Abstract
This paper proposed spherical local search (SLS) for solving unconstrained optimization problems in three dimensions. The algorithm begins with a randomly chosen point in the search domain. Then, spherical trust region around this point is defined by the radius of SLS; where any point in this region is feasible. Finally, SLS can move from current search point to obtain a new best point by using three strategies of search: radius, azimuth, and inclination. These strategies are modified during the search process. SLS is tested on the set of the CEC' 2005 special session on real parameter optimization. Results show the robustness and effectiveness of the proposed method.