Determining temporary admissible transmission loading using neural networks

The operation of power grids has grown more complex due to increased renewable energy integration and fluctuating demand. Temporary Admissible Transmission Loading (TATL) plays a crucial role in optimizing grid efficiency, especially in curative congestion management. This paper proposes a neural network-based method to predict TATL by integrating thermodynamic principles with real-time environmental factors. The approach improves prediction accuracy, providing more reliable estimates for transmission line performance. The findings highlight the potential of neural networks to support adaptive and efficient grid management in the face of dynamic energy flows, contributing to more resilient and cost-effective power systems.