DiffNILM: A Novel Framework for Non-Intrusive Load Monitoring Based on the Conditional Diffusion Model

Abstract

Non-intrusive Load Monitoring (NILM) is a critical technology that enables detailed analysis of household energy consumption without requiring individual metering of every appliance, and has the capability to provide valuable insights into energy usage behavior, facilitate energy conservation, and optimize load management. Currently, deep learning models have been widely adopted as state-of-the-art approaches for NILM. In this study, we introduce DiffNILM, a novel energy disaggregation framework that utilizes diffusion probabilistic models to distinguish power consumption patterns of individual appliances from aggregated power. Starting from a random Gaussian noise, the target waveform is iteratively reconstructed via a sampler conditioned on the total active power and encoded temporal features. The proposed method is evaluated on two public datasets, REDD and UKDALE. The results demonstrated that DiffNILM outperforms baseline models on several key metrics on both datasets and shows a remarkable ability to effectively recreate complex load signatures. The study highlights the potential of diffusion models to advance the field of NILM and presents a promising approach for future energy disaggregation research.

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

“…Similarly, the array indices are determined for the rest of the five features as x f , x v , x r , x p , and x t . The load corresponding to waveform i L that caused the event can be determined by (17).…”

“…This would result in a null set for L E . In such a case, the load search group is modified to L SG , and the event-causing load is recalculated using (17). Furthermore, a null set could still be returned when one or more features are not accurately calculated due to the error in framed load current i L .…”

“…On the other hand, the NILM approach as a pattern recognition problem predominantly uses clustering and classification algorithms such as an artificial neural network [ 14 , 15 ], a convolutional neural network [ 16 ], and diffusion models [ 17 ]. The above-mentioned machine-learning-based methods can be used to overcome the difficulty of distinguishing between similar rated loads by utilizing the features from the training data [ 18 ].…”