Intentional Islanding of Power Systems Through Self-Embedding Learning

Abstract

Intentional islanding is a procedure to divide the electrical grid into several parts to guarantee the stability of a system in the case of failure. This study provides an unsupervised deep neural network to deal with the issue of intentional islanding. We propose to use a self-learning neural network to improve the generalisation performance of the islanding task. In addition, we use a merging technology to assign isolated buses to their neighbour's label. Experiments are carried out on several grid cases to illustrate the effect of our solution.