Ensemble Learning-Based Dynamic Line Rating Forecasting Under Cyberattacks

Abstract

The transmission congestion issue from the high penetration of renewable energies places a premium on accurate dynamic line rating (DLR) as a short-term solution for the more efficient exploitation of the existing transmission infrastructure and the efficient and reliable operation of the power grids. Even though the DLR methods produce a worthy estimation of ampacity, they need the placement of measurement devices and communication networks along with the precise calibration of the estimators and the installation of sensors on the conductor surface. Herein, as a viable alternative, the DLR forecasting models with respect to historical meteorological data were developed using ensemble learning algorithms. Several cases were designed to explore the resiliency and accuracy of the presented approach for various forecasting horizons. The result of simulations proved that ensemble learning algorithms can be fruitfully used for DLR forecasting, even in the presence of severe cyberattacks. The proposed method yielded an approximate capacity increase of 30% for 400 kV lines between Ghadamgah and Binalood wind farms, which is enough to relieve the congestion issue. Ultimately, the developed models were tested against data that is measured at points different from what the algorithms had been trained with to investigate the generalizability of the predictors. Experiments revealed the generalizability and reliability of the forecasting models for the DLR at various points of the line without the deployment of measurement devices and communication infrastructures.