A Load Classification Strategy using NILM and DNN for Potential Demand-Side Management

Arsh Alam Bhatti; Fazeela Irshad Irshad; Abdulelah  Al-Suhaibi; Kamal Shahid; Akbar Ali Khan

doi:10.32350/icr.51.02

Arsh Alam Bhatti Institute of Electrical, Electronics and Computer Engineering, University of the Punjab Lahore, Pakistan
Fazeela Irshad Irshad Inistitue of Electrical Electronics and Computer Engineering , University of the Punjab
Abdulelah Al-Suhaibi Inistitue of Electrical Electronics and Computer Engineering , University of the Punjab
Kamal Shahid Inistitue of Electrical Electronics and Computer Engineering , University of the Punjab
Akbar Ali Khan

DOI: https://doi.org/10.32350/icr.51.02

Keywords: NILM, Demand Side Management, Deep Neural Networks, Smart Energy Meters, Real Time Energy Monitoring

Abstract

Abstract Views: 0

Uncoordinated and unplanned increases in electricity demand have become a critical concern in recent times due to growing population and appliance utilization. Significant focus has been placed on optimizing load patterns for appliances and capitalizing on the potential for savings in domestic energy management. This paper develops a low-cost demand-side management system for residential applications through smart energy meters, combined with non-Intrusive load monitoring (NILM) and machine learning for accurate load disaggregation. It also presents a real-time consumption-based dynamic pricing algorithm that exploits the use of deep neural networks (DNN) for classifying of essential and non-essential loads, utilizing real-time collected datasets. The system provides live energy monitoring through Modbus RTU and RS485 protocols, with data stored in Postgre SQL database, enabling data visualization on a Power BI dashboard. The dashboard highlights real-time advice on energy optimization. The proposed approach demonstrates an effective demand response (DR) mechanism, shifting electricity consumption to off-peak hours throughout the day without reducing overall energy use. This enhances optimizing the load curve metrics and improves energy efficiency.

Downloads

Download data is not yet available.

Author Biographies

Arsh Alam Bhatti, Institute of Electrical, Electronics and Computer Engineering, University of the Punjab Lahore, Pakistan

Electrical Engineer

Abdulelah Al-Suhaibi, Inistitue of Electrical Electronics and Computer Engineering , University of the Punjab

Electrical Engineer

Kamal Shahid, Inistitue of Electrical Electronics and Computer Engineering , University of the Punjab

Engr. Dr. Kamal Shahid is an Assistant Professor at the Institute of Electrical, Electronics, and Computer Engineering (IEECE), University of the Punjab, Lahore, Pakistan. With an M.Sc. in Computer Engineering and a Ph.D. fellowship from Aalborg University, Denmark, he specializes in communication networks for smart grids. His research focuses on renewable energy integration, IEC-61850-based communication standards, and dynamic data access in power grids. Dr. Shahid plays key roles in academia as Program Coordinator for M.Sc. Electrical Engineering, DDPC member, and IEEE spokesperson. He collaborates globally on innovative solutions for smart grid challenges.

Akbar Ali Khan

Dr. Akbar Ali Khan is a dedicated academic and researcher, currently serving as an Assistant Professor at this institute. His expertise and teaching interests encompass a broad range of areas, including Power Systems, Power Electronics, and Electrical Machines. With a passion for advancing knowledge and fostering innovation, Dr. Khan is committed to contributing to the development of these critical fields in electrical engineering

References

P. Palensky and D. Dietrich, “Demand side management: Demand response, intelligent energy systems, and smart loads,” IEEE Trans. Indust. Info., vol. 7, no. 3, pp. 381–388, Aug. 2011, doi: https://doi.org/10.1109/tii.2011.2158841.

M. A. Bhaagat, N. H. Mirjat, S. A. Khatri, A. Mahar, and M. A. Raza, “Demand side management for the energy-efficient future of Pakistan using a low emission analysis platform,” Eng. Proc., vol. 46, no. 1, p. 28, 2023, doi: https://doi.org/10. 3390/engproc2023046028.

G. Clark, The Smart Grid: Enabling Energy Efficiency and Demand Response. River Publishers, 2025.

G. W. Hart, “Nonintrusive appliance load monitoring,” Proc. IEEE, vol. 80, no. 12, pp. 1870–1891, 1992, doi: https://doi.org/10.1109/5.192069.

M. I. Azad, R. Rajabi, and A. Estebsari, “Nonintrusive Load Monitoring (NILM) using a deep learning model with a transformer-based attention mechanism and temporal pooling,” Electronics, vol. 13, no. 2, Art. no. 407, Jan. 2024, doi: https://doi.org/10.3390/electronics13020407.

J. Kelly and W. Knottenbelt, “Neural NILM,” in Proc. 2nd ACM Int. Conf. Embed. Syst. Energy-Efficient Built Environ., 2015, pp. 55–64, doi: https://doi.org/10.1145/2821650.2821672.

Y. Chen, W. Gong, C. Obrecht, and F. Kuznik, “A review of machine learning techniques for building electrical energy consumption prediction,” Energy AI, vol. 21, May 2025, Art. no. 100518, doi: https:// doi.org/10.1016/j.egyai.2025.100518.

A. Shahcheraghian and A. Ilinca, “Advanced machine learning techniques for energy consumption analysis and optimization at UBC campus: Correlations with meteorological variables,” Energies, vol. 17, no. 18, Sep. 2024, Art. no. 4714, doi: https://doi.org/10. 3390/en17184714.

A. Abdelaziz, V. Santos, and M. S. Dias, “Machine learning techniques in the energy consumption of buildings: A systematic literature review using text mining and bibliometric analysis,” Energies, vol. 14, no. 22, Nov. 2021, Art. no. 7810, doi: https://doi.org/10.3390/en14227810.

L. R. Chandran, N. Jayagopal, L. S. Lal, C. Narayanan, S. Deepak, and V. Harikrishnan, “Impact of dynamic pricing in residential load scheduling and energy management,” Presented at the 2nd Global Conference for Advancement in Technology (GCAT), Bangalore, India, Oct. 1–3, 2021, doi: https://doi.org/10.1109/gcat52182.2021.9587619.

M. H. Albadi and E. F. El-Saadany, “Demand response in electricity markets: An overview,” Presented at IEEE Power Engineering Society General Meeting, Tampa, FL, USA, June 42–28, 2007, doi: https://doi. org/10.1109/pes.2007.385728.

Q. H. Badar and A. Anvari-Moghaddam, “Smart home energy management system – a review,” Adv. Build. Energy Res., vol. 16, no. 1, pp. 1–26, Aug. 2020, doi: https://doi. org/10.1080/17512549.2020.1806925.

T. Nguyen, K. Shimada, Y. Ochi, T. Matsumoto, H. Matsugi, and T. Awata, “An experimental study of the impact of dynamic electricity pricing on consumer behavior: An analysis for a remote Island in Japan,” Energies, vol. 9, no. 12, Dec. 2016, Art. no. 1093, doi:https://doi.org/10.3390/en9121093

R. Mathumitha, P. Rathika, and K. Manimala, “Intelligent deep learning techniques for energy consumption forecasting in smart buildings: a review,” Artif. Intell. Rev., vol. 57, no. 2, Feb. 2024, Art. no. 35, doi: https://doi.org/10.1007/s10462-023-10660-8.

B. Gowrienanthan, N. Kiruthihan, K. D. I. S. Rathnayake, S. Kumarawadu, and V. Logeeshan, “Low-cost ensembling for deep neural network based non-intrusive load monitoring,” Presented at the IEEE World AI IoT Congress (AIIoT), Seattle, WA, US, June 6–9, 2022, doi: https://doi. org/10.1109/aiiot54504.2022.9817165

M. AL-Ghamdi, A. A.-M. AL-Ghamdi, and M. Ragab, “A Hybrid DNN multilayered LSTM model for energy consumption prediction,” Appl. Sci., vol. 13, no. 20, Art. no. 11408, Jan. 2023, doi: https://doi.org/10.3390/app132011408