The accurate estimation and prediction of charging demand are crucial for the planning of charging infrastructure, grid layout, and the efficient operation of charging networks. To address the shortcomings of existing methods in utilizing the spatial interdependencies among urban regions, this paper proposes a forecasting approach that integrates dynamic time warping (DTW) with a spatial–temporal attention graph convolutional neural network (ASTGCN). First, this method delves into the correlations between various regions within the target city, establishing intricate coupling relationships among them. Subsequently, the FastDTW algorithm is employed to construct an adjacency matrix, capturing the spatiotemporal correlation among different urban regions. Finally, the ASTGCN model is applied to predict the power load of each region, which can accurately capture the spatiotemporal characteristics of the power load. The experimental results indicate that the proposed model has a more powerful comprehensive ability to capture spatiotemporal relationships and improve accuracy and stability in different prediction steps.
A 100% renewable energy system (RES) satisfies a user’s energy demand using only renewable energy, which is an important energy supply in China given that the government aims to realize carbon neutrality by 2060. The design and operation of 100% RESs in different areas would vary significantly due to the impacts of climates and geographical features. This study aimed to investigate the economic and environmental performance of 100% RESs for residential communities in different areas of China. In total, 30 typical cities were chosen based on the climate characteristics and the availability of renewable energy resources. The genetic algorithm was selected to obtain the optimal design of the 100% RES in each area by taking the minimum total annual cost and the minimum CO2 emissions as optimization objectives. The results showed that 100% RESs were dominated by solar energy and biomass. The investment could be recovered in 8 years if the economic performance was optimized in most areas, but the payback period became longer when the 100% RES was optimized when considering environmental performance. The emissions could be reduced by 86–99% for CO2 and 64–97% for NOx. The results of this study would provide data support for the investment of 100% RESs in rural or suburban areas of China.
To detect open circuit faults of grid-connected T-type inverters, this paper proposed a real-time method based on fast S transform and random forest. The three-phase fault currents of the inverter were used as the inputs of the new method and no additional sensors were needed. Some fault current harmonics and direct current components were selected as the fault features. Then, fast S transform was used to extract the features of fault currents, and random forest was used to recognize the features and the fault type, as well as locate the faulted switches. The simulation and experiments showed that the new method could detect open-circuit faults with low computation complexity and the detection accuracy was 100%. The real-time and accurate open circuit fault detection method was proven effective for grid-connected T-type inverter monitoring.
Different kinds of power quality can be sensed in a smart substation. Power quality sensing and analysis are basic functions of a smart substation for situation awareness. The uncertainty principle, which states that the time uncertainty and frequency uncertainty cannot be minimized simultaneously, is a bottleneck problem that undermines the faithfulness of sensing and confines the accuracy of analysis. This paper studies the influence of the uncertainty principle on the power quality monitoring issue in detail and solves the problem by ideal atomic decomposition (IAD). The new method employs a pair of time and frequency bases where the power quality waveform is sensed. Then, both time uncertainty and frequency uncertainty can be minimized simultaneously. The sensing process is realized by orthogonal matching pursuit (OMP). By simulated and field power quality tests with comparisons of developed methods, the new method can give faithful sensing and accurate analysis for various power qualities, and is validated as an effective power quality monitoring method in smart substations.