SocketWatch: An autonomous appliance monitoring system

Abstract

A significant amount of energy is wasted by electrical appliances when they operate inefficiently either due to anomalies and/or incorrect usage. To address this problem, we present SocketWatch -an autonomous appliance monitoring system. SocketWatch is positioned between a wall socket and an appliance. SocketWatch learns the behavioral model of the appliance by analyzing its active and reactive power consumption patterns. It detects appliance malfunctions by observing any marked deviations from these patterns.SocketWatch is inexpensive and is easy to use: it neither requires any enhancement to the appliances nor to the power sockets nor any communication infrastructure. Moreover, the decentralized approach avoids communication latency and costs, and preserves data privacy. Real world experiments with multiple appliances indicate that SocketWatch can be an effective and inexpensive solution for reducing electricity wastage.

Evaluation of Non-intrusive Load Monitoring Algorithms for Appliance-level Anomaly Detection

“…The analysis of cyclical appliances shows that anomalies are reflected in the appliance signature in two ways: (i) the appliance has a longer on duration, possibly due to appliance malfunctioning, fridge/freezer door left open, cracked door, or mis-configured settings [10]; (ii) the appliance goes through a significantly higher number of cycles as compared to normal operation [19]. This is due to appliance malfunctioning, due to age or a fault.…”

“…Detecting anomalies by monitoring the energy consumption of an appliance over some time has been the subject of research. For example, Ganu et al [10] first create appliance specific energy models of several high energy consuming appliances and then use built models to identify anomalies. Similarly, Pereira et al [11] use clustering to identify anomalies by comparing the usage of an appliance along a period.…”

Smart power consumption abnormality detection in buildings using micromoments and improved K‐nearest neighbors

“…Different techniques have been proposed in the literature, such as DBSCAN, LOF, and Isolation Forest. In Reference [39], the authors design device‐specific power consumption models for a set of electrical appliances and thereby utilize developed models to detect abnormalities for each appliance operation cycle using its specific setting parameters. In a similar way, a clustering approach is implemented in Reference [40], which aims at detecting anomalous consumption via the comparison of device consumption fingerprints with developed models through various periods of time.…”

A Practical Approach to Residential Appliances on-Line Anomaly Detection: A Case Study of Standard and Smart Refrigerators

“…Indeed, the above remarks make refrigerators an appropriate candidate for an in-depth anomaly detection investigation with regard to twosate operation-time appliances. It should be noted that this appliance has been also an interesting candidate for anomaly detection analysis in other researches [13], [29].…”

“…In fact, NILM barriers to a useful anomaly detection stimulates taking advantage of sub-metered measurements with regard to low-priced smart plugs technology. Accordingly, Ganu et al have provided a limited study about an appliancelevel monitoring system [29]. They have utilized several electrical features to explain appliances behavior.…”