Fast yet accurate energy-loss-assessment approach for analyzing/sizing PV in distribution systems using machine learning

Research output: Contribution to journalArticle


Research units

  • Aswan University


The penetration of photovoltaic (PV) has obviously been increased in distribution systems throughout the world. To sufficiently assess the energy losses with PV, comprehensive simulations with high time-resolution data are required. These simulations have a heavy computational burden, which makes it difficult to analyze distribution systems and evaluate PV impacts with fine resolutions. To cope with this issue, most related works down-sample, cluster, or quantize the full data to reduce the computational time on the expense of the accuracy. In this paper, we propose a fast yet accurate energy-loss assessment approach in distribution systems using machine learning. The unique feature of the proposed approach is that it uses all data to estimate losses, which yields accurate results close to the exact solutions in a very short time. The simulation results demonstrate that the proposed approach extremely reduces the computational time of energy-loss estimation with high accuracy rates. The speedup of the proposed approach with respect to power flow simulations for a yearlong at a 30-s time resolution is 28 691 (99.9965% reduction in computational time). The effectiveness of the proposed approach is also illustrated by applying it to optimize the PV size for minimizing energy losses.


Original languageEnglish
Article number8418861
Pages (from-to)1025-1033
Number of pages9
JournalIEEE Transactions on Sustainable Energy
Issue number3
Publication statusPublished - 1 Jul 2019
MoE publication typeA1 Journal article-refereed

    Research areas

  • Distribution systems, Energy losses, Machine learning, Photovoltaic (PV)

ID: 35288909