An efficient substation placement and sizing strategy based on GIS using semi-supervised learning

As load and renewable penetration continues to grow, optimal placement and sizing of substations is becoming increasingly important in distribution system planning. This paper presents an improved methodology to solve the substation siting and sizing problem based on geographic information and supervised learning. The proposed approach can optimize the locations, capacities, and power supply ranges of substations with minimum investment and annual operation costs. Capital cost of land adds complexity and difficulty to the substation placement problem, especially for highly developed urban areas. This paper presents a theoretical framework to determine the optimal location of substations considering the cost of land. The state-of-the-art parallel computing techniques are employed so that co-optimization for substations of multiple voltage levels can be directly conducted in a computational efficient way. Case studies are presented to demonstrate the effectiveness of the proposed approach.