A Cloud-Based Energy Monitoring System Using IoT and Machine Learning
Finding means to encourage consumers to monitor their energy use is an important step toward optimizing on depleting natural resources used for energy production. The current proposal employs cloud computing and machine learning to analyze energy data collected from a nonintrusive IoT system to display energy consumption from several appliances connected to the same power line. For scalability purpose, all collected data from sensors are processed on the cloud and useful information such as appliance monitored and energy consumed can easily be accessed on a mobile app. Preliminary results indicate that the proposed system promises to be a suitable alternative for traditional monitoring systems to deliver instant and historical energy consumption data to consumers, who can, in turn, adopt efficient and smarter ways to use energy.
KeywordsIoT Machine learning Energy monitoring Cloud computing
Special thanks goes to Mr. Y. Beeharry from the University of Mauritius FoICDT computer lab for his valuable advice during the implementation phase of the prototype.
- 2.Basu, K.: Classification techniques for non-intrusive load monitoring and prediction of residential loads. Doctoral dissertation, University of Grenoble (2014)Google Scholar
- 3.Mashuque, E., Shaikh, R.H., Nafis, A.K., Hafiz, A.R.: Smart energy monitoring using off the-shelf hardware and software tools. In: IASTED International Conference on Power and Energy Systems, pp. 160–167. Thailand (2013)Google Scholar
- 4.Wood, G., Newborough, M.: Influencing user behaviour with energy information display systems for intelligent homes. J. Energy Res. 39(4), 495–503 (2007)Google Scholar
- 8.Sundramoorthy, V., Liu, Q., Cooper, G., Linge, N., Cooper, J.: DEHEMS: a user-driven domestic energy monitoring system. In: Internet of Things (IOT), pp. 1–8. Tokyo (2010)Google Scholar
- 9.Darby, S.: The effectiveness of feedback on energy consumption. Technical Report. Environmental Change Institute, University of Oxford (2006)Google Scholar
- 10.Noman, A.A., Rahaman, M.F., Ullah, H., Das, R.K.: Android based smart energy meter. In: 4th National Conference on Natural Science and Technology, pp. 1–3. Bangladesh (2017)Google Scholar
- 11.Mashuque, E., Shaikh, R.H., Nafis, A.K., Hafiz, A.R.: Smart energy monitoring using off the-shelf hardware and software tools. In: IASTED International Conference on Power and Energy Systems, pp. 160–167. Thailand (2013)Google Scholar
- 12.Fatima, E.B.: Smart home energy management system monitoring and control of appliances using an arduino based network in the context of a micro-grid. Dissertation, Al Akhawayn University, Morocco (2015)Google Scholar
- 14.Tamizharasi, G., Kathiresan, S., Sreenivasan, K.S.: Energy forecasting using artificial neural networks. Energy 3(3), 7568–7576 (2014)Google Scholar
- 19.Kushiro, N., Ide, T., Tomonaga, K., Ogawa, Y., Higuma, T.: Can electric devices be identified from their signatures of waveform? In: 12th Annual IEEE Consumer Communications and Networking Conference (CCNC), pp. 531–536. Las Vegas (2015)Google Scholar
- 20.Fogarty C., Carolyn A., Hudson, S.E.: Sensing from the basement: a feasibility study of unobtrusive and low-cost home activity recognition. In: Proceedings of the 19th Annual ACM Symposium on User Interface Software and Technology, pp. 91–100. Switzerland (2006)Google Scholar