Dielectric polymers for electrostatic energy storage suffer from low energy density and poor efficiency at elevated temperatures, which constrains their use in the harsh-environment electronic devices, circuits, and systems. Although incorporating insulating, inorganic nanostructures into dielectric polymers promotes the temperature capability, scalable fabrication of high-quality nanocomposite films remains a formidable challenge. Here, we report an all-organic composite comprising dielectric polymers blended with high-electron-affinity molecular semiconductors that exhibits concurrent high energy density (3.0 J cm⁻³) and high discharge efficiency (90%) up to 200 °C, far outperforming the existing dielectric polymers and polymer nanocomposites. We demonstrate that molecular semiconductors immobilize free electrons via strong electrostatic attraction and impede electric charge injection and transport in dielectric polymers, which leads to the substantial performance improvements. The all-organic composites can be fabricated into large-area and high-quality films with uniform dielectric and capacitive performance, which is crucially important for their successful commercialization and practical application in high-temperature electronics and energy storage devices.

We present in this paper a model for forecasting short-term electric load based on deep residual networks. The proposed model is able to integrate domain knowledge and researchers’ understanding of the task by virtue of different neural network building blocks. Specifically, a modified deep residual network is formulated to improve the forecast results. Further, a two-stage ensemble strategy is used to enhance the generalization capability of the proposed model. We also apply the proposed model to probabilistic load forecasting using Monte Carlo dropout. Three public datasets are used to prove the effectiveness of the proposed model. Multiple test cases and comparison with existing models show that the proposed model is able to provide accurate load forecasting results and has high generalization capability.

This paper develops a novel graph convolutional network (GCN) framework for fault location in power distribution networks. The proposed approach integrates multiple measurements at different buses while taking system topology into account. The effectiveness of the GCN model is corroborated by the IEEE 123 bus benchmark system. Simulation results show that the GCN model significantly outperforms other widely-used machine learning schemes with very high fault location accuracy. In addition, the proposed approach is robust to measurement noise and data loss errors. Data visualization results of two competing neural networks are presented to explore the mechanism of GCNs superior performance. A data augmentation procedure is proposed to increase the robustness of the model under various levels of noise and data loss errors. Further experiments show that the model can adapt to topology changes of distribution networks and perform well with a limited number of measured buses.

Many mainstream dielectric energy storage technologies in the emergent applications, such as renewable energy, electrified transportations and advanced propulsion systems, are usually required to operate under harsh-temperature conditions. However, excellent capacitive performance and thermal stability tend to be mutually exclusive in the current polymer dielectric materials and applications. Here, we report a strategy to tailor structural units for the design of high-temperature polymer dielectrics. A library of polyimide-derived polymers from diverse combinations of structural units are predicted, and 12 representative polymers are synthesized for direct experimental investigation. This study provides important insights into decisive structural factors necessary to achieve robust and stable dielectrics with high energy storage capabilities at elevated temperature. We also find that the high-temperature insulation performance would experience diminishing marginal utility as the bandgap increases beyond a critical point, which is strongly correlated to the dihedral angle between neighboring planes of conjugation in these polymers. By experimentally testing the optimized and predicted structures, an increased energy storage at temperatures up to 250 °C is observed. We discuss the possibility for this strategy to be generally applied to other polymer dielectrics to achieve further performance enhancement.