Reduced model state estimation for Wide-Area Monitoring Systems

Abstract

This paper presents an alternative approach to multiarea state estimation. The proposed approach utilizes a fewer number of measurements than conventional state estimators and is unaffected by errors in system models. The measurements used are identified using principal component analysis, while artificial neural networks are used to implement the state estimation function. The performance of the proposed technique is demonstrated on the IEEE 118-bus and Polish 2383-bus systems.