A Digital Twin Approach for Improving Estimation Accuracy in Dynamic Thermal Rating of Transmission Lines

The limitation of transmission lines thermal capacity plays a crucial role in the safety and reliability power systems. Dynamic line rating approaches aim to estimate line’s temperature assess its compliance with limitations above. Existing physics-based standards based on environment conditions measured by several sensors. This manuscript shows that estimation accuracy can be improved adopting data-driven Digital Twin approach. proposed method exploits machine learning input–output relation between physical sensors data actual conductor temperature, serving as digital equivalent standards. An experimental assessment real data, comparing approach IEEE 738 standard, reduction 60% Root Mean Squared Error decrease maximum error from above 10 °C below 7 °C. These preliminary results suggest provides more accurate robust estimations, complement, or potential alternative, traditional methods.