Decentralized LFC Design Using ANN Technique Based on Mixed H_2/H_∞ Robust Control in a Deregulated Electric Power System

摘要

This paper presents a new decentralized Artificial Neural Network (ANN) controller based on the mixed H_2/H_∞ control technique for load frequency Control (LFC) in a deregulated power system. To achieve decentralization, the effects of possible contracted scenarios and interfaces between control areas are treated as a set of new input disturbance signals. The proposed method combines advantages of the ANN and mixed H_2/H_∞ control techniques for improving robust performance and minimizing the effects of area load disturbances in the presence of large parametric uncertainties and physical constraints. This newly developed design strategy leads to a flexible controller with simple configuration, which can be useful in real world complex power systems. The proposed controller is tested on a twoarea power system and compared with mix-ed H_2/H_∞ and PI controllers to demonstrate its robust performance. The results ore shown for two scenarios of possible contracts under modeling uncertainties and large load demands in the presence of Generation Rale Constraints (GRC).