Deep learning based solar forecasting for optimal PV BESS sizing in ultra fast charging stations

Abstract

Abstract Ultra-fast charging stations (UFCS) present a significant challenge due to their high power demand and reliance on grid electricity. This paper proposes an optimization framework that integrates deep learning-based solar forecasting with a Genetic Algorithm (GA) for optimal sizing of photovoltaic (PV) and battery energy storage systems (BESS). A Gated Recurrent Unit (GRU) model is employed to forecast PV output, while the GA maximizes the Net Present Value (NPV) by selecting optimal PV and BESS sizes tailored to weekday and weekend demand profiles. The results show that PV integration alone improves the NPV by €6.19 million, while combining PV and BESS increases it to €33.97 million. With projected cost reductions, the system achieves a peak NPV of €34.05 million. Reliability analysis using Energy Sufficiency Ratio (ESR) and Autonomy Ratio (AR) confirms enhanced self-sufficiency and reduced grid dependency. This study demonstrates the techno-economic potential of hybrid renewable-powered UFCS using intelligent forecasting and evolutionary optimization.