A non-intrusive load monitoring data generation method

Abstract Non-intrusive load monitoring (NILM) is a technique that does not require access to the interior of the system or to the interior of each electrical appliance. Instead, it only installs monitoring equipment at the entrance of the user bus. In the course of investigating non-intrusive load identification techniques, it is often necessary to collect extensive user load data in order to confirm the applicability of the proposed load identification methods across various situations. This requirement inevitably entails a significant burden of data collection and organization. In order to overcome this challenge, a hybrid approach was proposed that combines the principle of Frequency Invariant Transformation for Periodic Signals (FIT-PS) with Time Series Generative Adversarial Networks (TimeGAN). This method was employed to generate single-loaded waveform and multi-loaded waveforms, in order to meet the test requirements.