The integration of renewable energy resources and the increasing need for grid balancing have inten-sified the demand for accurate short-term consumption and production forecasting in electricity grids.This progress h...The integration of renewable energy resources and the increasing need for grid balancing have inten-sified the demand for accurate short-term consumption and production forecasting in electricity grids.This progress has been facilitated by greater data availability and the development of advanced machine and deep learning algorithms.While models such as the Transformer have revolutionised temporal sequential data processing,spatial dependencies between nodes in electrical grids could improve predictions.This study proposes a spatial-temporal hybrid model that integrates a Graph Neural Network with a Transformer to capture both temporal and spatial relationships.The results show that the Transformer outperforms benchmark models,Long Short-Term Memory and Multilayer Perceptron,for consumption forecasting.Furthermore,incorporating a Graph Neural Network enhances consumption prediction accuracy.For production forecasting,the standalone Transformer slightly outperforms the hybrid model,suggesting less useful spatial correlations among production nodes.However,the hybrid model reduced trainable parameters by 57%,making it more compact with minimal accuracy loss.展开更多
基金supported by the"Leveraging Smart Meter Data to Optimize Grid Investments"and"Participation in IEA ISGAN Working Group 6‘Power T&D Systems’"projects,which are funded by the Danish Energy Agency under the Energy Technology Development and Demonstration program,ID number 64022-1049 and 134243-533635,respectively.
文摘The integration of renewable energy resources and the increasing need for grid balancing have inten-sified the demand for accurate short-term consumption and production forecasting in electricity grids.This progress has been facilitated by greater data availability and the development of advanced machine and deep learning algorithms.While models such as the Transformer have revolutionised temporal sequential data processing,spatial dependencies between nodes in electrical grids could improve predictions.This study proposes a spatial-temporal hybrid model that integrates a Graph Neural Network with a Transformer to capture both temporal and spatial relationships.The results show that the Transformer outperforms benchmark models,Long Short-Term Memory and Multilayer Perceptron,for consumption forecasting.Furthermore,incorporating a Graph Neural Network enhances consumption prediction accuracy.For production forecasting,the standalone Transformer slightly outperforms the hybrid model,suggesting less useful spatial correlations among production nodes.However,the hybrid model reduced trainable parameters by 57%,making it more compact with minimal accuracy loss.
