2019/09/09 by Anubhav Nath, Nath, Anubhav, Reetam Sen Biswas +3
Computer Science · Engineering · #Computational Physics and Python Applications #FOS: Electrical engineering #Power System Optimization and Stability #Smart Grid and Power Systems #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1909.04145
openalex publication_date 2019/09/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Large-scale blackouts that have occurred in the past few decades have\nnecessitated the need to do extensive research in the field of grid security\nassessment. With the aid of synchrophasor technology, which uses phasor\nmeasurement unit (PMU) data, dynamic security assessment (DSA) can be performed\nonline. However, existing applications of DSA are challenged by variability in\nsystem conditions and unaccounted for measurement errors. To overcome these\nchallenges, this research develops a DSA scheme to provide security prediction\nin real-time for load profiles of different seasons in presence of realistic\nerrors in the PMU measurements. The major contributions of this paper are: (1)\ndevelop a DSA scheme based on PMU data, (2) consider seasonal load profiles,\n(3) account for varying penetrations of renewable generation, and (4) compare\nthe accuracy of different machine learning (ML) algorithms for DSA with and\nwithout erroneous measurements. The performance of this approach is tested on\nthe IEEE-118 bus system. Comparative analysis of the accuracies of the ML\nalgorithms under different operating scenarios highlights the importance of\nconsidering realistic errors and variability in system conditions while\ncreating a DSA scheme.\n