Explainable Neural Network Framework Improves Smart Grid Power Demand Forecasting Accuracy
A deep learning framework combining gated memory refinement with convolutional and transformer attention achieved 94.78 percent accuracy in smart grid ...
A deep learning framework combining gated memory refinement with convolutional and transformer attention achieved 94.78 percent accuracy in smart grid ...
A co-simulation study of a German residential district reveals that pairing building efficiency, heat pumps, and solar-optimized vehicle charging cuts ...
A systematic review of 107 studies across Pakistan, Sri Lanka, and Australia reveals that developed power grids rely predominantly on ...
Researchers developed a two-stage virtual power plant scheduling and asymmetric Nash bargaining framework that reduced simulated daily operating costs by ...
A new framework combining an Unscented Kalman Filter and a Graph Neural Network effectively assesses stability and power quality in ...
Researchers establish energy informatics as a foundational scientific discipline bridging computational systems and physical power infrastructure to guide digital energy ...
A knowledge-grounded security assessment framework improves risk quantification and cross-domain access verification for large language models in smart-grid operations.
Information and communication technology has emerged as a powerful and statistically significant driver of access to electricity across Sub-Saharan Africa, ...
A new deep learning model combining wavelet decomposition, a CNN and LSTM layers achieved an RMSE of 0.09 in forecasting ...
Researchers argue that digitalizing and decentralizing electricity grids is a socio-technical transition requiring interdisciplinary study of technology, labor and grid ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine