Reproduce “Uncertainty-Aware Joint Generative Modeling of Fault Event Sequences and Sensor Time Series in Solar PV Plants” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jiayu Huang, Boyang Xu, Yongming Liu, Hao Yan
The authors introduce a history-conditioned model that simulates solar-plant sensor trajectories and predicts fault events, rolling outputs into finite stochastic scenarios. It encodes sensor and event histories with co-attention, using latent diffusion for sensors and score matching for next-event time and type. On an Arizona site, Macro F1 is 0.3323 versus 0.2627 for Event-only; generalization and event-time calibration remain unestablished.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.