C. Lucas - Intelligent Systems, Sharif University of Technology
H. Lesani - , University of Tehran
Alireza Fereidunian - Electerical Engineering, University of Tehran

A novel intelligent neural optimizer with two objective functions is designed for electrical distribution systems. The presented method is faster than alternative optimization methods and is comparable with the most powerful and precise ones. This optimizer is much smaller than similar neural systems. In this work, two intelligent estimators are designed, a load flow program is coded, and a special modified heuristic optimization algorithm is developed and used too. The load pattern concept is used for training ANNs. Finally, the designed optimizer is tested on an example distribution system; simulation results are presented, and compared with similar systems.

distribution systems, Pattern Recognition, Neural Networks, real, Time control, Loss reduction, Load Balancing, optimization, Decision Making