On the liberalized energy market, one of the main competitive parameters is control capability. Power plants must be able to operate at both high and low load, and they should allow rapid and smooth changes from one load level to another. However, most of the coal-fired power plants were designed to operate at high load at all times. To allow full-range operation of existing and new thermal power plants, novel control paradigms that can be adjusted online and can handle the "idiosyncracies" (non-constant, noisy, nonlinear, non-smooth behaviors) of these highly complex plants are required. The aim of the Ph.D. project is to undertake a rigorous study to improve the load following capabilities of a coal-fired power plant, from the input of fuel to the production of steam utilizing hybrid theory. The hope is to develop new, theoretically well-founded algorithms methods and/or tools for handling discrete changes in the processes, such that efficient control can be applied throughout the operating regime of the plant while avoiding instabilities at all times.