Machine Learning Based Method for Estimating Energy Losses in Large-Scale Unbalanced Distribution Systems with Photovoltaics

Identificador:  imarina:9249219

Handle: https://hdl.handle.net/20.500.11797/imarina9249219

Autores:  Mahmoud, Karar; Abdel-Nasser, Mohamed; Kashef, Heba; Puig, Domenec; Lehtonen, Matti

Resumen:
In the recent years, the penetration of photovoltaics (PV) has obviously been increased in unbalanced power distribution systems. Driven by this trend, comprehensive simulation tools are required to accurately analyze large-scale distribution systems with a fast-computational speed. In this paper, we propose an efficient method for performing time-series simulations for unbalanced power distribution systems with PV. Unlike the existing iterative methods, the proposed method is based on machine learning. Specifically, we propose a fast, reliable and accurate method for determining energy losses in distribution systems with PV. The proposed method is applied to a large-scale unbalanced distribution system (the IEEE 906 Bus European LV Test Feeder) with PV grid-connected units. The method is validated using OpenDSS software. The results demonstrate the high accuracy and computational performance of the proposed method.