Abstract: Methods and apparatus for optimizing operation of a combined cycle power plant which combines the use of both gas and steam turbines in a single power generating plant. In one embodiment there is provided a closed-loop hybrid neural network-first principles optimizer for optimally allocating fuel across power generation plant blocks and sub systems to minimize fuel costs while meeting capacity and ramp-rate commitments. Embodiments of the methods and apparatus include a steady state plant optimization model and a dynamic plant optimization model.