Niche Genetic Algorithm and Minimum Spanning Tree for Substation Planning

This paper presents a method based on niche genetic algorithm (NGA) and minimum spanning tree (MST) for substation planning. The problem of substation planning is divided into two parts: one is the capacity-determining and another is location-determining. The customer loads are represented a tree built by MST. Through clustering the loads, the capacity of every substation is calculated, and then the least square method is used to determine the location of substation with the objective function of minimal cost. NGA is employed to optimize the above process. Large amount of experiments show the effectiveness of our algorithm comparing with the other methods.