Precise forecasting of solar power is crucial for the development of sustainable energy systems.Contemporary forecasting approaches often fail to adequately consider the crucial role of weather factors in photovoltaic...Precise forecasting of solar power is crucial for the development of sustainable energy systems.Contemporary forecasting approaches often fail to adequately consider the crucial role of weather factors in photovoltaic(PV)power generation and encounter issues such as gradient explosion or disappearance when dealing with extensive time-series data.To overcome these challenges,this research presents a cutting-edge,multi-stage forecasting method called D-Informer.This method skillfully merges the differential transformation algorithm with the Informer model,leveraging a detailed array of meteorological variables and historical PV power generation records.The D-Informer model exhibits remarkable superiority over competing models across multiple performance metrics,achieving on average a 67.64%reduction in mean squared error(MSE),a 49.58%decrease in mean absolute error(MAE),and a 43.43%reduction in root mean square error(RMSE).Moreover,it attained an R2 value as high as 0.9917 during the winter season,highlighting its precision and dependability.This significant advancement can be primarily attributed to the incorporation of a multi-head self-attention mechanism,which greatly enhances the model’s ability to identify complex interactions among diverse input variables,and the inclusion of weather variables,enriching the model’s input data and strengthening its predictive accuracy in time series analysis.Additionally,the experimental results confirm the effectiveness of the proposed approach.展开更多
Oil spills can generate multiple effects in different time scales on the marine ecosystem. The numerical modeling of these processes is an important tool with low computational cost which provides a powerful appliance...Oil spills can generate multiple effects in different time scales on the marine ecosystem. The numerical modeling of these processes is an important tool with low computational cost which provides a powerful appliance to environmental agencies regarding the risk management. In this way, the objective of this work is to evaluate the influence of a number of physical forcing acting over a hypothetical oil spill along the Southern Brazilian Shelf. The numerical simulation was carried out using the ECOS model (Easy Coupling Oil System), an oil spill model developed at the Universidade Federal do Rio Grande—FURG, coupled with the tridimensional hydrodynamic model TELEMAC3D (EDF, France). The hydrodynamic model provides the current velocity, salinity and temperature fields used by the oil spill model to evaluate the behavior and the fate of the spilled oil. The results suggest that the local wind influence is the main forcing driven the fate of the spilled oil, and this forcing responds for more than 60% of the oil slick variability. The direction and intensity of the costal currents control between 20% and 40% of the oil variability, and the currents are important controlling the behavior and the tridimensional transportation of the oil. On the other hand, the turbulent diffusion is important for the horizontal drift of the oil. The weathering results indicate 40% of evaporation and 80% of emulsification, and the combination of these processes leads an increasing of the oil density around, 53.4 kg/m3 after 5 days of simulation.展开更多
基金supported by the Shenzhen Science and Technology Plan,Sustainable Development Technology Special Project (Dual-Carbon Special Project),Research and Development of Intelligent Virtual Power Plant Technology (KCXST20221021111402006)the Science and Technology project of Tianjin,China (No.22YFYSHZ00330).
文摘Precise forecasting of solar power is crucial for the development of sustainable energy systems.Contemporary forecasting approaches often fail to adequately consider the crucial role of weather factors in photovoltaic(PV)power generation and encounter issues such as gradient explosion or disappearance when dealing with extensive time-series data.To overcome these challenges,this research presents a cutting-edge,multi-stage forecasting method called D-Informer.This method skillfully merges the differential transformation algorithm with the Informer model,leveraging a detailed array of meteorological variables and historical PV power generation records.The D-Informer model exhibits remarkable superiority over competing models across multiple performance metrics,achieving on average a 67.64%reduction in mean squared error(MSE),a 49.58%decrease in mean absolute error(MAE),and a 43.43%reduction in root mean square error(RMSE).Moreover,it attained an R2 value as high as 0.9917 during the winter season,highlighting its precision and dependability.This significant advancement can be primarily attributed to the incorporation of a multi-head self-attention mechanism,which greatly enhances the model’s ability to identify complex interactions among diverse input variables,and the inclusion of weather variables,enriching the model’s input data and strengthening its predictive accuracy in time series analysis.Additionally,the experimental results confirm the effectiveness of the proposed approach.
文摘Oil spills can generate multiple effects in different time scales on the marine ecosystem. The numerical modeling of these processes is an important tool with low computational cost which provides a powerful appliance to environmental agencies regarding the risk management. In this way, the objective of this work is to evaluate the influence of a number of physical forcing acting over a hypothetical oil spill along the Southern Brazilian Shelf. The numerical simulation was carried out using the ECOS model (Easy Coupling Oil System), an oil spill model developed at the Universidade Federal do Rio Grande—FURG, coupled with the tridimensional hydrodynamic model TELEMAC3D (EDF, France). The hydrodynamic model provides the current velocity, salinity and temperature fields used by the oil spill model to evaluate the behavior and the fate of the spilled oil. The results suggest that the local wind influence is the main forcing driven the fate of the spilled oil, and this forcing responds for more than 60% of the oil slick variability. The direction and intensity of the costal currents control between 20% and 40% of the oil variability, and the currents are important controlling the behavior and the tridimensional transportation of the oil. On the other hand, the turbulent diffusion is important for the horizontal drift of the oil. The weathering results indicate 40% of evaporation and 80% of emulsification, and the combination of these processes leads an increasing of the oil density around, 53.4 kg/m3 after 5 days of simulation.
