The power network reconfiguration algorithm with an R modeling approach evaluates its behavior in computing new reconfiguration topologies for the power grid in the context of the Smart Grid. The power distribution network modelling with the R language is used to represent the network and support computation of different algorithm configurations for the evaluation of new reconfiguration topologies. This work presents a reconfiguration solution of distribution networks, with a construction of an algorithm that receiving the network configuration data and the nodal measurements and from these data build a radial network, after this and using a branch exchange algorithm And verifying the best configuration of the network through artificial intelligence, so that there are no unnecessary changes during the operation, and applied an algorithm that analyses the load levels, to suggest changes in the network.