Rule-Based Non-Intrusive Load Monitoring Using Steady-State Current Waveform Features

Abstract

Monitoring electricity energy usage can help to reduce power consumption considerably. Among load monitoring techniques, non-intrusive load monitoring (NILM) provides a cost-efficient solution to identify individual load consumption details from the aggregate voltage and current measurements. Existing load monitoring techniques often require large datasets or use complex algorithms to obtain acceptable performance. In this paper, a NILM technique using six non-redundant current waveform features with rule-based set theory (CRuST) is proposed. The architecture consists of an event detection stage followed by preprocessing and framing of the current signal, feature extraction, and finally, the load identification stage. During the event detection stage, a change in connected loads is ascertained using current waveform features. Once an event is detected, the aggregate current is processed and framed to obtain the event-causing load current. From the obtained load current, the six features are extracted. Furthermore, the load identification stage determines the event-causing load, utilizing the features extracted and the appliance model. The results of the CRuST NILM are evaluated using performance metrics for different scenarios, and it is observed to provide more than 96% accuracy for all test cases. The CRuST NILM is also observed to have superior performance compared to the feed-forward back-propagation network model and a few other existing NILM techniques.

Contactless Rotor Ground Fault Detection Method for Brushless Synchronous Machines Based on an AC/DC Rotating Current Sensor

“…Also, the field winding of the exciter is fed by an adjustable voltage source (6). Finally, the sensor-induced voltage is recorded by a FLUKE 196B oscilloscope (7), where FFT is performed. The main characteristics of the experimental setup (main machine, exciter, and sensor) are collected in Appendix A.…”

“…The development of novel techniques for current measurement is a very active research topic. For example, in the case of load monitoring [7], where the current wave form is very important, in the case of distortion in power systems [8], or even in the case of lightning current measurement [9] using optical sensors. The development of novel techniques for current measurement is a very active research topic.…”

Enhancing non-intrusive load monitoring with weather and calendar feature integration in DAE

“…Although deep learning methods have achieved commendable results in NILM, existing algorithms still exhibit shortcomings in the aspect of feature extraction. Specifically speaking, current algorithms typically extract features solely from single-dimensional electrical data, such as active power (Dinesh et al, 2016), reactive power (Valenti et al, 2018), and current waveforms (Shareef et al, 2023), while overlooking the correlations of weather and calendar factors with the energy usage of electrical appliances. For instance, colder weather will increase the usage of heating appliances, and holidays generally lead to more energy consumption in household devices.…”