Enhancing Predictive Performance of Non-Intrusive Load Monitoring Through Systematic Feature Extraction

N. K. Mensah, S. Nunoo, H. Abdel-Fatao, Y. Y. Ziggah

Abstract


Non-Intrusive Load Monitoring (NILM) is a highly effective method for maximizing energy efficiency by analysing recorded voltage and current measurements to determine appliance-level electricity consumption. Real-time power consumption information provided by NILM enables consumers to make informed decisions to save energy and resources. However, the challenge lies in extracting meaningful features for accurate appliance classification, and existing research in this area is limited. To address this gap, this study focuses on enhancing the predictive performance of NILM through the combination of various electrical features. A dataset derived from Intrusive Load Monitoring (ILM) is utilised, with emphasis placed on selecting the most significant electrical characteristics. Two experiments are conducted, with the first employing only the root mean square current (IRMS) as a feature and the second incorporating six electrical characteristics. Six machine learning classification algorithms are applied to each experiment, and their results are compared in terms of accuracy, precision, recall, and F-measure. The findings demonstrate that utilizing the six extracted features, including current, voltage, and day section, outperforms the standalone IRMS feature. This comparative analysis highlights the effectiveness of these six feature sets for NILM in achieving improved classification accuracy. In conclusion, this study emphasizes the importance of feature extraction in NILM and provides evidence of the superior performance obtained by incorporating multiple electrical features. The results contribute to understanding efficient appliance classification for NILM, enabling enhanced energy management and conservation. Future research may explore additional datasets and advanced techniques to further optimize appliance classification in NILM systems.


Keywords


Non-Intrusive Load Monitoring, Energy Consumption, Feature Extraction, Machine Learning, Time Series Analysis

Full Text:

PDF

References


Alghawazi, M., Alghazzawi, D. and Alarifi, S. (2022), “Detection of sql injection attack using machine learning techniques: a systematic literature review”, Journal of Cybersecurity and Privacy, Vol. 2, No. 4, pp. 764 - 777.

Angelis, G. F., Timplalexis, C., Krinidis, S., Ioannidis, D. and Tzovaras, D. (2022), “NILM applications: Literature review of learning appr-oaches, recent developments and challenges”, Energy and Buildings, p. 111951.

Chang, H. H, Chen, K. L., Tsai, Y. P. and Lee, W. J. (2011), “A New Measurement Method for Pow-er Signatures of Non-Intrusive Demand Monit-oring and Load Identification”, IEEE Transact-ions on Industry Applications, Vol. 48, pp. 764 – 771.

Chang, H. H., Lee, M. C., Chen, N., Chien, C. L. and Lee, W. J. (2015), “Feature Extraction Based Hellinger Distance Algorithm for Non-Intrusive Aging Load Identification in Residential Build-ings”, IEEE Transactions on Industry Applica-tions, pp. 1–8.

Cole, A. I. and Albicki, A. (1998), “Data Extraction for Effective Non-Intrusive Identification of Residential Power Loads” IMTC/98 Confere-nce Proceedings. IEEE Instrumentation and Measurement Technology Conference. Where Instrumentation is Going (Cat. No. 98CH3622-2), Vol. 2, pp. 812 – 815.

De Baets, L., Ruyssinck, J., Develder, C., Dhaene, T. and Deschrijver, D. (2018), “Appliance Classification using VI Trajectories and Convo-lutional Neural Networks”, Energy and Buildin-gs, Vol. 158, pp. 32–36.

Dong, M., Meira, P. C., Xu, W. and Freitas, W. (2012), “An Event Window Based Load Mon-itoring Technique for Smart Meters”, IEEE Transactions on Smart Grid, Vol. 3, pp. 787 – 796.

Drenker, S. and Kader, A. (1999), “Non-Intrusive Monitoring of Electric Loads”, IEEE Computer Applications in Power, Vol. 12, pp. 47 – 51.

Du, L., He, D., Harley, R. G., and Habetler, T. G. (2015), “Electric Load Classification by Binary Voltage–Current Trajectory Mapping”, IEEE Transactions on Smart Grid, Vol. 7, pp. 358 – 365.

Ghosh, S., Chatterjee, A and Chatterjee D. (2019), Improved Non-Intrusive Identification Techni-que of Electrical Appliances for a Smart Residential System”. IET Generation, Transmi-ssion & Distribution, Vol. 13, pp. 695 – 702.

Ghosh, S., Manna, D., Chatterjee, A. and Chatterjee, D. (2020), “Remote Appliance Load Monito-ring and Identification in a Modern Residential System with Smart Meter Data”, IEEE Sensors Journal, Vol. 21, pp. 5082 – 5090.

Gillis, J. M., Chung, J. A. and Morsi, W. G. (2017) “Designing New Orthogonal High-Order Wavelets for Nonintrusive Load Monitoring”, IEEE Transactions on Industrial Electronics, Vol. 65, pp. 2578 – 2589.

Gopinath, R., Kumar, M., Joshua, C. P. C. and Srinivas, K. (2020), “Energy Management using Non-Intrusive Load Monitoring Techni-ques State-of-the-Art and Future Research Directions”, Sustainable Cities and Society, Vol. 62, pp. 102411.

Gulati, M., Singh, V. K., Agarwal, S. K. and Bohara, V. A. (2016), “Appliance Activity Recognition using Radio Frequency Interference Emissio-ns”, IEEE Sensors Journal, Vol. 16, pp. 6197 – 6204.

Gungor V. Cagri, Sahin Dilan, Kocak Taskin, Ergut Salih, Buccella Concettina, Cecati Carlo and Hancke Gerhard P. (2013), "A Survey on Smart Grid Potential Applications and Communic-ation Requirements," IEEE Transactions on Industrial Informatics, vol. 9, no. 1, pp. 28–42.

Hamid, O., Barbarosou, M., Papageorgas, P., Prekas, K. and Salame, C. T. (2017), “Auto-matic recognition of electric loads analyzing the characteristic parameters of the consumed ele-ctric power through a Non-Intrusive Monitoring methodology” Energy Procedia International Conference on Technologies and Materials for Renewable Energy, Environment and Sustaina-bility, Vol. 119, pp. 742 - 751.

Hart G. W. (1992), “Nonintrusive Appliance Load Monitoring”, Proceedings of the IEEE. Vol. 80, pp. 1870 – 1891.

Hassan, T., Javed, F. and Arshad, N. (2013), “An Empirical Investigation of VI Trajectory Based Load Signatures for Non-Intrusive Load Monit-oring”, IEEE Transactions on Smart Grid., Vol. 5, pp. 870–878.

He, D., Du, L., Yang, Y., Harley, R. and Habetler, T. (2012), “Front End Electronic Circuit Topology Analysis for Model-Driven Classific-ation And Monitoring of Appliance Loads in Smart Buildings”, IEEE Transactions on Smart Grid, Vol. 3, pp. 2286–2293.

Himeur, Y., Alsalemi, A., Bensaali, F., Amira, A. and Al‐Kababji, A., 2022. “Recent trends of smart nonintrusive load monitoring in buildi-ngs: A review, open challenges, and future directions”, International Journal of Intelligent Systems, 37 (10), pp. 7124–7179.

Kahl, M. (2019), “Machine Learning for Non-Intrusive Load Monitoring”, Ph.D. thesis, Techn-ische Universität München, Vol. 196 pp. 112–123.

Kong, W., Dong, Z. Y., Wang, B., Zhao, J. and Huang, J. (2019), “A Practical Solution for Non-Intrusive Type II Load Monitoring Based on Deep Learning and Post-processing”, IEEE Transactions on Smart Grid, Vol. 148–160, pp 11.

Larcher, D. and Tarascon, J. M. (2015), “Towards Greener and More Sustainable Batteries for Ele-ctrical Energy Storage”, Nature Chemistry, Vol 7, pp 19 – 29.

Leeb, S. B., Shaw, S. R. and Kirtley, J. L. (1995), Transient Event Detection in Spectral Envelope Estimates for Non-Intrusive Load Monitoring”, IEEE Transactions On Power Delivery, Vol. 10, pp. 1200–1210.

Liu, H., Wu, H. and Yu, C. (2019), “A Hybrid Model for Appliance Classification Based on Time Se-ries Features, Energy and Buildings, Vol. 196 pp. 112–123.

Liu, Y., Wang, X., You, W. (2018), “Non-Intrusive Load Monitoring by Voltage–Current Trajec-tory Enabled Transfer Learning”, IEEE Transa-ctions on Smart Grid, Vol. 10, pp. 5609–5619.

Liu, Y, Zhong, L, Qiu, J., Lu, J. and Wang W. 2021. Unsupervised Domain Adaptation For Non-Intrusive Load Monitoring Via Adversarial And Joint Adaptation Network, IEEE Transactions on Industrial Informatics, Vol. 18 pp. 266–277.

Machlev, R., Belikov, J., Beck, Y. and Levron, Y. (2019), “Mo-NILM: A Multi-Objective Evol-utionary Algorithm for NILM Classification”, Energy and Buildings, Vol. 199, pp. 134–144.

Marchiori, A., Hakkarinen D., Han, Q. and Earle, L. (2010), “Circuit-level Load Monitoring for Ho-usehold Energy Management, IEEE Pervasive Computing, Vol. 10, pp. 40–48.

Nejat, P., Jomehzadeh, F., Taheri, M. M., Gohari, M. and Majid, M. Z. A. (2015), “A Global Review of Energy Consumption, CO2 Emissi-ons and Policy in The Residential Sector (With An Overview Of The Top Ten Co2 Emitting Countries)”, Renewable and Sustainable Ener-gy Reviews, Vol 43, pp 843–862.

Patel, S. N., Robertson, T., Kientz, J. A., Reynolds, M. S. and Abowd, G. D. (2007), “At the flick of a switch: Detecting and classifying unique elec-trical events on the residential power line (nom-inated for the best paper award)”, In UbiComp 2007: Ubiquitous Computing: 9th International Conference, UbiComp 2007, Innsbruck, Austr-ia, September 16-19, 2007 Proceedings 9, pp. 271-288.

Quek, Y. T., Woo, W. L. and Logenthiran, T. (2019), Load Disaggregation Using One-Directional Convolutional Stacked Long Short-Term Memory Recurrent Neural Network”, IE-EE Systems Journal, Vol 14, pp. 1395–1404.

Rafati, A., Shaker, H. R. and Ghahghahzadeh, S. (2022), “Fault Detection and Efficiency Assess-ment for HVAC Systems Using Non-Intrusive Load Monitoring: A Review”, Energies 2022, 15 (1), p. 341.

Robert, A. and Kummert, M. (2012), “Designing Net-Zero Energy Buildings for the Future Clim-ate, Not for the Past”, Building and Enviro-nment. Vol. 55, pp. 150–158.

Rode, I. (2021), “Enhancing Residential Energy Conservation: A Review of Financial and Non-Financial Policy Instruments”

Sadeghianpourhamami, N., Ruyssinck, J., Deschrijver, D., Dhaene, T. and Develder, C. (2017), “Comprehensive Feature Selection For Appliance Classification In NILM”, Energy and Buildings, Vol. 151, pp. 98–106.

Shaw, S. R., Leeb, S. B., Norford, L. K. and Cox, R. W. (2008), “Nonintrusive Load Monitoring and Diagnostics in Power Systems”, IEEE Trans-actions on Instrumentation and Measurement. Vol. 57, pp. 1445–1454.

Truong, N. C., McInerney, J., Tran-Thanh, L., Costanza, E. and Ramchurn, S. D. (2013), “Forecasting Multi-Appliance Usage for Smart Home Energy Management”.

Vickers, N. J. (2017), “Animal Communication: When I’m Calling You, Will You Answer Too?”, Current Biology, Vol 27, pp. R713–R715.

Wang Z. and Zheng G. (2011), “Residential Appliances Identification and Monitoring by a Non-Intrusive Method”, IEEE transactions on Smart Grid. Vol. 3, pp. 80–92.

Xing Y, Hewitt N, Griffiths P. (2011), “Zero Carbon Buildings Refurbishment -A Hierarchical Pathway”, Renewable and Sustainable Energy Reviews. Vol. 15, pp. 3229–3236.

Yan, D., Jin, Y., Sun, H., Dong, B., Ye, Z. and Li, Z, Yuan, Y. (2019), “Household Appliance Recognition Through a Bayes Classification Model”, Sustainable Cities and Society, Vol. 46, pp. 101393.


Refbacks

  • There are currently no refbacks.