Weather-aware edge AI improves extreme-grid load forecasting
A weather-aware recurrent neural network delivered more accurate extreme-condition electricity-load forecasts while using an 8.1 MB edge footprint and 9.2-millisecond ...
A weather-aware recurrent neural network delivered more accurate extreme-condition electricity-load forecasts while using an 8.1 MB edge footprint and 9.2-millisecond ...
A benchmark study found that an AI service hub combining sensor, text and visual data achieved high fault-detection and maintenance ...
Smart grids promise a cleaner, more responsive electricity system, but they also carry a hidden vulnerability: every smart meter is ...
A large language model that forecasts load during maintenance windows helps cut cumulative outage risk from 38.1 to 2.6 on ...
A new two-stage framework couples improved wind and solar power forecasting with multi-objective shared energy storage planning, achieving a 90.3 ...
Researchers have created a framework that uses a migrating battery and a service-adaptability index to cut rooftop solar curtailment in ...
A new FCN-GRU-Attention deep learning model with a confidence correction mechanism identifies overlapping composite power quality disturbances with over 99 ...
A hybrid feature selection framework combining correlation analysis, PCA, neural sensitivity testing, and SHAP/LIME explainability reveals that average battery voltage ...
A new physics-embedded machine learning framework called SPEL-VFL reconstructs hidden hydrogen energy flows in smart grids and pipeline networks even ...
A new Bentham Books reference volume examines how high-performance computing, artificial intelligence, cloud technologies and cybersecurity can converge to build ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine