INPUT-FEATURES BASED COMPARATIVE-STUDY OF INTELLIGENT TRANSIENT STABILITY ASSESSMENT

With the growing stress on today's power system, it is operated much c loser to its stability limit. Under such circumstances it is highly de sirable that one must be able to assess the security and stability of the electric power system when exposed to disturbances/faults. In the post-fault transient analysis of interconnected systems, the transient energy margin which is a complex function of prefault system conditio ns, structure of fault (type and location) and network topology at the specified fault clearing time gives a quantitative idea about the sta bility of the system. High adaptation capabilities of artificial neura l networks make them capable of synthesizing the complex mapping that transform the input features in to a single-valued space of energy mar gin. Appropriate input feature selection has a direct bearing on the c onsistency and accuracy of mapping. This issue has been addressed in t he present paper by comparing the prediction results based on approach es (Sobajic and Pao, 1989), (Sobajic and Pao 1992) (Jeyasurya, 1993) i n the time domain, energy domain and its corresponding time domain cal ibration. Subsequent to the above comparison, the much haunting questi on of whether to train the network in the energy or time domain has be en answered satisfactorily. It has been observed that fault clearing t ime is a key parameter that anticipates the success of possible calibr ation of energy margin results into the time domain. Test cases for pr ediction have been collected from many different operating conditions in power systems. Multilayer perceptron model with ADAPTIVE LEARNING A LGORITHM is used to carry out the present studies.