An increase in electricity demand and renewable penetration requires electrical utilities to improve and optimize the grid infrastructure. Fundamental components in this grid infrastructure are transformers, which are designed conservatively based on static rated power. However, load and weather change continuously and hence, transformers are not used most efficiently. For this reason, new technology has been developed: Dynamic transformer rating (DTR). Applying DTR makes it possible to load transformers above the nameplate rating without affecting their lifetime expectancy. This study uses DTR for short-term and long-term wind farm planning. The optimal wind farm is designed by applying DTR to the power transformer and using it as an input to a Mixed-Integer Linear Programming (MILP) model. Regarding the transformer thermal analysis, the linearized top oil model of IEEE Clause 7 is selected. The model is executed for 4 different types of power transformers: 63 MVA, 100 MVA, 200 MVA and 400 MVA. As a result, it is obtained that the net present value for the investment and the capacity of the wind farm increase linearly with respect to the size of the transformer. Then, a sensitivity analysis is carried out by modifying the wind speed, the electricity price, the lifetime of the transformer and the selected weather data. From this sensitivity analysis, it is possible to conclude that wind resources and electricity price are critical parameters for the wind farm’s feasibility.

This paper focuses on the thermal modelling of power transformers using physics-informed neural networks (PINNs). PINNs are neural networks trained to consider the physical laws provided by the general nonlinear partial differential equations (PDEs). The PDE considered for the study of power transformer’s thermal behaviour is the heat diffusion equation provided with boundary conditions given by the ambient temperature at the bottom and the top-oil temperature at the top. The model is one dimensional along the transformer height. The top-oil temperature and the transformer’s temperature distribution are estimated using field measurements of ambient temperature, top-oil temperature and the load factor. The measurements from a real transformer provide more realistic solution, but also an additional challenge. The Finite Volume Method (FVM) is used to calculate the solution of the equation and further to benchmark the predictions obtained by PINNs. The results obtained by PINNs for estimating the top-oil temperature and the transformer’s thermal distribution show high accuracy and almost exactly mimic FVM solution.