Deep Learning Surrogates For Low-Voltage Grid Expansion Planning

We introduce a deep learning surrogate approach, built on free, open-source data and tools, to predict transformer demand time series under future decarbonization with sector coupling scenarios for any German low-voltage grid. This work directly addresses the current research landscape of opaque national studies, unverifiable or imprecise modeling decisions, and privileged access to real grid data. First, a state-of-theart, scalable, ground-truth generation tool was developed, which replicates physical grids and populates them with harmonized time series data. This tool generated a representative dataset of 1,000 low-voltage grids for training a transformer architecturebased surrogate intended to replace expensive energy system optimization models. The surrogate reduces computation time by three orders of magnitude, while maintaining peak load prediction errors below 10% for the majority of our grids. With this surrogate, bottom-up results for all 500,000 low-voltage grids in Germany can be obtained within approximately 5 days of computation time.