As renewable energy (RE) grows, efficient grid integration is vital to reduce curtailment and defer costly infrastructure upgrades. Among available options, dynamic line rating (DLR) offers a low-cost, data-driven solution that enhances transmission line capacity based on real-time weather conditions. However, widespread adoption is often hindered by the scarcity of line-specific data. This paper presents a novel AI-powered DLR model that addresses the scarcity of transmission line data, enabling the prediction of thermal capacity for overhead transmission lines while ensuring safe operation. In simulations of the Saudi power system, wind speed emerges as a key enabler for increasing the thermal capacity of power lines through DLR. The model achieves a mean absolute percentage error below 3%, ensuring accurate and secure operation. Results indicate that DLR can double the static line capacity, making it especially beneficial for wind-abundant regions in Saudi Arabia. This enhanced capacity facilitates greater integration of renewables and more efficient power dispatch, leading to a reduction of up to 3% in annual electricity variable costs and a reduction in RE curtailment up to 46% under a 2030 reference scenario for Saudi Arabia. The study shows DLR reduces natural gas use, aiding Saudi Arabia’s energy transition through improved grid efficiency.
