Tag
Ars Technica examines global electrification trends, noting electricity's share of final energy rose from 16.7% in 2000 to 23.4% in 2025, while energy researchers warn that political, economic, and trade barriers make a rapid, inevitable transition far from certain.
The paper proposes clipping-aware objective conditioning for differentially private diffusion models applied to energy time-series imputation, using v-prediction and timestep-aware loss weighting to reduce pre-clipping gradient amplification and improve imputation utility over the epsilon-prediction baseline on five real-world energy datasets.
The article discusses how human threats remain the primary cybersecurity risk to energy systems, with generative AI acting as a force multiplier for attacks, rather than rogue AI being the immediate danger.
This paper investigates how adversarial data modifications to electricity price forecasts can impact industrial demand response, finding that while attacks can erode profits, limited perturbations preserve most of the financial benefit.
This paper proposes Continuous Power Forecasting, treating power forecasting as a continual learning problem to handle nonstationary conditions. It evaluates six CL approaches on real-world datasets, showing benefits in adaptation and mitigating catastrophic forgetting.