More Like this

1. Synthetic PMU Data Creation Based on Generative Adversarial Network under Time-Varying Load Conditions

   https://doi.org/10.35833/MPCE.2021.000783  

   Zheng, Xiangtian; Pinceti, Andrea; Sankar, Lalitha; Xie, Le (July 2022, Journal of modern power systems and clean energy)

   In this study, a machine learning based method is proposed for creating synthetic eventful phasor measurement unit (PMU) data under time-varying load conditions. The proposed method leverages generative adversarial networks to create quasi-steady states for the power system under slowly-varying load conditions and incorporates a framework of neural ordinary differential equations (ODEs) to capture the transient behaviors of the system during voltage oscillation events. A numerical example of a large power grid suggests that this method can create realistic synthetic eventful PMU voltage measurements based on the associated real PMU data without any knowledge of the underlying nonlinear dynamic equations. The results demonstrate that the synthetic voltage measurements have the key characteristics of real system behavior on distinct time scales. 

   more » « less
2. Generation of synthetic multi‐resolution time series load data

   https://doi.org/10.1049/stg2.12116  

   Pinceti, Andrea; Sankar, Lalitha; Kosut, Oliver (June 2023, IET Smart Grid)

   Abstract The availability of large datasets is crucial for the development of new power system applications and tools; unfortunately, very few are publicly and freely available. The authors designed an end‐to‐end generative framework for the creation of synthetic bus‐level time‐series load data for transmission networks. The model is trained on a real dataset of over 70 Terabytes of synchrophasor measurements spanning multiple years. Leveraging a combination of principal component analysis and conditional generative adversarial network models, the developed scheme allows for the generation of data at varying sampling rates (up to a maximum of 30 samples per second) and ranging in length from seconds to years. The generative models are tested extensively to verify that they correctly capture the diverse characteristics of real loads. Finally, an opensource tool called LoadGAN is developed which gives researchers access to the fully trained generative models via a graphical interface. 

   more » « less
3. AI Radar Sensor: Creating Radar Depth Sounder Images Based on Generative Adversarial Network

   https://doi.org/10.3390/s19245479  

   Rahnemoonfar, Maryam; Johnson, Jimmy; Paden, John (December 2019, Sensors)

   Significant resources have been spent in collecting and storing large and heterogeneous radar datasets during expensive Arctic and Antarctic fieldwork. The vast majority of data available is unlabeled, and the labeling process is both time-consuming and expensive. One possible alternative to the labeling process is the use of synthetically generated data with artificial intelligence. Instead of labeling real images, we can generate synthetic data based on arbitrary labels. In this way, training data can be quickly augmented with additional images. In this research, we evaluated the performance of synthetically generated radar images based on modified cycle-consistent adversarial networks. We conducted several experiments to test the quality of the generated radar imagery. We also tested the quality of a state-of-the-art contour detection algorithm on synthetic data and different combinations of real and synthetic data. Our experiments show that synthetic radar images generated by generative adversarial network (GAN) can be used in combination with real images for data augmentation and training of deep neural networks. However, the synthetic images generated by GANs cannot be used solely for training a neural network (training on synthetic and testing on real) as they cannot simulate all of the radar characteristics such as noise or Doppler effects. To the best of our knowledge, this is the first work in creating radar sounder imagery based on generative adversarial network. 

   more » « less
4. Self-Consuming Generative Models with Adversarially Curated Data

   Wei, Xiukun; Zhang, Xueru (July 2025, Forty-second International Conference on Machine Learning)

   Recent advances in generative models have made it increasingly difficult to distinguish real data from model-generated synthetic data. Using synthetic data for successive training of future model generations creates “self-consuming loops,” which may lead to model collapse or training instability. Furthermore, synthetic data is often subject to human feedback and curated by users based on their preferences. Ferbach et al. (2024) recently showed that when data is curated according to user preferences, the self-consuming retraining loop drives the model to converge toward a distribution that optimizes those preferences. However, in practice, data curation is often noisy or adversarially manipulated. For example, competing platforms may recruit malicious users to adversarially curate data and disrupt rival models. In this paper, we study how generative models evolve under self-consuming retraining loops with noisy and adversarially curated data. We theoretically analyze the impact of such noisy data curation on generative models and identify conditions for the robustness and stability of the retraining process. Building on this analysis, we design attack algorithms for competitive adversarial scenarios, where a platform with a limited budget employs malicious users to misalign a rival’s model from actual user preferences. Experiments on both synthetic and real-world datasets demonstrate the effectiveness of the proposed algorithms. 

   more » « less
5. Load profiles of residential off-grid solar systems on the Navajo Nation

   https://doi.org/10.1016/j.esd.2024.101572  

   Louie, Henry; O'Shea, Scott; Atcitty, Stanley; Terry, Derrick; Lee, Darrick; Romine, Peter (December 2024, Energy for Sustainable Development)

   Standalone off-grid electrical systems, no matter where they are deployed or for what user class, are designed based upon the load they are expected to serve. State-of-the-art computerized off-grid system design tools require the user to specify the expected load profile, that is, how the power consumption changes throughout the day. Often, this is at an hourly resolution, and some characterization of the distribution of power around the average values may be required. Specifying realistic and reasonable load profiles is a barrier to the appropriate design of standalone systems. This research extends previous studies on daily energy consumption of residential solarpowered off-grid systems on the Navajo Nation to provide hourly load profiles, statistical characteristics, and probabilistic models. The data analyzed come from 90 homes over a two-year period. K-means clustering is used to identify prototypical normalized load profiles when the data are grouped by year, season, weekday, and weekend. Eight parametric probability density functions are fit to the grouped data at an hourly resolution. Their fit to the data is evaluated using the Cram´er-von Mises (CvM) statistic. The results show that the load profiles tend to be night-peaking and that Log Normal and Gumbel distributions can reasonably model variation in the data. The load profiles and probabilistic models can be used in off-grid design software and to synthesize load profiles for design and future research. 

   more » « less