2024 journal article

MultiLoad-GAN: A GAN-Based Synthetic Load Group Generation Method Considering Spatial-Temporal Correlations

IEEE TRANSACTIONS ON SMART GRID, 15(2), 2309–2320.

By: Y. Hu n , Y. Li  n, L. Song n, H. Lee n, P. Rehm, M. Makdad, E. Miller, N. Lu n 

author keywords: Load modeling; Training; Transformers; Correlation; Data models; Generative adversarial networks; Predictive models; Data augmentation; generative adversarial networks; load profile group generation; machine learning; negative sample generation; synthetic data
TL;DR: Simulation results show that MultiLoad-GAN can generate more realistic load profiles than existing approaches, especially in group level characteristics. (via Semantic Scholar)
UN Sustainable Development Goal Categories
Source: Web Of Science
Added: April 15, 2024

This paper presents a deep-learning framework, Multi-load Generative Adversarial Network (MultiLoad-GAN), for generating a group of synthetic load profiles (SLPs) simultaneously. The main contribution of MultiLoad-GAN is the capture of spatial-temporal correlations among a group of loads that are served by the same distribution transformer. This enables the generation of a large amount of correlated SLPs required for microgrid and distribution system studies. The novelty and uniqueness of the MultiLoad-GAN framework are three-fold. First, to the best of our knowledge, this is the first method for generating a group of load profiles bearing realistic spatial-temporal correlations simultaneously. Second, two complementary realisticness metrics for evaluating generated load profiles are developed: computing statistics based on domain knowledge and comparing high-level features via a deep-learning classifier. Third, to tackle data scarcity, a novel iterative data augmentation mechanism is developed to generate training samples for enhancing the training of both the classifier and the MultiLoad-GAN model. Simulation results show that MultiLoad-GAN can generate more realistic load profiles than existing approaches, especially in group level characteristics. With little finetuning, MultiLoad-GAN can be readily extended to generate a group of load or PV profiles for a feeder or a service area.