Energy consumption has been increasing rapidly in the world. That is why production of energy from renewable resources is getting more and more important today. Hydroelectric power is the largest source of renewable electricity generation in the world. Countries that have large resources of hydropower use hydroelectricity as a base load energy source because of its secure and reliable energy production. Maintenance scheduling in energy production plants is very crucial since any unexpected malfunction leads to very serious economic losses. It is essential to decide how and when to perform maintenance activities for power plants, especially if they are among base load electricity producers. The control gates are one of the vital components in hydroelectric power plants which control the movement of water. In this study, we formulate the maintenance problem of control gates using Markov Decision Processes. Our aim is to find an optimum maintenance policy for the gates by considering maintenance related losses such as equipment cost, lost sales and time spent during maintenance. We create and analyze different scenarios based on the physical conditions of the plant and cost structures.