New Method for Solving Substation Expansion Planning Problem Using Fuzzy Clustering Algorithms

ABSTACT This paper presents a new method for solving Substation Expansion Planning (SEP) problem using three basic algorithms in fuzzy clustering. Clustering algorithms are mainly associated with distance functions and measure dissimilarities of data set in different clusters. It is equivalent to measure similarities of data in a cluster. That is, a lot of varieties exist to find and create such arranged clusters. The proposed clustering algorithms are Hard C-Means (HCM), Fuzzy C-Means and Possibilistic C-Means. At first, each algorithm is introduced and the differences are characterized. Objective function and optimization procedure of each algorithm are described afterward. Proper evaluation was done by simulating each algorithm. On the other hand, one of the complex and difficult issues in power systems is to find an appropriate response for substation expansion planning. By inspiring from HCM clustering method and by adding some necessary constraints, a new method was developed for solving SEP problem. The proposed method was applied to a typical network and good results were obtained. The results showed that the proposed method was highly effective in dealing with large networks. One of the features of this method is the possibility of introducing the location of new substations during the substation expansion planning. The fast convergence, conformity of solution with engineering perspectives, consideration of real-world networks limitations as problem constraints and simplicity in applying to real networks are the other features of the proposed method.