Unsupervised Residential Power Usage Monitoring Using a Wireless Sensor Network

Abstract

Appliance-level power usage monitoring may help conserve electricity in homes. Several existing systems achieve this goal by exploiting appliances’ power usage signatures identified in labor-intensive in situ training processes. Recent work shows that autonomous power usage monitoring can be achieved by supplementing a smart meter with distributed sensors that detect the working states of appliances. However, sensors must be carefully installed for each appliance, resulting in a high installation cost. This article presents Supero —the first ad hoc sensor system that can monitor appliance power usage without supervised training. By exploiting multisensor fusion and unsupervised machine learning algorithms, Supero can classify the appliance events of interest and autonomously associate measured power usage with the respective appliances. Our extensive evaluation in five real homes shows that Supero can estimate the energy consumption with errors less than 7.5%. Moreover, nonprofessional users can quickly deploy Supero with considerable flexibility.

A More Efficient Technique to Power Home Monitoring Systems Using Controlled Battery Charging

“…Sensors are used to measure various parameters of interest, and a communications system allows information to be gathered for decision making. Sensors related to energy monitoring measure parameters such as electric current consumption, power consumption, energy consumption, luminosity, movement detection, and acoustic event detection [8][9][10][11]. The major air quality parameters to be measured are carbon dioxide (CO 2 ), carbon monoxide (CO), sulfur dioxide (SO 2 ), nitrogen dioxide (NO 2 ), ozone (O 3 ), volatile organic compounds (VOC), particulate matter (PM), ambient temperature, and relative humidity [6,[12][13][14].…”

“…Several communication systems have been proposed to transmit the collected data. Many studies use Zigbee, based on the protocol IEEE802.15.4, created to support the area of wireless sensor networks [6,9,[16][17][18][19]. Bluetooth low energy (BLE) is also proposed for the communication system [20], while Bluetooth can be applied to configure smart devices [21].…”

“…Alkaline or lithium batteries are used when the sensor nodes can go into sleep mode most of the time. In this situation, the published works state that these systems must be able to operate for many weeks without changing the batteries [9]. However, this is only possible because the sampling frequency is very low.…”