Probabilistic forecasts of the distribution grid state using data-driven forecasts and probabilistic power flow

The uncertainty associated with renewable energies creates challenges in the operation of distribution grids. One way for Distribution System Operators to deal this is computation probabilistic forecasts full state grid. Recently, have seen increased interest quantifying generation and load. However, individual defining variables do not allow prediction probability joint events, instance, two line flows exceeding their limits simultaneously. To overcome issue estimating we present an approach that combines data-driven (obtained more specifically quantile regressions) power flow. Moreover, test presented method using data from a real-world grid part Energy Lab 2.0 Karlsruhe Institute Technology implement it within state-of-the-art computational framework.