Large-scale new energy grid-connected poses significant challenges to the safe and efficient operation of smart grids. Renewable energy probabilistic forecasting (REPF) technology can analyze uncertainties in power generation, quantitatively balance risks, and prevent the breakdown of the grid. However, current REPF methods reliant on spatio-temporal maps fail to accurately estimate the probability density function (PDF) of renewable energy, resulting lacking comprehensive uncertainty analysis for distributed power generation systems (DPGS). To fill this gap, in this study, an integrated sparse gated graph density network (ISGGDN) that incorporates transfer learning to tackle the REPF challenge. A sparse gated graph dynamic convolutional network based on cross attention and residual connection is developed, which can effectively extract spatial features and spatio-temporal interactions between sites and improve the accuracy of probabilistic prediction. Furthermore, to effectively identify the types of features lost during the transfer process and to enhance the transfer learning (TL) capability, we developed an integrated approach involving multiple fine-tuning strategies based on TL. We evaluated the proposed model using wind and photovoltaic (PV) power generation data from two neighboring multi-sites, and the experimental results demonstrate that ISGGDN outperforms other existing solutions in terms of accuracy and effectiveness in REPF.
Theory and stochastic lattice-gas modeling is developed for the formation of intercalated metal islands in the gallery between the top layer and the underlying layer at the surface of layered materials. Our model for this process involves deposition of atoms, some fraction of which then enter the gallery through well-separated pointlike defects in the top layer. Subsequently, these atoms diffuse within the subsurface gallery leading to nucleation and growth of intercalated islands nearby the defect point source. For the case of a single point defect, continuum diffusion equation analysis provides insight into the nucleation kinetics. However, complementary tailored lattice-gas modeling produces a more comprehensive and quantitative characterization. We analyze the large spread in nucleation times and positions relative to the defect for the first nucleated island. We also consider the formation of subsequent islands and the evolution of island growth shapes. The shapes reflect in part our natural adoption of a hexagonal close-packed island structure. Motivation and support for the model is provided by scanning tunneling microscopy observations of the formation of intercalated metal islands in highly-ordered pyrolytic graphite at higher temperatures.
22 December 2023 in Expert Systems with Applications
Interval forecasting for tourism demand holds significant theoretical and practical insights. However, research on integrating social reviews into multi-source for interval prediction is still developing. To fill this research gap, this study proposes an integrated method for tourism demand interval prediction by combining multi-source data with a modified swarm intelligence optimizer. This method can extract essential intrinsic features from multi-source data and select an appropriate probability density function to extend point predictions to initial prediction intervals, then further refine the initial prediction intervals to improve the prediction accuracy. Empirical studies on the tourism demand of Mount Siguniang and Jiuzhaigou validate the superior predictive capabilities of the proposed model. Experimental results demonstrate that (a) incorporating a multi-source dataset with social reviews significantly enhances the accuracy of the proposed model; and (b) the modified transit search algorithm effectively balances the coverage and width of prediction intervals, thus improving the generalizability of the model.