This paper presents a data-mining-based intelligent differential relaying scheme for transmission lines, including flexible ac transmission system device, such as unified power flow controller (UPFC) and wind farms. Initially, the current and voltage signals are processed through extended Kalman filter phasor measurement unit for phasor estimation, and 21 potential features are computed at both ends of the line. Once the features are extracted at both ends, the corresponding differential features are derived. These differential features are fed to a data-mining model known as decision tree (DT) to provide the final relaying decision. The proposed technique has been extensively tested for single-circuit transmission line, including UPFC and wind farms with in-feed, double-circuit line with UPFC on one line and wind farm as one of the substations with wide variations in operating parameters. The test results obtained from simulation as well as in real-time digital simulator testing indicate that the DT-based intelligent differential relaying scheme is highly reliable and accurate with a response time of 2.25 cycles from the fault inception.
The paper presents a decision tree (DT) induced fuzzy rule-based intelligent differential relaying scheme for transmission lines including unified power flow controller (UPFC) and wind-farms. The conventional distance relaying scheme fails miserably in protecting transmission lines including flexible AC transmission systems controllers such as UPFC and further, the protection issues become more challenging when wind-farm is integrated. The proposed protection scheme extracts features from the instantaneous voltage and current signals from both ends of the transmission line using discrete Fourier transform based pre-processor and computes corresponding differential features. The differential features are used to build the fault classification tree using a data-mining algorithm known as DT. Further, the fuzzy membership functions are drawn using the DT thresholds and the corresponding fuzzy rule-base is developed for final relaying decision. The proposed technique has been extensively tested (in MATLAB environment) for single circuit and double circuit transmission lines including UPFC and wind-farms with wide variations in operating conditions. The test results indicate that the proposed DTinduced fuzzy rule-based relaying scheme is highly reliable and robust for protection of complex transmission line including UPFC and wind-farm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.