NEURAL-NET BASED REAL-TIME ECONOMIC-DISPATCH FOR THERMAL POWER-PLANTS

This paper proposes the application of artificial neural networks to r eal-time optimal generation dispatch of thermal units. The approach ca n take into account the operational requirements and network losses. T he proposed economic dispatch uses an artificial neural network (ANN) for generation of penalty factors, depending on the input generator po wers and identified. system load change. Then, a few additional iterat ions are performed within computation procedure for the solution of eq uations, by using reference-bus penalty-factors derived from the Newto n-Raphson load flow. A coordination technique for environmental and ec onomic dispatch of pure thermal systems, based on the neural-net theor y for simplified solution algorithms and improved man-machine interfac e is introduced. Numerical results on two test examples show that the proposed algorithm can efficiently and accurately develop optimal and feasible generator output trajectories, by applying neural-net forecas ts of system load patterns.