Evolutionary approach to restoration service of electric power distribution networks

In the literature on the distribution systems operation the problem of power delivery recovery in case of the network failure is one of the very important aspects of a proper operation of the distribution systems. An idea of using a classifying system and co-evolutionary algorithm for operation support of electric power distribution systems operators has been presented in the paper. The elaborated method uses the theoretical background of genetic-based machine learning systems. The method shows the ability to collect experience on the base of information on faults, occurred or simulated in the power distribution systems. In the elaborated method the decisive variables, essential from the network operation reliability point of view, described with the use of fuzzy sets theory. A method enabling to formulate scenarios of network configuration changes (at changes in network operation conditions) has been characterised in the paper.