Hybrid algorithm for optimisation of m-loop electric power distribution networks

A heuristic method using artificial neural networks (ANN) for designing m-loop electric power distribution networks is presented. The task is to connect transformer stations (with given locations and loads) into m loops in order to minimise the given aim function, subject to technical constraints. The problem of designing the described network is similar to the travelling salesman problem and is a NP-hard problem. As the optimisation criterion, the minimal annual cost of electric power network was chosen. The network structure obtained with use of ANN is improved in the last stage of the proposed algorithm by the simulated annealing method or by manual exchange of transformer stations. Definition of the problem, as well as a short algorithm and some results of tests performed on m-loop electric power network models, are presented in the paper.