An efficient and inexpensive method for activity recognition within a smart home based on load signatures of appliances

Abstract

With the increasing demand in terms of non-intrusive appliance load monitoring (NIALM), more and more smart meters and smart analyzers were released on the market to extract well-defined load signatures and/or for performing autonomously the various monitoring operations as needed. Nevertheless, this hardware proves to be very expensive and not necessarily accessible to all. Moreover, most applications resulting of the use of these smart devices simply refer to energy saving and costs reducing of energy consumption. Thus, this paper proposes a new algorithmic method for an application field that is still very lightly exploited, i.e. the activity recognition of reduced-autonomy residents living in a smart habitat through load signatures. This one is based on steady-state operations and signatures and its extraction process of load signatures of appliances is carried out in a three-dimensional space through a single power analyzer which is non-intrusive (NIALM). This approach has been tested and verified rigorously through daily scenarios reproduced in the smart home prototype in a laboratory.. Hence, we can affirm that, with an exceptionally minimal investment and the exploitation of especially limited data, our method can recognize the use of appliances with high precision and low-cost allowing us to compete with other approaches which are much more expensive and require supplementary equipment.

Experimental Results on a Wireless Wattmeter Device for the Integration in Home Energy Management Systems

“…The reactive energy is performed in analog domain as an infinite integral of the instantaneous shifted phase voltage delayed by 90° and phase current signal given by: (22) where ∆ = 1/ is the sampling time, .…”

Development of distinct load signatures for higher efficiency of NILM algorithms

“…Although the authors utilize a sampling frequency two times larger than the one in this paper the identification rate is below 90%. In a recent published research [27], load signatures are formulated in a three dimensional space under the steady state. The results prove that the algorithm is efficient enough but the sampling frequency is relatively low.…”

Dealing with Demand in Electric Grids with an Adaptive Consumption Management Platform

“…In the year 2014, Belley et al [2] had already used a smart meter to obtain a house's consumption data. The authors made use of the activation periods of appliances that were in the house.…”