Data-Driven Short-Circuit Current Interval Prediction Method for Transmission Network

The short-circuit current feed mechanism of renewable energy source (RES) is unclear and has great randomness, which brings challenges to the speed and accuracy of short-circuit current calculation in new energy grid-connected transmission systems. In order to solve this problem, this paper proposes a data-driven short-circuit current interval prediction method in the transmission network, which can quickly evaluate the short-circuit current level based on the operating status of the transmission system. First, a short-circuit current prediction model based on back propagation neural network (BPNN) is proposed to accurately calculate the short-circuit current under the corresponding power grid operating mode. After that, considering the randomness of RES, a prediction intervals (PIs) construction method based on ensemble backpropagation neural networks (EBPNN) was proposed to achieve short-circuit current interval prediction. Finally, the effectiveness and efficiency of the proposed method were verified on the IEEE New England 39-node system. Compared with other data-driven algorithms, the calculation accuracy of the proposed method showed significant superiority.