Dynamic prediction of multi-time scale load capacity of transmission lines based on Elman neural network online learning

Dynamic forecasts of transmission line load capacity may be beneficial to the management of line fault repair and load scheduling schemes. Based on the changes in the operating environment, this approach can be used to forecast the multi-time scale load capacity of transmission lines. In order to achieve live learning, Elman neural networks are used to merge historical data of temperature, wind speed, and load. Dynamically forecasting the permitted load capacity of transmission lines at various operating periods is based on steady-state and transient heat capacity calculations. By comparing transmission line load with steady-state and transient load capacity, we suggest a method that takes advantage of the potential capacity of transmission lines.