ARTIFICIAL NEURAL-NETWORK-BASED FEEDER RECONFIGURATION FOR LOSS REDUCTION IN DISTRIBUTION-SYSTEMS

Neural networks include the capability to map the perplexed and extremely non-linear relationship between the load levels of zone and the system topologies, which is required for the feeder reconfiguration in distribution systems. This study is intended to propose the strategies to reconfigure the feeder, by using artificial neural networks with the mapping ability. Artificial neural networks determine the appropriate system topology that reduces the power loss according to the variation of load pattern. The control strategy can be easily obtained on the basis of the system topology which is provided by artificial neural networks. Artificial neural networks are designed to two groups. The first group is to estimate the proper load level from the load data of each zone, and the second is to determine the appropriate system topology from the input load level. In addition, several programs with the training set builder are developed for the design, the training and the accuracy test of artificial neural networks. Finally, we also evaluate the performance of neural networks designed here, on the test distribution system. Neural networks are implemented in FORTRAN language, and trained on the personal computer COMPAQ 386.