Generator Economic Dispatch Behavior Modeling Using the MLP Neural Network Trained with the Levenberg-Marquardt Algorithm

V.H.C. Watt, A.B. Darmand, and D. Reid (Jamaica)

Keywords

Economic Dispatch, Artificial Neural Networks, Power System Modeling, Levenberg-Marquardt.

Abstract

This paper presents a method to model the economic dispatch outputs of the generators in the Jamaica power system. This is done by using an MLP neural network to model the function that relates the generators’ outputs and total system demand at a time t to the output of a particular generator at time (t+T), where T is the dispatch period. This work is done as a first step in economic dispatch prediction where not only the system demand is predicted but also the economic outputs of the system generators with inherent knowledge of systems constraints and operating policies.

Important Links:

• DOI:
• From Proceeding (582) European Power and Energy Systems - 2007

Go Back