Application of a novel fuzzy neural network to real-time transient stability swings prediction based on synchronized phasor measurements

Wide-area Protection and Control System With WAMS Based

“…On the other side, the initial value could be provided to some existed algorithm, such as Extend Equal Area Criteria (EEAC) and Auto-Regression (AR) method and enhance the calculation speed and result precision of these algorithms, such as: transient energy function (TEF) and Artificial Neural Network (ANN). It can be concluded that the transient stability control technology should take on a new look if the suitable method is taken based on the PMU data [13][14][15][16].…”

Event stream processing for improved situational awareness in the smart grid

“…The latency suffered by mathematical calculations makes them unfit for real time situational awareness applications. Machine-learning algorithms, such as, Artificial Neural Networks (ANN) (Chih-Wen, Mu-chun, Shuenn-Shing, & Yi-Jen, 1999) and decision trees (DT) (Kai, Likhate, Vittal, Kolluri, & Mandal, 2007;Kamwa, Samantaray, & Joos, 2010;Nuqui, Phadke, Schulz, & Bhatt, 2001;Rovnyak, Kretsinger, Thorp, & Brown, 1994;Ruisheng, Vittal, & Logic, 2010), are being extensively studied for online prediction of power system stability based on phasor data in an actionable period of time. Conventional machine learning techniques such as ANN and DT are designed to work with a limited amount of available ''stored'' data samples.…”

Real-time transient stability assessment using stacked auto-encoders

“…The second class includes direct methods (Sauer and Pai, 1997;Pavella et al, 2000). In addition, we can consider phasor measurement unit (PMU)-based methods (The IEEE PSRC system protection subcommittee-working group C14, 2013; Phadke and Thorp, 2008;Gurusinghe and Rajapakse, 2016;Yamashita and Kameda, 2013;Xu et al, 2013;Hashiesh et al, 2012;Guo and Milanovi c, 2014;Rovnyak et al, 1994;Liu et al, 1999;Kamwa et al, 2009;Cepeda et al, 2014;Rajapakse et al, 2010;Zhang et al, 2015;Yu et al, 2018;Tan et al, 2019) as the third class. Although, time domain simulation-based methods are exact, they are too timeconsuming to be appropriate for real-time applications.…”

“…Many researchers have widely used conventional machine learning techniques to achieve a PMU-based transient stability assessment (Xu et al, 2013;Hashiesh et al, 2012;Guo and Milanovi c, 2014;Rovnyak et al, 1994;Liu et al, 1999;Kamwa et al, 2009;Cepeda et al, 2014; Transient stability assessment 971 Rajapakse et al, 2010). The reported response time of these methods varies from 300 ms to 2 s, while the transient instability might occur as short as in two cycles (Zhang et al, 2015).…”