Dynamic thermal line rating model of conductor based on prediction of meteorological parameters

Abstract

This paper developed a new algorithm to predict dynamic thermal line rating to increase the capacity of transmission lines, which can enhance the capacity of wind power integrated to the grid and reduce the curtailment. The proposed dynamic thermal line rating prediction model was trained by analyzing historical meteorological data and conductor physical parameters, and used deep learning with parameters optimized by an optimized algorithm. The prediction accuracy of the model is verified by Mean Absolute Error, R2 and comparison with other models. The simulation results show that the proposed prediction model has a good performance. The suggested dynamic thermal line rating algorithm, which bears resemblance to the actual value, boosts the static thermal line rating by varying degrees of 23% to 75% at different instances throughout the sample. At the same time, this paper designs an optimal power flow economic dispatch objective function. By comparing the economic dispatch of the power grid calculated by adding static thermal line rating and the prediction models, the method proposed in this paper can effectively increase the amount of wind power integration and reduce power generation costs.