September 10, 2025InformationOpen Access

A Spatiotemporal Deep Learning Framework for Joint Load and Renewable Energy Forecasting in Stability-Constrained Power Systems

View Full Paper

Ask AI

Bookmark

The proposed deep learning framework enhances forecasting accuracy by approximately 2.1% compared to Autoformer.
Scheduling performance improved by reducing total operating costs by 5.8% and decreasing frequency deviation to 0.129 Hz.
Combining CNN and LSTM, the model incorporates reinforcement learning to manage system stability during dynamic responses.
Ablation studies confirm that the uncertainty modeling module is essential for maintaining operational robustness.

Discussion

No takes yet. Share an insight, caveat, or question.

This framework demonstrates improved forecasting accuracy in power systems, highlighting benefits for renewable energy integration.

Cheng et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark