Data-driven congestion management for LV distribution networks

In this study, a mechanism is developed to support the distribution system operators (DSOs) with a better grid management scheme regarding congestion management by incorporating a data-driven congestion scheme and thus reducing the congestion. The objective of the work is to avoid/reduce the thermal overloading of the transformer with an affordable approach. A data-driven model is developed, which can help DSOs to solve congestion problems in the low-voltage (LV) distribution network. Demand response is applied for the procurement of flexibility, using available flexibility to mitigate the congestion in the distribution network. Once the congestion occurs, the DSO can refer to the data-driven classification model and mitigate the congestion with the minimised cost. A typical Dutch LV distribution network is considered for analysis. It is observed that the DSO has significant savings and reduction of congestion occurrence in the LV distribution network. The performance and accuracy of the developed data-driven model are also found to be well within satisfactory limits.