Home Occupancy Classification Using Machine Learning Techniques along with Feature Selection

Home Occupancy Classification Using Machine Learning Techniques along with Feature Selection

Автор: Abdullah-Al Nahid, Niloy Sikder, Mahmudul Hasan Abid, Rafia Nishat Toma, Iffat Ara Talin, Lasker Ershad Ali

Журнал: International Journal of Engineering and Manufacturing @ijem

Статья в выпуске: 3 vol.12, 2022 года.

Бесплатный доступ

Monitoring systems for electrical appliances have gained massive popularity nowadays. These frameworks can provide consumers with helpful information for energy consumption. Non-intrusive load monitoring (NILM) is the most common method for monitoring a household’s energy profile. This research presents an optimized approach for identifying load needs and improving the identification of NILM occupancy surveillance. Our study suggested implementing a dimensionality reduction algorithm, popularly known as genetic algorithm (GA) along with XGBoost, for optimized occupancy monitoring. This exclusive model can masterly anticipate the usage of appliances with a significantly reduced number of voltage-current characteristics. The proposed NILM approach pre-processed the collected data and validated the anticipation performance by comparing the outcomes with the raw dataset’s performance metrics. While reducing dimensionality from 480 to 238 features, our GA-based NILM approach accomplished the same performance score in terms of accuracy (73%), recall (81%), ROC-AUC Score (0.81), and PR-AUC Score (0.81) like the original dataset. This study demonstrates that introducing GA in NILM techniques can contribute remarkably to reduce computational complexity without compromising performance.

Еще

Occupancy, Energy Consumption, XGBoost, Genetic Algorithm, Feature Selection

Короткий адрес: https://sciup.org/15018417

IDR: 15018417   |   DOI: 10.5815/ijem.2022.03.04

Список литературы Home Occupancy Classification Using Machine Learning Techniques along with Feature Selection

  • M. Kahl, A. Haq, T. Kriechbaumer, and H. Jacobsen. (1994). “A Comprehensive Feature Study for Appliance Recognition on High Frequency Energy Data,” e-Energy, 2017, doi: 10.1145/3077839.3077845.Franklin, M.A. & Pan, T.. Performance Comparison of Asynchronous Adders. In: Symp. on Advanced Research in Asynchronous Circuits and Systems, pp. 117-125.
  • D. De Silva, X. Yu, D. Alahakoon, and G. Holmes. (2011). “A Data Mining Framework for Electricity Consumption Analysis From Meter Data,” IEEE Transactions on Industrial Informatics, vol. 7, no. 3, pp. 399–407, doi: 10.1109/TII.2011.2158844.
  • K. Amasyali and N. M. El-Gohary. (2018). “A review of data-driven building energy consumption prediction studies,” Renewable and Sustainable Energy Reviews, vol. 81, pp. 1192–1205, doi: 10.1016/j.rser.2017.04.095.
  • Z. Wang and Y. Ding. (2015). “An occupant-based energy consumption prediction model for office equipment,” Energy and Buildings, vol. 109, pp. 12–22, Dec. doi: 10.1016/j.enbuild.2015.10.002.
  • J. Z. Kolter and T. Jaakkola, (2012). “Approximate Inference in Additive Factorial HMMs with Application to Energy Disaggregation,” in Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, pp. 1472–1482. Accessed: Mar. 11, 2022. [Online]. Available: https://proceedings.mlr.press/v22/zico12.html
  • F. Li, Xu et al., (2018). “Classifier economics of Semi-Intrusive Load Monitoring,” International Journal of Electrical Power & Energy Systems, vol. 103, pp. 224–232, doi: 10.1016/j.ijepes.2018.05.010.
  • “Climate Change Act 2008.” https://www.legislation.gov.uk/ukpga/2008/27/contents/enacted (accessed Mar. 11, 2022).
  • N. Sadeghianpourhamami, J. Ruyssinck, D. Deschrijver, T. Dhaene, and C. Develder, (2017). “Comprehensive feature selection for appliance classification in NILM,” Energy and Buildings, vol. 151, pp. 98–106, doi: 10.1016/j.enbuild.2017.06.042.
  • T. Saitoh, T. Osaki, R. Konishi, and K. Sugahara, (2009). “Current Sensor Based Home Appliance and State of Appliance Recognition,” SICE Journal of Control, Measurement, and System Integration, vol. 3, pp. 86–93, doi: 10.9746/jcmsi.3.86.
  • H.-T. Yang, H.-H. Chang, and C.-L. Lin. (2007). “Design a Neural Network for Features Selection in Non-intrusive Monitoring of Industrial Electrical Loads,” 2007 11th International Conference on Computer Supported Cooperative Work in Design, doi: 10.1109/CSCWD.2007.4281579.
  • “EIA’s Annual Energy Outlook 2017,” Global Energy Institute. https://www.globalenergyinstitute.org/eias-annual-energy-outlook-2017 (accessed Mar. 11, 2022).
  • J. Alcalá, J. Ureña, Á. Hernández, and D. Gualda, (2017). “Event-Based Energy Disaggregation Algorithm for Activity Monitoring From a Single-Point Sensor,” IEEE Transactions on Instrumentation and Measurement, vol. 66, no. 10, pp. 2615–2626, doi: 10.1109/TIM.2017.2700987.
  • M. Dash and H. Liu. (1997). “Feature selection for classification,” Intelligent Data Analysis, vol. 1, no. 1, pp. 131–156, doi: 10.1016/S1088-467X(97)00008-5.
  • Y.-C. Su, K.-L. Lian, and H.-H. Chang, (2011). “Feature Selection of Non-intrusive Load Monitoring System Using STFT and Wavelet Transform,” in 2011 IEEE 8th International Conference on e-Business Engineering, pp. 293–298. doi: 10.1109/ICEBE.2011.49.
  • L. Mengqi, J. Gao, and Z. Li. (2018). Functional Intrusive Load Monitor (FILM): A Model-based Platform for Non-Intrusive Load Monitoring System Development.
  • K. Carrie Armel, A. Gupta, G. Shrimali, and A. Albert, (2013). “Is disaggregation the holy grail of energy efficiency? The case of electricity,” Energy Policy, vol. 52, no. C, pp. 213–234.
  • G. Castagneto Gissey, P. E. Dodds, and J. Radcliffe, (2018). “Market and regulatory barriers to electrical energy storage innovation,” Renewable and Sustainable Energy Reviews, vol. 82, pp. 781–790, doi: 10.1016/j.rser.2017.09.079.
  • R. Machlev, Y. Levron, and Y. Beck, (2019). “Modified Cross-Entropy Method for Classification of Events in NILM Systems,” IEEE Transactions on Smart Grid, vol. 10, no. 5, pp. 4962–4973, doi: 10.1109/TSG.2018.2871620.
  • M. Xia, W. Liu, K. Wang, Z. Xu, and Y. Xu. (2019). “Non-intrusive load disaggregation based on deep dilated residual network,” Electric Power Systems Research, vol. 170, pp. 277–285, doi: 10.1016/j.epsr.2019.01.034.
  • A. Zoha, A. Gluhak, M. A. Imran, and S. Rajasegarar, (2019). “Non-Intrusive Load Monitoring Approaches for Disaggregated Energy Sensing: A Survey,” Sensors, vol. 12, no. 12, Art. no. 12, doi: 10.3390/s121216838.
  • G. W. Hart, (1992) “Nonintrusive appliance load monitoring,” Proceedings of the IEEE, vol. 80, no. 12, pp. 1870–1891 doi: 10.1109/5.192069.
  • M. Zeifman and K. Roth, (2011). “Nonintrusive appliance load monitoring: Review and outlook,” IEEE Transactions on Consumer Electronics, vol. 57, no. 1, pp. 76–84, doi: 10.1109/TCE.2011.5735484.
  • J. Gao, S. Giri, E. C. Kara, and M. Bergés, (2014). “PLAID: a public dataset of high-resoultion electrical appliance measurements for load identification research: demo abstract,” in Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings, New York, NY, USA, Nov. pp. 198–199. doi: 10.1145/2674061.2675032.
  • I. Rahman, M. Kuzlu, and S. Rahman. (2018). “Power disaggregation of combined HVAC loads using supervised machine learning algorithms,” Energy and Buildings, vol. 172, pp. 57–66, doi: 10.1016/j.enbuild.2018.03.074.
  • J. P. Kelly and M. A. James. (2016). “Radiographic Outcomes of Hemiepiphyseal Stapling for Distal Radius Deformity Due to Multiple Hereditary Exostoses,” Journal of Pediatric Orthopaedics, vol. 36, no. 1, pp. 42–47, doi: 10.1097/BPO.0000000000000394.
  • J. A. Short, D. G. Infield, and L. L. Freris. (2007). “Stabilization of Grid Frequency Through Dynamic Demand Control,” IEEE Transactions on Power Systems, vol. 22, no. 3, pp. 1284–1293, doi: 10.1109/TPWRS.2007.901489.
  • S. Darby, (2006) “The Effectiveness of Feedback on Energy Consumption: A Review of the Literature on Metering, Billing and Direct Displays,” .
  • K. Basu, V. Debusschere, A. Douzal-Chouakria, and S. Bacha, (2015). “Time series distance-based methods for non-intrusive load monitoring in residential buildings,” Energy and Buildings, vol. 96, pp. 109–117 doi: 10.1016/j.enbuild.2015.03.021.
  • J. Abreu, F. Pereira, and P. Ferrão, (2012). “Using pattern recognition to identify habitual behavior in residential electricity consumption,” Energy and Buildings, vol. 49, pp. 479–487, doi: 10.1016/j.enbuild.2012.02.044.
  • T. Chen and C. Guestrin. (2016). “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA, pp. 785–794. doi: 10.1145/2939672.2939785.
  • “Chen and He - xgboost eXtreme Gradient Boosting.pdf.” Accessed: Mar. 11, 2022. [Online]. Available: https://cran.r-project.org/web/packages/xgboost/vignettes/xgboost.pdf
  • Computer Science and Engineering, SRM Institute of Science and Technology, Chennai, India. et al. (2019). “Network Intrusion Detection System using XG Boost,” IJEAT, vol. 9, no. 1, pp. 4070–4073, doi: 10.35940/ijeat.A1307.109119.
  • H. Musa, D. A. Y. Gital, F. U. Zambuk, A. Umar, A. Y. Umar, and J. U. Waziri. (2005). “A COMPARATIVE ANALYSIS OF PHISHING WEBSITE DETECTION USING XGBOOST ALGORITHM,” . Vol., no. 5, p. 10.
  • H.-S. Choi et al. (2018). “XGBoost-Based Instantaneous Drowsiness Detection Framework Using Multitaper Spectral Information of Electroencephalography,” in Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, New York, NY, USA, pp. 111–121. doi: 10.1145/3233547.3233567.
  • C. Krupitzer, T. Sztyler, J. Edinger, M. Breitbach, H. Stuckenschmidt, and C. Becker. (2019). “Beyond position-awareness—Extending a self-adaptive fall detection system,” Pervasive and Mobile Computing, vol. 58, p. 101026, doi: 10.1016/j.pmcj.2019.05.007.
  • “XGBoost Parameters | XGBoost Parameter Tuning.” https://www.analyticsvidhya.com/blog/2016/03/complete-guide-parameter-tuning-xgboost-with-codes-python/ (accessed Mar. 11, 2022).
  • lgayhardt, “Machine Learning Algorithm Cheat Sheet - designer - Azure Machine Learning.” https://docs.microsoft.com/en-us/azure/machine-learning/algorithm-cheat-sheet (accessed Mar. 11, 2022).
  • “ECO data set (Electricity Consumption & Occupancy) A Research Project of the Distributed Systems Group.” http://vs.inf.ethz.ch/res/show.html?what=eco-data.
  • W. Kleiminger, C. Beckel, and S. Santini. (2015). “Household occupancy monitoring using electricity meters,” UbiComp 2015 - Proc. 2015 ACM Int. Jt. Conf. Pervasive Ubiquitous Comput., pp. 975–986, doi: 10.1145/2750858.2807538.
  • C. Beckel, W. Kleiminger, R. Cicchetti, T. Staake, and S. Santini. (2014). “The ECO data set and the performance of non-intrusive load monitoring algorithms,” BuildSys 2014 - Proc. 1st ACM Conf. Embed. Syst. Energy-Efficient Build., pp. 80–89, doi: 10.1145/2674061.2674064.
  • C. Oh and J. Jeong, (2020). “Non-intrusive Load Monitoring Based on Regularized ResNet with Multivariate Control Chart,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 12250 LNCS, pp. 646–661, doi: 10.1007/978-3-030-58802-1_47.
  • W. Kleiminger, C. Beckel, T. Staake, and S. Santini. (2013) “Occupancy detection from electricity consumption data,” BuildSys 2013 - Proc. 5th ACM Work. Embed. Syst. Energy-Efficient Build., doi: 10.1145/2528282.2528295.
  • Fazli Wahid, Rozaida Ghazali, Muhammad Fayaz, Abdul Salam Shah. (2017)."Statistical Features Based Approach (SFBA) for Hourly Energy Consumption Prediction Using Neural Network", International Journal of Information Technology and Computer Science (IJITCS), Vol.9, No.5, pp.23-30, 2017. DOI: 10.5815/ijitcs.2017.05.04.
  • N. Chabbah Sekma, A. Elleuch, N. Dridi, (2016). "Automated Forecasting Approach Minimizing Prediction Errors of CPU Availability in Distributed Computing Systems", International Journal of Intelligent Systems and Applications(IJISA), Vol.8, No.9, pp.8-21, 2016. DOI: 10.5815/ijisa.2016.09.02.
  • Manisha Verma, Neelam Bhardwaj, Arun Kumar Yadav,"Real Time Efficient Scheduling Algorithm for Load Balancing in Fog Computing Environment", International Journal of Information Technology and Computer Science(IJITCS), Vol.8, No.4, pp.1-10, 2016. DOI: 10.5815/ijitcs.2016.04.01.
  • M. Hasan, R. N. Toma, A.-A. Nahid, Mm. Islam, and J.-M. Kim, (2019). “Electricity theft detection in smart grid systems: A CNN-LSTM based approach,” Energies, vol. 12, no. 17, p. 3310, 2019.
  • R. N. Toma, M. N. Hasan, A.-A. Nahid, and B. Li, (2019). “Electricity theft detection to reduce non-technical loss using support vector machine in smart grid,” in 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), 2019, pp. 1–6.
  • “Load Signature Study—Part I: Basic Concept, Structure, and Methodology | IEEE Journals & Magazine | IEEE Xplore.” https://ieeexplore.ieee.org/document/5337912 (accessed May 07, 2022).
  • J. Gao, E. Kara, S. Giri, and M. Bergés, (2015) “A feasibility study of automated plug-load identification from high-frequency measurements,” 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), doi: 10.1109/GlobalSIP.2015.7418189.
Еще
Статья научная
QR-код для установки приложения SciUp Наведите камеру и скачайте бесплатное приложение SciUp