Within Helmholtz AI funded project GANCSTR machine learning methods are developed for very accurate prediction and control of solar thermal power plants function. Such power plants consist of a large number of mirrors, so-called heliostats, which must be optimally controlled in order to achieve a very low levelized cost of energy. Generative models like generative adversarial networks and their variants are used to determine the distribution of solar radiation reflected from each heliostats and maximize the power plant's energy output.