Open AccessHybrid PSO–ANN algorithm to control TCR for voltage balancing
Author(s) -
Alkayyali Malek,
Ghaeb Jasim
Publication year - 2020
Publication title -
iet generation, transmission and distribution
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.92
H-Index - 110
eISSN - 1751-8695
pISSN - 1751-8687
DOI - 10.1049/iet-gtd.2019.1246
Subject(s) - particle swarm optimization , artificial neural network , matlab , algorithm , power balance , voltage , computer science , hybrid algorithm (constraint satisfaction) , transmission line , ac power , mode (computer interface) , set (abstract data type) , transmission (telecommunications) , electric power system , control theory (sociology) , power (physics) , engineering , control (management) , artificial intelligence , electrical engineering , constraint logic programming , telecommunications , physics , constraint satisfaction , quantum mechanics , probabilistic logic , programming language , operating system
Voltage unbalance is an important power quality issue, which occurs in electrical power systems (EPSs) and causes severe problems for them. In this work, a general mathematical model for EPS including its long transmission line is developed using the generalised circuit parameters method. Then, a hybrid Particle Swarm Optimisation–Artificial Neural Network (PSO–ANN) algorithm is proposed to overcome the voltage unbalance problem by controlling the firing angles of thyristor‐controlled reactor (TCR) which varies the amount of reactive power at the load side. PSO algorithm is responsible for determining the optimal set of TCR firing angles required to retrieve the balance conditions in offline mode for different load changes, employing the developed mathematical model of the EPS. Then, a dataset is taken as training samples for the ANN to be used in online mode. Aqaba Qatranah South‐Amman (AQSA) EPS is considered as a real case study and simulated in MATLAB environment to validate the proposed algorithm. The simulation results are compared with other ANN algorithms available in the literature. Finally, a laboratory prototype is built for AQSA EPS including its long transmission line to test the proposed hybrid PSO–ANN algorithm for real unbalance conditions acquired from the laboratory prototype.