A new paradigm based on Wasserstein Generative Adversarial Network and time-series graph for integrated energy system forecasting

Energy Conversion and Management, Journal Year: 2025, Volume and Issue: 326, P. 119484 - 119484

Published: Jan. 13, 2025

Language: Английский

Multi-task learning load time series situational prediction based on gated recurrent neural networks considering spatial correlations

Frontiers in Energy Research, Journal Year: 2025, Volume and Issue: 12

Published: Jan. 17, 2025

Accurate load forecasting plays a crucial role in the effective planning, operation, and management of modern power systems. In this study, novel approach to time series situational prediction is proposed, which integrates spatial correlations heterogeneous resources through application Random Matrix Theory (RMT) with Multi-Task Learning (MTL) framework based on Gated Recurrent Units (GRU). RMT utilized capture complex, high-dimensional statistical relationships among various profiles, enabling deeper understanding underlying data patterns that traditional methods may overlook. The GRU-based MTL employed exploit these spatiotemporal correlations, allowing for sharing essential features across multiple tasks, turn enhances accuracy robustness predictions. This was validated using real-world data, demonstrating notable improvements when compared single-task learning models. results indicate method effectively captures complex within leading more accurate forecasting. enhanced predictive capability expected contribute significantly improving demand-side management, reducing risks grid overloading, supporting integration renewable energy sources, thereby fostering overall sustainability resilience

Language: Английский

Enhancing solar radiation forecasting accuracy with a hybrid SA-Bi-LSTM-Bi-GRU model

Earth Science Informatics, Journal Year: 2025, Volume and Issue: 18(3)

Published: Feb. 19, 2025

Language: Английский