Residential appliance clustering based on their inherent characteristics for optimal use based K-means and hierarchical clustering method
محورهای موضوعی :
Shima Simsar
1
,
Mahmood Alborzi
2
,
Ali Rajabzadeh Ghatari
3
,
Ali Yazdian Varjani
4
1 - Department of Information Technology Management, Faculty of Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran
2 - Department of Information Technology Management, Faculty of Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran
3 - Department of Management, Faculty of Management and Economics, Tarbiat Modares University, Tehran, Iran
4 - Department of Electrical Engineering, Faculty of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran
کلید واژه: Demand Response, k-means clustering, Hierarchical Clustering, Appliance,
چکیده مقاله :
With global warming and energy shortages, smart grids have become a significant issue in the power grid. Demand response is one of the basic factors of smart grids. To enhance the efficiency of demand response, an intelligent home appliance control system is essential, which prioritizes the start-up of electrical appliances according to the necessity of use and efficiency. To properly manage the demand response, utilities use different signals such as price. One of the pricing methods that can be considered is different pricing for electrical appliance clusters. In this article, appliances are clustered by the K-means and hierarchical clustering based on the characteristics of the appliances themselves, such as the appliances’ extent of consumption, the type of use of home appliances, how home appliances work, the ability to change the working conditions of home appliances, home appliances usage time, etc. It seems that the K-means clustering method outperforms the hierarchical method in this issue, due to its lower value of DB coefficient. In this method, home appliances were classified into three clusters. The silhouette coefficient was developed as a measure of the K-means clustering model performance, where the average silhouette coefficient of 0.6 indicates the satisfactory value of the model. Based on the results, it was found that the proposed clustering method can rationally classify different types of home appliances by selecting the appropriate characteristics since the appliances in a cluster are very similar to each other and can help users understand the operating conditions of the appliances.
With global warming and energy shortages, smart grids have become a significant issue in the power grid. Demand response is one of the basic factors of smart grids. To enhance the efficiency of demand response, an intelligent home appliance control system is essential, which prioritizes the start-up of electrical appliances according to the necessity of use and efficiency. To properly manage the demand response, utilities use different signals such as price. One of the pricing methods that can be considered is different pricing for electrical appliance clusters. In this article, appliances are clustered by the K-means and hierarchical clustering based on the characteristics of the appliances themselves, such as the appliances’ extent of consumption, the type of use of home appliances, how home appliances work, the ability to change the working conditions of home appliances, home appliances usage time, etc. It seems that the K-means clustering method outperforms the hierarchical method in this issue, due to its lower value of DB coefficient. In this method, home appliances were classified into three clusters. The silhouette coefficient was developed as a measure of the K-means clustering model performance, where the average silhouette coefficient of 0.6 indicates the satisfactory value of the model. Based on the results, it was found that the proposed clustering method can rationally classify different types of home appliances by selecting the appropriate characteristics since the appliances in a cluster are very similar to each other and can help users understand the operating conditions of the appliances.
Azab, A., & Naderi, B. (2014). A variable neighborhood search metaheuristic for cellular manufacturing with multitask machine tools. Procedia CIRP, 20, 50-55.
Abudalfa, Sh., & Mikki, M. (2013). K-means algorithm with a novel distance measure. Turkish Journal of Electrical Engineering and Computer Sciences, 21(6), 1665-1684. doi:10.3906/elk-1010-869
Alborzi, M., Alikhani, M. (2016). Machine Learning. Sharif University of Technology's Press, Tehran, Iran.
Bagherighadikolaei, S., Ghousi, R., & Haeri, A. (2020). A Data Mining approach for forecasting failure root causes: A case study in an Automated Teller Machine (ATM) manufacturing company. Journal of Optimization in Industrial Engineering, 13(2), 101-121. doi: 10.22094/joie.2020.1863364.1630
Cen, S., Yoo, J.H. and Lim, C.G. (2022). Electricity Pattern Analysis by Clustering Domestic Load Profiles Using Discrete Wavelet Transform. Energies. 15(4), 1350. doi:10.3390/en15041350
Chhabra,G., Vashisht, V. & Ranjan, J. (2019). Crime Prediction Patterns Using Hybrid K-Means Hierarchical Clustering. Journal of Advanced Research in Dynamical and Control Systems, 11, 1249-1258.
Czétány,L., Vámos,V., Horváth,M., SzalayZ., Mota-Babiloni,A., Deme-Bélafi,Z., Csoknyai,T. (2021). Development of electricity consumption profiles of residential buildings based on smart meter data clustering. Energy and Buildings, 252, 111376. doi: 10.1016/j.enbuild.2021.111376
Davies, D.L., Bouldin, D.W.(2019). Hierarchical Clustering based on IndoorGML Document. IEEE Transactions on Pattern Analysis and Machine Intlligence, 177-182. doi: 10.1109/Informatics47936.2019.9119255
Delmastro, C., Lavagno, E. & Mutani, G. (2015). Chinese residential energy demand: scenarios to 2030 and policies implication. Energy Build, 89, 49–60. doi: 10.1016/j.enbuild.2014.12.004
Earle,R., Faruqui,A. (2006). Toward a new paradigm for valuing demand response. The Electricity Journal, 19(4), 21–31. doi: 10.1016/j.tej.2006.03.006
faezy razi, F., & Shadloo, N. (2017). A Hybrid Grey based Two Steps Clustering and Firefly Algorithm for Portfolio Selection. Journal of Optimization in Industrial Engineering, 10(22), 49-59. doi: 10.22094/joie.2017.276
Haider, H.T., See, O.H. & Elmenreich, W. (2016). A review of residential demand response of smart grid. Renewable and Sustainable Energy Reviews, 59, 166–178. doi: 10.1016/j.rser.2016.01.016
Han, J., Kamber, M. & Pei, J. (2012). Data Mining,Concepts and Techniques. Third Edition, Morgan Kaufmann, Waltham, MA, USA.
Hassan, N.U., Khalid, Y.I, Yuen,C., Huang,S., Pasha, M.A. et al. (2016). Framework for minimum user participation rate determination to achieve specific demand response management objectives in the residential smart grids. International Journal of Electrical Power & Energy Systems, 74, 91–103. doi: 10.1016/j.ijepes.2015.07.005
Iqbal, Z., Javaid, N., Iqbal, S., Aslam, Sh., Khan, Z.A. et al. (2018). A Domestic Microgrid with Optimized Home Energy Management System. Energies, 11(4). doi: 10.3390/en11041002
Javaid, S., Javaid, N., Javaid, M.Sh., Javaid, S., Qasim, U. et al. (2016). Optimal Scheduling in Smart Homes with Energy Storage Using Appliances' Super-Clustering. 10th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS), IEEE Press, Fukuoka, Japan, 342-348. doi: 10.1109/IMIS.2016.130
Jeong, HC., Jang, M., Kim, T., Joo, S-K. (2021). Clustering of Load Profiles of Residential Customers Using Extreme Points and Demographic Characteristics. Electronics, 10(3), 290. doi: 10.3390/electronics10030290
Kostková,K., Omelina,L., Kyčina, P., Jamrich, P. (2013). An introduction to load management. Electric Power Systems Research, 95, 184–191. doi: 10.1016/j.epsr.2012.09.006
Leroy,Y., Yannou, B. (2018). An activity-based modelling framework for quantifying occupants’ energy consumption in residential buildings. Computers in Industry, 103, 1-13. doi: 10.1016/j.compind.2018.08.009
Li, M., Li, G.Y., Chen, H.R., Jiang, C.W. (2018). QoE-Aware Smart Home Energy Management Considering Renewables and Electric Vehicles. Energies, 11(9). doi: doi.org/10.3390/en11092304
McLoughlin, F., Duffy, A., Conlon, M. A. (2015). Clustering approach to domestic electricity load profile characterisation using smart metering data. Applied Energy, 141, 190-199. doi: 10.1016/j.apenergy.2014.12.039
Muratori, M., Rizzoni, G. (2016). Residential Demand Response: Dynamic Energy Management and Time-Varying Electricity Pricing. IEEE Transactions on Power Systems, 31(2), 1108-1117. doi: 10.1109/TPWRS.2015.2414880
Olamaei, J., Ashouri, S. (2015). Demand response in the day-ahead operation of an isolated microgrid in the presence of uncertainty of wind power. Turkish Journal of Electrical Engineering and Computer Sciences, 23(2), 491-504. doi:10.3906/elk-1301-164
Rajabi,A., Eskandari,M., Jabbari,M., Li, Li, Zhang, J., Pierluigi, S. (2020). A comparative study of clustering techniques for electrical load pattern segmentation, Renewable and Sustainable Energy Reviews, 120, 109628. doi: 10.1016/j.rser.2019.109628
Rasheed, M.B., Javaid, N., Ahmad, A., Jamil, M., Khan, Z.A. et al. (2016). Energy Optimization in Smart Homes Using Customer Preference and Dynamic Pricing. Energies, 9(8). doi: 10.3390/en9080593
Semeraro, C., Lezoche, M., Panetto, H., Dassisti, M. (2021). Digital twin paradigm: A systematic literature review. Computers in Industry, 130. doi: 10.1016/j.compind.2021.103469
Shirazi, E., Jadid, Sh. (2015). Optimal residential appliance scheduling under dynamic pricing scheme via HEMDAS. Energy and Buildings, 93, 40-49. doi: 10.1016/j.enbuild.2015.01.061
Si, C., Xu, S., Wan, C., Chen, D., Cui, W. and Zhao, J. (2021). Electric Load Clustering in Smart Grid: Methodologies, Applications, and Future Trends. Modern Power Systems and Clean Energy, 9(2), 237-252. doi:10.35833/MPCE.2020.000472
Siano, P. (2014). Demand response and smart grids—a survey. Renewable and Sustainable Energy Reviews, 30, 461-478. doi: 10.1016/j.rser.2013.10.022
Tamas, J. (2019). Hierarchical Clustering based on IndoorGML Document. 15th International Scientific Conference on Informatics, IEEE Press, Poprad, Slovakia, 177-182. doi: 10.1109/Informatics47936.2019.9119255
Tambunan, H. B., Barus, D. H., Hartono, J., Alam, A. S., Nugraha, D. A. and Usman, H. H. H. (2020). Electrical Peak Load Clustering Analysis Using K-Means Algorithm and Silhouette Coefficient. International Conference on Technology and Policy in Energy and Electric Power (ICT-PEP), Bandung, Indonesia, 258-262. doi:10.1109/ICT-PEP50916.2020.9249773
Tian, K., Li, J., Zeng, J., Evans, A., Zhang, L. (2019). Segmentation of tomato leaf images based on adaptive clustering number of K-means algorithm. Computers and Electronics in Agriculture, 165. doi: 10.1016/j.compag.2019.104962
Wang, Z., Srinivasan, R.S. (2015). Classification of Household Appliance Operation Cycles: A Case-Study Approach. Energies, 8(9), 10522-10536. doi: 10.3390/en80910522
Warren, P. (2014). A review of demand-side management policy in the UK. Renewable and Sustainable Energy Reviews, 29, 941–951. doi: 10.1016/j.rser.2013.09.009
Zahedi, A. (2011). A review of drivers, benefits, and challenges in integrating renewable energy sources in to electricity grid. Renewable and Sustainable Energy Reviews, 15(9), 4775–4779. doi: 10.1016/j.rser.2011.07.074
