| Popis: |
This chapter presents applications of the meta-heuristic known as grey wolf optimizer (GWO) to solve the NP-hard transmission network expansion planning (TNEP) problem. The computational intelligence technique known as GWO mathematically models the hunting technique and social hierarchy of grey wolves to solve optimization problems. In this context, the candidate solutions for the optimization problem are the preys, and the grey wolves adapt their positions in the search space to reach the optimal solutions. A pack of grey wolves is composed of four types of wolves: \(\alpha \), \(\beta \), \(\delta \) and \(\omega \). The three dominant wolves in a population are the \(\alpha \), \(\beta \) and \(\delta \), and in an optimization context, they represent the three best solutions obtained in the searching process. The remaining wolves, called \(\omega \), renovate their positions over the course of iterations by calculating the mean distance between their location and the position of the three dominant wolves, and after evaluation through an objective function, the pack hierarchy is updated. Originally, the GWO algorithm was designed for continuous problems, and however, the TNEP problem is of binary nature. Thus, the authors propose the use of a sigmoid transfer function to convert the optimization variables into binary values. At last, a simple modification at the local search component of the algorithm is incorporated to the problem to best suit its application to the TNEP problem and escape local minima. |
