Xiangyu Tang

In recent years, with the continuous growth of global new energy installed capacity, it is imperative to improve the prediction accuracy of new energy power generation. Based upon the current development trends of photovoltaic power generation and deep learning, this paper proposes a solar irradiance prediction model based on TCB-GRU-MLP. First, based on the Pearson and Spearman correlation analysis methods, the influencing factors that are strongly related to photovoltaic meteorological factors and irradiance in the study area were selected; then, the solar irradiance is predicted, and the results are displayed in the visualization interface. Experimental results show that the trained prediction model performs better than the TCN and Transformer models.

In order to reduce the significant losses caused by wildfires to the power grid, a transmission line trip risk assessment method is proposed. This method is based on the divide-and-conquer approach and flame combustion model. It involves calculating the probability of a wildfire spreading beneath the power line and the probability of flashover caused by the wildfire. These two probabilities are then combined to determine the overall probability. To quickly obtain key parameters for wildfire propagation, a pole positioning algorithm based on the divide-and-conquer approach is proposed. This takes into account various factors such as meteorological conditions, vegetation, and terrain to calculate the probability of a wildfire spreading beneath the power line. Additionally, a nonlinear analysis approach is used to derive a formula for calculating the breakdown voltage in the flame zone. This takes into consideration different vegetation types and heights to compute the breakdown voltage for the air gaps between conductors and vegetation. By combining this with the voltage level of the transmission line, the flash over breakdown probability is determined. The integration of the propagation processes and the burning characteristics beneath the power line result in a more accurate real-time assessment model for the wildfire trip risk of transmission lines. In a case study analysis, the results obtained using this method were consistent with actual trip cases. Furthermore, the proposed pole positioning algorithm significantly outperformed other algorithms in terms of run time. Therefore, this method can effectively and in real-time calculate the wildfire trip probability for transmission lines, providing valuable reference for emergency response in the event of wildfires affecting the power grid.

As an important part of information technology in the new era, internet of things (IOT) technology has got a lot of attention from many countries and is widely used in smart city construction, medical and health care and transportation. In recent years, year-on-year increase in the number of motor cars, that adds pressure to the car parking, traditional car parking is facing problems such as difficult parking, high parking vacancy rate, non-transparency of payment leads to arbitrary charges and low parking management efficiency, in response to these problems, an intelligent parking system based on the internet of things has been designed. The system is mainly composed of control module, RFID card reading module, terminal sensor equipment, LCD and mobile applications. The STM32 microcontroller unit (MCU) is used as the control module of the whole system, similar to a microcomputer to receive and process data from each device; RFID card reading module identifies the IC card; LCD displays the information about the parking, The system implemented real-time updating of the number of available parking spaces, timing and billing, in and exit induction, the system is good to the construction of a smart city.