Reliability improvement of distribution system by optimal placement of DGs using PSO and neural network

The Distributed Generators (DGs) are connected in distribution system to reduce the power losses and to improve the reliability of the distribution system. The most important process to decrease the total power loss and to improve the reliability of the system is to identify the proper placement of DG units and also to find the amount of power to be generated by them. A hybrid technique is proposed which includes Particle Swarm Optimization (PSO) and Neural Network. By fixing DGs in suitable optimal locations and by generating power based on the load conditions, the total power loss in the system can be reduced and the system reliability can be improved. The proposed method is tested for different load conditions on IEEE 30 bus system, by connecting one DG, two DGs, three DGs and four DGs in the system. The results obtained show the improved voltage profiles and reliability indices like EENS and ECOST.