Optimal Power Flow using PSO algorithms based on Artificial Neural Networks

Al-Butti O. S., BURUNKAYA M., Rahebi J., Lopez-Guede J. M.

IEEE Access, cilt.12, ss.154778-154795, 2024 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 12
  • Basım Tarihi: 2024
  • Doi Numarası: 10.1109/access.2024.3479097
  • Dergi Adı: IEEE Access
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Directory of Open Access Journals
  • Sayfa Sayıları: ss.154778-154795
  • Anahtar Kelimeler: ANNs, metaheuristic algorithms, OPF, PSO
  • Gazi Üniversitesi Adresli: Evet

Özet

The improvement of electrical power system efficiency by solving the Optimal Power Flow problem involves identifying optimal controllable setpoints. This study presents a methodology that integrates a Particle Swarm Optimization algorithm with Artificial Neural Networks to minimize losses and costs. The objective is to reduce both generation fuel costs and transmission line losses while adhering to system constraints. The PSO algorithm is employed iteratively to generate initial results, which are then refined through ANN training and evaluation. This iterative process aids in determining the optimal parameters for the final PSO model.. The proposed approach is applied to the IEEE 30-bus and IEEE 14-bus standard system, resulting in a fuel cost of (797.25 /hour) and losses of (2.38 MW) for IEEE 30-bus and (828.29 /h), (2.79 MW) for IEEE-14 bus. Experimental findings underscore the method's effectiveness compared to other approaches documented in the recent literature in terms of minimizing the objective function.