Transient Stability Assessment using Decision Trees and Fuzzy Logic Techniques

Abstract

Many techniques are used for Transient Stability assessment (TSA) of synchronous generators encompassing traditional time domain state numerical integration, Lyapunov based methods, probabilistic approaches and Artificial Intelligence (AI) techniques like pattern recognition and artificial neural networks. This paper examines another two proposed artificial intelligence techniques to tackle the transient stability problem. The first technique is based on the Inductive Inference Reasoning (IIR) approach which belongs to a particular family of machine learning from examples. The second presents a simple fuzzy logic classifier system for TSA. Not only steady state but transient attributes are used for transient stability estimation so as to reflect machine dynamics and network changes due to faults. The two techniques are tested on a standard test power system. The performance evaluation demonstrated satisfactory results in early detection of machine instability. The advantage of the two techniques is that they are straightforward and simple for on-line implementation.