Simulating the dynamic characteristics of a PN junction at the microscopic level requires solving the Poisson's equation at every time step. Solving at every time step is a necessary but time-consuming process when using the traditional finite difference (FDM) approach. Deep learning is a powerful technique to fit complex functions. In this work, deep learning is utilized to accelerate solving Poisson's equation in a PN junction. The role of the boundary condition is emphasized in the loss function to ensure a better fitting. The resulting I-V curve for the PN junction, using the deep learning solver presented in this work, shows a perfect match to the I-V curve obtained using the finite difference method, with the advantage of being 10 times faster at every time step.

The smart grid is the latest trend and complex scientific issue in the development of power systems in the world today. With the new round of power system reform and the deregulation of the power market, comprehensive and scientific evaluation of the development level of the smart grid plays an important role in achieving the overall goal of smart grid construction. This paper constructed a comprehensive evaluation index system from the aspects of safety and reliability, economy, intelligence level and sustainability of smart distribution network. Then the comprehensive evaluation model of AHP-TOPSIS intelligent distribution network was established. Finally, an empirical study on the development level of smart distribution networks of four power companies in a province was carried out, and corresponding conclusions were drawn.

No abstract

No abstract

No abstract