Application of a Genetic Algorithm based Distribution Planning Method for Creating Diverse Link Layouts

Z. Zmijarević, M. Skok, D. Škrlec, and S. Krajcar (Croatia)


Power Distribution Planning, Optimization, Genetic Algorithms, Geographic Information Systems.


Long-term distribution planning methods have been explored vigorously to facilitate utilities seeking effective planning solutions. This particular paper deals with possible applications of a single-stage long-term planning method based on evolutionary algorithms for medium voltage networks. Although a brief description of the underlying algorithm is provided for explanatory reasons, the emphasis of the paper is focused on the how the method may be used to create fairly different designs of distribution networks with link structures. This diversity of solutions is built upon the opportunity to define a substation's category in the network (supply or switching). Such designs are interesting because conventional link networks are altered with junction points providing more flexibility during outages. These designs allow easier automation and protection, which coincides with demands for higher availability in distribution networks. Within this paper, the method's usage is described in more detail and demonstrated on a real-world example. Special emphasis is given on planning criteria and method's features in order to provide a better perspective on distribution planning and encourage additional research related to practical use of planning tools.

Important Links:

Go Back