Integrated adaptive protection and control for controllable series compensated transmission systems using neural networks

Abstract

This paper proposes a novel integrated adaptive protection and control scheme by using neural networks for controllable series compensated (CSC) EHV transmission systems. The emphasis is placed on the feature extraction, the selection of appropriate neural network architectures and their training. The adaptive protection scheme is tested under the influences of various factors, such as different fault type, fault position, fault resistance, fault inception angle, source capacity and load angle. All the test results demonstrate the proposed protection scheme has higher speed, reliability and sensitivity compared with convectional approaches when used for series compensated EHV transmission systems. By identifying the characteristic features of the faulted voltage waveforms, a neural network based adaptive autoreclosure scheme is then developed. The outcome of the study indicates that the neural network can be used as effective strategy for the development of adaptive protection and control schemes for controllable series compensated transmission systems.