Optimized Anticipatory Control Applied to Electric Power Systems

A new anticipatory control algorithm is presented to address an important challenge emerging in deregulated power systems, that is, matching power demand in a local area grid with the power delivered by a (local) power plant. A neural network anticipatory controller for a model power plant is coupled with a neural network time-series forecaster which prescribes power output for the grid. The goal of the system is to keep inadvertent flow of power across a control area's boundary as small as possible. If a difference exists between the power supplied and the power demanded in a control area, the load deficit or surplus would be either borrowed from or stored as the kinetic energy in rotating machines in the grid. The results presented show that the anticipatory approach may lead to substantial savings in maintenance and significant reliability gains.