Learning Through Energy Refinement and Manifold Projection: A Cooperative EBM-AE Framework
本文提出一种结合能量精炼与流形投影的EBM-AE框架，通过联合训练EBM和自编码器来解决EBM训练中的挑战，提高了生成质量和重建能力。
0 citationsRead paper
Selected work
Representative Papers
Modular Foundation Models for Time-Series Perception in Digital Twins
This work addresses the limitations of task-specific, data-hungry, and poorly generalizable temporal-aware modules in digital twin and Prognostics and Health Management (PHM) systems, which also suffer from integration challenges. To overcome these issues, the authors propose a modular foundation model based on an ensemble of pretrained encoders. The model leverages self-supervised learning to acquire transferable temporal representations, employs a gating mechanism for dynamic encoder selection, and utilizes Transformer-based self-attention to enable cross-encoder interaction and representation fusion. Innovatively, it adopts a shared latent space alignment combined with an adaptive aggregation strategy, allowing lightweight multi-task adaptation and conditional computation while keeping the pretrained encoders frozen. The approach demonstrates superior performance on the ETT benchmark and validates its practical utility in an industrial virtual sensing application for hydro-generator rotor temperature monitoring.
0 citationsRead paper
SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting
This study addresses the lack of reliability guarantees in existing time series imputation methods under limited sample sizes, which hinders their applicability in high-stakes domains such as power systems. To overcome this limitation, the authors propose SPLICE, a novel framework that integrates distribution-free online adaptive conformal inference (ACI) with a diffusion-based imputation model built upon a JEPA self-supervised encoder and a conditional latent-space bridging mechanism—augmented with a flow-matching variant—to achieve both high-efficiency imputation and rigorous coverage guarantees, while enabling cross-domain transfer. Evaluated on 13 load forecasting datasets, SPLICE achieves the lowest average MSE (0.056) and best CRPS (0.161), with empirical coverage rates consistently between 93% and 95%, significantly outperforming current state-of-the-art approaches.
0 citationsRead paper
Deceiving Flexibility: A Stealthy False Data Injection Model in Vehicle-to-Grid Coordination
This study addresses the risk of stealthy false data injection attacks in vehicle-to-grid (V2G) systems based on extended state-space models (eSSMs). The authors propose an attack strategy that manipulates only a subset of electric vehicles’ reported state-of-charge and power data, without compromising the control layer. By carefully crafting falsified data to align with the system’s aggregate model expectations, the attack remains undetected by conventional anomaly detection mechanisms. As the first work to demonstrate a purely data-layer stealth attack in V2G scenarios, the study shows through simulations that such manipulation can significantly degrade grid frequency stability without disrupting the physical charging or discharging processes. These findings expose a critical cybersecurity vulnerability in existing aggregative V2G architectures, highlighting the need for enhanced data integrity safeguards.
0 citationsRead paper
A Weather Foundation Model for the Power Grid
While existing weather foundation models excel in global forecasting, their capability for ultra-local, asset-level prediction of electricity infrastructure–critical meteorological variables—such as surface temperature, precipitation, hub-height wind speed, wind turbine icing risk, and overhead conductor rime ice accumulation—remains unexplored. Method: This work pioneers the domain adaptation of a 1.5-billion-parameter generative forecasting Transformer (GFT) to the power sector, performing post-training and fine-tuning using data from transmission-line weather stations, wind farm met masts, and icing sensors. Contribution/Results: For 6–72-hour forecasts, the adapted model reduces RMSE by 15% (temperature), 35% (precipitation), and 15% (wind speed); achieves a mean precision of 0.72 for rime ice accumulation detection; and delivers several hours of actionable lead time. By transcending the spatial resolution and physical parameterization constraints of traditional numerical weather prediction, this approach establishes a novel operational paradigm for power grid hazard early warning.
0 citationsRead paper
Recent publications
Latest Papers
Learning Through Energy Refinement and Manifold Projection: A Cooperative EBM-AE Framework
本文提出一种结合能量精炼与流形投影的EBM-AE框架，通过联合训练EBM和自编码器来解决EBM训练中的挑战，提高了生成质量和重建能力。
0 citationsRead paper
Modular Foundation Models for Time-Series Perception in Digital Twins
This work addresses the limitations of task-specific, data-hungry, and poorly generalizable temporal-aware modules in digital twin and Prognostics and Health Management (PHM) systems, which also suffer from integration challenges. To overcome these issues, the authors propose a modular foundation model based on an ensemble of pretrained encoders. The model leverages self-supervised learning to acquire transferable temporal representations, employs a gating mechanism for dynamic encoder selection, and utilizes Transformer-based self-attention to enable cross-encoder interaction and representation fusion. Innovatively, it adopts a shared latent space alignment combined with an adaptive aggregation strategy, allowing lightweight multi-task adaptation and conditional computation while keeping the pretrained encoders frozen. The approach demonstrates superior performance on the ETT benchmark and validates its practical utility in an industrial virtual sensing application for hydro-generator rotor temperature monitoring.
0 citationsRead paper
SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting
This study addresses the lack of reliability guarantees in existing time series imputation methods under limited sample sizes, which hinders their applicability in high-stakes domains such as power systems. To overcome this limitation, the authors propose SPLICE, a novel framework that integrates distribution-free online adaptive conformal inference (ACI) with a diffusion-based imputation model built upon a JEPA self-supervised encoder and a conditional latent-space bridging mechanism—augmented with a flow-matching variant—to achieve both high-efficiency imputation and rigorous coverage guarantees, while enabling cross-domain transfer. Evaluated on 13 load forecasting datasets, SPLICE achieves the lowest average MSE (0.056) and best CRPS (0.161), with empirical coverage rates consistently between 93% and 95%, significantly outperforming current state-of-the-art approaches.
0 citationsRead paper
Deceiving Flexibility: A Stealthy False Data Injection Model in Vehicle-to-Grid Coordination
This study addresses the risk of stealthy false data injection attacks in vehicle-to-grid (V2G) systems based on extended state-space models (eSSMs). The authors propose an attack strategy that manipulates only a subset of electric vehicles’ reported state-of-charge and power data, without compromising the control layer. By carefully crafting falsified data to align with the system’s aggregate model expectations, the attack remains undetected by conventional anomaly detection mechanisms. As the first work to demonstrate a purely data-layer stealth attack in V2G scenarios, the study shows through simulations that such manipulation can significantly degrade grid frequency stability without disrupting the physical charging or discharging processes. These findings expose a critical cybersecurity vulnerability in existing aggregative V2G architectures, highlighting the need for enhanced data integrity safeguards.
0 citationsRead paper
A Weather Foundation Model for the Power Grid
While existing weather foundation models excel in global forecasting, their capability for ultra-local, asset-level prediction of electricity infrastructure–critical meteorological variables—such as surface temperature, precipitation, hub-height wind speed, wind turbine icing risk, and overhead conductor rime ice accumulation—remains unexplored. Method: This work pioneers the domain adaptation of a 1.5-billion-parameter generative forecasting Transformer (GFT) to the power sector, performing post-training and fine-tuning using data from transmission-line weather stations, wind farm met masts, and icing sensors. Contribution/Results: For 6–72-hour forecasts, the adapted model reduces RMSE by 15% (temperature), 35% (precipitation), and 15% (wind speed); achieves a mean precision of 0.72 for rime ice accumulation detection; and delivers several hours of actionable lead time. By transcending the spatial resolution and physical parameterization constraints of traditional numerical weather prediction, this approach establishes a novel operational paradigm for power grid hazard early warning.
0 citationsRead paper