Title
MACHINE LEARNING ASSISTED ENERGY AUDIT AND POWER CONSUMPTION PREDICTION FOR SOLAR NET-METERING SYSTEMS USING KNN ML ALGORITHM
Authors
C. Maheswari , S. Sathishkumar
Abstract
Energy audit system plays a pivotal role in energy conservation among several industries and household applications. Recent advancements in smart energy management have encouraged the integration of machine learning techniques for forecasting energy consumption and optimizing renewable energy utilization. In this work, initially import and export energy is measured from net metering system for a specific period through a specific IoT enabled system. From the observations, net energy consumption is calculated and used as an input for predictive model. KNN-based predictive model is incorporated to forecast future power consumption using historical import-export energy data collected from the solar net-metering system. The integration of KNN with energy audit systems provides valuable insights into future power demand patterns, enabling industries to optimize energy import-export decisions, improve solar energy utilization, and reduce electricity costs.
Keywords
Energy Audit, Net Metering, IoT, Machine Learning Algorithm, KNN
Full Text
References
[1] S. W. Chisale and P. Mangani, “Energy audit and feasibility of solar PV energy system: Case of a commercial
building,” Journal of Energy, vol. 2021, pp. 1–9, 2021.
[2] I. Bosu, H. Mahmoud, and H. Hassan, “Energy audit, techno-economic and environmental assessment of
integrating solar technologies for energy management in a university residential building: A case study,” Applied
Energy, vol. 341, p. 121141, 2023.
[3] A. T. Umoette, U. J. Paul, and E. A. Ubom, “Energy audit and standalone solar-power generation design for
Akwa Ibom State University Main Campus,” Energy, vol. 8, no. 6, 2023.
[4] M. A. Omar and M. M. Mahmoud, “An economic evaluation of residential grid-connected PV systems based
on net-metering and feed-in-tariff schemes in Palestine,” International Journal of Renewable Energy Research,
vol. 8, no. 4, pp. 16–27, 2018.
[5] R. H. Tan and T. L. Chow, “A comparative study of feed-in tariff and net metering for UCSI University North
Wing Campus with 100 kW solar photovoltaic system,” Energy Procedia, vol. 100, pp. 86–91, 2016.
[6] A. R. Kalair, M. Seyedmahmoudian, N. Abas, M. S. Saleem, A. Stojcevski, S. Mekhilef, and K. Koh, “Energy
audit in buildings for sustainable economic development,” in Proc. International Conference on Applied
Economics, Cham, Switzerland: Springer, 2022, pp. 587–612.
[7] O. E. Atiba, U. K. Efemwenkiekie, R. O. Olatunji, O. S. Ohunakin, D. S. Adelekan, and O. A. Oyeleke, “Walkthrough energy audit of an institutional building,” in Journal of Physics: Conference Series, vol. 1378, no. 3, Art.
no. 032051, 2019.
[8] S. Soni, I. Kaur, and D. Kumar, “Optimization of electricity bill on study of energy audit by using grid
integration of renewable energy sources,” in Cognitive Informatics and Soft Computing: Proceedings of CISC
2017, Singapore: Springer, 2019, pp. 669–676.
[9] A. R. Yusoff, M. M. Foudzi, M. Y. Taib, and A. A. Shah, “Monitoring energy audit for energy savings using
non-cost technique at electronics company,” Journal of Modern Manufacturing Systems and Technology, vol. 5,
no. 1, pp. 71–79, 2021.
[10] A. Kluczek and P. Olszewski, “Energy audits in industrial processes,” Journal of Cleaner Production, vol.
142, pp. 3437–3453, 2017.
[11] Y. Wang, Q. Chen, T. Hong, and C. Kang, “Review of smart meter data analytics: Applications,
methodologies, and challenges,” IEEE Transactions on Smart Grid, vol. 10, no. 3, pp. 3125–3148, 2019.
[12] L. Hernández, C. Baladrón, J. M. Aguiar, L. Calavia, B. Carro, A. Sánchez-Esguevillas, et al., “Short-term
load forecasting for microgrids based on artificial neural networks and K-nearest neighbours algorithms,”
Energies, vol. 7, no. 3, pp. 1576–1598, 2014.
[13] T. Ahmad and H. Chen, “Short and medium-term forecasting of cooling and heating load demand in building
environment with data-mining based approaches,” Energy and Buildings, vol. 166, pp. 460–476, 2019.
[14] Y. Wang, J. Wang, and G. Zhao, “Application of K-nearest neighbour algorithm in short-term electric load
forecasting,” Energy Procedia, vol. 152, pp. 284–289, 2018.
[15] A. Ahmad, N. Javaid, A. Mateen, M. Awais, and Z. A. Khan, “Short-term load forecasting in smart grids:
An intelligent modular approach,” Energies, vol. 12, no. 1, Art. no. 164, 2019.
[16] D. Wang, Y. Luo, and X. Grunder, “Solar irradiance prediction for photovoltaic systems using machine
learning methods,” Renewable Energy, vol. 145, pp. 2187–2199, 2020.
[17] S. Fan, L. Chen, W. Lee, and J. Zhang, “Building energy consumption prediction using K-nearest neighbor
algorithm and feature selection,” Energy Reports, vol. 7, pp. 920–930, 2021.
[18] S. Shankar, G. Abbas, M. M. Chander Prakash, and V. E. Sathishkumar, "Predictive Modelling of PM2.5
Impact on Pulmonary Function Among Indian Textile Workers Diagnosed with Chronic Obstructive Pulmonary
Disease: A Machine Learning-Based Study," PMRP Journal of Research–Part A: Computational Engineering,
vol. 1, no. 1, pp. 1–13, 2025.
[19] S. M. Moghimi, T. A. Gulliver, and I. T. Chelvan, “Energy Management in Modern Buildings Based on
Demand Prediction and Machine Learning—A Review,” Energies, vol. 17, no. 3, Art. no. 555, 2024.
[20] N. Ahmed, Y. Ding, G. Canti, and N. Anglani, “Sustainable Building’s Energy Management with Artificial
Intelligence and Machine Learning: A Decadal Scoping Review (2014–2024),” Energy Reports, vol. 12, pp.
109082, 2026.
[21] R. Kowalik, M. Nowak, and P. Zieliński, “Artificial Intelligence in Photovoltaic-Integrated Buildings:
Forecasting, Optimization and Energy Management,” Energies, vol. 19, no. 11, Art. no. 2534, 2026.
[22] Vaisali S, Maheswari C, Shankar S, Naveenkumar R. Predicting the performance of assistive device for
elderly people using weighted KNN machine learning algorithm. Journal of Back and Musculoskeletal
Rehabilitation, Vol.38, no.4, pp.852-864. 2025.
[23] Priyanka E. Bhaskaran, C. Maheswari, S. Thangavel, M. Ponnibala, T. Kalavathidevi, N.S. Sivakumar, IoT
Based monitoring and control of fluid transportation using machine learning, Computers & Electrical
Engineering, Vol. 89, p.106899, 2021.