Non-intrusive load monitoring and deep learning applied to Ambient Assisted Living
Mentor: Álvaro Hernández Alonso and Jesús Ureña Ureña
Phone: (+34) 918856583
University: Universidad de Alcalá
Partner Host Institution: ATOS
Keywords: .- Non-Intrusive Load Monitoring (NILM) based on Smart Meters. .- Techniques for energy disaggregation and power demand prediction. .- Techniques to promote efficient consumption and distribution. .- Deep learning. .- Inference of activity routines and patterns. .-Ambient Assisted Living (AAL).

Non-intrusive load monitoring and deep learning applied to Ambient Assisted Living

The massive deployment of smart meters and other customized meters has motivated the development of non-intrusive load monitoring (NILM) systems. This is the process of disaggregating the total energy consumption in a building or household into individual electrical loads using a single-point sensor. This information can be oriented to different applications, such as power demand prediction or efficient consumption and monitoring. On the other hand, the ageing of the population has raised the interest in homecare monitoring systems and assisted living in recent years. Most studies pursue non-intrusiveness and scalability to meet the requirements of this ever-growing community. Nonetheless, they are still limited by the technique: wearables need to be carried and sensor networks imply installation.
NILM and smart meters imply a new approach to monitor elderlies by using one single sensor, enabling scalability and non-intrusiveness. The energy disaggregation and appliance identification are actually the foundations, where a deep learning approach can propose novel methods to identity, determine and analyse behaviours, patterns and routines in the daily activities of people living in the households under analysis. These methods can provide relatives and carers with a powerful tool to evaluate and/or infer a person’s situation with a null intrusiveness over time, not only in the short but also in the long term.

Departament: Electronics
Research Group: Electronic Engineering Applied to Intelligent Spaces and Transport Group
More Information:
Relevants projects on the area: Efficient SoC-based architectures for realiable physical layer technologies in powerline communications (SOC-PLC). Ministry of Economy and Competitiveness (ref. TEC2015-64835-C3-2-R). Universidad de Alcalá, Universidad Politécnica de Madrid. 2016/2018. IP: Álvaro Hernández Alonso.
Relevants publications on the area: 1.- J. M. Alcalá, J. Ureña, A. Hernández, D. Gualda. Sustainable Homecare Monitoring System by Sensing Electricity Data. IEEE Sensors Journal, vol. 17(23), pp. 7741-7749, 2017.
2.- J. Alcalá, J. Ureña, A. Hernández, D. Gualda. Event-based Energy Disaggregation Algorithm for Activity Monitoring from a Single-Point Sensor. IEEE Transactions on Instrumentation & Measurement, vol. 66(10), pp. 2615-2626, 2017.