This paper presents a multimodal generative model designed to simulate a solar energy plant system for predictive maintenance and fault prediction. We propose a novel approach to enhance system generation through conditional generation by leveraging both event sequences and time-series data and improve next event prediction. The framework employs a Transformer Hawkes Process (THP) to encode event data and an iTransformer to encode time-series data, integrated via a co-attention mechanism that effectively captures cross-modal dependencies between discrete events and continuous signals. From these integrated representations, we employ two specialized decoders for simulation: a Conditional Latent Diffusion Model (CLDM) for modeling future sensor trajectories and the Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process (SMURF-THP) for high-fidelity event prediction. This dual-decoder strategy supports uncertainty-aware, history-conditioned simulation by rolling the model forward for a specified number of generation iterations, producing finite stochastic scenarios rather than deterministic extrapolations over the full observational record. Evaluated on a comprehensive dataset from the Red Rock Solar Site in Arizona, our approach improves aggregate event-prediction F1 relative to baselines and supports applications in predictive maintenance, fault detection, and energy optimization for solar power systems.
Figures & tables
Fig. 1: Overall encoder–decoder architecture: iTransformer and THP fused by co-attention; CLDM and SMURF-THP decoders.
Data Level
No. of Variables
Examples
System Level
47
curtail, weather, feeder
Inverter Level
11
power output (current, voltage)
Module Level
3
status, T-IGBT
TABLE I: Variables at Different Operational Levels of the PV Plant
Fig. 2: Power-signal forecast on a representative test sample (more samples in Supp. Section S3 ).
Fault Type
Baseline Models
Proposed Model
RNNPP
Event-only
4
0.0000
0.0000
0.0000
18
0.5000
0.5000
0.5556
19
0.0930
0.1138
0.2017
36
0.1636
0.1250
0.1839
40
0.5766
0.2500
0.5326
TABLE II: Per-type next-event F1: baselines vs. proposed model.
Fig. 3: Five-day origin-aggregated next-event counting processes (true dashed, predicted solid) for types 19, 40, 42, and 67.
Metric / Type
CLDM+MLP
Event-only
Proposed
Supp.
Overall
TS MSE
0.4631
–
0.3522
–
TS MAE
0.4244
–
0.3418
–
Micro F1
0.0462
0.2209
0.3390
584
Macro F1
0.0200
0.2627
0.3323
584
Weighted F1
0.0326
0.2299
0.3565
584
TABLE III: Ablation: overall metrics and per-class F1 (CLDM+MLP, Event-only, Proposed). “–”: N/A; Supp.: test support.
Fig. S1: Finite-step rollout structure. At each iteration, only the available history (context window of time series and last K events up to current time t ) is used to predict the next event and to generate the time series segment up to the predicted event time, capped by the seven-day prediction window; then the window is rolled forward. The number of generation iterations Niter is specified, while the calendar duration is induced by generated inter-event intervals and the per-iteration seven-day cap.
Fig. S2: Supplementary rollout flowchart. The rollout initializes from the available history, predicts or samples the next event, generates the sensor segment capped by the seven-day prediction window, updates the history, and repeats until the specified number of generation iterations Niter is reached.
Fig. S3: Multi-day rollout visualization showing iterative event prediction and time series generation.
Fig. S4: Multi-step rollout error accumulation over Niter=8 iterations. The blue curve shows per-iteration MSE and the orange curve shows cumulative MSE relative to ground truth; shaded regions denote the standard deviation across samples. Cumulative MSE remains stable near 0.30 without exponential growth, indicating controlled trajectory drift under event-driven alignment.
Fig. S5: Additional seven-day CLDM power-signal generation examples on six randomly selected test samples. Blue: ground truth; red: predicted mean; shaded red: sample-based uncertainty bands. Each panel reports the sample index and MSE.
Fig. S6: Mean predictive uncertainty (averaged across variables) over a 7-day horizon on the test set.
Parameter
Range
Learning rate
[5×10−5,3×10−4]
Number of event types
14
Training sampler
Event-balanced
Batch size
128
Maximum epochs
{80,100,120}
Early-stopping patience
{15,25}
TABLE S1: Common hyperparameter settings for all models.
Hyperparameter
Candidate values
Time-series loss weight, wts
{0.5,0.7,1.0}
Projection loss weight, wproj
{1.0,1.5,2.0}
Number of latent diffusion steps
{100,200}
Event classification loss weight, wevent
{0.5,1.0,2.0}
Next-event loss weight, wnext
{0.05,0.1,0.2}
Focal-loss parameter, γ
{0.0,1.0,2.0}
TABLE S2: Hyperparameter search space for the proposed model.
Parameter
Range
Learning rate
[5×10−5,3×10−4]
Event loss weight, wevent
{0.5,1.0,2.0}
Next-event loss weight, wnext
{0.05,0.1,0.2}
Focal-loss parameter, γ
{0,1,2}
Event-class weighting
{Inv. sqrt., Inv.}
Sample-weight exponent, α
{0.5,0.75,1.0}
TABLE S3: Hyperparameter search space for the THP baseline.
Parameter
Range
Time-series loss weight, wts
{0.5,0.7,1.0}
Projection loss weight, wproj
{1.0,1.5,2.0}
Latent diffusion steps
{100,200}
Event loss weight, wevent
{0.5,1.0,2.0}
Next-event loss weight, wnext
{0.05,0.1,0.2}
Focal-loss parameter, γ
{0,1,2}
TABLE S4: Hyperparameter search space for the CLDM+MLP baseline.
Parameter
Range
Time-series loss weight, wts
0 (fixed)
Event loss weight, wevent
{0.5,1.0,2.0}
Next-event loss weight, wnext
{0.05,0.1,0.2}
Focal-loss parameter, γ
{0,1,2}
Event-class weighting
{Inv. sqrt., Inv.}
Sample-weight exponent, α
{0.5,0.75,1.0}
TABLE S5: Hyperparameter search space for the event-only model.
Parameter
Range
Time-series loss weight, wts
0 (fixed)
Event loss weight, wevent
{0.5,1.0,2.0}
Next-event loss weight, wnext
{0.05,0.1,0.2}
Focal-loss parameter, γ
{0,1,2}
Event-class weighting
{Inv. sqrt., Inv.}
Sample-weight exponent, α
{0.5,0.75,1.0}
TABLE S6: Hyperparameter search space for the RNNPP baseline.
Method
Conditioning
Scope / design
Event sequences (TPP): diffusion / flow
ADD-THIN [ 49 ]
Event history
Full-sequence denoising via add-and-thin; handles discrete+continuous components
DLTPP [ 52 ]
History (mapped)
Non-autoregressive long-horizon; bidirectional map between sequences and Euclidean space
Zeng et al. (CDiff) [ 50 ]
Event history
Interacting diffusion processes for inter-arrival times and types (sequence-to-sequence)
ADiff4TPP [ 51 ]
Event history
Asynchronous noise schedule to strengthen long-horizon conditioning
EventFlow [ 53 ]
Event history
Flow-matching-based forecasting for continuous-time event sequences
TABLE S7: Representative methods for event diffusion/flow, joint event–time-series co-prediction, and time-series forecasting (Transformers and diffusion/score-based).
Fig. S7: Comparison between vanilla Transformer (top) and the iTransformer (bottom): normalized time series from five randomly chosen sensors over 7 days, segmented into 96 time intervals per day. The iTransformer treats each variate as a token and applies attention across sensors.
Fig. S8: Co-attention Layer Architecture [ 9 ] . The bidirectional cross-attention mechanism enables each modality to attend to the other, capturing cross-modal interdependencies.
Fault type
Description
4
Over current S/W
12
Multiple issues
18
Multiple issues
19
AC Overcurrent issue
36
High grid frequency
40
Homopolar current Fault
TABLE S8: Fault Codes’ Descriptions
Event Start Time
Gap Time (mins)
Event Type
Duration (mins)
2019-06-24 11:53:10
0
55
17.06
2019-06-24 14:01:18
128.13
18
401.73
2019-06-30 18:18:14
8896.93
55
1736.66
2019-07-02 05:29:34
2111.33
55
3979.33
2019-07-05 05:29:26
4319.86
55
1065.73
2019-07-06 05:41:50
1452.39
55
2406.93
TABLE S9: Processed Real-Time Fault Data Sample
Metric
Value
Total / Trainable Parameters
171,086,433 ( ∼ 171.1 M)
Peak GPU Memory Footprint
8,241 MiB ( ∼ 8.2 GB)
Training Time per Epoch
1m 11.97s
Total Epochs
120
Estimated Total Training Time
∼ 2 hours 24 minutes
TABLE S10: Computational Efficiency and Model Footprint
In this paper, we propose a novel conditional diffusion-based framework for multivariable time-series solar power forecasting. The proposed method reformulates temporal PV data as structured two-dimensional representations (images) using a sliding-window patch construction, enabling the application of Denoising Diffusion Probabilistic Models (DDPM) within a unified spatiotemporal learning paradigm. A key contribution of this work is the formulation of solar forecasting as an inpainting problem, where future time steps are treated as missing regions to be reconstructed. This is achieved through a mask-based conditional diffusion mechanism, in which historical observations are preserved as conditioning context while the target (future) region is progressively corrupted and subsequently recovered via reverse diffusion. The model learns to generate coherent future sequences conditioned on observed data, effectively performing time-series inpainting. To fully utilize all available features and ensure compatibility with U-Net architectural constraints, a zero-padding strategy is introduced to construct fixed-size inputs. The model is trained using a supervised denoising objective to predict injected noise, enabling accurate iterative reconstruction during the reverse process. Extensive experiments conducted on benchmark PV dataset, including GEFCom2014, demonstrate that the proposed approach achieves high forecasting accuracy, particularly for short-term horizons. The results highlight the effectiveness of integrating diffusion-based generative modeling with an inpainting formulation for robust, flexible, and high-fidelity solar power forecasting.
Power-outage planning requires scenarios before an event occurs. These scenarios must represent uncertainty in magnitude, timing, and duration while preserving temporal dependence. However, severe events are rare, and data from any single region contain few examples of extreme outage and restoration patterns. To address this challenge, we introduce OutageDiT, a foundation model for generating seven-day outage trajectories at 15-minute resolution, trained on outage and weather records across the United States. Specifically, a condition encoder processes historical context and known future covariates once per forecast, and a shallow flow-matching decoder reuses the resulting horizon-aligned states to sample complete outage trajectories. This enables point forecasting, uncertainty quantification, and conditional scenario generation within one deep generative model. Across outage forecasting benchmarks, OutageDiT improves forecast accuracy and scenario quality over strong baselines and supports zero-shot transfer to held-out regions. Together, these results position conditional outage scenario generation as a bridge from outage forecasting to operational planning under uncertainty.
Yunqin Zhu, Feng Qiu, Yao Xie
H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology · Argonne National Laboratory
Accurate solar irradiance forecasting is essential for the reliable integration of photovoltaic power into modern electricity grids. All-sky imagers (ASI) provide high-resolution observations of clouds, making them well suited for intra-hour forecasting. Recent deep learning approaches have substantially improved forecast accuracy but are often limited by deterministic predictions and a reduced capability to anticipate ramp events. This work proposes FarSky, a generative forecasting framework that leverages latent-space coupling to learn task-aware representations of sky images. A multi-task autoencoder first learns a shared latent representation for image reconstruction and irradiance estimation. A latent diffusion model then generates future latent states conditioned on recent observations, from which irradiance forecasts are directly decoded. Probabilistic forecasts are inherently obtained through stochastic sampling. The framework is developed using a multi-year ASI dataset acquired at the Plataforma Solar de Almería, Spain, and evaluated on two independent test datasets against persistence, state-of-the-art end-to-end, and generative forecasting approaches. FarSky achieves the best overall deterministic and probabilistic forecasting performance, improving forecast skill by up to 11 percentage points. Furthermore, it substantially improves ramp event detection over existing methods, achieving F1-scores above 60%. These results demonstrate the potential of combining generative models with task-aware latent-space coupling for solar forecasting.
Yann Fabel, Bijan Nouri, Milon Miah +4
1DLR, Institute of Solar Research · 2RWTH Aachen University · 3CIEMAT, Energy Department, Renewable Energy Division