This thesis focuses on improving forecasting-based grid congestion management (GCM) of grids with high penetration from renewable distributed energy resources. The grid operators must predict the grid congestion and plan flexibility for GCM correspondently. The core challenge of the process is the high computational overhead, which is addressed in this thesis by developing innovative computational tools. Firstly, a high-performance grid simulator with GPU acceleration is developed, such as for the probabilistic grid simulation. Secondly, a multi-purpose Artificial Intelligence (AI) optimization approach is developed for, e. g., the minimization of active power curtailment in GCM. Thirdly, for the flexibility planning, the AI optimization approach is extended for active/reactive power (PQ) flexibility area estimation at the transmission system - distribution system interface. The optimization considers the robustness against forecasting uncertainties and the realistic N-1 grid security criterion while remains computational efficient. The proposed tools are verified with case studies and find successful applications in multiple projects and research works.
