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.

Many protection applications are based upon the Phasor Measurement Units (PMUs) technology. Therefore, PMUs have been increasingly widespread throughout the power network, and there are several researches have been made to locate the PMUs for complete system observability. This paper introduces an important application of PMUs in power system protection which is the detection of single line outage. In addition, a detection of the out of service line is achieved depending on the variations of phase angles measured at the system buses where the PMUs are located. Hence, a protection scheme from unexpected overloading in the network that may lead to system collapse can be achieved. Such detections are based upon an artificial intelligence technique which is the support Vector Machine (SVM) classification tool. To demonstrate the effectiveness of the proposed approach, the algorithm is tested using offline simulation for both the 14-bus IEEE and the 30-bus IEEE systems. Two different kernels of the SVM are tested to select the more appropriate one (i.e. polynomial and Radial Basis Function (RBF) kernels are used).

Voltage stability is a major concern in planning and operations of power systems. It is well known that voltage instability and collapse have led to major system failures. Modern transmission networks are more heavily loaded than ever before to meet the growing demand. One of the major consequences resulted from such a stressed system is voltage collapse or instability. This paper presents maximum loadability identification of a load bus in a power transmission network. In this study, Fast Voltage Stability Index (FVSI) is utilized as the indicator of the maximum loadability termed as Qmax. In this technique, reactive power loading will be increased gradually at particular load bus until the FVSI reaches close to unity. Therefore, a critical value of FVSI was set as the maximum loadability point. This value ensures the system from entering voltage-collapse region. The main purpose in the maximum loadability assessment is to plan for the maximum allowable load value to avoid voltage collapse; which is important in power system planning risk assessment.
The most important task in security analysis is the problem of identifying the critical contingencies from a large list of credible contingencies and ranks them according to their severity. The condition of voltage stability in a power system can be characterized by the use of voltage stability indices. This paper presents fuzzy approach for ranking the contingencies using composite-index based on parallel operated fuzzy inference engine. The Line Flow index (L.F) and bus Voltage Magnitude (VM) of the load buses are expressed in fuzzy set notation. Further, they are evaluated using Fuzzy rules to obtain overall Criticality Index. Contingencies are ranked based on decreasing order of Criticality Index and then provides the comparison of ranking obtained with FVSI method.