A new method for substation planning problem based on weighted K-mean

Abstract

Substation planning is considered the most important step in the power system planning process. It represents the main link between transmission and distribution system. In this paper, the substation planning problem is looked as a clustering process to divide all the loads into several clusters. The capacity of substation is estimated by the total value of loads. The location and links are solved iteratively using weighted k-means, whose objective function is the investment cost. Each cluster is charged by a substation which is in the cluster weighted center. The performance of the proposed method as compared to that of an evolutionary computing approach is promising. © 2009 Springer Berlin Heidelberg.