Application of artificial intelligence in power grid state analysis and -diagnosis

Abstract:
The new global trend in the field of electrical energy supply is the application of artificial intelligence both for monitoring and controlling energy systems. To avoid grid anomalies, especially in the low-voltage-grid with his high single-phase loads and generation, the calculation of the three-phase grid state is essential. Load flow calculations help to detect the overload situations and voltage band violations that occur by comparing them with the limit values in regular operation. The approach presented here describes a method based on artificial neural networks to perform a load flow calculation and a grid state diagnosis for different switching states in distribution grids. Furthermore, the introduced procedure conducts a grid protection scheme analysis in the overload range as part of the grid state diagnosis. The proposed concept is finally demonstrated using a synthetic reference network.