To ensure a reliable supply of demand and reliable operation of the generation units an accurate maintenance scheduling is needed. Maintenance scheduling is a large, mixed integer, nonlinear, multi objective, and multi constraint problem. Evolutionary approaches are used to solve this crucial problem. This paper presents a genetic algorithm approach in combination with extremal optimization to tackle maintenance scheduling problem. The goal is to levelize the reserve throughout the year. Local search is used to improve genetic algorithm members in each iteration. The proposed algorithm is applied to a test problem and the results are compared with other methodologies. The results of the simulation show the capability of the proposed method in maintenance scheduling of the generators in power systems.

Keywords