Decomposition-Based Stacked Bagging Boosting Ensemble for Dynamic Line Rating Forecasting

Abstract

Effective exploitation of overhead transmission lines needs reliable and precise dynamic line rating forecasting. High-accuracy dynamic line rating forecasting, in particular, is an important short-term method for coping with grid congestion, enhancing grid stability, and accommodating high renewable energy penetration. Due to the non-stationarity and stochasticity of the meteorological variables, a single model is often not sufficient to accurately predict the dynamic line rating. Herein, a new stacked bagging boosting ensemble is developed based on multivariate empirical mode decomposition to overcome single models' restrictions and increase the dynamic line rating forecasting performance. The developed ensemble is utilized on the data gathered from a 400 kV aluminum conductor steel-reinforced overhead power line with a length of 32.85 Km between Ghadamgah and Binalood wind farms, located in the northeast of Iran. The simulation results substantiate that the proposed ensemble can capture meteorological variables' non-linear characteristics, yielding more accurate yet robust to noisy data forecasts than single forecasting models.