Hybrid Intelligence for Optimal Power Flow: Artificial Hummingbird Algorithm and Artificial Neural Networks

Al-Butti O. S. T., BURUNKAYA M.

13th IEEE International Conference on Smart Grid, icSmartGrid 2025, Glasgow, İngiltere, 27 - 29 Mayıs 2025, ss.181-188, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/icsmartgrid66138.2025.11071784
  • Basıldığı Şehir: Glasgow
  • Basıldığı Ülke: İngiltere
  • Sayfa Sayıları: ss.181-188
  • Anahtar Kelimeler: Artificial Hummingbird Algorithm, Artificial Neural Networks, Optimal Power Flow
  • Gazi Üniversitesi Adresli: Evet

Özet

This study proposes a new methodology to enhance the efficiency of electric power systems by solving the Optimal Power Flow (OPF) problem and determining the optimal values of controllable variables to minimize certain objective function. This research presents a new methodology that combines the Artificial Hummingbird Algorithm (AHA) and Artificial Neural Networks (ANNs) to achieve optimal power flow. The goal is to minimize fuel costs and transmission line losses while ensuring compliance with system constraints. Through an iterative process, the AHA algorithm produces preliminary results, which are then refined and improved by training and evaluating data extracted from the AHA in the ANNs. This iterative refinement enables the identification of optimal parameters for the final AHA model. The proposed approach was tested on a standard IEEE 30-bus system, yielding a fuel cost of (798.6054 $/h) and losses of (2.6884 MW). After comparison, results experiments show that this strategy outperforms other strategies described in recent research in terms of minimizing the objective function and speed.