Journal
IEEE TRANSACTIONS ON POWER SYSTEMS
Volume 34, Issue 2, Pages 908-917Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TPWRS.2018.2878535
Keywords
Composite power system reliability evaluation; multi label classification; KNN learning algorithm; Monte Carlo simulation
Categories
Ask authors/readers for more resources
This paper presents a new approach for reliability evaluation of composite power systems by combining Monte Carlo simulation and multi label k-nearest neighbor (MLKNN) algorithm. MLKNN is a classification technique in which target vector of each instance is assigned into multiple classes. In this paper, MLKNN is used to classify states (failure or success at system or bus level) of a complete power system without requiring optimal power flow (OPF) analysis, except in the training phase. As a result, the computational burden to perform OPF is reduced dramatically. For illustration, the proposed method is applied to the IEEE 30 BUS Test System and IEEE Reliability Test System. The obtained results from various case studies demonstrate that MLKNN based reliability evaluation provides promising results in both classification accuracy and computation time in evaluating the composite power system reliability.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available