INTERNATIONAL JOURNAL OF SCIENCE AND INNOVATIVE ENGINEERING & TECHNOLOGY MAY 2015 ISSUE VOLUME 1 ISBN 978-81-904760-6-5 AN EFFICIENT FAULT ZONE IDENTIFICATION OF BUS SYSTEM IN DATA MINING TECHNIQUE Mr.Koilpillai G.K.M. College of Engineering and Tech. Department of Electrical and Electronics Engineering, Chennai. Email:koilpillai11@gmail.com Abstract- Mrs.S.Thangalakshmi, M.E, G.K.M. College of Engineering and Tech. Associate Professor Department of Electrical and Electronics Engineering, Chennai. Email: thangalakshmiprakash@yahoo.com The system presents a data-mining model for fault- zone identification of a flexible ac transmission system (FACTS)-based transmission line including a unified power-flow controller (UPFC), using ensemble decision trees. With the presence of UPFC to maintain the voltage stability of all the buses contains loads, lines with generators and their real and reactive power are compensated . Given the randomness in the ensemble of decision trees stacked inside the random forests model, it provides effective decision on fault-zone identification. Half-cycle postfault current and voltage samples from the fault inception are used as an input vector against target output for the fault after UPFC and for the fault before UPFC for fault-zone identification. The algorithm is tested on [MATLAB (SIMULINK) - version 2011] and also find out the various power system parameters such as voltage, current, real power , reactive power of all buses , generators are connected in the 14 bus power system network with simulated fault data are wide variations in operating parameters of the power system network, including noisy environment providing reliability with faster response time. The results of the presented approach using the Random Forest (RFs) model identify the fault zone and check the every buses and lines with its predicted ensemble value along with fault data. They are highly reliable identification of the fault zone in FACTS-based transmission lines and the results indicate that the ensemble tree is highly effective. Index Terms—Unified power flow controller, Data mining, Random forest, 14 bus system, MATLAB, PSAT. Introduction The ongoing expansion and growth of the electric utility industry continuously introduce changes to a once predictable business. Electricity increasingly being considered and handled as a commodity. Thus transmission systems are being pushed closer to their stability and thermal limits with the focus on the quality of power delivered. In the evolving utility environment, financial and market forces will continue to demand a more optimal and profitable operation of the power system with respect to generation, transmission and distribution. Advanced technologies are paramount for the reliable and secure operation of power systems. To achieve both operational reliability and financial profitability it is clear that more efficient utilization and control of the existing transmission system infrastructure is required. Improved utilization of the existing power system is provided through the Application of advanced control technologies. Power electronics based equipment or Flexible AC Transmission systems (FACTS) provide proven technical solutions to address these new operating challenges being presented today. FACTS technologies allow for improved transmission system operation with minimal infrastructure investment, environmental impact and implementation time compared to the construction of new transmission lines. FACTS technologies provide advanced solutions as cost effective alternative to new transmission line construction. FACTS provide the needed corrections of transmission functions in order to efficiently utilize existing transmission systems and therefore, minimize the gap between the stability and the thermal level. Unified Power Flow Controller (UPFC) is a Voltage Source Converter (VSC) based FACTS controller for controlling power in single-line system located at a sub-station. Unified Power Flow Controller (UPFC) is the subject of interest and hence forms the title for this main project. The proposed model of this paper explains that data mining forest and random forest techniques are used to solve the efficient fault zone identification.