Industrial Energy Disaggregation with Digital Twin-generated Dataset and Efficient Data Augmentation

TL;DR

This paper introduces SIDED, a synthetic industrial energy dataset generated via Digital Twins, and proposes AMDA, a data augmentation method that improves NILM model accuracy and generalization for complex industrial appliances.

Contribution

The paper presents SIDED, a novel synthetic dataset for industrial energy disaggregation, and introduces AMDA, an efficient data augmentation technique that enhances NILM model performance.

Findings

AMDA significantly reduces Normalized Disaggregation Error to 0.093.

Models trained with AMDA outperform those without augmentation.

AMDA effectively aligns training and test data distributions.

Abstract

Industrial Non-Intrusive Load Monitoring (NILM) is limited by the scarcity of high-quality datasets and the complex variability of industrial energy consumption patterns. To address data scarcity and privacy issues, we introduce the Synthetic Industrial Dataset for Energy Disaggregation (SIDED), an open-source dataset generated using Digital Twin simulations. SIDED includes three types of industrial facilities across three different geographic locations, capturing diverse appliance behaviors, weather conditions, and load profiles. We also propose the Appliance-Modulated Data Augmentation (AMDA) method, a computationally efficient technique that enhances NILM model generalization by intelligently scaling appliance power contributions based on their relative impact. We show in experiments that NILM models trained with AMDA-augmented data significantly improve the disaggregation of energy consumption of complex industrial appliances like combined heat and power systems. Specifically, in our out-of-sample scenarios, models trained with AMDA achieved a Normalized Disaggregation Error of 0.093, outperforming models trained without data augmentation (0.451) and those trained with random data augmentation (0.290). Data distribution analyses confirm that AMDA effectively aligns training and test data distributions, enhancing model generalization.