris: International Energy Agency; 2024 [cited 2026 Jul 13]. Available from: https://www.iea.org/reports/electricity2024/executive-summary
[22] Utility Dive. US Electric Demand Forecast and Data Center Growth [Internet]. Washington (DC): Utility Dive; 2024 [cited 2026 Jul 13]. Available from: https://www.utilitydive.com/news/us-electric-demandiea-forecast-data-center/705452
[23] Enerdata. India Energy Market Report [Internet]. Greno-ble (France): Enerdata; 2024 [cited 2026 Jul 13]. Available from: https://www.enerdata.net/estore/energy-market/india/
[24] International Energy Agency (IEA). India Energy Outlook 2021: Energy in India Today [Internet]. Paris: International Energy Agency; 2021 [cited 2026 Jul 13]. Available from: https://www.iea.org/reports/india-energy-outlook-2021/energy-in-india-today
[25] Centre for Policy Research (CPR). Trends in India’s Residential Electricity Consumption [Internet]. New Delhi: Centre for Policy Research; [cited 2026 Jul 13]. Available from: https://cprindia.org/trends-inindias-residential-electricity-consumption/
[26] CLASP. How Pandemic Power Use Could Reshape India’s Residential Energy Demand [Internet]. Washington (DC): CLASP; [cited 2026 Jul 13]. Available from: https://www.clasp.ngo/updates/howpandemic-power-use-could-reshape-indias-residential-energy-demand
[27] Trejo-Perea M, Moreno GR, Castañeda-Miranda A, Vargas-Vázquez D, Carrillo-Serrano RV, Herrera-Ruiz G. Development of a real-time energy monitoring platform user-friendly for buildings. Procedia Technol. 2013;7:238-247. doi:10.1016/j.protcy.2013.04.030.
[28] Ueno T, Inada R, Saeki O, Tsuji K. Effectiveness of displaying energy consumption data in residential houses. In: European Council for an Energy-Efficient Economy Summer Study; 2005. p. 19-28.
[29] Philpott D, Qi L. Solid-state fault current limiters for residential houses and commercial buildings. IEEE Trans Ind Appl. 2019;55(4):3431-3436. doi:10.1109/TIA.2019.2905758.
[30] De Ocampo ALP, Baes AMM, Ronquillo DGD. Non-intrusive load monitoring and forecasting for home appliances using artificial intelligence – A review. In: 2022 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON); 2022. p. 1-6. doi:10.1109/SMARTGENCON56628.2022.10084310.
[31] Smart Distribution Board with IoT Integration. In: Proceedings of Advances in Smart Grid and Energy Systems. Singapore: Springer; 2022. doi:10.1007/978-981-16-9008-2_12.
[32] Fang X, Misra S, Xue G, Yang D. Smart grid—The new and improved power grid: A survey. IEEE Commun Surv Tutor. 2012;14(4):944-980. doi:10.1109/SURV.2011.101911.00087.
[33] Halder T. A smart grid. In: 2014 6th IEEE Power India International Conference (PIICON); Delhi, India; 2014. p. 1-6. doi:10.1109/POWERI.2014.7117674.
[34] Brown HE, Suryanarayanan S. A survey seeking a definition of a smart distribution system. In: 2009 North American Power Symposium (NAPS); 2009. p. 1-7. doi:10.1109/NAPS.2009.5484066.
[35] Qmerit. It’s Time to Get Smart: Your Guide to Smart Electrical Panels—What They Are and Why You Need One [Internet]. Irvine (CA): Qmerit; [cited 2026 Jul 13]. Available from: https://qmerit.com/blog/its-time-to-get-smart-your-guide-to-smart-electrical-panels-what-they-are-and-why-you-need-one/
[36] Jose A, Varghese AM, Jenson FE, Jacob P, Anumod DM, Thomas D. Solid-state circuit breaker based smart distribution board with IoT integration. In: 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT); 2020. p. 1180-1185. doi:10.1109/ICSSIT48917.2020.9214193.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Hamsa Priyaa K S, Prabaakaran K, Kaliappan E, Ragavendran C R, Hemakumar V S, Srividhya R
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
